Academic Radiology最新文献

英文中文

Editorial Comment: On a New Kind of Radiology—The Nascent Technologies and the Future of Our Profession 编辑评论：一种新的放射学——新生技术和我们职业的未来。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2026-03-02 DOI: 10.1016/j.acra.2026.01.020

Anna Rozenshtein MD, MPH

引用次数: 0

AI as an Education Tool for Radiology Residents 人工智能作为放射科住院医师的教育工具。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2025-08-29 DOI: 10.1016/j.acra.2025.08.025

Youngjae Cha BA , Omer A. Awan MD MPH CIIP

引用次数: 0

Letter to the Editor Re: "Automatic Identification of the Reference System Based on the Fourth Ventricular Landmarks in T1-weighted MR Images" 回复：“基于t1加权MR图像中第四心室标志的参考系统自动识别”。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2025-12-01 DOI: 10.1016/j.acra.2025.11.029

Michael Jesus Martinez MD Candidate

引用次数: 0

Prediction of Obstructive Sleep Apnea Using Hypothalamic Radiomics and Machine Learning 使用下丘脑放射组学和机器学习预测阻塞性睡眠呼吸暂停。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2025-12-16 DOI: 10.1016/j.acra.2025.11.044

Zhenliang Xiong , Youquan Ning , Yinglin Zhou , Yan Gong , Yuwan Yang , Lisha Nie , Rongpin Wang , Xianchun Zeng

Rationale and Objectives

To explore the potential of hypothalamic radiomics derived from T1-weighted magnetic resonance imaging (MRI) as an exploratory biomarker for predicting obstructive sleep apnea (OSA).

Methods

This study included 251 participants, comprising 127 OSA patients and 124 healthy controls (HCs), from two medical centers. Hypothalamic subunits were automatically segmented by a published deep convolutional neural network on 3D T1-weighted MRI. Radiomics features were extracted using PyRadiomics, including shape, first-order, texture, and wavelet features. Feature selection was performed using the Mann-Whitney U test, Pearson correlation, and LASSO regression. Seven classifiers were trained with three input types: clinical-only, radiomics-only, and radiomics-clinical. Model performance was evaluated using AUC, accuracy, precision, F1-score, and specificity in both internal and independent external validation cohorts. SHapley Additive exPlanations (SHAP) analysis was used to identify key predictive features.

Results

A total of 4255 radiomics features were extracted, with 52 retained after feature selection. The radiomics-clinical Gradient Boosting Machine (GBM) model achieved the best performance, with an AUC of 0.808 in the internal validation cohort and 0.777 in the external validation cohort. Body mass index (BMI) was the most influential predictor, followed by radiomics features, notably the wavelet-LHL_firstorder_InterquartileRange_posterior from the posterior hypothalamic subunit.

Conclusions

Hypothalamic radiomics combined with clinical features offers a promising exploratory approach for predicting OSA. These findings highlight the potential of radiomics in identifying hypothalamic changes associated with OSA.

理由和目的：探讨来自t1加权磁共振成像（MRI）的下丘脑放射组学作为预测阻塞性睡眠呼吸暂停（OSA）的探索性生物标志物的潜力。方法：本研究包括来自两个医疗中心的251名参与者，其中包括127名OSA患者和124名健康对照（hc）。下丘脑亚单位通过已发表的深度卷积神经网络在3D t1加权MRI上自动分割。利用PyRadiomics提取放射组学特征，包括形状、一阶、纹理和小波特征。使用Mann-Whitney U检验、Pearson相关和LASSO回归进行特征选择。七个分类器用三种输入类型进行训练：仅临床、仅放射组学和放射组学-临床。在内部和独立的外部验证队列中，使用AUC、准确度、精密度、f1评分和特异性来评估模型的性能。SHapley加性解释（SHAP）分析用于识别关键预测特征。结果：共提取放射组学特征4255个，经特征选择后保留52个。放射组学-临床梯度增强机（GBM）模型表现最佳，内部验证队列的AUC为0.808，外部验证队列的AUC为0.777。身体质量指数（BMI）是最具影响力的预测因子，其次是放射组学特征，特别是来自下丘脑后亚基的小波- lhl_firstorder_interquartilerange_posterior。结论：下丘脑放射组学结合临床特征为预测OSA提供了一种有前景的探索性方法。这些发现强调了放射组学在识别与OSA相关的下丘脑变化方面的潜力。

