首页 > 最新文献

European Radiology Experimental最新文献

英文 中文
An AI deep learning algorithm for detecting pulmonary nodules on ultra-low-dose CT in an emergency setting: a reader study. 急诊超低剂量 CT 上检测肺结节的人工智能深度学习算法:读者研究。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-20 DOI: 10.1186/s41747-024-00518-1
Inge A H van den Berk, Colin Jacobs, Maadrika M N P Kanglie, Onno M Mets, Miranda Snoeren, Alexander D Montauban van Swijndregt, Elisabeth M Taal, Tjitske S R van Engelen, Jan M Prins, Shandra Bipat, Patrick M M Bossuyt, Jaap Stoker

Background: To retrospectively assess the added value of an artificial intelligence (AI) algorithm for detecting pulmonary nodules on ultra-low-dose computed tomography (ULDCT) performed at the emergency department (ED).

Methods: In the OPTIMACT trial, 870 patients with suspected nontraumatic pulmonary disease underwent ULDCT. The ED radiologist prospectively read the examinations and reported incidental pulmonary nodules requiring follow-up. All ULDCTs were processed post hoc using an AI deep learning software marking pulmonary nodules ≥ 6 mm. Three chest radiologists independently reviewed the subset of ULDCTs with either prospectively detected incidental nodules in 35/870 patients or AI marks in 458/870 patients; findings scored as nodules by at least two chest radiologists were used as true positive reference standard. Proportions of true and false positives were compared.

Results: During the OPTIMACT study, 59 incidental pulmonary nodules requiring follow-up were prospectively reported. In the current analysis, 18/59 (30.5%) nodules were scored as true positive while 104/1,862 (5.6%) AI marks in 84/870 patients (9.7%) were scored as true positive. Overall, 5.8 times more (104 versus 18) true positive pulmonary nodules were detected with the use of AI, at the expense of 42.9 times more (1,758 versus 41) false positives. There was a median number of 1 (IQR: 0-2) AI mark per ULDCT.

Conclusion: The use of AI on ULDCT in patients suspected of pulmonary disease in an emergency setting results in the detection of many more incidental pulmonary nodules requiring follow-up (5.8×) with a high trade-off in terms of false positives (42.9×).

Relevance statement: AI aids in the detection of incidental pulmonary nodules that require follow-up at chest-CT, aiding early pulmonary cancer detection but also results in an increase of false positive results that are mainly clustered in patients with major abnormalities.

Trial registration: The OPTIMACT trial was registered on 6 December 2016 in the National Trial Register (number NTR6163) (onderzoekmetmensen.nl).

Key points: An AI deep learning algorithm was tested on 870 ULDCT examinations acquired in the ED. AI detected 5.8 times more pulmonary nodules requiring follow-up (true positives). AI resulted in the detection of 42.9 times more false positive results, clustered in patients with major abnormalities. AI in the ED setting may aid in early pulmonary cancer detection with a high trade-off in terms of false positives.

背景:回顾性评估人工智能(AI)算法在急诊科(ED)超低剂量计算机断层扫描(ULDCT)上检测肺结节的附加值:在 OPTIMACT 试验中,870 名疑似非创伤性肺部疾病患者接受了超低剂量计算机断层扫描。急诊科放射科医生对检查结果进行前瞻性阅读,并报告需要随访的偶发肺结节。使用人工智能深度学习软件对所有 ULDCT 进行事后处理,标记出≥ 6 毫米的肺结节。35/870 例患者的 ULDCT 中有前瞻性检测到的偶发结节,458/870 例患者的 ULDCT 中有人工智能标记,由三位胸部放射科医生独立审查;至少两位胸部放射科医生评分为结节的结果作为真阳性参考标准。比较了真阳性和假阳性的比例:结果:在 OPTIMACT 研究期间,前瞻性地报告了 59 例需要随访的偶然肺结节。在目前的分析中,18/59(30.5%)个结节被评为真阳性,而 84/870 病人(9.7%)中的 104/1,862 (5.6%)个 AI 标记被评为真阳性。总体而言,使用人工智能检测到的真阳性肺结节是假阳性的 5.8 倍(104 对 18),而假阳性则是真阳性的 42.9 倍(1,758 对 41)。每例 ULDCT 的 AI 中位数为 1(IQR:0-2)个:结论:在急诊环境中对疑似肺部疾病患者的 ULDCT 使用 AI 会导致发现更多需要随访的偶然肺结节(5.8 倍),而在假阳性方面则需要付出高昂的代价(42.9 倍):人工智能有助于发现需要进行胸部 CT 随访的偶发肺结节,有助于早期肺癌的发现,但也会导致假阳性结果的增加,而这些假阳性结果主要集中在有重大异常的患者身上:OPTIMACT试验于2016年12月6日在国家试验注册中心(onderzoekmetmensen.nl)注册(编号NTR6163):在急诊室获得的870例ULDCT检查中测试了人工智能深度学习算法。人工智能检测出的需要随访的肺结节(真阳性)比人工智能多 5.8 倍。人工智能检测出的假阳性结果是真阳性的42.9倍,主要集中在有重大异常的患者身上。在急诊室进行人工智能检查可能有助于早期肺癌的检测,但在假阳性结果方面需要做出较高的权衡。
{"title":"An AI deep learning algorithm for detecting pulmonary nodules on ultra-low-dose CT in an emergency setting: a reader study.","authors":"Inge A H van den Berk, Colin Jacobs, Maadrika M N P Kanglie, Onno M Mets, Miranda Snoeren, Alexander D Montauban van Swijndregt, Elisabeth M Taal, Tjitske S R van Engelen, Jan M Prins, Shandra Bipat, Patrick M M Bossuyt, Jaap Stoker","doi":"10.1186/s41747-024-00518-1","DOIUrl":"10.1186/s41747-024-00518-1","url":null,"abstract":"<p><strong>Background: </strong>To retrospectively assess the added value of an artificial intelligence (AI) algorithm for detecting pulmonary nodules on ultra-low-dose computed tomography (ULDCT) performed at the emergency department (ED).</p><p><strong>Methods: </strong>In the OPTIMACT trial, 870 patients with suspected nontraumatic pulmonary disease underwent ULDCT. The ED radiologist prospectively read the examinations and reported incidental pulmonary nodules requiring follow-up. All ULDCTs were processed post hoc using an AI deep learning software marking pulmonary nodules ≥ 6 mm. Three chest radiologists independently reviewed the subset of ULDCTs with either prospectively detected incidental nodules in 35/870 patients or AI marks in 458/870 patients; findings scored as nodules by at least two chest radiologists were used as true positive reference standard. Proportions of true and false positives were compared.</p><p><strong>Results: </strong>During the OPTIMACT study, 59 incidental pulmonary nodules requiring follow-up were prospectively reported. In the current analysis, 18/59 (30.5%) nodules were scored as true positive while 104/1,862 (5.6%) AI marks in 84/870 patients (9.7%) were scored as true positive. Overall, 5.8 times more (104 versus 18) true positive pulmonary nodules were detected with the use of AI, at the expense of 42.9 times more (1,758 versus 41) false positives. There was a median number of 1 (IQR: 0-2) AI mark per ULDCT.</p><p><strong>Conclusion: </strong>The use of AI on ULDCT in patients suspected of pulmonary disease in an emergency setting results in the detection of many more incidental pulmonary nodules requiring follow-up (5.8×) with a high trade-off in terms of false positives (42.9×).</p><p><strong>Relevance statement: </strong>AI aids in the detection of incidental pulmonary nodules that require follow-up at chest-CT, aiding early pulmonary cancer detection but also results in an increase of false positive results that are mainly clustered in patients with major abnormalities.</p><p><strong>Trial registration: </strong>The OPTIMACT trial was registered on 6 December 2016 in the National Trial Register (number NTR6163) (onderzoekmetmensen.nl).</p><p><strong>Key points: </strong>An AI deep learning algorithm was tested on 870 ULDCT examinations acquired in the ED. AI detected 5.8 times more pulmonary nodules requiring follow-up (true positives). AI resulted in the detection of 42.9 times more false positive results, clustered in patients with major abnormalities. AI in the ED setting may aid in early pulmonary cancer detection with a high trade-off in terms of false positives.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"132"},"PeriodicalIF":3.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11579269/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142677180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Evaluation of pulmonary artery pressure, blood indices, and myocardial microcirculation in rats returning from high altitude to moderate altitude. 评估从高海拔地区返回中等海拔地区的大鼠的肺动脉压力、血液指数和心肌微循环。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-20 DOI: 10.1186/s41747-024-00514-5
Chunlong Yan, Jinfeng Ma, Dengfeng Tian, Tingjun Yan, Chenhong Zhang, Fengjuan Zhang, Yuchun Zhao, Shihan Fu, Qiang Zhang, Mengxue Xia, Yue Li, Yanqiu Sun

Background: To investigate changes in pulmonary artery pressure (PAP), blood indices, and myocardial microcirculation in rats returning from high altitude (HA) to moderate altitude (MA).

