European Journal of Radiology Open最新文献_第8页

A systematic review on deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction 基于深度学习的冠状动脉CT血管造影用于斑块和狭窄量化和心脏风险预测的系统综述

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-05-02 DOI: 10.1016/j.ejro.2025.100652

Priyal Shrivastava , Shivali Kashikar , P.H. Parihar , Pachyanti Kasat , Paritosh Bhangale , Prakher Shrivastava

Background

Coronary artery disease (CAD) is a major worldwide health concern, contributing significantly to the global burden of cardiovascular diseases (CVDs). According to the 2023 World Health Organization (WHO) report, CVDs account for approximately 17.9 million deaths annually. This emphasizies the need for advanced diagnostic tools such as coronary computed tomography angiography (CCTA). The incorporation of deep learning (DL) technologies could significantly improve CCTA analysis by automating the quantification of plaque and stenosis, thus enhancing the precision of cardiac risk assessments. A recent meta-analysis highlights the evolving role of CCTA in patient management, showing that CCTA-guided diagnosis and management reduced adverse cardiac events and improved event-free survival in patients with stable and acute coronary syndromes.

Methods

An extensive literature search was carried out across various electronic databases, such as MEDLINE, Embase, and the Cochrane Library. This search utilized a specific strategy that included both Medical Subject Headings (MeSH) terms and pertinent keywords. The review adhered to PRISMA guidelines and focused on studies published between 2019 and 2024 that employed deep learning (DL) for coronary computed tomography angiography (CCTA) in patients aged 18 years or older. After implementing specific inclusion and exclusion criteria, a total of 10 articles were selected for systematic evaluation regarding quality and bias.

Results

This systematic review included a total of 10 studies, demonstrating the high diagnostic performance and predictive capabilities of various deep learning models compared to different imaging modalities. This analysis highlights the effectiveness of these models in enhancing diagnostic accuracy in imaging techniques. Notably, strong correlations were observed between DL-derived measurements and intravascular ultrasound findings, enhancing clinical decision-making and risk stratification for CAD.

Conclusion

Deep learning-enabled CCTA represents a promising advancement in the quantification of coronary plaques and stenosis, facilitating improved cardiac risk prediction and enhancing clinical workflow efficiency. Despite variability in study designs and potential biases, the findings support the integration of DL technologies into routine clinical practice for better patient outcomes in CAD management.

冠状动脉疾病（CAD）是世界范围内主要的健康问题，是全球心血管疾病（cvd）负担的重要组成部分。根据世界卫生组织（世卫组织）2023年的报告，心血管疾病每年造成约1790万人死亡。这强调需要先进的诊断工具，如冠状动脉计算机断层血管造影（CCTA）。结合深度学习（DL）技术可以通过自动量化斑块和狭窄来显著改善CCTA分析，从而提高心脏风险评估的准确性。最近的一项荟萃分析强调了CCTA在患者管理中的不断发展的作用，表明CCTA指导的诊断和管理减少了稳定和急性冠状动脉综合征患者的不良心脏事件并提高了无事件生存期。方法在MEDLINE、Embase、Cochrane图书馆等电子数据库中进行广泛的文献检索。这个搜索使用了一个特定的策略，包括医学主题标题（MeSH）术语和相关关键词。该综述遵循PRISMA指南，重点关注2019年至2024年间发表的研究，这些研究在18岁或以上的患者中使用深度学习（DL）进行冠状动脉计算机断层扫描血管造影（CCTA）。在实施具体的纳入和排除标准后，共选择10篇文章进行质量和偏倚的系统评价。本系统综述共包括10项研究，与不同的成像方式相比，展示了各种深度学习模型的高诊断性能和预测能力。这一分析强调了这些模型在提高成像技术诊断准确性方面的有效性。值得注意的是，dl衍生的测量结果与血管内超声结果之间存在很强的相关性，从而增强了CAD的临床决策和风险分层。结论基于深度学习的CCTA在冠状动脉斑块和狭窄量化方面取得了很好的进展，有助于改进心脏风险预测，提高临床工作效率。尽管研究设计存在差异和潜在的偏差，但研究结果支持将DL技术整合到常规临床实践中，以改善CAD管理中的患者预后。

{"title":"A systematic review on deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction","authors":"Priyal Shrivastava , Shivali Kashikar , P.H. Parihar , Pachyanti Kasat , Paritosh Bhangale , Prakher Shrivastava","doi":"10.1016/j.ejro.2025.100652","DOIUrl":"10.1016/j.ejro.2025.100652","url":null,"abstract":"<div><h3>Background</h3><div>Coronary artery disease (CAD) is a major worldwide health concern, contributing significantly to the global burden of cardiovascular diseases (CVDs). According to the 2023 World Health Organization (WHO) report, CVDs account for approximately 17.9 million deaths annually. This emphasizies the need for advanced diagnostic tools such as coronary computed tomography angiography (CCTA). The incorporation of deep learning (DL) technologies could significantly improve CCTA analysis by automating the quantification of plaque and stenosis, thus enhancing the precision of cardiac risk assessments. A recent meta-analysis highlights the evolving role of CCTA in patient management, showing that CCTA-guided diagnosis and management reduced adverse cardiac events and improved event-free survival in patients with stable and acute coronary syndromes.</div></div><div><h3>Methods</h3><div>An extensive literature search was carried out across various electronic databases, such as MEDLINE, Embase, and the Cochrane Library. This search utilized a specific strategy that included both Medical Subject Headings (MeSH) terms and pertinent keywords. The review adhered to PRISMA guidelines and focused on studies published between 2019 and 2024 that employed deep learning (DL) for coronary computed tomography angiography (CCTA) in patients aged 18 years or older. After implementing specific inclusion and exclusion criteria, a total of 10 articles were selected for systematic evaluation regarding quality and bias.</div></div><div><h3>Results</h3><div>This systematic review included a total of 10 studies, demonstrating the high diagnostic performance and predictive capabilities of various deep learning models compared to different imaging modalities. This analysis highlights the effectiveness of these models in enhancing diagnostic accuracy in imaging techniques. Notably, strong correlations were observed between DL-derived measurements and intravascular ultrasound findings, enhancing clinical decision-making and risk stratification for CAD.</div></div><div><h3>Conclusion</h3><div>Deep learning-enabled CCTA represents a promising advancement in the quantification of coronary plaques and stenosis, facilitating improved cardiac risk prediction and enhancing clinical workflow efficiency. Despite variability in study designs and potential biases, the findings support the integration of DL technologies into routine clinical practice for better patient outcomes in CAD management.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100652"},"PeriodicalIF":1.8,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bone lesions of the tibia: Multimodal iconographic review and diagnostic algorithms, Part 1: Diagnostic algorithms, dysplasia and diaphyseal lesions 胫骨骨病变：多模态图像回顾和诊断算法，第1部分：诊断算法，发育不良和骨干病变

