首页 > 最新文献

BMC Medical Imaging最新文献

英文 中文
Clinical study of colorViz fusion image vascular grading based on multi-phase CTA reconstruction in acute ischemic stroke. 基于多期CTA重建的colorViz融合图像血管分级在急性缺血性脑卒中中的临床研究。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-21 DOI: 10.1186/s12880-024-01490-3
Qi Wang, Qiang Wang, Yunfa Xu, Xue Li, Dingbin Zhou, Xiaotong Sun, Bo Feng

Objective: This study aimed to evaluate the diagnostic value of ColorViz fused images from multi-phase computed tomography angiography (mCTA) using GE Healthcare's FastStroke software for newly diagnosed cerebral infarctions in patients with acute ischemic stroke (AIS).

Methods: A total of 106 AIS patients with unilateral anterior circulation occlusion were prospectively enrolled. All patients underwent mCTA scans during the arterial peak phase, venous peak phase, and venous late phase. The vascular information from these mCTA phases was combined into a time-varying color-coded image using GE Healthcare's FastStroke software. All participants also underwent magnetic resonance diffusion-weighted imaging (MR-DWI) within three days. The diagnostic capability of the mCTA ColorViz fusion images for identifying newly diagnosed intracranial infarction was assessed using MR-DWI as the gold standard, focusing on the degree of delayed vascular perfusion and the number of visible blood vessels.

Results: The mCTA ColorViz fusion images revealed ischemic changes in brain tissue, demonstrating a sensitivity of 88.7% for superficial infarctions and 48.5% for deep infarctions. Additionally, the subjective vascular grading score of the mCTA ColorViz fusion images showed a strong negative correlation with the infarct area identified by MR-DWI (r = - 0.6, P < 0.001).

Conclusion: The mCTA ColorViz fusion images produced by FastStroke software provide valuable diagnostic insights for newly diagnosed cerebral infarction in AIS patients. The sensitivity of these images is notably higher for superficial infarctions compared to deep ones. This technique allows for relatively accurate detection of the ischemic extent and the likelihood of infarction in the superficial regions where lesions are located.

目的:本研究旨在评估使用GE医疗的FastStroke软件对急性缺血性脑卒中(AIS)患者新诊断脑梗死的多期计算机断层血管造影(mCTA)的ColorViz融合图像的诊断价值。方法:前瞻性纳入106例单侧前循环闭塞的AIS患者。所有患者均在动脉峰值期、静脉峰值期和静脉晚期进行了mCTA扫描。使用GE医疗的FastStroke软件,将这些mCTA阶段的血管信息合并成随时间变化的彩色编码图像。所有参与者均在三天内接受磁共振弥散加权成像(MR-DWI)检查。以MR-DWI为金标准,评估mCTA ColorViz融合图像对新诊断颅内梗死的诊断能力,重点关注血管灌注延迟程度和可见血管数量。结果:mCTA ColorViz融合图像显示脑组织缺血改变,对浅表梗死的敏感性为88.7%,对深部梗死的敏感性为48.5%。此外,mCTA ColorViz融合图像的主观血管分级评分与MR-DWI识别的梗死面积呈强负相关(r = - 0.6, P)。结论:FastStroke软件生成的mCTA ColorViz融合图像为AIS患者新诊断的脑梗死提供了有价值的诊断见解。这些图像对浅表梗死的灵敏度明显高于深部梗死。这种技术可以相对准确地检测出病变所在的浅表区域的缺血程度和梗死的可能性。
{"title":"Clinical study of colorViz fusion image vascular grading based on multi-phase CTA reconstruction in acute ischemic stroke.","authors":"Qi Wang, Qiang Wang, Yunfa Xu, Xue Li, Dingbin Zhou, Xiaotong Sun, Bo Feng","doi":"10.1186/s12880-024-01490-3","DOIUrl":"10.1186/s12880-024-01490-3","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to evaluate the diagnostic value of ColorViz fused images from multi-phase computed tomography angiography (mCTA) using GE Healthcare's FastStroke software for newly diagnosed cerebral infarctions in patients with acute ischemic stroke (AIS).</p><p><strong>Methods: </strong>A total of 106 AIS patients with unilateral anterior circulation occlusion were prospectively enrolled. All patients underwent mCTA scans during the arterial peak phase, venous peak phase, and venous late phase. The vascular information from these mCTA phases was combined into a time-varying color-coded image using GE Healthcare's FastStroke software. All participants also underwent magnetic resonance diffusion-weighted imaging (MR-DWI) within three days. The diagnostic capability of the mCTA ColorViz fusion images for identifying newly diagnosed intracranial infarction was assessed using MR-DWI as the gold standard, focusing on the degree of delayed vascular perfusion and the number of visible blood vessels.</p><p><strong>Results: </strong>The mCTA ColorViz fusion images revealed ischemic changes in brain tissue, demonstrating a sensitivity of 88.7% for superficial infarctions and 48.5% for deep infarctions. Additionally, the subjective vascular grading score of the mCTA ColorViz fusion images showed a strong negative correlation with the infarct area identified by MR-DWI (r = - 0.6, P < 0.001).</p><p><strong>Conclusion: </strong>The mCTA ColorViz fusion images produced by FastStroke software provide valuable diagnostic insights for newly diagnosed cerebral infarction in AIS patients. The sensitivity of these images is notably higher for superficial infarctions compared to deep ones. This technique allows for relatively accurate detection of the ischemic extent and the likelihood of infarction in the superficial regions where lesions are located.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"25"},"PeriodicalIF":2.9,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11748880/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142999253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Which PSMA PET/CT interpretation criteria most effectively diagnose prostate cancer? a retrospective cohort study. 哪种PSMA PET/CT判读标准最有效诊断前列腺癌?回顾性队列研究。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-20 DOI: 10.1186/s12880-025-01557-9
Le Ma, Yaxin Hao, Luoping Zhai, Wanchun Zhang, Xiaoming Cao, Kaiyuan Jia

Background: PSMA PET/CT emerges as a pivotal technology in the diagnostic landscape of prostate cancer (PCa). It offers a suite of imaging interpretation criteria, notably the maximum standardized uptake value (SUVmax), the molecular imaging prostate-specific membrane antigen score (miPSMA score), and the PSMA reporting and data system (PSMA-RADS). Identifying the most valuable criteria for diagnosing PCa and standardizing imaging interpretation across various tracers is an unresolved question. Our study endeavors to pinpoint the most optimal criteria to enhance the precision of PCa diagnosis, encompassing clinically significant PCa (csPCa), by evaluating the consistency and diagnostic accuracy of these three criteria using two [18F]-labeled PSMA tracers.

Method: This retrospective analysis spans a five-year period, focusing on patients with clinically suspected or newly diagnosed, treatment-naïve PCa who underwent 18F-PSMA PET/CT. The study is bifurcated into two segments: 1.A direct comparison assessing the consistency in SUVmax, miPSMA scores, and PSMA-RADS among PSMA PET/CT tracers ([18F]DCFPyL and [18F]PSMA-1007) for prostate foci in 24 patients. 2. An analysis of the diagnostic accuracy of these three criteria for both PCa and csPCa across 55 [18F]DCFPyL and 65 [18F]PSMA-1007 PET/CT scans, respectively.