Methods: Forty 4-week-old male Sprague-Dawley rats were randomly divided into four groups with ten rats in each group. One group was transported to the MA area (MA-group), and the other three groups were transported to HA (HA-group-A, HA-group-B, and HA-group-C). After 28 weeks of age, the rats from the HA area were transported to the MA area for 0 days, 10 days, and 20 days, respectively. PAP, routine blood tests, and computed tomography myocardial perfusion indices were measured.

Results: Compared with the MA-group, the body weight of HA-groups decreased (p < 0.05), and PAP in HA-group-A and HA-group-B increased (p < 0.05). In the HA groups, PAP initially increased and then decreased. Compared with the MA-group, red blood cells (RBC), hemoglobin (HGB), and hematocrit (HCT) of rats in HA-group-A increased (p < 0.05). Compared with the HA-group-A, RBC, HGB, and HCT of HA-group-B gradually decreased (p < 0.05) while MCV decreased (p < 0.05), and PLT of HA-group-C increased (p < 0.05). Compared with the MA group, blood flow (BF) and blood volume (BV) of the HA-group-A decreased (p < 0.05). Compared with the HA-group-A, TTP increased first and then decreased (p < 0.05), and BF and BV increased gradually (p < 0.05). Pathological results showed that myocardial fiber arrangement was disordered, and cell space widened in the HA group.

Conclusion: PAP, blood parameters, and myocardial microcirculation in rats returning from high to MA exhibited significant changes.

Relevance statement: This study provides an experimental basis for understanding the physiological and pathological mechanisms during the process of deacclimatization to HA and offers new insights for the prevention and treatment of deacclimatization to HA syndrome.

Key points: Forty rats were raised in a real plateau environment. Myocardial microcirculation was detected by CT myocardial perfusion imaging. The PAP of the unacclimated rats increased first and then decreased. The myocardial microcirculation of the deacclimated rats showed hyperperfusion changes.

背景:研究从高海拔地区(HA)返回中等海拔地区(MA)的大鼠肺动脉压力(PAP)、血液指数和心肌微循环的变化:研究从高海拔地区(HA)返回中等海拔地区(MA)的大鼠肺动脉压力(PAP)、血液指数和心肌微循环的变化:将 40 只 4 周大的雄性 Sprague-Dawley 大鼠随机分为 4 组,每组 10 只。一组被送往 MA 地区(MA 组),另外三组被送往 HA 地区(HA-A 组、HA-B 组和 HA-C 组)。28 周龄后,HA 区域的大鼠被送往 MA 区域,分别停留 0 天、10 天和 20 天。对大鼠的PAP、血常规和计算机断层扫描心肌灌注指数进行测量:结果:与 MA 组相比,HA 组体重下降(P结果:与 MA 组相比,HA 组大鼠的体重下降(p 结论:从高体重回归到 MA 组大鼠的 PAP、血液参数和心肌微循环发生了显著变化:本研究为了解脱适应 HA 过程中的生理和病理机制提供了实验依据,为预防和治疗脱适应 HA 综合征提供了新的思路:在真实的高原环境中饲养了40只大鼠。要点:40 只大鼠在真实的高原环境中饲养,通过 CT 心肌灌注成像检测心肌微循环。未适应环境的大鼠的PAP先升高后降低。脱敏大鼠的心肌微循环出现高灌注变化。
{"title":"Evaluation of pulmonary artery pressure, blood indices, and myocardial microcirculation in rats returning from high altitude to moderate altitude.","authors":"Chunlong Yan, Jinfeng Ma, Dengfeng Tian, Tingjun Yan, Chenhong Zhang, Fengjuan Zhang, Yuchun Zhao, Shihan Fu, Qiang Zhang, Mengxue Xia, Yue Li, Yanqiu Sun","doi":"10.1186/s41747-024-00514-5","DOIUrl":"10.1186/s41747-024-00514-5","url":null,"abstract":"<p><strong>Background: </strong>To investigate changes in pulmonary artery pressure (PAP), blood indices, and myocardial microcirculation in rats returning from high altitude (HA) to moderate altitude (MA).</p><p><strong>Methods: </strong>Forty 4-week-old male Sprague-Dawley rats were randomly divided into four groups with ten rats in each group. One group was transported to the MA area (MA-group), and the other three groups were transported to HA (HA-group-A, HA-group-B, and HA-group-C). After 28 weeks of age, the rats from the HA area were transported to the MA area for 0 days, 10 days, and 20 days, respectively. PAP, routine blood tests, and computed tomography myocardial perfusion indices were measured.</p><p><strong>Results: </strong>Compared with the MA-group, the body weight of HA-groups decreased (p < 0.05), and PAP in HA-group-A and HA-group-B increased (p < 0.05). In the HA groups, PAP initially increased and then decreased. Compared with the MA-group, red blood cells (RBC), hemoglobin (HGB), and hematocrit (HCT) of rats in HA-group-A increased (p < 0.05). Compared with the HA-group-A, RBC, HGB, and HCT of HA-group-B gradually decreased (p < 0.05) while MCV decreased (p < 0.05), and PLT of HA-group-C increased (p < 0.05). Compared with the MA group, blood flow (BF) and blood volume (BV) of the HA-group-A decreased (p < 0.05). Compared with the HA-group-A, TTP increased first and then decreased (p < 0.05), and BF and BV increased gradually (p < 0.05). Pathological results showed that myocardial fiber arrangement was disordered, and cell space widened in the HA group.</p><p><strong>Conclusion: </strong>PAP, blood parameters, and myocardial microcirculation in rats returning from high to MA exhibited significant changes.</p><p><strong>Relevance statement: </strong>This study provides an experimental basis for understanding the physiological and pathological mechanisms during the process of deacclimatization to HA and offers new insights for the prevention and treatment of deacclimatization to HA syndrome.</p><p><strong>Key points: </strong>Forty rats were raised in a real plateau environment. Myocardial microcirculation was detected by CT myocardial perfusion imaging. The PAP of the unacclimated rats increased first and then decreased. The myocardial microcirculation of the deacclimated rats showed hyperperfusion changes.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"131"},"PeriodicalIF":3.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11579275/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142677181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Image biomarkers and explainable AI: handcrafted features versus deep learned features. 图像生物标记和可解释的人工智能:手工特征与深度学习特征。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-19 DOI: 10.1186/s41747-024-00529-y
Leonardo Rundo, Carmelo Militello

Feature extraction and selection from medical data are the basis of radiomics and image biomarker discovery for various architectures, including convolutional neural networks (CNNs). We herein describe the typical radiomics steps and the components of a CNN for both deep feature extraction and end-to-end approaches. We discuss the curse of dimensionality, along with dimensionality reduction techniques. Despite the outstanding performance of deep learning (DL) approaches, the use of handcrafted features instead of deep learned features needs to be considered for each specific study. Dataset size is a key factor: large-scale datasets with low sample diversity could lead to overfitting; limited sample sizes can provide unstable models. The dataset must be representative of all the "facets" of the clinical phenomenon/disease investigated. The access to high-performance computational resources from graphics processing units is another key factor, especially for the training phase of deep architectures. The advantages of multi-institutional federated/collaborative learning are described. When large language models are used, high stability is needed to avoid catastrophic forgetting in complex domain-specific tasks. We highlight that non-DL approaches provide model explainability superior to that provided by DL approaches. To implement explainability, the need for explainable AI arises, also through post hoc mechanisms. RELEVANCE STATEMENT: This work aims to provide the key concepts for processing the imaging features to extract reliable and robust image biomarkers. KEY POINTS: The key concepts for processing the imaging features to extract reliable and robust image biomarkers are provided. The main differences between radiomics and representation learning approaches are highlighted. The advantages and disadvantages of handcrafted versus learned features are given without losing sight of the clinical purpose of artificial intelligence models.