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-05-02 DOI: 10.1016/j.ejro.2025.100653

Vincent Salmon, Pedro Augusto Gondim Teixeira, Alain Blum

This article focuses on the analysis of bone lesions of the tibia, addressing the main diagnostic challenges and imaging strategies used to characterize them. It examines the different etiologies of tibial lesions, emphasizing the importance of a systematic approach to distinguishing tumoral from non-tumoral lesions, as well as from bone dysplasia. The article underlines the essential role of imaging, particularly radiography, CT, and MRI, in accurate lesion characterization. It also highlights typical clinical and radiological features that help guide diagnosis and management. The main aim is to provide radiologists with clear guidelines for improving the identification of bony lesions of the tibia. Part 1 of this 2-part article proposes simplified diagnostic algorithms and some illustrations of dysplasia and diaphyseal lesions of the tibia.

这篇文章的重点是胫骨骨病变的分析，解决主要的诊断挑战和成像策略，用于表征他们。它检查了胫骨病变的不同病因，强调了区分肿瘤与非肿瘤病变以及骨发育不良的系统方法的重要性。文章强调了成像的重要作用，特别是x线摄影，CT和MRI，在准确的病变表征。它还强调了典型的临床和放射学特征，有助于指导诊断和管理。主要目的是为放射科医生提供明确的指导方针，以改善胫骨骨病变的识别。这篇2部分文章的第1部分提出了简化的诊断算法和一些胫骨发育不良和骨干病变的插图。

引用次数: 0

Deep learning-based acceleration of high-resolution compressed sense MR imaging of the hip 基于深度学习的髋关节高分辨率压缩感MR成像加速

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-05-02 DOI: 10.1016/j.ejro.2025.100656

Alexander W. Marka , Felix Meurer , Vanessa Twardy , Markus Graf , Saba Ebrahimi Ardjomand , Kilian Weiss , Marcus R. Makowski , Alexandra S. Gersing , Dimitrios C. Karampinos , Jan Neumann , Klaus Woertler , Ingo J. Banke , Sarah C. Foreman

Purpose

To evaluate a Compressed Sense Artificial Intelligence framework (CSAI) incorporating parallel imaging, compressed sense (CS), and deep learning for high-resolution MRI of the hip, comparing it with standard-resolution CS imaging.

Methods

Thirty-two patients with femoroacetabular impingement syndrome underwent 3 T MRI scans. Coronal and sagittal intermediate-weighted TSE sequences with fat saturation were acquired using CS (0.6 ×0.8 mm resolution) and CSAI (0.3 ×0.4 mm resolution) protocols in comparable acquisition times (7:49 vs. 8:07 minutes for both planes). Two readers systematically assessed the depiction of the acetabular and femoral cartilage (in five cartilage zones), labrum, ligamentum capitis femoris, and bone using a five-point Likert scale. Diagnostic confidence and abnormality detection were recorded and analyzed using the Wilcoxon signed-rank test.

Results

CSAI significantly improved the cartilage depiction across most cartilage zones compared to CS. Overall Likert scores were 4.0 ± 0.2 (CS) vs 4.2 ± 0.6 (CSAI) for reader 1 and 4.0 ± 0.2 (CS) vs 4.3 ± 0.6 (CSAI) for reader 2 (p ≤ 0.001). Diagnostic confidence increased from 3.5 ± 0.7 and 3.9 ± 0.6 (CS) to 4.0 ± 0.6 and 4.1 ± 0.7 (CSAI) for readers 1 and 2, respectively (p ≤ 0.001). More cartilage lesions were detected with CSAI, with significant improvements in diagnostic confidence in certain cartilage zones such as femoral zone C and D for both readers. Labrum and ligamentum capitis femoris depiction remained similar, while bone depiction was rated lower. No abnormalities detected in CS were missed in CSAI.

Conclusion

CSAI provides high-resolution hip MR images with enhanced cartilage depiction without extending acquisition times, potentially enabling more precise hip cartilage assessment.

目的评估一种结合并行成像、压缩感（CS）和深度学习的压缩感人工智能框架（CSAI），用于高分辨率髋关节MRI，并将其与标准分辨率CS成像进行比较。方法对32例股髋臼撞击综合征患者行3次 T MRI扫描。采用CS（0.6 ×0.8 mm分辨率）和CSAI（0.3 ×0.4 mm分辨率）方案获得脂肪饱和的冠状面和矢状面中权重TSE序列，获取时间相当（两个平面分别为7:49和8:07 分钟）。两位读者系统地评估了髋臼和股骨软骨的描述（在五个软骨区），唇，股头韧带和骨骼使用五点李克特量表。诊断置信度和异常检测记录并使用Wilcoxon符号秩检验进行分析。结果与CS相比，scsai显著改善了大部分软骨区的软骨描绘。整体李克特 分数4.0±0.2 (CS)和4.2 ± 0.6 (CSAI)为读者1和4.0 ± 0.2 (CS)和4.3 ± 0.6 (CSAI)读者2 (p ≤ 0.001)。诊断信心增加从3.5 ±  0.7和3.9±0.6 (CS) 4.0 ±  0.6和4.1±0.7 (CSAI)读者1和2,分别(p ≤ 0.001)。CSAI检测到更多的软骨病变，在某些软骨区，如股骨C区和D区，两位读者的诊断信心都有显著提高。肱骨唇和股头韧带的描述保持相似，而骨描述的评分较低。在CSAI中未发现CS异常。结论csai提供了高分辨率的髋关节MR图像，增强了软骨的描绘，而不延长采集时间，有可能实现更精确的髋关节软骨评估。