Results: 1.Our head-to-head study reveals that SUVmax and miPSMA score exhibit near-perfect consistency, with PSMA-RADS demonstrating substantial consistency. 2. The diagnostic accuracy ranking, considering both PCa and csPCa, stands as miPSMA score ≈ SUVmax > PSMA-RADS for [18F]DCFPyL PET/CT, contrasting with miPSMA score > SUVmax ≈ PSMA-RADS for [18F]PSMA-1007 PET/CT.

Conclusion: The miPSMA score outperforms SUVmax and PSMA-RADS in terms of inter-tracer consistency and diagnostic accuracy for the detection of PCa, including csPCa, when comparing [18F]DCFPyL and [18F]PSMA-1007 PET/CT scans. This underscores the miPSMA score's potential as a robust criterion for PCa and csPCa diagnosis, holding substantial promise for refining clinical decision-making and patient management strategies.

Clinical trial number: not applicable.

背景:PSMA PET/CT成为前列腺癌诊断领域的关键技术。它提供了一套成像解释标准,特别是最大标准化摄取值(SUVmax),前列腺特异性膜抗原分子成像评分(miPSMA评分)和PSMA报告和数据系统(PSMA- rads)。确定诊断PCa的最有价值的标准和标准化各种示踪剂的成像解释是一个未解决的问题。我们的研究试图通过使用两种[18F]标记的PSMA示踪剂评估这三个标准的一致性和诊断准确性,从而确定提高PCa诊断精度的最优标准,包括临床显著性PCa (csPCa)。方法:回顾性分析为期5年,重点关注临床疑似或新诊断的treatment-naïve PCa患者,并接受18F-PSMA PET/CT检查。本研究分为两个部分:1。对24例前列腺病灶的PSMA PET/CT示踪剂([18F]DCFPyL和[18F]PSMA-1007)的SUVmax、miPSMA评分和PSMA- rads的一致性进行直接比较。2. 分析这三个标准在55例[18F]DCFPyL和65例[18F]PSMA-1007 PET/CT扫描中对PCa和csPCa的诊断准确性。结果:1。我们的对比研究表明,SUVmax和miPSMA得分表现出近乎完美的一致性,PSMA-RADS表现出实质性的一致性。2. 考虑PCa和csPCa的诊断准确性排名为[18F]DCFPyL PET/CT的miPSMA评分≈SUVmax > pma - rads,与[18F]PSMA-1007 PET/CT的miPSMA评分> SUVmax≈pma - rads形成对比。结论:当比较[18F]DCFPyL和[18F]PSMA-1007 PET/CT扫描时,miPSMA评分在检测PCa(包括csPCa)的示踪物一致性和诊断准确性方面优于SUVmax和PSMA-RADS。这强调了miPSMA评分作为PCa和csPCa诊断的可靠标准的潜力,在改进临床决策和患者管理策略方面有着巨大的希望。临床试验号:不适用。
{"title":"Which PSMA PET/CT interpretation criteria most effectively diagnose prostate cancer? a retrospective cohort study.","authors":"Le Ma, Yaxin Hao, Luoping Zhai, Wanchun Zhang, Xiaoming Cao, Kaiyuan Jia","doi":"10.1186/s12880-025-01557-9","DOIUrl":"10.1186/s12880-025-01557-9","url":null,"abstract":"<p><strong>Background: </strong>PSMA PET/CT emerges as a pivotal technology in the diagnostic landscape of prostate cancer (PCa). It offers a suite of imaging interpretation criteria, notably the maximum standardized uptake value (SUVmax), the molecular imaging prostate-specific membrane antigen score (miPSMA score), and the PSMA reporting and data system (PSMA-RADS). Identifying the most valuable criteria for diagnosing PCa and standardizing imaging interpretation across various tracers is an unresolved question. Our study endeavors to pinpoint the most optimal criteria to enhance the precision of PCa diagnosis, encompassing clinically significant PCa (csPCa), by evaluating the consistency and diagnostic accuracy of these three criteria using two [<sup>18</sup>F]-labeled PSMA tracers.</p><p><strong>Method: </strong>This retrospective analysis spans a five-year period, focusing on patients with clinically suspected or newly diagnosed, treatment-naïve PCa who underwent <sup>18</sup>F-PSMA PET/CT. The study is bifurcated into two segments: 1.A direct comparison assessing the consistency in SUVmax, miPSMA scores, and PSMA-RADS among PSMA PET/CT tracers ([<sup>18</sup>F]DCFPyL and [<sup>18</sup>F]PSMA-1007) for prostate foci in 24 patients. 2. An analysis of the diagnostic accuracy of these three criteria for both PCa and csPCa across 55 [<sup>18</sup>F]DCFPyL and 65 [<sup>18</sup>F]PSMA-1007 PET/CT scans, respectively.</p><p><strong>Results: </strong>1.Our head-to-head study reveals that SUVmax and miPSMA score exhibit near-perfect consistency, with PSMA-RADS demonstrating substantial consistency. 2. The diagnostic accuracy ranking, considering both PCa and csPCa, stands as miPSMA score ≈ SUVmax > PSMA-RADS for [<sup>18</sup>F]DCFPyL PET/CT, contrasting with miPSMA score > SUVmax ≈ PSMA-RADS for [<sup>18</sup>F]PSMA-1007 PET/CT.</p><p><strong>Conclusion: </strong>The miPSMA score outperforms SUVmax and PSMA-RADS in terms of inter-tracer consistency and diagnostic accuracy for the detection of PCa, including csPCa, when comparing [<sup>18</sup>F]DCFPyL and [<sup>18</sup>F]PSMA-1007 PET/CT scans. This underscores the miPSMA score's potential as a robust criterion for PCa and csPCa diagnosis, holding substantial promise for refining clinical decision-making and patient management strategies.</p><p><strong>Clinical trial number: </strong>not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"23"},"PeriodicalIF":2.9,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11749428/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142999409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Association between non-alcoholic fatty liver disease and progression of abdominal aortic aneurysm: a multicenter study. 非酒精性脂肪性肝病与腹主动脉瘤进展的关系:一项多中心研究
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-20 DOI: 10.1186/s12880-025-01559-7
Ximing Wang, Jingxiang Sun, Na Chang, Menghan Liu, Shuai Zhang

Background: The purpose of our study was to investigate the association between non-alcoholic fatty liver disease (NAFLD) and abdominal aortic aneurysms (AAA) progression using non-enhanced computed tomography (CT) and CT angiography (CTA).

Methods: Patients with AAA and age- and sex-matched healthy subjects who underwent abdominal CTA and non-enhanced CT examination between January 2015 and January 2023 from four hospitals were retrospectively analyzed. Patients with AAA were divided into progression (growth rate > 10 mL/year) and non-progression groups, as well as those with NAFLD and without NAFLD, based on abdominal CT results. The Kaplan-Meier and Cox regression were used to investigate the association between NAFLD and AAA progression.

Results: A total of 151 patients with AAA (mean age: 69.1 ± 10.5 years old, 133 men) were included, among which 66 patients (43.7%) had NAFLD. During a median of 10.7 months (6.0-76.0 months), 57 patients (37.7%) had AAA progression. The prevalence of NAFLD was significantly higher in the AAA group compared to the control group (43.7% vs. 31.1%, p = 0.024). Multivariable regression analysis revealed that the NAFLD was independently associated with AAA progression (HR, 4.28; 95% CI, 2.20-8.31; p < 0.001). The area under curve of combined NAFLD and AAA maximal diameter was 0.857 for predicting AAA progression.