从医疗数据中提取和选择特征是包括卷积神经网络(CNN)在内的各种架构进行放射组学和图像生物标记发现的基础。在此,我们将介绍典型的放射组学步骤以及深度特征提取和端到端方法的 CNN 组件。我们讨论了维度诅咒以及降维技术。尽管深度学习(DL)方法表现出色,但每项具体研究仍需考虑使用手工特征而非深度学习特征。数据集规模是一个关键因素:样本多样性低的大规模数据集可能会导致过度拟合;样本规模有限可能会提供不稳定的模型。数据集必须能代表所研究的临床现象/疾病的所有 "方面"。从图形处理单元获取高性能计算资源是另一个关键因素,尤其是在深度架构的训练阶段。本文介绍了多机构联合/协作学习的优势。在使用大型语言模型时,需要较高的稳定性,以避免在复杂的特定领域任务中发生灾难性遗忘。我们强调,非 DL 方法提供的模型可解释性优于 DL 方法。要实现可解释性,就需要可解释的人工智能,这也是通过事后机制实现的。相关性声明:这项工作旨在提供处理成像特征的关键概念,以提取可靠、稳健的图像生物标记。关键点:提供了处理成像特征以提取可靠、稳健的图像生物标记物的关键概念。强调放射组学和表征学习方法之间的主要区别。在不忽视人工智能模型临床用途的前提下,介绍了手工特征与学习特征的优缺点。
{"title":"Image biomarkers and explainable AI: handcrafted features versus deep learned features.","authors":"Leonardo Rundo, Carmelo Militello","doi":"10.1186/s41747-024-00529-y","DOIUrl":"10.1186/s41747-024-00529-y","url":null,"abstract":"<p><p>Feature extraction and selection from medical data are the basis of radiomics and image biomarker discovery for various architectures, including convolutional neural networks (CNNs). We herein describe the typical radiomics steps and the components of a CNN for both deep feature extraction and end-to-end approaches. We discuss the curse of dimensionality, along with dimensionality reduction techniques. Despite the outstanding performance of deep learning (DL) approaches, the use of handcrafted features instead of deep learned features needs to be considered for each specific study. Dataset size is a key factor: large-scale datasets with low sample diversity could lead to overfitting; limited sample sizes can provide unstable models. The dataset must be representative of all the \"facets\" of the clinical phenomenon/disease investigated. The access to high-performance computational resources from graphics processing units is another key factor, especially for the training phase of deep architectures. The advantages of multi-institutional federated/collaborative learning are described. When large language models are used, high stability is needed to avoid catastrophic forgetting in complex domain-specific tasks. We highlight that non-DL approaches provide model explainability superior to that provided by DL approaches. To implement explainability, the need for explainable AI arises, also through post hoc mechanisms. RELEVANCE STATEMENT: This work aims to provide the key concepts for processing the imaging features to extract reliable and robust image biomarkers. KEY POINTS: The key concepts for processing the imaging features to extract reliable and robust image biomarkers are provided. The main differences between radiomics and representation learning approaches are highlighted. The advantages and disadvantages of handcrafted versus learned features are given without losing sight of the clinical purpose of artificial intelligence models.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"130"},"PeriodicalIF":3.7,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11576747/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142669341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Technical feasibility of automated blur detection in digital mammography using convolutional neural network. 利用卷积神经网络在数字乳腺 X 射线摄影中自动检测模糊的技术可行性。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-18 DOI: 10.1186/s41747-024-00527-0
S Nowakowska, V Vescoli, T Schnitzler, C Ruppert, K Borkowski, A Boss, C Rossi, B Wein, A Ciritsis

Background: The presence of a blurred area, depending on its localization, in a mammogram can limit diagnostic accuracy. The goal of this study was to develop a model for automatic detection of blur in diagnostically relevant locations in digital mammography.

Methods: A retrospective dataset consisting of 152 examinations acquired with mammography machines from three different vendors was utilized. The blurred areas were contoured by expert breast radiologists. Normalized Wiener spectra (nWS) were extracted in a sliding window manner from each mammogram. These spectra served as input for a convolutional neural network (CNN) generating the probability of the spectra originating from a blurred region. The resulting blur probability mask, upon thresholding, facilitated the classification of a mammogram as either blurred or sharp. Ground truth for the test set was defined by the consensus of two radiologists.

Results: A significant correlation between the view (p < 0.001), as well as between the laterality and the presence of blur (p = 0.004) was identified. The developed model AUROC of 0.808 (95% confidence interval 0.794-0.821) aligned with the consensus in 78% (67-83%) of mammograms classified as blurred. For mammograms classified by consensus as sharp, the model achieved agreement in 75% (67-83%) of them.

Conclusion: A model for blur detection was developed and assessed. The results indicate that a robust approach to blur detection, based on feature extraction in frequency space, tailored to radiologist expertise regarding clinical relevance, could eliminate the subjectivity associated with the visual assessment.

Relevance statement: This blur detection model, if implemented in clinical practice, could provide instantaneous feedback to technicians, allowing for prompt mammogram retakes and ensuring that only high-quality mammograms are sent for screening and diagnostic tasks.

Key points: Blurring in mammography limits radiologist interpretation and diagnostic accuracy. This objective blur detection tool ensures image quality, and reduces retakes and unnecessary exposures. Wiener spectrum analysis and CNN enabled automated blur detection in mammography.

背景:乳房 X 射线照片中出现模糊区域(取决于其定位)会限制诊断的准确性。本研究的目的是开发一个模型,用于自动检测数字乳腺 X 射线照相术中与诊断相关位置的模糊区域:方法:研究人员使用了一个回顾性数据集,该数据集由三个不同供应商的乳腺 X 射线摄影机采集的 152 次检查组成。模糊区域由乳腺放射专家进行轮廓分析。归一化维纳光谱(nWS)以滑动窗口的方式从每张乳房 X 光照片中提取。这些光谱作为卷积神经网络(CNN)的输入,生成光谱来自模糊区域的概率。产生的模糊概率掩码经阈值处理后,有助于将乳房 X 光照片分类为模糊或清晰。测试集的基本真相由两名放射科医生共同确定:结果:视图(p 结论:视图(p 结论:视图(p 结论:视图(p 结论:视图(p 结论:视图(p开发并评估了模糊检测模型。结果表明,基于频率空间的特征提取,并根据放射科医生在临床相关性方面的专业知识量身定制的模糊检测稳健方法,可以消除与视觉评估相关的主观性:如果在临床实践中采用这种模糊检测模型,就能为技术人员提供即时反馈,从而及时重拍乳房 X 光照片,并确保只有高质量的乳房 X 光照片才会被送去进行筛查和诊断:要点:乳腺 X 射线摄影中的模糊现象会限制放射医师的判读和诊断准确性。这种客观的模糊检测工具可确保图像质量,减少重拍和不必要的曝光。维纳频谱分析和 CNN 实现了乳腺 X 射线照相术中的自动模糊检测。
{"title":"Technical feasibility of automated blur detection in digital mammography using convolutional neural network.","authors":"S Nowakowska, V Vescoli, T Schnitzler, C Ruppert, K Borkowski, A Boss, C Rossi, B Wein, A Ciritsis","doi":"10.1186/s41747-024-00527-0","DOIUrl":"10.1186/s41747-024-00527-0","url":null,"abstract":"<p><strong>Background: </strong>The presence of a blurred area, depending on its localization, in a mammogram can limit diagnostic accuracy. The goal of this study was to develop a model for automatic detection of blur in diagnostically relevant locations in digital mammography.</p><p><strong>Methods: </strong>A retrospective dataset consisting of 152 examinations acquired with mammography machines from three different vendors was utilized. The blurred areas were contoured by expert breast radiologists. Normalized Wiener spectra (nWS) were extracted in a sliding window manner from each mammogram. These spectra served as input for a convolutional neural network (CNN) generating the probability of the spectra originating from a blurred region. The resulting blur probability mask, upon thresholding, facilitated the classification of a mammogram as either blurred or sharp. Ground truth for the test set was defined by the consensus of two radiologists.</p><p><strong>Results: </strong>A significant correlation between the view (p < 0.001), as well as between the laterality and the presence of blur (p = 0.004) was identified. The developed model AUROC of 0.808 (95% confidence interval 0.794-0.821) aligned with the consensus in 78% (67-83%) of mammograms classified as blurred. For mammograms classified by consensus as sharp, the model achieved agreement in 75% (67-83%) of them.</p><p><strong>Conclusion: </strong>A model for blur detection was developed and assessed. The results indicate that a robust approach to blur detection, based on feature extraction in frequency space, tailored to radiologist expertise regarding clinical relevance, could eliminate the subjectivity associated with the visual assessment.</p><p><strong>Relevance statement: </strong>This blur detection model, if implemented in clinical practice, could provide instantaneous feedback to technicians, allowing for prompt mammogram retakes and ensuring that only high-quality mammograms are sent for screening and diagnostic tasks.</p><p><strong>Key points: </strong>Blurring in mammography limits radiologist interpretation and diagnostic accuracy. This objective blur detection tool ensures image quality, and reduces retakes and unnecessary exposures. Wiener spectrum analysis and CNN enabled automated blur detection in mammography.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"129"},"PeriodicalIF":3.7,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11574226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142649020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Quantification of breast biopsy clip marker artifact on routine breast MRI sequences: a phantom study. 常规乳腺 MRI 序列上乳腺活检夹标记伪影的量化:一项模型研究。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-15 DOI: 10.1186/s41747-024-00525-2
Christian Kremser, Leonhard Gruber, Matthias Dietzel, Birgit Amort, Wolfram Santner, Martin Daniaux

Background: To investigate the artifact sizes of four common breast clip-markers on a standard breast magnetic resonance imaging (MRI) protocol in an in vitro phantom model.