{"title":"Prediction of Obstructive Sleep Apnea Using Hypothalamic Radiomics and Machine Learning","authors":"Zhenliang Xiong , Youquan Ning , Yinglin Zhou , Yan Gong , Yuwan Yang , Lisha Nie , Rongpin Wang , Xianchun Zeng","doi":"10.1016/j.acra.2025.11.044","DOIUrl":"10.1016/j.acra.2025.11.044","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To explore the potential of hypothalamic radiomics derived from T1-weighted magnetic resonance imaging (MRI) as an exploratory biomarker for predicting obstructive sleep apnea (OSA).</div></div><div><h3>Methods</h3><div>This study included 251 participants, comprising 127 OSA patients and 124 healthy controls (HCs), from two medical centers. Hypothalamic subunits were automatically segmented by a published deep convolutional neural network on 3D T1-weighted MRI. Radiomics features were extracted using PyRadiomics, including shape, first-order, texture, and wavelet features. Feature selection was performed using the Mann-Whitney U test, Pearson correlation, and LASSO regression. Seven classifiers were trained with three input types: clinical-only, radiomics-only, and radiomics-clinical. Model performance was evaluated using AUC, accuracy, precision, F1-score, and specificity in both internal and independent external validation cohorts. SHapley Additive exPlanations (SHAP) analysis was used to identify key predictive features.</div></div><div><h3>Results</h3><div>A total of 4255 radiomics features were extracted, with 52 retained after feature selection. The radiomics-clinical Gradient Boosting Machine (GBM) model achieved the best performance, with an AUC of 0.808 in the internal validation cohort and 0.777 in the external validation cohort. Body mass index (BMI) was the most influential predictor, followed by radiomics features, notably the wavelet-LHL_firstorder_InterquartileRange_posterior from the posterior hypothalamic subunit.</div></div><div><h3>Conclusions</h3><div>Hypothalamic radiomics combined with clinical features offers a promising exploratory approach for predicting OSA. These findings highlight the potential of radiomics in identifying hypothalamic changes associated with OSA.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 3","pages":"Pages 1095-1104"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145769921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Author Response to “Letter to Editor: Deep Learning-Based Differentiation of DCIS and IDC from Mammographic Microcalcifications” 作者回复“致编辑的信：基于深度学习的乳腺造影微钙化中DCIS和IDC的鉴别”。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2025-12-20 DOI: 10.1016/j.acra.2025.12.001

Wenjie Xu , Yongyu An

引用次数: 0

Harnessing Large Language Models for Radiology Report Simplification and Improving Patient Comprehension: A Narrative Review 利用大型语言模型简化放射学报告和提高患者理解：叙述回顾。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2026-01-03 DOI: 10.1016/j.acra.2025.12.008

Shreyas U. Naidu B.S. , Hanzhou Li M.D , John T. Moon M.D , Ryan Kim , Emily Patel BS , Zachary L. Bercu M.D , Janice Newsome MD , Judy W. Gichoya M.D, MS , Hari Trivedi MD