Conclusions: NAFLD on non-enhanced CT is an independent predictor of AAA progression. It can improve the diagnostic efficacy of predicting the progression of abdominal aortic aneurysms.

Clinical trial number: Not applicable. This research is a retrospective analysis.

背景:本研究的目的是利用非增强计算机断层扫描(CT)和CT血管造影(CTA)研究非酒精性脂肪性肝病(NAFLD)与腹主动脉瘤(AAA)进展之间的关系。方法:回顾性分析2015年1月至2023年1月4家医院行腹部CTA和非增强CT检查的AAA患者和年龄、性别匹配的健康受试者。根据腹部CT结果,将AAA患者分为进展组(生长速度bbb10 mL/年)和非进展组,以及NAFLD和非NAFLD组。应用Kaplan-Meier和Cox回归分析NAFLD与AAA进展之间的关系。结果:共纳入151例AAA患者(平均年龄:69.1±10.5岁,男性133例),其中66例(43.7%)合并NAFLD。在中位10.7个月(6.0-76.0个月)期间,57例患者(37.7%)发生AAA进展。AAA组NAFLD患病率明显高于对照组(43.7%比31.1%,p = 0.024)。多变量回归分析显示NAFLD与AAA进展独立相关(HR, 4.28;95% ci, 2.20-8.31;结论:非增强CT显示的NAFLD是AAA进展的独立预测因子。可提高腹主动脉瘤进展的诊断效率。临床试验号:不适用。本研究为回顾性分析。
{"title":"Association between non-alcoholic fatty liver disease and progression of abdominal aortic aneurysm: a multicenter study.","authors":"Ximing Wang, Jingxiang Sun, Na Chang, Menghan Liu, Shuai Zhang","doi":"10.1186/s12880-025-01559-7","DOIUrl":"10.1186/s12880-025-01559-7","url":null,"abstract":"<p><strong>Background: </strong>The purpose of our study was to investigate the association between non-alcoholic fatty liver disease (NAFLD) and abdominal aortic aneurysms (AAA) progression using non-enhanced computed tomography (CT) and CT angiography (CTA).</p><p><strong>Methods: </strong>Patients with AAA and age- and sex-matched healthy subjects who underwent abdominal CTA and non-enhanced CT examination between January 2015 and January 2023 from four hospitals were retrospectively analyzed. Patients with AAA were divided into progression (growth rate > 10 mL/year) and non-progression groups, as well as those with NAFLD and without NAFLD, based on abdominal CT results. The Kaplan-Meier and Cox regression were used to investigate the association between NAFLD and AAA progression.</p><p><strong>Results: </strong>A total of 151 patients with AAA (mean age: 69.1 ± 10.5 years old, 133 men) were included, among which 66 patients (43.7%) had NAFLD. During a median of 10.7 months (6.0-76.0 months), 57 patients (37.7%) had AAA progression. The prevalence of NAFLD was significantly higher in the AAA group compared to the control group (43.7% vs. 31.1%, p = 0.024). Multivariable regression analysis revealed that the NAFLD was independently associated with AAA progression (HR, 4.28; 95% CI, 2.20-8.31; p < 0.001). The area under curve of combined NAFLD and AAA maximal diameter was 0.857 for predicting AAA progression.</p><p><strong>Conclusions: </strong>NAFLD on non-enhanced CT is an independent predictor of AAA progression. It can improve the diagnostic efficacy of predicting the progression of abdominal aortic aneurysms.</p><p><strong>Clinical trial number: </strong>Not applicable. This research is a retrospective analysis.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"24"},"PeriodicalIF":2.9,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11749205/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142999252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors. 基于内镜超声检查的胰腺神经内分泌肿瘤病理分级预测机器学习超声组学模型。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-18 DOI: 10.1186/s12880-025-01555-x
Shuangyang Mo, Cheng Huang, Yingwei Wang, Shanyu Qin

Objectives: The objective is to develop and validate intratumoral and peritumoral ultrasomics models utilizing endoscopic ultrasonography (EUS) to predict pathological grading in pancreatic neuroendocrine tumors (PNETs).

Methods: Eighty-one patients, including 51 with grade 1 PNETs and 30 with grade 2/3 PNETs, were included in this retrospective study after confirmation through pathological examination. The patients were randomly allocated to the training or test group in a 6:4 ratio. Univariate and multivariate logistic regression were used for screening clinical and ultrasonic characteristics. Ultrasomics is ultrasound-based radiomics. Ultrasomics features were extracted from both the intratumoral and peritumoral regions of conventional EUS images. Subsequently, the dimensionality of these radiomics features was reduced using the least absolute shrinkage and selection operator (LASSO) algorithm. A machine learning algorithm, namely multilayer perception (MLP), was employed to construct prediction models using only the nonzero coefficient features and retained clinical features, respectively.

Results: One hundred seven ultrasomics features based on EUS were extracted, and only features with nonzero coefficients were ultimately retained. Among all the models, the combined ultrasomics model achieved the greatest performance, with an AUC of 0.858 (95% CI, 0.7512 - 0.9642) in the training group and 0.842 (95% CI, 0.7061 - 0.9785) in the test group. A calibration curve and a decision curve analysis (DCA) also demonstrated its accuracy and utility.

Conclusions: The integrated model using EUS ultrasomics features from intratumoral and peritumoral tumors accurately predicts PNETs' pathological grades pre-surgery, aiding personalized treatment planning.

Trial registration: ChiCTR2400091906.

目的:目的是建立和验证利用超声内镜(EUS)预测胰腺神经内分泌肿瘤(PNETs)病理分级的瘤内和瘤周超声组学模型。方法:经病理证实,81例PNETs为1级51例,2/3级30例,纳入回顾性研究。患者按6:4的比例随机分为训练组和试验组。单因素和多因素logistic回归用于筛选临床和超声特征。超声组学是基于超声的放射组学。超声组学特征从常规EUS图像的肿瘤内和肿瘤周围区域提取。随后,使用最小绝对收缩和选择算子(LASSO)算法降低这些放射组学特征的维数。采用多层感知(multilayer perception, MLP)机器学习算法,分别仅利用非零系数特征和保留的临床特征构建预测模型。结果:基于EUS的超声组学特征提取了107个,最终只保留了非零系数的特征。在所有模型中,联合超声组学模型的表现最好,训练组的AUC为0.858 (95% CI, 0.7512 ~ 0.9642),试验组的AUC为0.842 (95% CI, 0.7061 ~ 0.9785)。标定曲线和决策曲线分析(DCA)也证明了该方法的准确性和实用性。结论:利用EUS肿瘤内及肿瘤周围超声组学特征的综合模型可准确预测术前PNETs的病理分级,有助于个性化治疗计划。试验注册:ChiCTR2400091906。
{"title":"Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors.","authors":"Shuangyang Mo, Cheng Huang, Yingwei Wang, Shanyu Qin","doi":"10.1186/s12880-025-01555-x","DOIUrl":"10.1186/s12880-025-01555-x","url":null,"abstract":"<p><strong>Objectives: </strong>The objective is to develop and validate intratumoral and peritumoral ultrasomics models utilizing endoscopic ultrasonography (EUS) to predict pathological grading in pancreatic neuroendocrine tumors (PNETs).</p><p><strong>Methods: </strong>Eighty-one patients, including 51 with grade 1 PNETs and 30 with grade 2/3 PNETs, were included in this retrospective study after confirmation through pathological examination. The patients were randomly allocated to the training or test group in a 6:4 ratio. Univariate and multivariate logistic regression were used for screening clinical and ultrasonic characteristics. Ultrasomics is ultrasound-based radiomics. Ultrasomics features were extracted from both the intratumoral and peritumoral regions of conventional EUS images. Subsequently, the dimensionality of these radiomics features was reduced using the least absolute shrinkage and selection operator (LASSO) algorithm. A machine learning algorithm, namely multilayer perception (MLP), was employed to construct prediction models using only the nonzero coefficient features and retained clinical features, respectively.</p><p><strong>Results: </strong>One hundred seven ultrasomics features based on EUS were extracted, and only features with nonzero coefficients were ultimately retained. Among all the models, the combined ultrasomics model achieved the greatest performance, with an AUC of 0.858 (95% CI, 0.7512 - 0.9642) in the training group and 0.842 (95% CI, 0.7061 - 0.9785) in the test group. A calibration curve and a decision curve analysis (DCA) also demonstrated its accuracy and utility.</p><p><strong>Conclusions: </strong>The integrated model using EUS ultrasomics features from intratumoral and peritumoral tumors accurately predicts PNETs' pathological grades pre-surgery, aiding personalized treatment planning.</p><p><strong>Trial registration: </strong>ChiCTR2400091906.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"22"},"PeriodicalIF":2.9,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11743008/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142999387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis. 利用人工智能驱动的放射组学分析开发CTR≥50%的良恶性肺结节临床预测模型。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-17 DOI: 10.1186/s12880-024-01533-9
Wensong Shi, Yuzhui Hu, Guotao Chang, He Qian, Yulun Yang, Yinsen Song, Zhengpan Wei, Liang Gao, Hang Yi, Sikai Wu, Kun Wang, Huandong Huo, Shuaibo Wang, Yousheng Mao, Siyuan Ai, Liang Zhao, Xiangnan Li, Huiyu Zheng