{"title":"Deep learning-based acceleration of high-resolution compressed sense MR imaging of the hip","authors":"Alexander W. Marka , Felix Meurer , Vanessa Twardy , Markus Graf , Saba Ebrahimi Ardjomand , Kilian Weiss , Marcus R. Makowski , Alexandra S. Gersing , Dimitrios C. Karampinos , Jan Neumann , Klaus Woertler , Ingo J. Banke , Sarah C. Foreman","doi":"10.1016/j.ejro.2025.100656","DOIUrl":"10.1016/j.ejro.2025.100656","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate a Compressed Sense Artificial Intelligence framework (CSAI) incorporating parallel imaging, compressed sense (CS), and deep learning for high-resolution MRI of the hip, comparing it with standard-resolution CS imaging.</div></div><div><h3>Methods</h3><div>Thirty-two patients with femoroacetabular impingement syndrome underwent 3 T MRI scans. Coronal and sagittal intermediate-weighted TSE sequences with fat saturation were acquired using CS (0.6 ×0.8 mm resolution) and CSAI (0.3 ×0.4 mm resolution) protocols in comparable acquisition times (7:49 vs. 8:07 minutes for both planes). Two readers systematically assessed the depiction of the acetabular and femoral cartilage (in five cartilage zones), labrum, ligamentum capitis femoris, and bone using a five-point Likert scale. Diagnostic confidence and abnormality detection were recorded and analyzed using the Wilcoxon signed-rank test.</div></div><div><h3>Results</h3><div>CSAI significantly improved the cartilage depiction across most cartilage zones compared to CS. Overall Likert scores were 4.0 ± 0.2 (CS) vs 4.2 ± 0.6 (CSAI) for reader 1 and 4.0 ± 0.2 (CS) vs 4.3 ± 0.6 (CSAI) for reader 2 (p ≤ 0.001). Diagnostic confidence increased from 3.5 ± 0.7 and 3.9 ± 0.6 (CS) to 4.0 ± 0.6 and 4.1 ± 0.7 (CSAI) for readers 1 and 2, respectively (p ≤ 0.001). More cartilage lesions were detected with CSAI, with significant improvements in diagnostic confidence in certain cartilage zones such as femoral zone C and D for both readers. Labrum and ligamentum capitis femoris depiction remained similar, while bone depiction was rated lower. No abnormalities detected in CS were missed in CSAI.</div></div><div><h3>Conclusion</h3><div>CSAI provides high-resolution hip MR images with enhanced cartilage depiction without extending acquisition times, potentially enabling more precise hip cartilage assessment.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100656"},"PeriodicalIF":1.8,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bone lesions of the tibia: Multimodal iconographic review and diagnostic algorithms, Part 2: Metaphyseal and epiphyseal lesions 胫骨骨病变：多模态影像学回顾和诊断算法，第2部分：干骺端和骨骺病变

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-05-01 DOI: 10.1016/j.ejro.2025.100654

Vincent Salmon, Pedro Augusto Gondim Teixeira, Alain Blum

This article focuses on the analysis of bone lesions of the tibia, addressing the main diagnostic challenges and imaging strategies used to characterize them. It examines the different etiologies of tibial lesions, emphasizing the importance of a systematic approach to distinguishing tumoral from non-tumoral lesions, as well as from bone dysplasia. The article underlines the essential role of imaging, particularly radiography, CT, and MRI, in accurate lesion characterization. It also highlights typical clinical and radiological features that help guide diagnosis and management. The main aim is to provide radiologists with clear guidelines for improving the identification of bony lesions of the tibia. Part 2 of this 2-part article proposes some illustrations of metaphyseal and epiphyseal lesions of the tibia.

这篇文章的重点是胫骨骨病变的分析，解决主要的诊断挑战和成像策略，用于表征他们。它检查了胫骨病变的不同病因，强调了区分肿瘤与非肿瘤病变以及骨发育不良的系统方法的重要性。文章强调了成像的重要作用，特别是x线摄影，CT和MRI，在准确的病变表征。它还强调了典型的临床和放射学特征，有助于指导诊断和管理。主要目的是为放射科医生提供明确的指导方针，以改善胫骨骨病变的识别。这篇2部分文章的第2部分提出了一些胫骨干骺端和骨骺病变的插图。

引用次数: 0

Evaluation of large language models in generating pulmonary nodule follow-up recommendations 大语言模型在生成肺结节随访建议中的评价

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-04-30 DOI: 10.1016/j.ejro.2025.100655

Junzhe Wen , Wanyue Huang , Huzheng Yan , Jie Sun , Mengshi Dong , Chao Li , Jie Qin

Rationale and objectives

To evaluate the performance of large language models (LLMs) in generating clinically follow-up recommendations for pulmonary nodules by leveraging radiological report findings and management guidelines.

Materials and methods

This retrospective study included CT follow-up reports of pulmonary nodules documented by senior radiologists from September 1st, 2023, to April 30th, 2024. Sixty reports were collected for prompting engineering additionally, based on few-shot learning and the Chain of Thought methodology. Radiological findings of pulmonary nodules, along with finally prompt, were input into GPT-4o-mini or ERNIE-4.0-Turbo-8K to generate follow-up recommendations. The AI-generated recommendations were evaluated against radiologist-defined guideline-based standards through binary classification, assessing nodule risk classifications, follow-up intervals, and harmfulness. Performance metrics included sensitivity, specificity, positive/negative predictive values, and F1 score.

Results

On 1009 reports from 996 patients (median age, 50.0 years, IQR, 39.0–60.0 years; 511 male patients), ERNIE-4.0-Turbo-8K and GPT-4o-mini demonstrated comparable performance in both accuracy of follow-up recommendations (94.6 % vs 92.8 %, P = 0.07) and harmfulness rates (2.9 % vs 3.5 %, P = 0.48). In nodules classification, ERNIE-4.0-Turbo-8K and GPT-4o-mini performed similarly with accuracy rates of 99.8 % vs 99.9 % sensitivity of 96.9 % vs 100.0 %, specificity of 99.9 % vs 99.9 %, positive predictive value of 96.9 % vs 96.9 %, negative predictive value of 100.0 % vs 99.9 %, f1-score of 96.9 % vs 98.4 %, respectively.

Conclusion

LLMs show promise in providing guideline-based follow-up recommendations for pulmonary nodules, but require rigorous validation and supervision to mitigate potential clinical risks. This study offers insights into their potential role in automated radiological decision support.