Methods: Using 1.5-T and 3-T whole-body scanners with an 18-channel breast coil, artifact dimensions of four breast biopsy markers in an agarose-gel phantom were measured by two readers on images obtained with the following sequences: T2-weighted fast spin-echo short inversion time fat-suppressed inversion-recovery with magnitude reconstruction (T2-TIRM); T1-weighted spoiled gradient-echo with fat suppression (T1_FL3D), routinely used for dynamic contrast-enhanced imaging; diffusion-weighted imaging (DWI), including a readout segmented echo-planar imaging (RESOLVE-DWI) and echo-planar imaging sequence (EPI-DWI). After outlining the artifacts by freehand regions of interest, sagittal and lateral diameters in axial images were measured.

Results: Interreader agreement for artifact size quantification was high, depending on the sequence (80.4-94.8%). Overall, the size, shape, and appearance of artifacts depended on clip type and MRI sequence. The artifact size ranged from 5.7 × 8.5 mm2 to 13.4 × 17.7 mm2 at 1.5 T and from 6.6 × 8.2 mm2 to 17.7 × 20.7 mm2 at 3 T. Clip artifacts were largest on EPI-DWI and RESOLVE-DWI (p ≤ 0.016). In three out of four clips, T2-TIRM showed the smallest artifact (p ≤ 0.002), while in one clip the artifact was smallest on T1_FL3D (p = 0.026). With the exception of one clip in the RESOLVE sequence, all clips showed a decrease in the artifact area from DWI to ADC images (p ≤ 0.037).

Conclusion: Breast clip-marker MRI artifact appearances depend on clip type, field strength, and sequence and may reach a significant size, potentially obscuring smaller lesions and hindering accurate assessment of breast tumors.

Relevance statement: Considerable variations in artifact size and characteristics across different breast clips, MRI sequences, and field strengths exist. Awareness of these artifacts and their characteristics is essential to ensure accurate interpretation of scans and appropriate treatment planning.

Key points: Awareness of breast clip artifacts is essential for accurate interpretation of MRI. The appearance of artifacts depends on breast clip type, field strength, and sequence. Clip-related artifacts might hinder the visibility of small lesions.

背景:在体外模型中研究标准乳腺磁共振成像(MRI)方案中四种常见乳腺夹标记物的伪影大小:目的:在体外模型中研究标准乳腺磁共振成像(MRI)方案中四种常见乳腺夹标记物的伪影尺寸:方法:使用配备 18 通道乳腺线圈的 1.5-T 和 3-T 全身扫描仪,由两名读片员在以下序列获得的图像上测量琼脂糖凝胶模型中四种乳腺活检标记物的伪影尺寸:T2加权快速自旋回波短反转时间脂肪抑制反转恢复与幅度重建(T2-TIRM);T1加权破坏梯度回波与脂肪抑制(T1_FL3D),常规用于动态对比增强成像;扩散加权成像(DWI),包括读出分割回声平面成像(RESOLVE-DWI)和回声平面成像序列(EPI-DWI)。通过自由手绘感兴趣区勾勒出伪影轮廓后,测量轴向图像的矢状和侧向直径:结果:根据序列的不同,读片者之间对伪影大小量化的一致性很高(80.4%-94.8%)。总体而言,伪影的大小、形状和外观取决于夹片类型和磁共振成像序列。在 1.5 T 下,伪影大小从 5.7 × 8.5 mm2 到 13.4 × 17.7 mm2 不等,在 3 T 下,伪影大小从 6.6 × 8.2 mm2 到 17.7 × 20.7 mm2 不等。夹片伪影在 EPI-DWI 和 RESOLVE-DWI 中最大(p ≤ 0.016)。在四个片段中的三个片段中,T2-TIRM 显示的伪影最小(p ≤ 0.002),而在一个片段中,T1_FL3D 显示的伪影最小(p = 0.026)。除RESOLVE序列中的一个片段外,所有片段的伪影面积从DWI图像到ADC图像均有所减少(p≤0.037):结论:乳腺片段标记 MRI 伪影的出现取决于片段类型、磁场强度和序列,并可能达到相当大的尺寸,可能会遮挡较小的病灶,妨碍对乳腺肿瘤的准确评估:不同的乳腺片段、磁共振成像序列和磁场强度在伪影大小和特征方面存在相当大的差异。了解这些伪影及其特征对于确保准确解读扫描结果和制定适当的治疗计划至关重要:要点:认识乳房夹伪影对准确解读核磁共振成像至关重要。伪影的出现取决于乳夹类型、磁场强度和序列。与乳夹相关的伪影可能会影响小病灶的可见度。
{"title":"Quantification of breast biopsy clip marker artifact on routine breast MRI sequences: a phantom study.","authors":"Christian Kremser, Leonhard Gruber, Matthias Dietzel, Birgit Amort, Wolfram Santner, Martin Daniaux","doi":"10.1186/s41747-024-00525-2","DOIUrl":"10.1186/s41747-024-00525-2","url":null,"abstract":"<p><strong>Background: </strong>To investigate the artifact sizes of four common breast clip-markers on a standard breast magnetic resonance imaging (MRI) protocol in an in vitro phantom model.</p><p><strong>Methods: </strong>Using 1.5-T and 3-T whole-body scanners with an 18-channel breast coil, artifact dimensions of four breast biopsy markers in an agarose-gel phantom were measured by two readers on images obtained with the following sequences: T2-weighted fast spin-echo short inversion time fat-suppressed inversion-recovery with magnitude reconstruction (T2-TIRM); T1-weighted spoiled gradient-echo with fat suppression (T1_FL3D), routinely used for dynamic contrast-enhanced imaging; diffusion-weighted imaging (DWI), including a readout segmented echo-planar imaging (RESOLVE-DWI) and echo-planar imaging sequence (EPI-DWI). After outlining the artifacts by freehand regions of interest, sagittal and lateral diameters in axial images were measured.</p><p><strong>Results: </strong>Interreader agreement for artifact size quantification was high, depending on the sequence (80.4-94.8%). Overall, the size, shape, and appearance of artifacts depended on clip type and MRI sequence. The artifact size ranged from 5.7 × 8.5 mm<sup>2</sup> to 13.4 × 17.7 mm<sup>2</sup> at 1.5 T and from 6.6 × 8.2 mm<sup>2</sup> to 17.7 × 20.7 mm<sup>2</sup> at 3 T. Clip artifacts were largest on EPI-DWI and RESOLVE-DWI (p ≤ 0.016). In three out of four clips, T2-TIRM showed the smallest artifact (p ≤ 0.002), while in one clip the artifact was smallest on T1_FL3D (p = 0.026). With the exception of one clip in the RESOLVE sequence, all clips showed a decrease in the artifact area from DWI to ADC images (p ≤ 0.037).</p><p><strong>Conclusion: </strong>Breast clip-marker MRI artifact appearances depend on clip type, field strength, and sequence and may reach a significant size, potentially obscuring smaller lesions and hindering accurate assessment of breast tumors.</p><p><strong>Relevance statement: </strong>Considerable variations in artifact size and characteristics across different breast clips, MRI sequences, and field strengths exist. Awareness of these artifacts and their characteristics is essential to ensure accurate interpretation of scans and appropriate treatment planning.</p><p><strong>Key points: </strong>Awareness of breast clip artifacts is essential for accurate interpretation of MRI. The appearance of artifacts depends on breast clip type, field strength, and sequence. Clip-related artifacts might hinder the visibility of small lesions.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"128"},"PeriodicalIF":3.7,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11568078/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142640022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Material decomposition approaches for monosodium urate (MSU) quantification in gouty arthritis: a (bio)phantom study. 痛风性关节炎中单钠尿酸盐 (MSU) 定量的物质分解方法:(生物)模型研究。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-08 DOI: 10.1186/s41747-024-00528-z
Torsten Diekhoff, Sydney Alexandra Schmolke, Karim Khayata, Jürgen Mews, Maximilian Kotlyarov

Background: Dual-energy computed tomography (DECT) is a noninvasive diagnostic tool for gouty arthritis. This study aimed to compare two postprocessing techniques for monosodium urate (MSU) detection: conventional two-material decomposition and material map-based decomposition.

Methods: A raster phantom and an ex vivo biophantom, embedded with four different MSU concentrations, were scanned in two high-end CT scanners. Scanner 1 used the conventional postprocessing method while scanner 2 employed the material map approach. Volumetric analysis was performed to determine MSU detection, and image quality parameters, such as signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), were computed.

Results: The material map-based method demonstrated superior MSU detection. Specifically, scanner 2 yielded total MSU volumes of 5.29 ± 0.28 mL and 4.52 ± 0.29 mL (mean ± standard deviation) in the raster and biophantom, respectively, versus 2.35 ± 0.23 mL and 1.15 ± 0.17 mL for scanner 1. Radiation dose correlated positively with detection for the conventional scanner, while there was no such correlation for the material map-based decomposition method in the biophantom. Despite its higher detection rate, material map-based decomposition was inferior in terms of SNR, CNR, and artifacts.