Radiological reports are essential clinical documents often written in highly technical language that is challenging for patients to comprehend. Despite advancements in digital imaging and reporting technologies, the inherent complexity of radiology reports creates significant barriers to effective patient understanding. Recently, large language models (LLMs) have emerged as a promising solution to simplify radiological reports. Therefore, this narrative review aims to provide a comprehensive overview of LLMs for simplifying patient-centered radiology reports. We examined 19 studies evaluating various LLMs including GPT-3.5, GPT-4, Claude, Gemini, and others across multiple imaging modalities. All studies reported descriptive/consistent improvements in readability metrics, with simplified reports typically achieving 5th-8th grade reading levels compared to the original 10th-14th grade levels. However, many studies identified accuracy concerns, with reports containing a range of omissions, commissions, and distortions depending on modality and model. Building upon these findings, we discuss medicolegal considerations, workflow integration challenges, and strategies for effective LLM implementation. We also explore potential impacts on radiologist workflow, including the impact of LLM biases and liability for simplified reports. Despite promising results, significant challenges remain in ensuring accurate simplification across diverse patient populations while maintaining clinical precision. In conclusion, this review underscores the transformative potential of LLMs in enhancing patient understanding of radiological findings while highlighting the need for careful implementation with appropriate oversight mechanisms.

放射报告是重要的临床文件，通常用高度技术性的语言书写，对患者来说是具有挑战性的理解。尽管数字成像和报告技术取得了进步，但放射学报告固有的复杂性为有效的患者理解造成了重大障碍。最近，大型语言模型（llm）作为简化放射学报告的一种有希望的解决方案出现了。因此，本综述旨在为简化以患者为中心的放射学报告提供法学硕士的全面概述。我们检查了19项研究，评估了各种llm，包括GPT-3.5、GPT-4、Claude、Gemini等多种成像方式。所有研究都报告了可读性指标的描述性/一致性改进，与原来的10 -14年级水平相比，简化的报告通常达到5 -8年级的阅读水平。然而，许多研究发现了准确性问题，根据模式和模型的不同，报告中包含了一系列的遗漏、佣金和扭曲。在这些发现的基础上，我们讨论了医学方面的考虑，工作流集成的挑战，以及有效实施法学硕士的策略。我们还探讨了对放射科医生工作流程的潜在影响，包括LLM偏差的影响和简化报告的责任。尽管结果令人鼓舞，但在确保不同患者群体的准确简化同时保持临床精度方面仍然存在重大挑战。总之，这篇综述强调了法学硕士在增强患者对放射学发现的理解方面的变革潜力，同时强调了在适当的监督机制下谨慎实施的必要性。

{"title":"Harnessing Large Language Models for Radiology Report Simplification and Improving Patient Comprehension: A Narrative Review","authors":"Shreyas U. Naidu B.S. , Hanzhou Li M.D , John T. Moon M.D , Ryan Kim , Emily Patel BS , Zachary L. Bercu M.D , Janice Newsome MD , Judy W. Gichoya M.D, MS , Hari Trivedi MD","doi":"10.1016/j.acra.2025.12.008","DOIUrl":"10.1016/j.acra.2025.12.008","url":null,"abstract":"<div><div>Radiological reports are essential clinical documents often written in highly technical language that is challenging for patients to comprehend. Despite advancements in digital imaging and reporting technologies, the inherent complexity of radiology reports creates significant barriers to effective patient understanding. Recently, large language models (LLMs) have emerged as a promising solution to simplify radiological reports. Therefore, this narrative review aims to provide a comprehensive overview of LLMs for simplifying patient-centered radiology reports. We examined 19 studies evaluating various LLMs including GPT-3.5, GPT-4, Claude, Gemini, and others across multiple imaging modalities. All studies reported descriptive/consistent improvements in readability metrics, with simplified reports typically achieving 5th-8th grade reading levels compared to the original 10th-14th grade levels. However, many studies identified accuracy concerns, with reports containing a range of omissions, commissions, and distortions depending on modality and model. Building upon these findings, we discuss medicolegal considerations, workflow integration challenges, and strategies for effective LLM implementation. We also explore potential impacts on radiologist workflow, including the impact of LLM biases and liability for simplified reports. Despite promising results, significant challenges remain in ensuring accurate simplification across diverse patient populations while maintaining clinical precision. In conclusion, this review underscores the transformative potential of LLMs in enhancing patient understanding of radiological findings while highlighting the need for careful implementation with appropriate oversight mechanisms.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 3","pages":"Pages 762-773"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145901629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Teleradiology, Edge Computing, and the Internet of Things in Radiology: A RRA Perspective on Decentralized Diagnostics 远程放射学、边缘计算和放射学中的物联网：分散诊断的RRA视角。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2026-03-02 DOI: 10.1016/j.acra.2025.12.040