Objective: In clinical practice, diagnosing the benignity and malignancy of solid-component-predominant pulmonary nodules is challenging, especially when 3D consolidation-to-tumor ratio (CTR) ≥ 50%, as malignant ones are more invasive. This study aims to develop and validate an AI-driven radiomics prediction model for such nodules to enhance diagnostic accuracy.

Methods: Data of 2,591 pulmonary nodules from five medical centers (Zhengzhou People's Hospital, etc.) were collected. Applying exclusion criteria, 370 nodules (78 benign, 292 malignant) with 3D CTR ≥ 50% were selected and randomly split 7:3 into training and validation cohorts. Using R programming, Lasso regression with 10-fold cross-validation filtered features, followed by univariate and multivariate logistic regression to construct the model. Its efficacy was evaluated by ROC, DCA curves and calibration plots.

Results: Lasso regression picked 18 non-zero coefficients from 108 features. Three significant factors-patient age, solid component volume and mean CT value-were identified. The logistic regression equation was formulated. In the training set, the ROC AUC was 0.721 (95%CI: 0.642-0.801); in the validation set, AUC was 0.757 (95%CI: 0.632-0.881), showing the model's stability and predictive ability.

Conclusion: The model has moderate accuracy in differentiating benign from malignant 3D CTR ≥ 50% nodules, holding clinical potential. Future efforts could explore more to improve its precision and value.

Clinical trial number: Not applicable.

目的:在临床实践中,实性成分为主的肺结节的良恶性诊断具有挑战性,特别是当三维实变与肿瘤比(CTR)≥50%时,因为恶性结节更具侵袭性。本研究旨在开发和验证人工智能驱动的此类结节放射组学预测模型,以提高诊断准确性。方法:收集郑州市人民医院等5个医疗中心2591例肺结节的资料。采用排除标准,选择3D CTR≥50%的370例结节(78例为良性,292例为恶性),按7:3随机分为训练组和验证组。使用R编程,Lasso回归与10倍交叉验证过滤特征,然后单变量和多变量逻辑回归构建模型。采用ROC曲线、DCA曲线和标定图评价其疗效。结果:Lasso回归从108个特征中选出18个非零系数。确定了患者年龄、固相成分体积和CT平均值三个重要因素。建立了logistic回归方程。在训练集中,ROC AUC为0.721 (95%CI: 0.642-0.801);在验证集中,AUC为0.757 (95%CI: 0.632 ~ 0.881),表明模型具有较好的稳定性和预测能力。结论:该模型对良恶性结节鉴别准确率中等,三维CTR≥50%,具有临床应用价值。未来的努力可以探索更多,以提高其精度和价值。临床试验号:不适用。
{"title":"Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis.","authors":"Wensong Shi, Yuzhui Hu, Guotao Chang, He Qian, Yulun Yang, Yinsen Song, Zhengpan Wei, Liang Gao, Hang Yi, Sikai Wu, Kun Wang, Huandong Huo, Shuaibo Wang, Yousheng Mao, Siyuan Ai, Liang Zhao, Xiangnan Li, Huiyu Zheng","doi":"10.1186/s12880-024-01533-9","DOIUrl":"10.1186/s12880-024-01533-9","url":null,"abstract":"<p><strong>Objective: </strong>In clinical practice, diagnosing the benignity and malignancy of solid-component-predominant pulmonary nodules is challenging, especially when 3D consolidation-to-tumor ratio (CTR) ≥ 50%, as malignant ones are more invasive. This study aims to develop and validate an AI-driven radiomics prediction model for such nodules to enhance diagnostic accuracy.</p><p><strong>Methods: </strong>Data of 2,591 pulmonary nodules from five medical centers (Zhengzhou People's Hospital, etc.) were collected. Applying exclusion criteria, 370 nodules (78 benign, 292 malignant) with 3D CTR ≥ 50% were selected and randomly split 7:3 into training and validation cohorts. Using R programming, Lasso regression with 10-fold cross-validation filtered features, followed by univariate and multivariate logistic regression to construct the model. Its efficacy was evaluated by ROC, DCA curves and calibration plots.</p><p><strong>Results: </strong>Lasso regression picked 18 non-zero coefficients from 108 features. Three significant factors-patient age, solid component volume and mean CT value-were identified. The logistic regression equation was formulated. In the training set, the ROC AUC was 0.721 (95%CI: 0.642-0.801); in the validation set, AUC was 0.757 (95%CI: 0.632-0.881), showing the model's stability and predictive ability.</p><p><strong>Conclusion: </strong>The model has moderate accuracy in differentiating benign from malignant 3D CTR ≥ 50% nodules, holding clinical potential. Future efforts could explore more to improve its precision and value.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"21"},"PeriodicalIF":2.9,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11742483/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142999342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Value of combining lung ultrasound score with oxygenation and functional indices in determining weaning timing for critically ill pediatric patients. 肺超声评分与氧合及功能指标结合在小儿危重症患者判断脱机时机中的价值。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-16 DOI: 10.1186/s12880-025-01552-0
Ximeng Hao, Hongnian Duan, Qiushuang Li, Dan Wang, Xin Yin, Zhiyan Di, Shanshan Du

Objective: This study aims to investigate the predictive effectiveness of bedside lung ultrasound score (LUS) in conjunction with rapid shallow breathing index (RSBI) and oxygenation index (P/F ratio) for weaning pediatric patients from mechanical ventilation.