Conclusion: While material map-based decomposition resulted in superior MSU detection, it is limited by challenges such as increased artifacts. Our findings highlight the potential of this method for gout diagnosis while underscoring the need for further research to enhance its clinical reliability.

Relevance statement: Advanced postprocessing such as material-map-based two-material decomposition might improve the sensitivity for gouty arthritis in clinical practice, thus, allowing for lower radiation doses or better sensitivity for gouty tophi.

Key points: Dual-energy CT showed limited sensitivity for tophi with low MSU concentrations. Materiel-map-based decomposition increased sensitivity compared to conventional two-material decomposition. The advantages of material-map-based decomposition outweigh lower image quality and increased artifact load.

背景:双能计算机断层扫描(DECT)是痛风性关节炎的一种无创诊断工具。本研究旨在比较两种检测尿酸单钠(MSU)的后处理技术:传统的双材料分解和基于材料图的分解:方法:在两台高端 CT 扫描仪上扫描了嵌入四种不同浓度 MSU 的光栅模型和体外生物模型。扫描仪 1 采用传统的后处理方法,而扫描仪 2 则采用材料图方法。进行了容积分析以确定 MSU 检测情况,并计算了信噪比 (SNR) 和对比度-噪声比 (CNR) 等图像质量参数:结果:基于材料图的方法在 MSU 检测方面表现优异。具体而言,扫描仪 2 在光栅和生物模型中检测到的 MSU 总体积分别为 5.29 ± 0.28 mL 和 4.52 ± 0.29 mL(平均值 ± 标准偏差),而扫描仪 1 检测到的 MSU 总体积分别为 2.35 ± 0.23 mL 和 1.15 ± 0.17 mL。传统扫描仪的辐射剂量与检出率呈正相关,而基于材料图的分解方法在生物模型中则没有这种相关性。尽管基于材料图的分解法的检测率较高,但在信噪比、净信噪比和伪影方面却较差:结论:虽然基于材料图的分解法在 MSU 检测方面更胜一筹,但它也受到诸如伪影增加等挑战的限制。我们的研究结果凸显了这种方法在痛风诊断中的潜力,同时也强调了进一步研究以提高其临床可靠性的必要性:先进的后处理方法,如基于材料图的双材料分解,可能会提高临床实践中痛风性关节炎的灵敏度,从而降低辐射剂量或提高痛风性趾脓的灵敏度:要点:双能量 CT 对 MSU 浓度较低的痛风灶的敏感性有限。与传统的双材料分解法相比,基于材料图的分解法提高了灵敏度。基于材料图的分解方法的优势大于较低的图像质量和增加的伪影负荷。
{"title":"Material decomposition approaches for monosodium urate (MSU) quantification in gouty arthritis: a (bio)phantom study.","authors":"Torsten Diekhoff, Sydney Alexandra Schmolke, Karim Khayata, Jürgen Mews, Maximilian Kotlyarov","doi":"10.1186/s41747-024-00528-z","DOIUrl":"10.1186/s41747-024-00528-z","url":null,"abstract":"<p><strong>Background: </strong>Dual-energy computed tomography (DECT) is a noninvasive diagnostic tool for gouty arthritis. This study aimed to compare two postprocessing techniques for monosodium urate (MSU) detection: conventional two-material decomposition and material map-based decomposition.</p><p><strong>Methods: </strong>A raster phantom and an ex vivo biophantom, embedded with four different MSU concentrations, were scanned in two high-end CT scanners. Scanner 1 used the conventional postprocessing method while scanner 2 employed the material map approach. Volumetric analysis was performed to determine MSU detection, and image quality parameters, such as signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), were computed.</p><p><strong>Results: </strong>The material map-based method demonstrated superior MSU detection. Specifically, scanner 2 yielded total MSU volumes of 5.29 ± 0.28 mL and 4.52 ± 0.29 mL (mean ± standard deviation) in the raster and biophantom, respectively, versus 2.35 ± 0.23 mL and 1.15 ± 0.17 mL for scanner 1. Radiation dose correlated positively with detection for the conventional scanner, while there was no such correlation for the material map-based decomposition method in the biophantom. Despite its higher detection rate, material map-based decomposition was inferior in terms of SNR, CNR, and artifacts.</p><p><strong>Conclusion: </strong>While material map-based decomposition resulted in superior MSU detection, it is limited by challenges such as increased artifacts. Our findings highlight the potential of this method for gout diagnosis while underscoring the need for further research to enhance its clinical reliability.</p><p><strong>Relevance statement: </strong>Advanced postprocessing such as material-map-based two-material decomposition might improve the sensitivity for gouty arthritis in clinical practice, thus, allowing for lower radiation doses or better sensitivity for gouty tophi.</p><p><strong>Key points: </strong>Dual-energy CT showed limited sensitivity for tophi with low MSU concentrations. Materiel-map-based decomposition increased sensitivity compared to conventional two-material decomposition. The advantages of material-map-based decomposition outweigh lower image quality and increased artifact load.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"127"},"PeriodicalIF":3.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11549270/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142605137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Quantitative modeling of lenticulostriate arteries on 7-T TOF-MRA for cerebral small vessel disease. 针对脑小血管疾病的 7-T TOF-MRA 图谱动脉定量建模。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-05 DOI: 10.1186/s41747-024-00512-7
Zhixin Li, Dongbiao Sun, Chen Ling, Li Bai, Jinyuan Zhang, Yue Wu, Yun Yuan, Zhaoxia Wang, Zhe Wang, Yan Zhuo, Rong Xue, Zihao Zhang

Background: We developed a framework for segmenting and modeling lenticulostriate arteries (LSAs) on 7-T time-of-flight magnetic resonance angiography and tested its performance on cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) patients and controls.

Methods: We prospectively included 29 CADASIL patients and 21 controls. The framework includes a small-patch convolutional neural network (SP-CNN) for fine segmentation, a random forest for modeling LSAs, and a screening model for removing wrong branches. The segmentation performance of our SP-CNN was compared to competitive networks. External validation with different resolution was performed on ten patients with aneurysms. Dice similarity coefficient (DSC) and Hausdorff distance (HD) between each network and manual segmentation were calculated. The modeling results of the centerlines, diameters, and lengths of LSAs were compared against manual labeling by four neurologists.

Results: The SP-CNN achieved higher DSC (92.741 ± 2.789, mean ± standard deviation) and lower HD (0.610 ± 0.141 mm) in the segmentation of LSAs. It also outperformed competitive networks in the external validation (DSC 82.6 ± 5.5, HD 0.829 ± 0.143 mm). The framework versus manual difference was lower than the manual inter-observer difference for the vessel length of primary branches (median -0.040 mm, interquartile range -0.209 to 0.059 mm) and secondary branches (0.202 mm, 0.016-0.537 mm), as well as for the offset of centerlines of primary branches (0.071 mm, 0.065-0.078 mm) and secondary branches (0.072, 0.064-0.080 mm), with p < 0.001 for all comparisons.

Conclusion: Our framework for LSAs modeling/quantification demonstrated high reliability and accuracy when compared to manual labeling.

Trial registration: NCT05902039 ( https://clinicaltrials.gov/study/NCT05902039?cond=NCT05902039 ).

Relevance statement: The proposed automatic segmentation and modeling framework offers precise quantification of the morphological parameters of lenticulostriate arteries. This innovative technology streamlines diagnosis and research of cerebral small vessel disease, eliminating the burden of manual labeling, facilitating cohort studies and clinical diagnosis.

Key points: The morphology of LSAs is important in the diagnosis of CSVD but difficult to quantify. The proposed algorithm achieved the performance equivalent to manual labeling by neurologists. Our method can provide standardized quantitative results, reducing radiologists' workload in cohort studies.