Vidya Sankar Viswanathan MBBS , Daphne Zhu BS , Dogan Polat MD , Florence Doo MD , Christopher Straus MD , Anna Rozenshtein MD, MPH , Michele Retrouvey MD

Radiology is undergoing a fundamental transformation driven by the convergence of teleradiology, edge computing, and the Internet of Things (IoT). These technologies are reshaping traditional imaging workflows by enabling data to be acquired, processed, and interpreted in near real time across distributed networks. This shift from centralized, linear systems to decentralized, intelligent architectures enhance diagnostic responsiveness, improves access to subspecialty care, and supports more personalized and context-aware decision-making. IoT devices, ranging from mobile X-ray units to AI-enabled ultrasound systems, extend diagnostic capabilities to the point of care, while edge computing reduces latency and safeguards sensitive data through localized processing. Teleradiology integrates these tools by enabling remote interpretation and cross-institutional collaboration, expanding coverage and facilitating workflow scalability. Together, these technologies form an interdependent ecosystem that is particularly impactful in rural, low-bandwidth, and resource-constrained environments. However, their integration also raises new ethical, regulatory, and operational challenges, including concerns about algorithm transparency, data security, and workforce identity. As part 4 of the Radiology Research Alliance (RRA) review series on emerging technologies, this paper explores the opportunities and challenges of decentralized diagnostics and their implications for the future of radiology practice.

在远程放射学、边缘计算和物联网（IoT）融合的推动下，放射学正在经历一场根本性的变革。这些技术通过在分布式网络中近乎实时地获取、处理和解释数据，正在重塑传统的成像工作流程。这种从集中式线性系统到分散式智能架构的转变增强了诊断响应能力，改善了亚专科护理的可及性，并支持更加个性化和情境感知的决策。从移动x射线设备到支持人工智能的超声波系统，物联网设备将诊断功能扩展到护理点，而边缘计算则通过本地化处理减少延迟并保护敏感数据。远程放射学通过支持远程解释和跨机构协作、扩大覆盖范围和促进工作流可扩展性来集成这些工具。这些技术共同构成了一个相互依存的生态系统，在农村、低带宽和资源受限的环境中尤其具有影响力。然而，它们的整合也带来了新的道德、监管和运营挑战，包括对算法透明度、数据安全性和劳动力身份的担忧。作为放射学研究联盟（RRA）新兴技术回顾系列的第4部分，本文探讨了分散诊断的机遇和挑战及其对放射学实践未来的影响。

{"title":"Teleradiology, Edge Computing, and the Internet of Things in Radiology: A RRA Perspective on Decentralized Diagnostics","authors":"Vidya Sankar Viswanathan MBBS , Daphne Zhu BS , Dogan Polat MD , Florence Doo MD , Christopher Straus MD , Anna Rozenshtein MD, MPH , Michele Retrouvey MD","doi":"10.1016/j.acra.2025.12.040","DOIUrl":"10.1016/j.acra.2025.12.040","url":null,"abstract":"<div><div>Radiology is undergoing a fundamental transformation driven by the convergence of teleradiology, edge computing, and the Internet of Things (IoT). These technologies are reshaping traditional imaging workflows by enabling data to be acquired, processed, and interpreted in near real time across distributed networks. This shift from centralized, linear systems to decentralized, intelligent architectures enhance diagnostic responsiveness, improves access to subspecialty care, and supports more personalized and context-aware decision-making. IoT devices, ranging from mobile X-ray units to AI-enabled ultrasound systems, extend diagnostic capabilities to the point of care, while edge computing reduces latency and safeguards sensitive data through localized processing. Teleradiology integrates these tools by enabling remote interpretation and cross-institutional collaboration, expanding coverage and facilitating workflow scalability. Together, these technologies form an interdependent ecosystem that is particularly impactful in rural, low-bandwidth, and resource-constrained environments. However, their integration also raises new ethical, regulatory, and operational challenges, including concerns about algorithm transparency, data security, and workforce identity. As part 4 of the Radiology Research Alliance (RRA) review series on emerging technologies, this paper explores the opportunities and challenges of decentralized diagnostics and their implications for the future of radiology practice.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 3","pages":"Pages 646-652"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147357273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Expanding Artificial Intelligence Translation Research to More Complex Radiology Reports and Diverse Sociocultural Cohorts 将人工智能翻译研究扩展到更复杂的放射学报告和不同的社会文化群体。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2025-10-28 DOI: 10.1016/j.acra.2025.10.019