依据放射学报告结果和管理指南，评估大语言模型（LLMs）在生成肺结节临床随访建议方面的表现。材料与方法本回顾性研究纳入2023年9月1日至2024年4月30日资深放射科医师记录的肺结节CT随访报告。采用少弹学习和思维链方法，收集了60份报告，并进行了额外的工程提示。肺结节的影像学表现，以及最终提示，输入gpt - 40 -mini或ERNIE-4.0-Turbo-8K，以产生随访建议。通过二元分类、评估结节风险分类、随访间隔和危害，根据放射科医生定义的基于指南的标准对人工智能生成的建议进行评估。性能指标包括敏感性、特异性、阳性/阴性预测值和F1评分。结果996例患者报告1009份(中位年龄50.0岁，IQR 39.0 ~ 60.0岁；511例男性患者)、erie -4.0- turbo - 8k和gpt - 40 -mini在随访建议的准确性（94.6 % vs 92.8 %,P = 0.07）和有害率（2.9 % vs 3.5 %,P = 0.48）方面表现相当。结节的分类、厄尼- 4.0 -涡轮- 8 - k和GPT-4o-mini执行同样的准确率为99.8 vs 99.9  % % 96.9 vs 100.0  % %的敏感性,特异性99.9 vs 99.9  % %,阳性预测值96.9 vs 96.9  % %,负面预测值100.0 vs 99.9  % %,f1-score 96.9 vs 98.4  % %,分别。结论llm有望为肺结节提供基于指南的随访建议，但需要严格的验证和监督以降低潜在的临床风险。这项研究为它们在自动化放射决策支持中的潜在作用提供了见解。

{"title":"Evaluation of large language models in generating pulmonary nodule follow-up recommendations","authors":"Junzhe Wen , Wanyue Huang , Huzheng Yan , Jie Sun , Mengshi Dong , Chao Li , Jie Qin","doi":"10.1016/j.ejro.2025.100655","DOIUrl":"10.1016/j.ejro.2025.100655","url":null,"abstract":"<div><h3>Rationale and objectives</h3><div>To evaluate the performance of large language models (LLMs) in generating clinically follow-up recommendations for pulmonary nodules by leveraging radiological report findings and management guidelines.</div></div><div><h3>Materials and methods</h3><div>This retrospective study included CT follow-up reports of pulmonary nodules documented by senior radiologists from September 1st, 2023, to April 30th, 2024. Sixty reports were collected for prompting engineering additionally, based on few-shot learning and the Chain of Thought methodology. Radiological findings of pulmonary nodules, along with finally prompt, were input into GPT-4o-mini or ERNIE-4.0-Turbo-8K to generate follow-up recommendations. The AI-generated recommendations were evaluated against radiologist-defined guideline-based standards through binary classification, assessing nodule risk classifications, follow-up intervals, and harmfulness. Performance metrics included sensitivity, specificity, positive/negative predictive values, and F1 score.</div></div><div><h3>Results</h3><div>On 1009 reports from 996 patients (median age, 50.0 years, IQR, 39.0–60.0 years; 511 male patients), ERNIE-4.0-Turbo-8K and GPT-4o-mini demonstrated comparable performance in both accuracy of follow-up recommendations (94.6 % vs 92.8 %, P = 0.07) and harmfulness rates (2.9 % vs 3.5 %, P = 0.48). In nodules classification, ERNIE-4.0-Turbo-8K and GPT-4o-mini performed similarly with accuracy rates of 99.8 % vs 99.9 % sensitivity of 96.9 % vs 100.0 %, specificity of 99.9 % vs 99.9 %, positive predictive value of 96.9 % vs 96.9 %, negative predictive value of 100.0 % vs 99.9 %, f1-score of 96.9 % vs 98.4 %, respectively.</div></div><div><h3>Conclusion</h3><div>LLMs show promise in providing guideline-based follow-up recommendations for pulmonary nodules, but require rigorous validation and supervision to mitigate potential clinical risks. This study offers insights into their potential role in automated radiological decision support.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100655"},"PeriodicalIF":1.8,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Preoperative MR - based model for predicting prognosis in patients with intracranial extraventricular ependymoma 颅内室外室管膜瘤的术前MR预测预后模型

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-04-08 DOI: 10.1016/j.ejro.2025.100650

Liyan Li , Xueying Wang , Zeming Tan , Yipu Mao , Deyou Huang , Xiaoping Yi , Muliang Jiang , Bihong T. Chen

Objectives

To develop and validate a prediction model based on brain MRI features to predict disease-free survival (DFS) and overall survival (OS) for patients with intracranial extraventricular ependymoma (IEE).

Methods

The study included 114 patients with pathology-proven IEE, of whom 80 were randomly assigned to a training group and 34 to a validation group. Preoperative brain MRI images were assessed with the Visually AcceSAble Rembrandt Images (VASARI) feature set. Clinical variables were assessed including age, gender, KPS, pathological grade of the tumor and blood test data such as eosinophil, blood urea nitrogen and serum creatinine. Multivariate Cox proportional hazards regression analysis was performed to select the independent prognostic factors for DFS and OS. Three prediction models were built with clinical variables, MRI-VASARI features, and combined clinical and MRI-VASARI data, respectively. The predictive power of survival models was assessed using c-index and calibration curve.

Results

Clinical variables such as eosinophil, blood urea nitrogen and serum creatinine, and MRI-VASARI feature for definition of the non-enhancing margin (F13) were significantly correlated with the prognosis of DFS. Blood urea nitrogen, D-dimer, tumor location (F1), eloquent brain (F3), and T1/FLAIR ratio (F10) were independent predictors of OS. Based on these factors, prediction models were constructed. The concordance indices of the three survival models for OS were 0.732, 0.729, and 0.768, respectively. For DFS, the concordance indices were respectively 0.694, 0.576, and 0.714.

Conclusion

Predictive modelling combining both clinical and MRI-VASARI features is robust and may assist in the assessment of prognosis in patients with IEE.

目的建立并验证一种基于脑MRI特征的预测模型，用于预测颅内室外室管膜瘤（IEE）患者的无病生存期（DFS）和总生存期（OS）。方法114例经病理证实的IEE患者随机分为训练组80例，验证组34例。术前脑MRI图像使用视觉可访问伦勃朗图像（VASARI）特征集进行评估。临床变量包括年龄、性别、KPS、肿瘤病理分级及嗜酸性粒细胞、尿素氮、血清肌酐等血检数据。采用多因素Cox比例风险回归分析选择影响DFS和OS的独立预后因素。分别用临床变量、MRI-VASARI特征、临床和MRI-VASARI数据联合建立3个预测模型。采用c指数和校准曲线评估生存模型的预测能力。结果嗜酸性粒细胞、血尿素氮、血清肌酐等临床指标及MRI-VASARI特征定义的非增强边界（F13）与DFS的预后显著相关。血尿素氮、d -二聚体、肿瘤位置（F1）、雄辩脑（F3）和T1/FLAIR比（F10）是OS的独立预测因子。基于这些因素，构建了预测模型。3种生存模型OS的一致性指数分别为0.732、0.729和0.768。DFS的一致性指数分别为0.694、0.576和0.714。结论结合临床和MRI-VASARI特征的预测模型是可靠的，可以帮助评估IEE患者的预后。