背景:我们开发了一个框架,用于在 7 T 飞行时间磁共振血管造影上分割和建模扁桃体状动脉(LSA),并在脑常染色体显性动脉病伴皮层下梗死和白质脑病(CADASIL)患者和对照组中测试了该框架的性能:我们对 29 名 CADASIL 患者和 21 名对照组进行了前瞻性研究。该框架包括一个用于精细分割的小片段卷积神经网络(SP-CNN)、一个用于LSA建模的随机森林和一个用于去除错误分支的筛选模型。我们将 SP-CNN 的分割性能与竞争网络进行了比较。对十名动脉瘤患者进行了不同分辨率的外部验证。计算了每个网络与人工分割之间的骰子相似系数(DSC)和豪斯多夫距离(HD)。将 LSA 中心线、直径和长度的建模结果与四位神经学家的手动标记结果进行了比较:结果:在分割 LSA 时,SP-CNN 获得了更高的 DSC(92.741 ± 2.789,平均值 ± 标准差)和更低的 HD(0.610 ± 0.141 mm)。在外部验证中,它的表现也优于竞争网络(DSC 82.6 ± 5.5,HD 0.829 ± 0.143 mm)。在一级分支血管长度(中位数-0.040 毫米,四分位距-0.209 至 0.059 毫米)和二级分支血管长度(0.202 毫米,0.016 至 0.537 毫米)以及一级分支血管中心线偏移量(0.071 毫米,0.065 至 0.078 毫米)和二级分支血管中心线偏移量(0.072 毫米,0.064 至 0.080 毫米)方面,框架与人工的差异低于人工观察者之间的差异,P 为 结论:与人工标注相比,我们的 LSA 建模/量化框架具有很高的可靠性和准确性:NCT05902039 ( https://clinicaltrials.gov/study/NCT05902039?cond=NCT05902039 ).相关性声明:所提出的自动分割和建模框架可精确量化皮样动脉的形态参数。这项创新技术简化了脑小血管疾病的诊断和研究,消除了人工标记的负担,促进了队列研究和临床诊断:要点:LSA 的形态对 CSVD 的诊断非常重要,但难以量化。所提出的算法达到了与神经科医生手工标记相当的效果。我们的方法可以提供标准化的定量结果,减轻放射科医生在队列研究中的工作量。
{"title":"Quantitative modeling of lenticulostriate arteries on 7-T TOF-MRA for cerebral small vessel disease.","authors":"Zhixin Li, Dongbiao Sun, Chen Ling, Li Bai, Jinyuan Zhang, Yue Wu, Yun Yuan, Zhaoxia Wang, Zhe Wang, Yan Zhuo, Rong Xue, Zihao Zhang","doi":"10.1186/s41747-024-00512-7","DOIUrl":"10.1186/s41747-024-00512-7","url":null,"abstract":"<p><strong>Background: </strong>We developed a framework for segmenting and modeling lenticulostriate arteries (LSAs) on 7-T time-of-flight magnetic resonance angiography and tested its performance on cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) patients and controls.</p><p><strong>Methods: </strong>We prospectively included 29 CADASIL patients and 21 controls. The framework includes a small-patch convolutional neural network (SP-CNN) for fine segmentation, a random forest for modeling LSAs, and a screening model for removing wrong branches. The segmentation performance of our SP-CNN was compared to competitive networks. External validation with different resolution was performed on ten patients with aneurysms. Dice similarity coefficient (DSC) and Hausdorff distance (HD) between each network and manual segmentation were calculated. The modeling results of the centerlines, diameters, and lengths of LSAs were compared against manual labeling by four neurologists.</p><p><strong>Results: </strong>The SP-CNN achieved higher DSC (92.741 ± 2.789, mean ± standard deviation) and lower HD (0.610 ± 0.141 mm) in the segmentation of LSAs. It also outperformed competitive networks in the external validation (DSC 82.6 ± 5.5, HD 0.829 ± 0.143 mm). The framework versus manual difference was lower than the manual inter-observer difference for the vessel length of primary branches (median -0.040 mm, interquartile range -0.209 to 0.059 mm) and secondary branches (0.202 mm, 0.016-0.537 mm), as well as for the offset of centerlines of primary branches (0.071 mm, 0.065-0.078 mm) and secondary branches (0.072, 0.064-0.080 mm), with p < 0.001 for all comparisons.</p><p><strong>Conclusion: </strong>Our framework for LSAs modeling/quantification demonstrated high reliability and accuracy when compared to manual labeling.</p><p><strong>Trial registration: </strong>NCT05902039 ( https://clinicaltrials.gov/study/NCT05902039?cond=NCT05902039 ).</p><p><strong>Relevance statement: </strong>The proposed automatic segmentation and modeling framework offers precise quantification of the morphological parameters of lenticulostriate arteries. This innovative technology streamlines diagnosis and research of cerebral small vessel disease, eliminating the burden of manual labeling, facilitating cohort studies and clinical diagnosis.</p><p><strong>Key points: </strong>The morphology of LSAs is important in the diagnosis of CSVD but difficult to quantify. The proposed algorithm achieved the performance equivalent to manual labeling by neurologists. Our method can provide standardized quantitative results, reducing radiologists' workload in cohort studies.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"126"},"PeriodicalIF":3.7,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11538103/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142584685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Dark-field radiography for the detection of bone microstructure changes in osteoporotic human lumbar spine specimens. 用于检测骨质疏松人体腰椎标本中骨微结构变化的暗视野射线照相术。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-11-04 DOI: 10.1186/s41747-024-00524-3
Jon F Rischewski, Florian T Gassert, Theresa Urban, Johannes Hammel, Alexander Kufner, Christian Braun, Maximilian Lochschmidt, Marcus R Makowski, Daniela Pfeiffer, Alexandra S Gersing, Franz Pfeiffer

Background: Dark-field radiography imaging exploits the wave character of x-rays to measure small-angle scattering on material interfaces, providing structural information with low radiation exposure. We explored the potential of dark-field imaging of bone microstructure to improve the assessment of bone strength in osteoporosis.

Methods: We prospectively examined 14 osteoporotic/osteopenic and 21 non-osteoporotic/osteopenic human cadaveric vertebrae (L2-L4) with a clinical dark-field radiography system, micro-computed tomography (CT), and spectral CT. Dark-field images were obtained in both vertical and horizontal sample positions. Bone microstructural parameters (trabecular number, Tb.N; trabecular thickness, Tb.Th; bone volume fraction, BV/TV; degree of anisotropy, DA) were measured using standard ex vivo micro-CT, while hydroxyapatite density was measured using spectral CT. Correlations were assessed using Spearman rank correlation coefficients.

Results: The measured dark-field signal was lower in osteoporotic/osteopenic vertebrae (vertical position, 0.23 ± 0.05 versus 0.29 ± 0.04, p < 0.001; horizontal position, 0.28 ± 0.06 versus 0.34 ± 0.04, p = 0.003). The dark-field signal from the vertical position correlated significantly with Tb.N (ρ = 0.46, p = 0.005), BV/TV (ρ = 0.45, p = 0.007), DA (ρ = -0.43, p = 0.010), and hydroxyapatite density (ρ = 0.53, p = 0.010). The calculated ratio of vertical/horizontal dark-field signal correlated significantly with Tb.N (ρ = 0.43, p = 0.011), BV/TV (ρ = 0.36, p = 0.032), DA (ρ = -0.51, p = 0.002), and hydroxyapatite density (ρ = 0.42, p = 0.049).

Conclusion: Dark-field radiography is a feasible modality for drawing conclusions on bone microarchitecture in human cadaveric vertebral bone.

Relevance statement: Gaining knowledge of the microarchitecture of bone contributes crucially to predicting bone strength in osteoporosis. This novel radiographic approach based on dark-field x-rays provides insights into bone microstructure at a lower radiation exposure than that of CT modalities.

Key points: Dark-field radiography can give information on bone microstructure with low radiation exposure. The dark-field signal correlated positively with bone microstructure parameters. Dark-field signal correlated negatively with the degree of anisotropy. Dark-field radiography helps to determine the directionality of trabecular loss.