Deniz Esin Tekcan Sanli MD , Ahmet Necati Sanli MD

引用次数: 0

In Reply: Toward Multilingual, Patient-Centered AI Translations of Radiology Reports 回复：面向多语言、以患者为中心的放射学报告人工智能翻译。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2025-10-30 DOI: 10.1016/j.acra.2025.10.018

André Euler MD, MHBA, EBCR, Dusan Pisarcik, Rahel A. Kubik-Huch

引用次数: 0

A Multi-view Deep Survival Combined Model for Predicting Stroke Recurrence in Symptomatic Intracranial Atherosclerosis 多视角深度生存联合模型预测症状性颅内动脉粥样硬化卒中复发。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-03-01 Epub Date: 2025-11-15 DOI: 10.1016/j.acra.2025.10.052

Ziang Li , Tingting Huang , Lan Zhang , Xiaoyang Zhai , Qiuyi Zhao , Hanqi Lu , Qian Xu , Lin Han , Jie Wang , Gang Zhang , Yu Gao

Background

Symptomatic intracranial atherosclerotic stenosis (sICAS) is associated with a high risk of stroke recurrence. Current risk stratification approaches based on high-resolution vessel wall imaging (HR-VWI) remain dependent on subjective human assessment, which limits their precision.

Methods

From June 2020 to December 2024, HR-VWI images were retrospectively collected from 363 patients with sICAS across 2 medical institutions. Among the 363 patients, there were 79 cases of stroke recurrence (21.76%) and 284 cases without recurrence (78.24%). The cohort was divided into a Training/Validation set (n = 290) and a Test set (n = 73). Using the T1-weighted contrast-enhanced sequence, we developed a Multi-View Deep Survival Combined Model. This model employs a Vision Transformer and radiomics to analyze MR images and uses DeepSurv to extend the modeling capacity of the traditional Cox proportional hazards model. It enables the prediction of stroke recurrence risk related to intracranial culprit plaques. Model performance was evaluated using time-dependent receiver operating characteristic curves and the C-index. Additionally, decision curve analysis and calibration curves were used to comprehensively validate the model’s practical value and clinical application prospects.

Results

The Combined Model exhibited superior predictive performance, achieving a C-index of 0.872 (95% CI: 0.785–0.958) in the internal validation set and 0.803 (95% CI: 0.711–0.895) in the external test set. This performance significantly outperformed that of clinical models, radiomics models, and standalone deep learning models. The model also demonstrated excellent time-dependent predictive accuracy for 1, 2, and 3-year recurrence (area under the curve: 0.841, 0.870, and 0.802, respectively). Calibration and decision curve analysis confirmed the model’s clinical utility.

Conclusion

By integrating automated multi-view deep feature learning and DeepSurv-based survival analysis, the Combined Model provides a robust and objective tool for stratifying recurrence risk in patients with sICAS. It outperforms conventional methods and holds significant potential for guiding personalized secondary prevention strategies.