{"title":"Preoperative MR - based model for predicting prognosis in patients with intracranial extraventricular ependymoma","authors":"Liyan Li , Xueying Wang , Zeming Tan , Yipu Mao , Deyou Huang , Xiaoping Yi , Muliang Jiang , Bihong T. Chen","doi":"10.1016/j.ejro.2025.100650","DOIUrl":"10.1016/j.ejro.2025.100650","url":null,"abstract":"<div><h3>Objectives</h3><div>To develop and validate a prediction model based on brain MRI features to predict disease-free survival (DFS) and overall survival (OS) for patients with intracranial extraventricular ependymoma (IEE).</div></div><div><h3>Methods</h3><div>The study included 114 patients with pathology-proven IEE, of whom 80 were randomly assigned to a training group and 34 to a validation group. Preoperative brain MRI images were assessed with the Visually AcceSAble Rembrandt Images (VASARI) feature set. Clinical variables were assessed including age, gender, KPS, pathological grade of the tumor and blood test data such as eosinophil, blood urea nitrogen and serum creatinine. Multivariate Cox proportional hazards regression analysis was performed to select the independent prognostic factors for DFS and OS. Three prediction models were built with clinical variables, MRI-VASARI features, and combined clinical and MRI-VASARI data, respectively. The predictive power of survival models was assessed using c-index and calibration curve.</div></div><div><h3>Results</h3><div>Clinical variables such as eosinophil, blood urea nitrogen and serum creatinine, and MRI-VASARI feature for definition of the non-enhancing margin (F13) were significantly correlated with the prognosis of DFS. Blood urea nitrogen, D-dimer, tumor location (F1), eloquent brain (F3), and T1/FLAIR ratio (F10) were independent predictors of OS. Based on these factors, prediction models were constructed. The concordance indices of the three survival models for OS were 0.732, 0.729, and 0.768, respectively. For DFS, the concordance indices were respectively 0.694, 0.576, and 0.714.</div></div><div><h3>Conclusion</h3><div>Predictive modelling combining both clinical and MRI-VASARI features is robust and may assist in the assessment of prognosis in patients with IEE.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100650"},"PeriodicalIF":1.8,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792716","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

Ultrasound-based radiomics and machine learning for enhanced diagnosis of knee osteoarthritis: Evaluation of diagnostic accuracy, sensitivity, specificity, and predictive value 基于超声的放射组学和机器学习增强膝骨关节炎的诊断：诊断准确性、敏感性、特异性和预测价值的评估

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-04-02 DOI: 10.1016/j.ejro.2025.100649

Takeharu Kiso , Yukinori Okada , Satoru Kawata , Kouta Shichiji , Eiichiro Okumura , Noritaka Hatsumi , Ryohei Matsuura , Masaki Kaminaga , Hikaru Kuwano , Erika Okumura

Purpose

To evaluate the usefulness of radiomics features extracted from ultrasonographic images in diagnosing and predicting the severity of knee osteoarthritis (OA).

Methods

In this single-center, prospective, observational study, radiomics features were extracted from standing radiographs and ultrasonographic images of knees of patients aged 40–85 years with primary medial OA and without OA. Analysis was conducted using LIFEx software (version 7.2.n), ANOVA, and LASSO regression. The diagnostic accuracy of three different models, including a statistical model incorporating background factors and machine learning models, was evaluated.

Results

Among 491 limbs analyzed, 318 were OA and 173 were non-OA cases. The mean age was 72.7 (±8.7) and 62.6 (±11.3) years in the OA and non-OA groups, respectively. The OA group included 81 (25.5 %) men and 237 (74.5 %) women, whereas the non-OA group included 73 men (42.2 %) and 100 (57.8 %) women. A statistical model using the cutoff value of MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) achieved a specificity of 0.98 and sensitivity of 0.47. Machine learning diagnostic models (Model 2) demonstrated areas under the curve (AUCs) of 0.88 (discriminant analysis) and 0.87 (logistic regression), with sensitivities of 0.80 and 0.81 and specificities of 0.82 and 0.80, respectively. For severity prediction, the statistical model using MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) showed sensitivity and specificity values of 0.78 and 0.86, respectively, whereas machine learning models achieved an AUC of 0.92, sensitivity of 0.81, and specificity of 0.85 for severity prediction.

Conclusion

The use of radiomics features in diagnosing knee OA shows potential as a supportive tool for enhancing clinicians' decision-making.

目的评价超声图像放射组学特征在诊断和预测膝关节骨关节炎（OA）严重程度中的价值。方法在这项单中心、前瞻性、观察性研究中，从40-85岁原发性内侧骨关节炎和非骨关节炎患者的站立x线片和超声图像中提取放射组学特征。采用LIFEx软件（version 7.2.n）、方差分析和LASSO回归进行分析。评估了三种不同模型的诊断准确性，包括结合背景因素和机器学习模型的统计模型。结果491例肢体中OA 318例，非OA 173例。OA组和非OA组的平均年龄分别为72.7（±8.7）岁和62.6（±11.3）岁。OA组包括81名男性（25.5 %）和237名女性（74.5 %），而非OA组包括73名男性（42.2% %）和100名女性（57.8 %）。使用MORPHOLOGICAL_SurfaceToVolumeRatio （IBSI:2PR5）截断值的统计模型的特异性为0.98，敏感性为0.47。机器学习诊断模型（模型2）的曲线下面积（auc）分别为0.88（判别分析）和0.87（逻辑回归），敏感性分别为0.80和0.81，特异性分别为0.82和0.80。对于严重程度预测，使用MORPHOLOGICAL_SurfaceToVolumeRatio （IBSI:2PR5）的统计模型的灵敏度和特异性分别为0.78和0.86，而机器学习模型的严重程度预测的AUC为0.92，灵敏度为0.81，特异性为0.85。结论放射组学特征在膝关节OA诊断中的应用为临床医生的决策提供了一种支持工具。