背景:暗场射线成像利用 X 射线的波特性测量材料界面上的小角散射,以较低的辐射暴露提供结构信息。我们探讨了骨微结构暗视野成像在改善骨质疏松症患者骨强度评估方面的潜力:我们使用临床暗视野放射成像系统、微型计算机断层扫描(CT)和光谱 CT 对 14 个骨质疏松症/骨质疏松和 21 个非骨质疏松症/骨质疏松的人体尸体脊椎(L2-L4)进行了前瞻性检查。暗视野图像是在垂直和水平样本位置获得的。骨微结构参数(骨小梁数,Tb.N;骨小梁厚度,Tb.Th;骨体积分数,BV/TV;各向异性程度,DA)使用标准体外显微 CT 测量,羟基磷灰石密度使用光谱 CT 测量。相关性采用斯皮尔曼等级相关系数进行评估:结果:在骨质疏松症/骨质疏松的椎体中,测得的暗视野信号较低(垂直位置,0.23 ± 0.05 对 0.29 ± 0.04,P 结论:暗视野放射成像是一种可行的方法:暗场射线摄影是一种可行的模式,可用于对人体尸体椎骨的骨微观结构得出结论:了解骨的微观结构对预测骨质疏松症患者的骨强度至关重要。这种基于暗视野 X 射线的新型放射学方法可以深入了解骨的微观结构,而且辐射量低于 CT 模式:要点:暗视野X射线摄影能以较低的辐射量提供有关骨微观结构的信息。暗场信号与骨微观结构参数呈正相关。暗场信号与各向异性程度呈负相关。暗场射线照相术有助于确定骨小梁丢失的方向性。
{"title":"Dark-field radiography for the detection of bone microstructure changes in osteoporotic human lumbar spine specimens.","authors":"Jon F Rischewski, Florian T Gassert, Theresa Urban, Johannes Hammel, Alexander Kufner, Christian Braun, Maximilian Lochschmidt, Marcus R Makowski, Daniela Pfeiffer, Alexandra S Gersing, Franz Pfeiffer","doi":"10.1186/s41747-024-00524-3","DOIUrl":"10.1186/s41747-024-00524-3","url":null,"abstract":"<p><strong>Background: </strong>Dark-field radiography imaging exploits the wave character of x-rays to measure small-angle scattering on material interfaces, providing structural information with low radiation exposure. We explored the potential of dark-field imaging of bone microstructure to improve the assessment of bone strength in osteoporosis.</p><p><strong>Methods: </strong>We prospectively examined 14 osteoporotic/osteopenic and 21 non-osteoporotic/osteopenic human cadaveric vertebrae (L2-L4) with a clinical dark-field radiography system, micro-computed tomography (CT), and spectral CT. Dark-field images were obtained in both vertical and horizontal sample positions. Bone microstructural parameters (trabecular number, Tb.N; trabecular thickness, Tb.Th; bone volume fraction, BV/TV; degree of anisotropy, DA) were measured using standard ex vivo micro-CT, while hydroxyapatite density was measured using spectral CT. Correlations were assessed using Spearman rank correlation coefficients.</p><p><strong>Results: </strong>The measured dark-field signal was lower in osteoporotic/osteopenic vertebrae (vertical position, 0.23 ± 0.05 versus 0.29 ± 0.04, p < 0.001; horizontal position, 0.28 ± 0.06 versus 0.34 ± 0.04, p = 0.003). The dark-field signal from the vertical position correlated significantly with Tb.N (ρ = 0.46, p = 0.005), BV/TV (ρ = 0.45, p = 0.007), DA (ρ = -0.43, p = 0.010), and hydroxyapatite density (ρ = 0.53, p = 0.010). The calculated ratio of vertical/horizontal dark-field signal correlated significantly with Tb.N (ρ = 0.43, p = 0.011), BV/TV (ρ = 0.36, p = 0.032), DA (ρ = -0.51, p = 0.002), and hydroxyapatite density (ρ = 0.42, p = 0.049).</p><p><strong>Conclusion: </strong>Dark-field radiography is a feasible modality for drawing conclusions on bone microarchitecture in human cadaveric vertebral bone.</p><p><strong>Relevance statement: </strong>Gaining knowledge of the microarchitecture of bone contributes crucially to predicting bone strength in osteoporosis. This novel radiographic approach based on dark-field x-rays provides insights into bone microstructure at a lower radiation exposure than that of CT modalities.</p><p><strong>Key points: </strong>Dark-field radiography can give information on bone microstructure with low radiation exposure. The dark-field signal correlated positively with bone microstructure parameters. Dark-field signal correlated negatively with the degree of anisotropy. Dark-field radiography helps to determine the directionality of trabecular loss.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"125"},"PeriodicalIF":3.7,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11534944/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142569685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o. 探查清晰:由 ChatGPT-4o 支持的人工智能生成的简化乳腺成像报告可提高患者的理解能力。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-10-30 DOI: 10.1186/s41747-024-00526-1
Roberto Maroncelli, Veronica Rizzo, Marcella Pasculli, Federica Cicciarelli, Massimo Macera, Francesca Galati, Carlo Catalano, Federica Pediconi

Background: To assess the reliability and comprehensibility of breast radiology reports simplified by artificial intelligence using the large language model (LLM) ChatGPT-4o.

Methods: A radiologist with 20 years' experience selected 21 anonymized breast radiology reports, 7 mammography, 7 breast ultrasound, and 7 breast magnetic resonance imaging (MRI), categorized according to breast imaging reporting and data system (BI-RADS). These reports underwent simplification by prompting ChatGPT-4o with "Explain this medical report to a patient using simple language". Five breast radiologists assessed the quality of these simplified reports for factual accuracy, completeness, and potential harm with a 5-point Likert scale from 1 (strongly agree) to 5 (strongly disagree). Another breast radiologist evaluated the text comprehension of five non-healthcare personnel readers using a 5-point Likert scale from 1 (excellent) to 5 (poor). Descriptive statistics, Cronbach's α, and the Kruskal-Wallis test were used.

Results: Mammography, ultrasound, and MRI showed high factual accuracy (median 2) and completeness (median 2) across radiologists, with low potential harm scores (median 5); no significant group differences (p ≥ 0.780), and high internal consistency (α > 0.80) were observed. Non-healthcare readers showed high comprehension (median 2 for mammography and MRI and 1 for ultrasound); no significant group differences across modalities (p = 0.368), and high internal consistency (α > 0.85) were observed. BI-RADS 0, 1, and 2 reports were accurately explained, while BI-RADS 3-6 reports were challenging.

Conclusion: The model demonstrated reliability and clarity, offering promise for patients with diverse backgrounds. LLMs like ChatGPT-4o could simplify breast radiology reports, aid in communication, and enhance patient care.

Relevance statement: Simplified breast radiology reports generated by ChatGPT-4o show potential in enhancing communication with patients, improving comprehension across varying educational backgrounds, and contributing to patient-centered care in radiology practice.

Key points: AI simplifies complex breast imaging reports, enhancing patient understanding. Simplified reports from AI maintain accuracy, improving patient comprehension significantly. Implementing AI reports enhances patient engagement and communication in breast imaging.

背景:评估人工智能简化乳腺放射学报告的可靠性和可理解性:评估人工智能使用大型语言模型(LLM)ChatGPT-4o简化的乳腺放射学报告的可靠性和可理解性:一位有 20 年经验的放射科医生选择了 21 份匿名的乳腺放射学报告,其中 7 份是乳腺 X 线照相术,7 份是乳腺超声波检查,7 份是乳腺磁共振成像(MRI),并根据乳腺成像报告和数据系统(BI-RADS)进行了分类。在 ChatGPT-4o 中提示 "用简单的语言向患者解释这份医疗报告",从而简化了这些报告。五位乳腺放射科医生用 1 分(非常同意)到 5 分(非常不同意)的 5 点李克特量表评估了这些简化报告在事实准确性、完整性和潜在危害方面的质量。另一名乳腺放射科医生采用 1 分(优秀)到 5 分(较差)的 5 级李克特量表对五名非医护人员读者的文字理解能力进行了评估。使用了描述性统计、Cronbach's α 和 Kruskal-Wallis 检验:结果:不同放射科医生的乳腺 X 射线照相术、超声波检查和核磁共振成像显示出较高的事实准确性(中位数为 2)和完整性(中位数为 2),潜在危害得分较低(中位数为 5);没有观察到显著的组间差异(p ≥ 0.780)和较高的内部一致性(α > 0.80)。非医疗保健读者的理解能力较高(乳腺 X 射线照相术和核磁共振成像的中位数为 2,超声波为 1);不同模式之间无明显组间差异(p = 0.368),内部一致性较高(α > 0.85)。BI-RADS0、1和2报告得到了准确的解释,而BI-RADS3-6报告则具有挑战性:结论:该模型显示了可靠性和清晰度,为不同背景的患者提供了希望。像 ChatGPT-4o 这样的 LLM 可以简化乳腺放射学报告、帮助沟通并加强患者护理:由 ChatGPT-4o 生成的简化乳腺放射学报告在加强与患者的沟通、提高不同教育背景的患者的理解能力以及在放射学实践中促进以患者为中心的护理方面显示出潜力:人工智能简化了复杂的乳腺成像报告,提高了患者的理解能力。人工智能简化的报告保持了准确性,大大提高了患者的理解能力。实施人工智能报告可提高患者对乳腺成像的参与度和沟通能力。
{"title":"Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o.","authors":"Roberto Maroncelli, Veronica Rizzo, Marcella Pasculli, Federica Cicciarelli, Massimo Macera, Francesca Galati, Carlo Catalano, Federica Pediconi","doi":"10.1186/s41747-024-00526-1","DOIUrl":"10.1186/s41747-024-00526-1","url":null,"abstract":"<p><strong>Background: </strong>To assess the reliability and comprehensibility of breast radiology reports simplified by artificial intelligence using the large language model (LLM) ChatGPT-4o.</p><p><strong>Methods: </strong>A radiologist with 20 years' experience selected 21 anonymized breast radiology reports, 7 mammography, 7 breast ultrasound, and 7 breast magnetic resonance imaging (MRI), categorized according to breast imaging reporting and data system (BI-RADS). These reports underwent simplification by prompting ChatGPT-4o with \"Explain this medical report to a patient using simple language\". Five breast radiologists assessed the quality of these simplified reports for factual accuracy, completeness, and potential harm with a 5-point Likert scale from 1 (strongly agree) to 5 (strongly disagree). Another breast radiologist evaluated the text comprehension of five non-healthcare personnel readers using a 5-point Likert scale from 1 (excellent) to 5 (poor). Descriptive statistics, Cronbach's α, and the Kruskal-Wallis test were used.</p><p><strong>Results: </strong>Mammography, ultrasound, and MRI showed high factual accuracy (median 2) and completeness (median 2) across radiologists, with low potential harm scores (median 5); no significant group differences (p ≥ 0.780), and high internal consistency (α > 0.80) were observed. Non-healthcare readers showed high comprehension (median 2 for mammography and MRI and 1 for ultrasound); no significant group differences across modalities (p = 0.368), and high internal consistency (α > 0.85) were observed. BI-RADS 0, 1, and 2 reports were accurately explained, while BI-RADS 3-6 reports were challenging.</p><p><strong>Conclusion: </strong>The model demonstrated reliability and clarity, offering promise for patients with diverse backgrounds. LLMs like ChatGPT-4o could simplify breast radiology reports, aid in communication, and enhance patient care.</p><p><strong>Relevance statement: </strong>Simplified breast radiology reports generated by ChatGPT-4o show potential in enhancing communication with patients, improving comprehension across varying educational backgrounds, and contributing to patient-centered care in radiology practice.</p><p><strong>Key points: </strong>AI simplifies complex breast imaging reports, enhancing patient understanding. Simplified reports from AI maintain accuracy, improving patient comprehension significantly. Implementing AI reports enhances patient engagement and communication in breast imaging.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"124"},"PeriodicalIF":3.7,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525358/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142548114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep learning-based segmentation of kidneys and renal cysts on T2-weighted MRI from patients with autosomal dominant polycystic kidney disease. 基于深度学习的常染色体显性多囊肾患者 T2 加权核磁共振成像上的肾脏和肾囊肿分割。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-10-30 DOI: 10.1186/s41747-024-00520-7
Rémi Sore, Pascal Cathier, Anna Sesilia Vlachomitrou, Jérôme Bailleux, Karine Arnaud, Laurent Juillard, Sandrine Lemoine, Olivier Rouvière