Methods: This was a retrospective study. Eighty-two critically ill pediatric patients, who were admitted to the Pediatric Intensive Care Unit (PICU) and underwent mechanical ventilation from January 2023 to April 2024, were enrolled in this study. Prior to weaning, all patients underwent bedside LUS, with concurrent measurements of their RSBI and P/F ratio. Patients were followed up for weaning outcomes and categorized into successful and failed weaning groups based on these outcomes. Differences in clinical baseline data, LUS scores, RSBI and P/F ratios between the two groups were compared. The predictive value of LUS scores, RSBI and P/F ratios for weaning outcomes was assessed using receiver operating characteristic (ROC) curves and the area under the curve (AUC).

Results: Out of the 82 subjects, 73 (89.02%) successfully weaned, while 9 (10.98%) failed. No statistically significant differences were observed in age, gender, BMI, and respiratory failure-related comorbidities between the successful and failed weaning groups (P > 0.05). Compared to the successful weaning group, the failed weaning group exhibited longer hospital and intubation durations, higher LUS and RSBI, and lower P/F ratios, with statistically significant differences (P < 0.05). An LUS score ≥ 15.5 was identified as the optimal cutoff for predicting weaning failure, with superior predictive power compared to RSBI and P/F ratios. The combined use of LUS, RSBI and P/F ratios for predicting weaning outcomes yielded a larger area under the curve, indicating higher predictive efficacy.

Conclusion: The LUS demonstrates a high predictive value for the weaning outcomes of pediatric patients on mechanical ventilation.

目的:本研究旨在探讨床边肺超声评分(LUS)联合快速浅呼吸指数(RSBI)和氧合指数(P/F比)对脱机儿童机械通气患者的预测效果。方法:回顾性研究。本研究纳入了2023年1月至2024年4月期间入住儿科重症监护病房(PICU)并接受机械通气的82例危重儿科患者。在断奶之前,所有患者都进行了床边LUS,同时测量了他们的RSBI和P/F比。随访患者的断奶结果,并根据这些结果分为成功和失败的断奶组。比较两组临床基线数据、LUS评分、RSBI和P/F比值的差异。采用受试者工作特征(ROC)曲线和曲线下面积(AUC)评估LUS评分、RSBI和P/F比对断奶结局的预测价值。结果:82例患者中,成功断奶73例(89.02%),失败9例(10.98%)。成功断奶组与失败断奶组在年龄、性别、BMI、呼吸衰竭相关合并症方面差异无统计学意义(P < 0.05)。与脱机成功组相比,脱机失败组住院时间和插管时间更长,LUS和RSBI更高,P/F比更低,差异有统计学意义(P)。结论:LUS对儿童机械通气患者的脱机结局具有较高的预测价值。
{"title":"Value of combining lung ultrasound score with oxygenation and functional indices in determining weaning timing for critically ill pediatric patients.","authors":"Ximeng Hao, Hongnian Duan, Qiushuang Li, Dan Wang, Xin Yin, Zhiyan Di, Shanshan Du","doi":"10.1186/s12880-025-01552-0","DOIUrl":"10.1186/s12880-025-01552-0","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to investigate the predictive effectiveness of bedside lung ultrasound score (LUS) in conjunction with rapid shallow breathing index (RSBI) and oxygenation index (P/F ratio) for weaning pediatric patients from mechanical ventilation.</p><p><strong>Methods: </strong>This was a retrospective study. Eighty-two critically ill pediatric patients, who were admitted to the Pediatric Intensive Care Unit (PICU) and underwent mechanical ventilation from January 2023 to April 2024, were enrolled in this study. Prior to weaning, all patients underwent bedside LUS, with concurrent measurements of their RSBI and P/F ratio. Patients were followed up for weaning outcomes and categorized into successful and failed weaning groups based on these outcomes. Differences in clinical baseline data, LUS scores, RSBI and P/F ratios between the two groups were compared. The predictive value of LUS scores, RSBI and P/F ratios for weaning outcomes was assessed using receiver operating characteristic (ROC) curves and the area under the curve (AUC).</p><p><strong>Results: </strong>Out of the 82 subjects, 73 (89.02%) successfully weaned, while 9 (10.98%) failed. No statistically significant differences were observed in age, gender, BMI, and respiratory failure-related comorbidities between the successful and failed weaning groups (P > 0.05). Compared to the successful weaning group, the failed weaning group exhibited longer hospital and intubation durations, higher LUS and RSBI, and lower P/F ratios, with statistically significant differences (P < 0.05). An LUS score ≥ 15.5 was identified as the optimal cutoff for predicting weaning failure, with superior predictive power compared to RSBI and P/F ratios. The combined use of LUS, RSBI and P/F ratios for predicting weaning outcomes yielded a larger area under the curve, indicating higher predictive efficacy.</p><p><strong>Conclusion: </strong>The LUS demonstrates a high predictive value for the weaning outcomes of pediatric patients on mechanical ventilation.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"19"},"PeriodicalIF":2.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11740644/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142999395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ultrasonographic examination of the maturational effect of maternal vitamin D use on fetal clavicle bone development. 超声检查母体维生素D使用对胎儿锁骨发育的影响。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-16 DOI: 10.1186/s12880-025-01558-8
Fatma Ozdemir, Banu Acmaz, Fatma Latifoglu, Sabahattin Muhtaroglu, Nefise Tanrıdan Okcu, Gokhan Acmaz, Iptisam Ipek Muderris

Aim: This study aimed to evaluate the effect of maternal vitamin D use during intrauterine life on fetal bone development using ultrasonographic image processing techniques.

Materials and methods: We evaluated 52 pregnant women receiving vitamin D supplementation and 50 who refused vitamin D supplementation. Ultrasonographic imaging was performed on the fetal clavicle at 37-40 weeks of gestation. The fetal clavicle images were compared with adult male clavicle images. The texture features obtained from these images were used for analysis.

Results: No difference was observed in bone formation and destruction markers between the two groups. However, the texture analysis of ultrasonographic images revealed similarities in the characteristics of fetal clavicles in pregnant women receiving vitamin D supplementation and those of adult male clavicles.

Conclusions: Vitamin D supplementation in pregnancy has significant positive effects on fetal bone maturation besides contributing to maternal bone health. Texture feature analyses using ultrasonographic images successfully demonstrated fetal bone maturation.