{"title":"Ultrasound-based radiomics and machine learning for enhanced diagnosis of knee osteoarthritis: Evaluation of diagnostic accuracy, sensitivity, specificity, and predictive value","authors":"Takeharu Kiso , Yukinori Okada , Satoru Kawata , Kouta Shichiji , Eiichiro Okumura , Noritaka Hatsumi , Ryohei Matsuura , Masaki Kaminaga , Hikaru Kuwano , Erika Okumura","doi":"10.1016/j.ejro.2025.100649","DOIUrl":"10.1016/j.ejro.2025.100649","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the usefulness of radiomics features extracted from ultrasonographic images in diagnosing and predicting the severity of knee osteoarthritis (OA).</div></div><div><h3>Methods</h3><div>In this single-center, prospective, observational study, radiomics features were extracted from standing radiographs and ultrasonographic images of knees of patients aged 40–85 years with primary medial OA and without OA. Analysis was conducted using LIFEx software (version 7.2.n), ANOVA, and LASSO regression. The diagnostic accuracy of three different models, including a statistical model incorporating background factors and machine learning models, was evaluated.</div></div><div><h3>Results</h3><div>Among 491 limbs analyzed, 318 were OA and 173 were non-OA cases. The mean age was 72.7 (±8.7) and 62.6 (±11.3) years in the OA and non-OA groups, respectively. The OA group included 81 (25.5 %) men and 237 (74.5 %) women, whereas the non-OA group included 73 men (42.2 %) and 100 (57.8 %) women. A statistical model using the cutoff value of MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) achieved a specificity of 0.98 and sensitivity of 0.47. Machine learning diagnostic models (Model 2) demonstrated areas under the curve (AUCs) of 0.88 (discriminant analysis) and 0.87 (logistic regression), with sensitivities of 0.80 and 0.81 and specificities of 0.82 and 0.80, respectively. For severity prediction, the statistical model using MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) showed sensitivity and specificity values of 0.78 and 0.86, respectively, whereas machine learning models achieved an AUC of 0.92, sensitivity of 0.81, and specificity of 0.85 for severity prediction.</div></div><div><h3>Conclusion</h3><div>The use of radiomics features in diagnosing knee OA shows potential as a supportive tool for enhancing clinicians' decision-making.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100649"},"PeriodicalIF":1.8,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143746739","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

MRI-based risk factors for intensive care unit admissions in acute neck infections 急性颈部感染重症监护病房入院的核磁共振危险因素

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-04-01 DOI: 10.1016/j.ejro.2025.100648

Jari-Pekka Vierula , Harri Merisaari , Jaakko Heikkinen , Tatu Happonen , Aapo Sirén , Jarno Velhonoja , Heikki Irjala , Tero Soukka , Kimmo Mattila , Mikko Nyman , Janne Nurminen , Jussi Hirvonen

Objectives

We assessed risk factors and developed a score to predict intensive care unit (ICU) admissions using MRI findings and clinical data in acute neck infections.

Methods

This retrospective study included patients with MRI-confirmed acute neck infection. Abscess diameters were measured on post-gadolinium T1-weighted Dixon MRI, and specific edema patterns, retropharyngeal (RPE) and mediastinal edema, were assessed on fat-suppressed T2-weighted Dixon MRI. A multivariate logistic regression model identified ICU admission predictors, with risk scores derived from regression coefficients. Model performance was evaluated using the area under the curve (AUC) from receiver operating characteristic analysis. Machine learning models (random forest, XGBoost, support vector machine, neural networks) were tested.

Results

The sample included 535 patients, of whom 373 (70 %) had an abscess, and 62 (12 %) required ICU treatment. Significant predictors for ICU admission were RPE, maximal abscess diameter (≥40 mm), and C-reactive protein (CRP) (≥172 mg/L). The risk score (0−7) (AUC=0.82, 95 % confidence interval [CI] 0.77–0.88) outperformed CRP (AUC=0.73, 95 % CI 0.66–0.80, p = 0.001), maximal abscess diameter (AUC=0.72, 95 % CI 0.64–0.80, p < 0.001), and RPE (AUC=0.71, 95 % CI 0.65–0.77, p < 0.001). The risk score at a cut-off > 3 yielded the following metrics: sensitivity 66 %, specificity 82 %, positive predictive value 33 %, negative predictive value 95 %, accuracy 80 %, and odds ratio 9.0. Discriminative performance was robust in internal (AUC=0.83) and hold-out (AUC=0.81) validations. ML models were not better than regression models.

Conclusions

A risk model incorporating RPE, abscess size, and CRP showed moderate accuracy and high negative predictive value for ICU admissions, supporting MRI’s role in acute neck infections.

目的：我们评估了危险因素，并根据急性颈部感染的MRI结果和临床数据制定了预测重症监护病房（ICU）入院的评分。方法回顾性研究mri确诊的急性颈部感染患者。在钆后t1加权Dixon MRI上测量脓肿直径，在脂肪抑制的t2加权Dixon MRI上评估特定水肿模式，咽后（RPE）和纵隔水肿。多变量逻辑回归模型确定了ICU入院的预测因素，并根据回归系数得出风险评分。利用接收机工作特性分析的曲线下面积（AUC）来评估模型性能。机器学习模型（随机森林，XGBoost，支持向量机，神经网络）进行了测试。结果共纳入535例患者，其中373例（70 %）存在脓肿，62例（12 %）需要ICU治疗。RPE、最大脓肿直径（≥40 mm）和c反应蛋白（CRP）（≥172 mg/L）是ICU入院的重要预测因素。风险评分(0−7)(AUC = 0.82, 95 %可信区间(CI) 0.77 - -0.88)优于CRP (AUC = 0.73, 95 %可信区间0.66 - -0.80,p = 0.001),最大直径脓肿(AUC = 0.72, 95 %可信区间0.64 - -0.80,p & lt; 0.001),和RPE (AUC = 0.71, 95 %可信区间0.65 - -0.77,p & lt; 0.001)。截止值>； 3的风险评分产生以下指标：敏感性66 %，特异性82 %，阳性预测值33 %，阴性预测值95 %，准确性80 %，优势比9.0。在内部验证（AUC=0.83）和保留验证（AUC=0.81）中，判别性能是稳健的。ML模型并不优于回归模型。结论结合RPE、脓肿大小和CRP的风险模型对ICU入院患者具有中等准确性和较高的阴性预测值，支持MRI在急性颈部感染中的作用。