Background: Our aim was to train and test a deep learning-based algorithm for automatically segmenting kidneys and renal cysts in patients with autosomal dominant polycystic kidney disease (ADPKD).

Methods: We retrospectively selected all ADPKD patients who underwent renal MRI with coronal T2-weighted imaging at our institution from 2008 to 2022. The 20 most recent examinations constituted the test dataset, to mimic pseudoprospective enrolment. The remaining ones constituted the training dataset to which eight normal renal MRIs were added. Kidneys and cysts ground truth segmentations were performed on coronal T2-weighted images by a junior radiologist supervised by an experienced radiologist. Kidneys and cysts of the 20 test MRIs were segmented by the algorithm and three independent human raters. Segmentations were compared using overlap metrics. The total kidney volume (TKV), total cystic volume (TCV), and cystic index (TCV divided by TKV) were compared using Bland-Altman analysis.

Results: We included 164 ADPKD patients. Dice similarity coefficients ranged from 85.9% to 87.4% between the algorithms and the raters' segmentations and from 84.2% to 86.2% across raters' segmentations. For TCV assessment, the biases ± standard deviations (SD) were 3-19 ± 137-151 mL between the algorithm and the raters, and 22-45 ± 49-57 mL across raters. The algorithm underestimated TKV and TCV in two outliers with TCV > 2800 mL. For cystic index assessment, the biases ± SD were 2.5-6.9% ± 6.7-8.3% between the algorithm and the raters, and 2.1-9.4 ± 7.4-11.6% across raters.

Conclusion: The algorithm's performance fell within the range of inter-rater variability, but large TKV and TCV were underestimated.

Relevance statement: Accurate automated segmentation of the renal cysts will enable the large-scale evaluation of the prognostic value of TCV and cystic index in ADPKD patients. If these biomarkers are prognostic, then automated segmentation will facilitate their use in daily routine.

Key points: Cystic volume is an emerging biomarker in ADPKD. The algorithm's performance in segmenting kidneys and cysts fell within interrater variability. The segmentation of very large cysts, under-represented in the training dataset, needs improvement.

背景:我们的目的是训练和测试一种基于深度学习的算法,用于自动分割常染色体显性多囊肾(ADPKD)患者的肾脏和肾囊肿:我们回顾性地选择了2008年至2022年期间在我院接受冠状T2加权成像肾脏核磁共振检查的所有ADPKD患者。最近的 20 次检查构成测试数据集,以模拟伪回顾性登记。其余的构成训练数据集,并在此基础上添加 8 个正常的肾脏 MRI。一名初级放射科医生在一名经验丰富的放射科医生的指导下,对冠状 T2 加权图像上的肾脏和囊肿进行地面实况分割。20 张测试核磁共振成像的肾脏和囊肿由算法和三位独立的人类评分员进行分割。使用重叠度量对分割结果进行比较。使用Bland-Altman分析比较肾脏总体积(TKV)、囊肿总体积(TCV)和囊肿指数(TCV除以TKV):我们共纳入了 164 名 ADPKD 患者。算法与评分者分段之间的骰子相似系数从85.9%到87.4%不等,评分者分段之间的相似系数从84.2%到86.2%不等。在 TCV 评估中,算法与评分者之间的偏差(± 标准差,SD)为 3-19 ± 137-151 mL,不同评分者之间的偏差(± 标准差,SD)为 22-45 ± 49-57 mL。在 TCV > 2800 mL 的两个异常值中,算法低估了 TKV 和 TCV。在囊肿指数评估方面,算法与评分者之间的偏差(± SD)为 2.5-6.9% ± 6.7-8.3%,不同评分者之间的偏差(± SD)为 2.1-9.4 ± 7.4-11.6%:结论:该算法的性能在评分者之间的变异范围内,但大TKV和TCV被低估了:对肾囊肿进行准确的自动分割将有助于大规模评估 TCV 和囊肿指数在 ADPKD 患者中的预后价值。如果这些生物标志物具有预后价值,那么自动分割将有助于它们在日常工作中的应用:囊肿体积是ADPKD的一种新兴生物标志物。该算法在分割肾脏和囊肿方面的表现在评定者之间存在差异。超大囊肿在训练数据集中所占比例较低,因此需要改进对超大囊肿的分割。
{"title":"Deep learning-based segmentation of kidneys and renal cysts on T2-weighted MRI from patients with autosomal dominant polycystic kidney disease.","authors":"Rémi Sore, Pascal Cathier, Anna Sesilia Vlachomitrou, Jérôme Bailleux, Karine Arnaud, Laurent Juillard, Sandrine Lemoine, Olivier Rouvière","doi":"10.1186/s41747-024-00520-7","DOIUrl":"10.1186/s41747-024-00520-7","url":null,"abstract":"<p><strong>Background: </strong>Our aim was to train and test a deep learning-based algorithm for automatically segmenting kidneys and renal cysts in patients with autosomal dominant polycystic kidney disease (ADPKD).</p><p><strong>Methods: </strong>We retrospectively selected all ADPKD patients who underwent renal MRI with coronal T2-weighted imaging at our institution from 2008 to 2022. The 20 most recent examinations constituted the test dataset, to mimic pseudoprospective enrolment. The remaining ones constituted the training dataset to which eight normal renal MRIs were added. Kidneys and cysts ground truth segmentations were performed on coronal T2-weighted images by a junior radiologist supervised by an experienced radiologist. Kidneys and cysts of the 20 test MRIs were segmented by the algorithm and three independent human raters. Segmentations were compared using overlap metrics. The total kidney volume (TKV), total cystic volume (TCV), and cystic index (TCV divided by TKV) were compared using Bland-Altman analysis.</p><p><strong>Results: </strong>We included 164 ADPKD patients. Dice similarity coefficients ranged from 85.9% to 87.4% between the algorithms and the raters' segmentations and from 84.2% to 86.2% across raters' segmentations. For TCV assessment, the biases ± standard deviations (SD) were 3-19 ± 137-151 mL between the algorithm and the raters, and 22-45 ± 49-57 mL across raters. The algorithm underestimated TKV and TCV in two outliers with TCV > 2800 mL. For cystic index assessment, the biases ± SD were 2.5-6.9% ± 6.7-8.3% between the algorithm and the raters, and 2.1-9.4 ± 7.4-11.6% across raters.</p><p><strong>Conclusion: </strong>The algorithm's performance fell within the range of inter-rater variability, but large TKV and TCV were underestimated.</p><p><strong>Relevance statement: </strong>Accurate automated segmentation of the renal cysts will enable the large-scale evaluation of the prognostic value of TCV and cystic index in ADPKD patients. If these biomarkers are prognostic, then automated segmentation will facilitate their use in daily routine.</p><p><strong>Key points: </strong>Cystic volume is an emerging biomarker in ADPKD. The algorithm's performance in segmenting kidneys and cysts fell within interrater variability. The segmentation of very large cysts, under-represented in the training dataset, needs improvement.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"122"},"PeriodicalIF":3.7,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525362/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142548113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
European Radiology Experimental
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1