目的:利用超声图像处理技术,探讨孕期母体维生素D的使用对胎儿骨骼发育的影响。材料和方法:我们评估了52名补充维生素D的孕妇和50名拒绝补充维生素D的孕妇。在妊娠37 ~ 40周对胎儿锁骨进行超声成像。将胎儿锁骨图像与成年男性锁骨图像进行比较。利用这些图像得到的纹理特征进行分析。结果:两组骨形成及破坏指标无明显差异。然而,超声图像的纹理分析显示,补充维生素D的孕妇的胎儿锁骨特征与成年男性的锁骨相似。结论:妊娠期补充维生素D对胎儿骨成熟有显著的积极作用,并有助于产妇骨骼健康。超声图像的纹理特征分析成功地证明了胎儿骨的成熟。
{"title":"Ultrasonographic examination of the maturational effect of maternal vitamin D use on fetal clavicle bone development.","authors":"Fatma Ozdemir, Banu Acmaz, Fatma Latifoglu, Sabahattin Muhtaroglu, Nefise Tanrıdan Okcu, Gokhan Acmaz, Iptisam Ipek Muderris","doi":"10.1186/s12880-025-01558-8","DOIUrl":"10.1186/s12880-025-01558-8","url":null,"abstract":"<p><strong>Aim: </strong>This study aimed to evaluate the effect of maternal vitamin D use during intrauterine life on fetal bone development using ultrasonographic image processing techniques.</p><p><strong>Materials and methods: </strong>We evaluated 52 pregnant women receiving vitamin D supplementation and 50 who refused vitamin D supplementation. Ultrasonographic imaging was performed on the fetal clavicle at 37-40 weeks of gestation. The fetal clavicle images were compared with adult male clavicle images. The texture features obtained from these images were used for analysis.</p><p><strong>Results: </strong>No difference was observed in bone formation and destruction markers between the two groups. However, the texture analysis of ultrasonographic images revealed similarities in the characteristics of fetal clavicles in pregnant women receiving vitamin D supplementation and those of adult male clavicles.</p><p><strong>Conclusions: </strong>Vitamin D supplementation in pregnancy has significant positive effects on fetal bone maturation besides contributing to maternal bone health. Texture feature analyses using ultrasonographic images successfully demonstrated fetal bone maturation.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"20"},"PeriodicalIF":2.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11740525/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142999392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Investigating resting-state functional connectivity changes within procedural memory network across neuropsychiatric disorders using fMRI. 利用功能磁共振成像研究神经精神疾病中程序记忆网络的静息状态功能连接变化。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-13 DOI: 10.1186/s12880-024-01527-7
Mahdi Mohammadkhanloo, Mohammad Pooyan, Hamid Sharini, Mitra Yousefpour

Background: Cognitive networks impairments are common in neuropsychiatric disorders like Attention Deficit Hyperactivity Disorder (ADHD), bipolar disorder (BD), and schizophrenia (SZ). While previous research has focused on specific brain regions, the role of the procedural memory as a type of long-term memory to examine cognitive networks impairments in these disorders remains unclear. This study investigates alterations in resting-state functional connectivity (rs-FC) within the procedural memory network to explore brain function associated with cognitive networks in patients with these disorders.

Methods: This study analyzed resting-state functional magnetic resonance imaging (rs-fMRI) data from 40 individuals with ADHD, 49 with BD, 50 with SZ, and 50 healthy controls (HCs). A procedural memory network was defined based on the selection of 34 regions of interest (ROIs) associated with the network in the Harvard-Oxford Cortical Structural Atlas (default atlas). Multivariate region of interest to region of interest connectivity (mRRC) was used to analyze the rs-FC between the defined network regions. Significant differences in rs-FC between patients and HCs were identified (P < 0.001).

Results: ADHD patients showed increased Cereb45 l - Cereb3 r rs-FC (p = 0.000067) and decreased Cereb1 l - Cereb6 l rs-FC (p = 0.00092). BD patients exhibited increased rs-FC between multiple regions, including Claustrum r - Caudate r (p = 0.00058), subthalamic nucleus r - Pallidum l (p = 0.00060), substantia nigra l - Cereb2 l (p = 0.00082), Cereb10 r - SMA r (p = 0.00086), and Cereb9 r - SMA l (p = 0.00093) as well as decreased rs-FC in subthalamic nucleus r - Cereb6 l (p = 0.00013) and Cereb9 r - Cereb9 l (p = 0.00033). SZ patients indicated increased Caudate r- putamen l rs-FC (p = 0.00057) and decreased rs-FC in subthalamic nucleus r - Cereb6 l (p = 0.000063), and Cereb1 r - subthalamic nucleus r (p = 0.00063).

Conclusions: This study found significant alterations in rs-FC within the procedural memory network in patients with ADHD, BD, and SZ compared to HCs. These findings suggest that disrupted rs-FC within this network may related to cognitive networks impairments observed in these disorders.

Clinical trial number: Not applicable.

背景:认知网络障碍在神经精神疾病中很常见,如注意缺陷多动障碍(ADHD)、双相情感障碍(BD)和精神分裂症(SZ)。虽然以前的研究主要集中在特定的大脑区域,但程序记忆作为一种长期记忆在这些疾病中检查认知网络损伤的作用仍不清楚。本研究研究了程序记忆网络中静息状态功能连接(rs-FC)的改变,以探索这些疾病患者与认知网络相关的脑功能。方法:本研究分析了40例ADHD患者、49例双相障碍患者、50例SZ患者和50例健康对照(hc)的静息状态功能磁共振成像(rs-fMRI)数据。程序记忆网络的定义是基于在哈佛-牛津皮质结构图谱(默认图谱)中选择与网络相关的34个感兴趣区域(roi)。使用多元感兴趣区域到感兴趣区域连接(mRRC)来分析定义网络区域之间的rs-FC。结果:ADHD患者的rs-FC升高(P = 0.000067),而Cereb1 1 - Cereb6 - rs-FC降低(P = 0.00092)。BD患者在丘脑屏状核-尾状核(p = 0.00058)、丘脑下核-白质核(p = 0.00060)、黑质-脑b1 (p = 0.00082)、大脑10核- SMA r (p = 0.00086)、大脑9核- SMA 1 (p = 0.00093)等多个区域之间的rs-FC升高,丘脑下核-大脑6 l (p = 0.00013)、大脑9核-大脑9 l (p = 0.00033)的rs-FC降低。SZ患者尾状核r-壳核l rs-FC升高(p = 0.00057),丘脑下核r- Cereb6 l和Cereb1 r-丘脑下核r rs-FC降低(p = 0.000063)。结论:本研究发现,与hc相比,ADHD、BD和SZ患者程序性记忆网络中的rs-FC发生了显著变化。这些发现表明,该网络中rs-FC的破坏可能与这些疾病中观察到的认知网络损伤有关。临床试验号:不适用。
{"title":"Investigating resting-state functional connectivity changes within procedural memory network across neuropsychiatric disorders using fMRI.","authors":"Mahdi Mohammadkhanloo, Mohammad Pooyan, Hamid Sharini, Mitra Yousefpour","doi":"10.1186/s12880-024-01527-7","DOIUrl":"10.1186/s12880-024-01527-7","url":null,"abstract":"<p><strong>Background: </strong>Cognitive networks impairments are common in neuropsychiatric disorders like Attention Deficit Hyperactivity Disorder (ADHD), bipolar disorder (BD), and schizophrenia (SZ). While previous research has focused on specific brain regions, the role of the procedural memory as a type of long-term memory to examine cognitive networks impairments in these disorders remains unclear. This study investigates alterations in resting-state functional connectivity (rs-FC) within the procedural memory network to explore brain function associated with cognitive networks in patients with these disorders.</p><p><strong>Methods: </strong>This study analyzed resting-state functional magnetic resonance imaging (rs-fMRI) data from 40 individuals with ADHD, 49 with BD, 50 with SZ, and 50 healthy controls (HCs). A procedural memory network was defined based on the selection of 34 regions of interest (ROIs) associated with the network in the Harvard-Oxford Cortical Structural Atlas (default atlas). Multivariate region of interest to region of interest connectivity (mRRC) was used to analyze the rs-FC between the defined network regions. Significant differences in rs-FC between patients and HCs were identified (P < 0.001).</p><p><strong>Results: </strong>ADHD patients showed increased Cereb45 l - Cereb3 r rs-FC (p = 0.000067) and decreased Cereb1 l - Cereb6 l rs-FC (p = 0.00092). BD patients exhibited increased rs-FC between multiple regions, including Claustrum r - Caudate r (p = 0.00058), subthalamic nucleus r - Pallidum l (p = 0.00060), substantia nigra l - Cereb2 l (p = 0.00082), Cereb10 r - SMA r (p = 0.00086), and Cereb9 r - SMA l (p = 0.00093) as well as decreased rs-FC in subthalamic nucleus r - Cereb6 l (p = 0.00013) and Cereb9 r - Cereb9 l (p = 0.00033). SZ patients indicated increased Caudate r- putamen l rs-FC (p = 0.00057) and decreased rs-FC in subthalamic nucleus r - Cereb6 l (p = 0.000063), and Cereb1 r - subthalamic nucleus r (p = 0.00063).</p><p><strong>Conclusions: </strong>This study found significant alterations in rs-FC within the procedural memory network in patients with ADHD, BD, and SZ compared to HCs. These findings suggest that disrupted rs-FC within this network may related to cognitive networks impairments observed in these disorders.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"18"},"PeriodicalIF":2.9,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730468/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142977505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimizing hip MRI: enhancing image quality and elevating inter-observer consistency using deep learning-powered reconstruction. 优化髋关节MRI:利用深度学习重建增强图像质量和提高观察者之间的一致性。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-13 DOI: 10.1186/s12880-025-01554-y
Yimeng Kang, Wenjing Li, Qingqing Lv, Qiuying Tao, Jieping Sun, Jinghan Dang, Xiaoyu Niu, Zijun Liu, Shujian Li, Zanxia Zhang, Kaiyu Wang, Baohong Wen, Jingliang Cheng, Yong Zhang, Weijian Wang