{"title":"MRI-based risk factors for intensive care unit admissions in acute neck infections","authors":"Jari-Pekka Vierula , Harri Merisaari , Jaakko Heikkinen , Tatu Happonen , Aapo Sirén , Jarno Velhonoja , Heikki Irjala , Tero Soukka , Kimmo Mattila , Mikko Nyman , Janne Nurminen , Jussi Hirvonen","doi":"10.1016/j.ejro.2025.100648","DOIUrl":"10.1016/j.ejro.2025.100648","url":null,"abstract":"<div><h3>Objectives</h3><div>We assessed risk factors and developed a score to predict intensive care unit (ICU) admissions using MRI findings and clinical data in acute neck infections.</div></div><div><h3>Methods</h3><div>This retrospective study included patients with MRI-confirmed acute neck infection. Abscess diameters were measured on post-gadolinium T1-weighted Dixon MRI, and specific edema patterns, retropharyngeal (RPE) and mediastinal edema, were assessed on fat-suppressed T2-weighted Dixon MRI. A multivariate logistic regression model identified ICU admission predictors, with risk scores derived from regression coefficients. Model performance was evaluated using the area under the curve (AUC) from receiver operating characteristic analysis. Machine learning models (random forest, XGBoost, support vector machine, neural networks) were tested.</div></div><div><h3>Results</h3><div>The sample included 535 patients, of whom 373 (70 %) had an abscess, and 62 (12 %) required ICU treatment. Significant predictors for ICU admission were RPE, maximal abscess diameter (≥40 mm), and C-reactive protein (CRP) (≥172 mg/L). The risk score (0−7) (AUC=0.82, 95 % confidence interval [CI] 0.77–0.88) outperformed CRP (AUC=0.73, 95 % CI 0.66–0.80, p = 0.001), maximal abscess diameter (AUC=0.72, 95 % CI 0.64–0.80, p < 0.001), and RPE (AUC=0.71, 95 % CI 0.65–0.77, p < 0.001). The risk score at a cut-off > 3 yielded the following metrics: sensitivity 66 %, specificity 82 %, positive predictive value 33 %, negative predictive value 95 %, accuracy 80 %, and odds ratio 9.0. Discriminative performance was robust in internal (AUC=0.83) and hold-out (AUC=0.81) validations. ML models were not better than regression models.</div></div><div><h3>Conclusions</h3><div>A risk model incorporating RPE, abscess size, and CRP showed moderate accuracy and high negative predictive value for ICU admissions, supporting MRI’s role in acute neck infections.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100648"},"PeriodicalIF":1.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143746740","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

Assessment of bone-implant interface image quality for in-vivo acetabular cup implants using photon-counting detector CT: Impact of tin pre-filtration 利用光子计数检测器CT评估体内髋臼杯植入物骨-植入物界面图像质量：锡预过滤的影响

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-03-27 DOI: 10.1016/j.ejro.2025.100646

Ronald Booij , Pauline de Klerk , Erik Tesselaar , Mischa Woisetschläger , Anne Brandts , Mariëlle Olsthoorn , Jakob van Oldenrijk , Koen Bos , Jörg Schilcher , Edwin H.G. Oei

Purpose

To assess the image quality of the bone-implant interface of acetabular cup implants using photon-counting detector (PCD) CT with and without tin pre-filtration in a clinical setting.

Methods and materials

Twenty-four patients underwent PCD-CT imaging of their total hip replacement (THR). Twelve patients were scanned using 140 kVp and twelve patients using 140 kVp with tin pre-filtration (Sn140 kVp). All scans were acquired with a collimation of 120 × 0.2 mm. The acquired data was reconstructed with different slice thickness (0.2 mm – 0.6 mm) and kernel (Qr) strengths (56, 76, 89) with and without metal artifact reduction (iMAR). Two observers assessed the image quality of the bone-implant interface for the cup based on four image quality criteria. Bone contrast, contrast-to-noise ratio (CNR) of bone/fat and cortical sharpness was performed as quantitative measures.

Results

Image quality was rated highest for 0.2 mm slice thickness and Qr89 kernel across all four criteria for both the 140 kVp and Sn140 kVp by both observers, with a slight preference for the Sn140kVp over the 140 kVp. In all cases and for all image criteria the 0.2 mm/Qr89 was preferred above the Qr76 and Qr56/iMAR for both the 140 kVp and Sn140 kVp by both observers. Quantitative measurements confirmed significantly improved bone contrast as well as cortical sharpness using 0.2 mm/Qr89. Tin pre-filtration did not affect the CNR at 0.2 mm/Qr89 but tended to decrease cortical sharpness.

Conclusions

High resolution PCD-CT allows for in-vivo assessment of the bone-implant interface in patients with THR and is preferably acquired with tin pre-filtration.

目的在临床应用光子计数CT （PCD）对有锡预滤和无锡预滤的髋臼杯状假体骨-假体界面图像质量进行评价。方法与材料24例患者行全髋关节置换术（THR）的PCD-CT成像。12例患者使用140 kVp进行扫描，12例患者使用140 kVp进行锡预过滤（Sn140 kVp）。所有扫描都是在120 × 0.2 mm的准直下获得的。用不同的切片厚度（0.2 mm - 0.6 mm）和核（Qr）强度（56、76、89）对采集的数据进行重建，并进行金属伪影还原（iMAR）。两名观察员根据四项图像质量标准评估骨-种植体杯界面的图像质量。骨对比，骨/脂肪对比噪声比（CNR）和皮质锐度作为定量测量。结果在140kVp和Sn140kVp的所有四个标准中，两个观察者对0.2 mm切片厚度和Qr89内核的图像质量评价最高，Sn140kVp略高于140kVp。在所有情况下，对于所有图像标准，对于140 kVp和Sn140 kVp， 0.2 mm/Qr89优于Qr76和Qr56/iMAR。定量测量证实，使用0.2 mm/Qr89可显著改善骨对比和皮质锐度。在0.2 mm/Qr89时，锡预滤不影响CNR，但有降低皮质锐度的趋势。结论高分辨率PCD-CT可以在体内评估THR患者的骨-种植体界面，并且最好通过锡预过滤获得。

{"title":"Assessment of bone-implant interface image quality for in-vivo acetabular cup implants using photon-counting detector CT: Impact of tin pre-filtration","authors":"Ronald Booij , Pauline de Klerk , Erik Tesselaar , Mischa Woisetschläger , Anne Brandts , Mariëlle Olsthoorn , Jakob van Oldenrijk , Koen Bos , Jörg Schilcher , Edwin H.G. Oei","doi":"10.1016/j.ejro.2025.100646","DOIUrl":"10.1016/j.ejro.2025.100646","url":null,"abstract":"<div><h3>Purpose</h3><div>To assess the image quality of the bone-implant interface of acetabular cup implants using photon-counting detector (PCD) CT with and without tin pre-filtration in a clinical setting.</div></div><div><h3>Methods and materials</h3><div>Twenty-four patients underwent PCD-CT imaging of their total hip replacement (THR). Twelve patients were scanned using 140 kVp and twelve patients using 140 kVp with tin pre-filtration (Sn140 kVp). All scans were acquired with a collimation of 120 × 0.2 mm. The acquired data was reconstructed with different slice thickness (0.2 mm – 0.6 mm) and kernel (Qr) strengths (56, 76, 89) with and without metal artifact reduction (iMAR). Two observers assessed the image quality of the bone-implant interface for the cup based on four image quality criteria. Bone contrast, contrast-to-noise ratio (CNR) of bone/fat and cortical sharpness was performed as quantitative measures.</div></div><div><h3>Results</h3><div>Image quality was rated highest for 0.2 mm slice thickness and Qr89 kernel across all four criteria for both the 140 kVp and Sn140 kVp by both observers, with a slight preference for the Sn140kVp over the 140 kVp. In all cases and for all image criteria the 0.2 mm/Qr89 was preferred above the Qr76 and Qr56/iMAR for both the 140 kVp and Sn140 kVp by both observers. Quantitative measurements confirmed significantly improved bone contrast as well as cortical sharpness using 0.2 mm/Qr89. Tin pre-filtration did not affect the CNR at 0.2 mm/Qr89 but tended to decrease cortical sharpness.</div></div><div><h3>Conclusions</h3><div>High resolution PCD-CT allows for in-vivo assessment of the bone-implant interface in patients with THR and is preferably acquired with tin pre-filtration.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100646"},"PeriodicalIF":1.8,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143705470","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