背景：症状性颅内动脉粥样硬化性狭窄（sICAS）与卒中复发的高风险相关。目前基于高分辨率血管壁成像（HR-VWI）的风险分层方法仍然依赖于主观的人类评估，这限制了它们的准确性。方法：回顾性收集2020年6月至2024年12月2家医疗机构363例sICAS患者的HR-VWI图像。363例患者中卒中复发79例（21.76%），无复发284例（78.24%）。将队列分为训练/验证集（n=290）和测试集（n=73）。使用t1加权对比度增强序列，我们开发了一个多视图深度生存组合模型。该模型采用Vision Transformer和radiomics对MR图像进行分析，并使用DeepSurv扩展了传统Cox比例风险模型的建模能力。它能够预测颅内罪魁祸首斑块相关的卒中复发风险。使用随时间变化的接收者工作特征曲线和c指数来评估模型的性能。采用决策曲线分析和标定曲线综合验证模型的实用价值和临床应用前景。结果：联合模型具有较好的预测性能，内部验证集的c指数为0.872 (95% CI: 0.785-0.958)，外部检验集的c指数为0.803 （95% CI: 0.711-0.895）。该性能明显优于临床模型、放射组学模型和独立深度学习模型。该模型还对1年、2年和3年的复发表现出极好的随时间变化的预测精度（曲线下面积分别为0.841、0.870和0.802）。校正和决策曲线分析证实了该模型的临床实用性。结论：通过集成自动化多视图深度特征学习和基于deepsurv的生存分析，联合模型为sICAS患者的复发风险分层提供了一个强大而客观的工具。它优于传统方法，并具有指导个性化二级预防战略的巨大潜力。

{"title":"A Multi-view Deep Survival Combined Model for Predicting Stroke Recurrence in Symptomatic Intracranial Atherosclerosis","authors":"Ziang Li , Tingting Huang , Lan Zhang , Xiaoyang Zhai , Qiuyi Zhao , Hanqi Lu , Qian Xu , Lin Han , Jie Wang , Gang Zhang , Yu Gao","doi":"10.1016/j.acra.2025.10.052","DOIUrl":"10.1016/j.acra.2025.10.052","url":null,"abstract":"<div><h3>Background</h3><div>Symptomatic intracranial atherosclerotic stenosis (sICAS) is associated with a high risk of stroke recurrence. Current risk stratification approaches based on high-resolution vessel wall imaging (HR-VWI) remain dependent on subjective human assessment, which limits their precision.</div></div><div><h3>Methods</h3><div>From June 2020 to December 2024, HR-VWI images were retrospectively collected from 363 patients with sICAS across 2 medical institutions. Among the 363 patients, there were 79 cases of stroke recurrence (21.76%) and 284 cases without recurrence (78.24%). The cohort was divided into a Training/Validation set <em>(n  </em>=73). Using the T1-weighted contrast-enhanced sequence, we developed a Multi-View Deep Survival Combined Model. This model employs a Vision Transformer and radiomics to analyze MR images and uses DeepSurv to extend the modeling capacity of the traditional Cox proportional hazards model. It enables the prediction of stroke recurrence risk related to intracranial culprit plaques. Model performance was evaluated using time-dependent receiver operating characteristic curves and the C-index. Additionally, decision curve analysis and calibration curves were used to comprehensively validate the model’s practical value and clinical application prospects.</div></div><div><h3>Results</h3><div>The Combined Model exhibited superior predictive performance, achieving a C-index of 0.872 (95% CI: 0.785–0.958) in the internal validation set and 0.803 (95% CI: 0.711–0.895) in the external test set. This performance significantly outperformed that of clinical models, radiomics models, and standalone deep learning models. The model also demonstrated excellent time-dependent predictive accuracy for 1, 2, and 3-year recurrence (area under the curve: 0.841, 0.870, and 0.802, respectively). Calibration and decision curve analysis confirmed the model’s clinical utility.</div></div><div><h3>Conclusion</h3><div>By integrating automated multi-view deep feature learning and DeepSurv-based survival analysis, the Combined Model provides a robust and objective tool for stratifying recurrence risk in patients with sICAS. It outperforms conventional methods and holds significant potential for guiding personalized secondary prevention strategies.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 3","pages":"Pages 1070-1082"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145535022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Academic Radiology

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.

﹀