Background: Conventional hip joint MRI scans necessitate lengthy scan durations, posing challenges for patient comfort and clinical efficiency. Previously, accelerated imaging techniques were constrained by a trade-off between noise and resolution. Leveraging deep learning-based reconstruction (DLR) holds the potential to mitigate scan time without compromising image quality.

Methods: We enrolled a cohort of sixty patients who underwent DL-MRI, conventional MRI, and No-DL MRI examinations to evaluate image quality. Key metrics considered in the assessment included scan duration, overall image quality, quantitative assessments of Relative Signal-to-Noise Ratio (rSNR), Relative Contrast-to-Noise Ratio (rCNR), and diagnostic efficacy. Two experienced radiologists independently assessed image quality using a 5-point scale (5 indicating the highest quality). To gauge interobserver agreement for the assessed pathologies across image sets, we employed weighted kappa statistics. Additionally, the Wilcoxon signed rank test was employed to compare image quality and quantitative rSNR and rCNR measurements.

Results: Scan time was significantly reduced with DL-MRI and represented an approximate 66.5% reduction. DL-MRI consistently exhibited superior image quality in both coronal T2WI and axial T2WI when compared to both conventional MRI (p < 0.01) and No-DL-MRI (p < 0.01). Interobserver agreement was robust, with kappa values exceeding 0.735. For rSNR data, coronal fat-saturated(FS) T2WI and axial FS T2WI in DL-MRI consistently outperformed No-DL-MRI, with statistical significance (p < 0.01) observed in all cases. Similarly, rCNR data revealed significant improvements (p < 0.01) in coronal FS T2WI of DL-MRI when compared to No-DL-MRI. Importantly, our findings indicated that DL-MRI demonstrated diagnostic performance comparable to conventional MRI.

Conclusion: Integrating deep learning-based reconstruction methods into standard clinical workflows has the potential to the promise of accelerating image acquisition, enhancing image clarity, and increasing patient throughput, thereby optimizing diagnostic efficiency.

Trial registration: Retrospectively registered.

背景:传统的髋关节MRI扫描需要较长的扫描时间,对患者的舒适度和临床效率提出了挑战。以前,加速成像技术受到噪声和分辨率之间权衡的限制。利用基于深度学习的重建(DLR)有可能在不影响图像质量的情况下缩短扫描时间。方法:我们招募了60名患者,他们接受了DL-MRI、常规MRI和No-DL MRI检查,以评估图像质量。评估中考虑的关键指标包括扫描时间、整体图像质量、相对信噪比(rSNR)、相对对比噪声比(rCNR)的定量评估和诊断效果。两名经验丰富的放射科医生使用5分制独立评估图像质量(5表示最高质量)。为了衡量跨图像集评估病理的观察者间一致性,我们采用加权kappa统计。此外,采用Wilcoxon符号秩检验比较图像质量和定量rSNR和rCNR测量值。结果:DL-MRI扫描时间明显缩短,约减少66.5%。与传统MRI相比,DL-MRI在冠状位T2WI和轴位T2WI上均表现出更高的图像质量(p结论:将基于深度学习的重建方法整合到标准临床工作流程中,有可能加速图像采集,提高图像清晰度,提高患者吞吐量,从而优化诊断效率。试验注册:回顾性注册。
{"title":"Optimizing hip MRI: enhancing image quality and elevating inter-observer consistency using deep learning-powered reconstruction.","authors":"Yimeng Kang, Wenjing Li, Qingqing Lv, Qiuying Tao, Jieping Sun, Jinghan Dang, Xiaoyu Niu, Zijun Liu, Shujian Li, Zanxia Zhang, Kaiyu Wang, Baohong Wen, Jingliang Cheng, Yong Zhang, Weijian Wang","doi":"10.1186/s12880-025-01554-y","DOIUrl":"10.1186/s12880-025-01554-y","url":null,"abstract":"<p><strong>Background: </strong>Conventional hip joint MRI scans necessitate lengthy scan durations, posing challenges for patient comfort and clinical efficiency. Previously, accelerated imaging techniques were constrained by a trade-off between noise and resolution. Leveraging deep learning-based reconstruction (DLR) holds the potential to mitigate scan time without compromising image quality.</p><p><strong>Methods: </strong>We enrolled a cohort of sixty patients who underwent DL-MRI, conventional MRI, and No-DL MRI examinations to evaluate image quality. Key metrics considered in the assessment included scan duration, overall image quality, quantitative assessments of Relative Signal-to-Noise Ratio (rSNR), Relative Contrast-to-Noise Ratio (rCNR), and diagnostic efficacy. Two experienced radiologists independently assessed image quality using a 5-point scale (5 indicating the highest quality). To gauge interobserver agreement for the assessed pathologies across image sets, we employed weighted kappa statistics. Additionally, the Wilcoxon signed rank test was employed to compare image quality and quantitative rSNR and rCNR measurements.</p><p><strong>Results: </strong>Scan time was significantly reduced with DL-MRI and represented an approximate 66.5% reduction. DL-MRI consistently exhibited superior image quality in both coronal T2WI and axial T2WI when compared to both conventional MRI (p < 0.01) and No-DL-MRI (p < 0.01). Interobserver agreement was robust, with kappa values exceeding 0.735. For rSNR data, coronal fat-saturated(FS) T2WI and axial FS T2WI in DL-MRI consistently outperformed No-DL-MRI, with statistical significance (p < 0.01) observed in all cases. Similarly, rCNR data revealed significant improvements (p < 0.01) in coronal FS T2WI of DL-MRI when compared to No-DL-MRI. Importantly, our findings indicated that DL-MRI demonstrated diagnostic performance comparable to conventional MRI.</p><p><strong>Conclusion: </strong>Integrating deep learning-based reconstruction methods into standard clinical workflows has the potential to the promise of accelerating image acquisition, enhancing image clarity, and increasing patient throughput, thereby optimizing diagnostic efficiency.</p><p><strong>Trial registration: </strong>Retrospectively registered.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"17"},"PeriodicalIF":2.9,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730829/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142977506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
High-risk habitat radiomics model based on ultrasound images for predicting lateral neck lymph node metastasis in differentiated thyroid cancer. 基于超声影像的高危生境放射组学模型预测分化型甲状腺癌侧颈淋巴结转移。
IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-13 DOI: 10.1186/s12880-025-01551-1
Han Liu, Chun-Jie Hou, Min Wei, Ke-Feng Lu, Ying Liu, Pei Du, Li-Tao Sun, Jing-Lan Tang

Background: This study aims to evaluate the predictive usefulness of a habitat radiomics model based on ultrasound images for anticipating lateral neck lymph node metastasis (LLNM) in differentiated thyroid cancer (DTC), and for pinpointing high-risk habitat regions and significant radiomics traits.