Implementation of an automated breast ultrasound system in an academic radiology department: Lesson learned in the first three years 在学术放射科实施自动乳腺超声系统：头三年的经验教训

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-03-25 DOI: 10.1016/j.ejro.2025.100645

Elizabet Nikolova , Julia Weber , Giulia Zanetti , Jann Wieler , Thomas Frauenfelder , Andreas Boss , Magda Marcon

Purpose

To evaluate the diagnostic performance of an ABUS in an academic radiology department over the first three years after its implementation.

Methods

In this retrospective study women undergoing ABUS examination for screening and diagnostic purposes between October 2015–2018 were included in case of sufficient follow-up and established diagnosis. Women underwent ABUS + /- mammography in the same day. BI-RADS 1/ 2 cases with cancer diagnosis during follow-up and already visible in the previous exam were considered false negative (FN). BI-RADS 3/4 cases proved benign were considered false positive (FP). FP and number of additional targeted HHUS (addHHUS) were compared over the three years.

Results

1248 women (51.2 ± 11.2 years) were included: 956 (77.3 %) underwent ABUS+mammography; 283 (29.3 %) ABUS only. Mean follow-up ± SD was 53.5 ± 17.8 month. Thirty-three malignancies were present in the investigated exams. In 28/ 33 cases (84.8 %), lesions were classified BI-RADS 4 or 5 and one (3.6 %) lesion was only visible in ABUS. 3/33 malignancies (9 %) were classified BI-RADS 3. 2/33 (6 %) were visible in mammography and ABUS but not recognized and classified BI-RADS 2 (FN rate 6.1 %). Retrospectively, both cases had “retraction phenomenon sign” in the coronal images. BI-RADS 3 and BI-RADS 4 without a malignancy were attributed to 172 (13.8 %) and 14 (1.1 %) cases, respectively corresponding to a FP rate of 15.3 %. The number of FP as well as the number of addHHUS significantly reduced over the three years (both p < 0.001).

Conclusions

After the implementation of an ABUS FP cases and addHHUS reduce over the time.

目的评价ABUS在某学术放射科实施后3年内的诊断效果。方法在本回顾性研究中，纳入了2015年10月至2018年10月期间接受ABUS筛查和诊断的女性，这些女性均有足够的随访和明确的诊断。妇女在同一天接受了ABUS + /-乳房x光检查。1/ 2的BI-RADS患者在随访期间诊断为癌症，且在之前的检查中已经可见，被认为是假阴性（FN）。3/4的BI-RADS呈良性，被认为是假阳性（FP）。比较了三年来FP和额外靶向HHUS （addHHUS）的数量。结果纳入1248例女性（51.2 ± 11.2岁）：956例（77.3% %）行ABUS+乳房x光检查；283（29.3 %）仅限ABUS。平均随访时间± SD为53.5 ± 17.8个月。在调查的检查中发现33例恶性肿瘤。28/ 33例（84.8 %）病变被划分为BI-RADS 4或5级，1例（3.6 %）病变仅在ABUS中可见。3/33例恶性肿瘤（9 %）BI-RADS为3级。2/33（6 %）在乳腺x线摄影和ABUS中可见，但未被识别和分类为BI-RADS 2 （FN率6.1 %）。回顾性分析，两例患者冠状像均有“缩进现象征”。无恶性BI-RADS 3和BI-RADS 4分别为172例（13.8 %）和14例（1.1 %），FP率分别为15.3 %。三年中，FP的数量以及addhsus的数量显著减少（p均为 <； 0.001）。结论实施ABUS后，FP病例和addhus随时间的推移而减少。

{"title":"Implementation of an automated breast ultrasound system in an academic radiology department: Lesson learned in the first three years","authors":"Elizabet Nikolova , Julia Weber , Giulia Zanetti , Jann Wieler , Thomas Frauenfelder , Andreas Boss , Magda Marcon","doi":"10.1016/j.ejro.2025.100645","DOIUrl":"10.1016/j.ejro.2025.100645","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the diagnostic performance of an ABUS in an academic radiology department over the first three years after its implementation.</div></div><div><h3>Methods</h3><div>In this retrospective study women undergoing ABUS examination for screening and diagnostic purposes between October 2015–2018 were included in case of sufficient follow-up and established diagnosis. Women underwent ABUS + /- mammography in the same day. BI-RADS 1/ 2 cases with cancer diagnosis during follow-up and already visible in the previous exam were considered false negative (FN). BI-RADS 3/4 cases proved benign were considered false positive (FP). FP and number of additional targeted HHUS (addHHUS) were compared over the three years.</div></div><div><h3>Results</h3><div>1248 women (51.2 ± 11.2 years) were included: 956 (77.3 %) underwent ABUS+mammography; 283 (29.3 %) ABUS only. Mean follow-up ± SD was 53.5 ± 17.8 month. Thirty-three malignancies were present in the investigated exams. In 28/ 33 cases (84.8 %), lesions were classified BI-RADS 4 or 5 and one (3.6 %) lesion was only visible in ABUS. 3/33 malignancies (9 %) were classified BI-RADS 3. 2/33 (6 %) were visible in mammography and ABUS but not recognized and classified BI-RADS 2 (FN rate 6.1 %). Retrospectively, both cases had “retraction phenomenon sign” in the coronal images. BI-RADS 3 and BI-RADS 4 without a malignancy were attributed to 172 (13.8 %) and 14 (1.1 %) cases, respectively corresponding to a FP rate of 15.3 %. The number of FP as well as the number of addHHUS significantly reduced over the three years (both p < 0.001).</div></div><div><h3>Conclusions</h3><div>After the implementation of an ABUS FP cases and addHHUS reduce over the time.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100645"},"PeriodicalIF":1.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687569","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