Methods: A group of 214 patients diagnosed with differentiated thyroid carcinoma (DTC) between August 2021 and August 2023 were included, consisting of 107 patients with confirmed postoperative lateral lymph node metastasis (LLNM) and 107 patients without metastasis or lateral cervical lymph node involvement. An additional cohort of 43 patients was recruited to serve as an independent external testing group for this study. Patients were randomly divided into training and internal testing group at an 8:2 ratio. Region of interest (ROI) was manually outlined, and habitat analysis subregions were defined using the K-means method. The ideal number of subregions (n = 5) was determined using the Calinski-Harabasz score, leading to the creation of a habitat radiomics model with 5 subregions and the identification of the high-risk habitat model. Area under the curve (AUC) values were calculated for all models to assess their validity, and predictive model nomograms were created by integrating clinical features. The internal and external testing dataset is employed to assess the predictive performance and stability of the model.

Results: In internal testing group, Habitat 3 was identified as the high-risk habitat model in the study, showing the best diagnostic efficacy among all models (AUC(CRM) vs. AUC(Habitat 3) vs. AUC(CRM + Habitat 3) = 0.84(95%CI:0.71-0.97) vs. 0.90(95%CI:0.80-1.00) vs. 0.79(95%CI:0.65-0.93)). Moreover, integrating the Habitat 3 model with clinical features and constructing nomograms enhanced the predictive capability of the combined model (AUC = 0.95(95%CI:0.88-1.00)). In this study, an independent external testing cohort was utilized to assess the model's accuracy, yielding an AUC of 0.88 (95%CI: 0.78-0.98).

Conclusion: The integration of the High-Risk Habitats (Habitat 3) radiomics model with clinical characteristics demonstrated a high predictive accuracy in identifying LLNM. This model has the potential to offer valuable guidance to surgeons in deciding the necessity of LLNM dissection for DTC.

Clinical trial number: Not applicable.

背景:本研究旨在评估基于超声图像的栖息地放射组学模型在预测分化型甲状腺癌(DTC)侧颈淋巴结转移(LLNM)、精确定位高危栖息地区域和重要放射组学特征方面的预测价值。方法:选取2021年8月至2023年8月诊断为分化型甲状腺癌(DTC)的214例患者,其中107例术后确认有侧淋巴结转移(LLNM), 107例未发生转移或颈部外侧淋巴结受累。另外招募了43名患者作为本研究的独立外部测试组。患者按8:2的比例随机分为训练组和内测组。人工绘制感兴趣区域(ROI),使用K-means方法定义生境分析子区域。利用Calinski-Harabasz评分法确定理想亚区数(n = 5),建立了包含5个亚区的生境放射组学模型,并确定了高危生境模型。计算所有模型的曲线下面积(AUC)值以评估其有效性,并通过整合临床特征生成预测模型图。利用内部和外部测试数据集来评估模型的预测性能和稳定性。结果:在内测组中,生境3被确定为本研究的高危生境模型,在所有模型中具有最佳的诊断效果(AUC(CRM) vs AUC(生境3)vs AUC(CRM +生境3)= 0.84(95%CI:0.71 ~ 0.97) vs 0.90(95%CI:0.80 ~ 1.00) vs 0.79(95%CI:0.65 ~ 0.93))。此外,将Habitat 3模型与临床特征相结合并构建nomogram可提高组合模型的预测能力(AUC = 0.95(95%CI:0.88-1.00))。在本研究中,使用独立的外部测试队列来评估模型的准确性,得出AUC为0.88 (95%CI: 0.78-0.98)。结论:将高危生境(Habitat 3)放射组学模型与临床特征相结合,对LLNM具有较高的预测准确性。该模型有可能为外科医生决定在DTC中进行LLNM解剖的必要性提供有价值的指导。临床试验号:不适用。
{"title":"High-risk habitat radiomics model based on ultrasound images for predicting lateral neck lymph node metastasis in differentiated thyroid cancer.","authors":"Han Liu, Chun-Jie Hou, Min Wei, Ke-Feng Lu, Ying Liu, Pei Du, Li-Tao Sun, Jing-Lan Tang","doi":"10.1186/s12880-025-01551-1","DOIUrl":"10.1186/s12880-025-01551-1","url":null,"abstract":"<p><strong>Background: </strong>This study aims to evaluate the predictive usefulness of a habitat radiomics model based on ultrasound images for anticipating lateral neck lymph node metastasis (LLNM) in differentiated thyroid cancer (DTC), and for pinpointing high-risk habitat regions and significant radiomics traits.</p><p><strong>Methods: </strong>A group of 214 patients diagnosed with differentiated thyroid carcinoma (DTC) between August 2021 and August 2023 were included, consisting of 107 patients with confirmed postoperative lateral lymph node metastasis (LLNM) and 107 patients without metastasis or lateral cervical lymph node involvement. An additional cohort of 43 patients was recruited to serve as an independent external testing group for this study. Patients were randomly divided into training and internal testing group at an 8:2 ratio. Region of interest (ROI) was manually outlined, and habitat analysis subregions were defined using the K-means method. The ideal number of subregions (n = 5) was determined using the Calinski-Harabasz score, leading to the creation of a habitat radiomics model with 5 subregions and the identification of the high-risk habitat model. Area under the curve (AUC) values were calculated for all models to assess their validity, and predictive model nomograms were created by integrating clinical features. The internal and external testing dataset is employed to assess the predictive performance and stability of the model.</p><p><strong>Results: </strong>In internal testing group, Habitat 3 was identified as the high-risk habitat model in the study, showing the best diagnostic efficacy among all models (AUC(CRM) vs. AUC(Habitat 3) vs. AUC(CRM + Habitat 3) = 0.84(95%CI:0.71-0.97) vs. 0.90(95%CI:0.80-1.00) vs. 0.79(95%CI:0.65-0.93)). Moreover, integrating the Habitat 3 model with clinical features and constructing nomograms enhanced the predictive capability of the combined model (AUC = 0.95(95%CI:0.88-1.00)). In this study, an independent external testing cohort was utilized to assess the model's accuracy, yielding an AUC of 0.88 (95%CI: 0.78-0.98).</p><p><strong>Conclusion: </strong>The integration of the High-Risk Habitats (Habitat 3) radiomics model with clinical characteristics demonstrated a high predictive accuracy in identifying LLNM. This model has the potential to offer valuable guidance to surgeons in deciding the necessity of LLNM dissection for DTC.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"16"},"PeriodicalIF":2.9,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11727229/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142977504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","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
BMC Medical Imaging
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