首页 > 最新文献

Radiology-Artificial Intelligence最新文献

英文 中文
Editor's Recognition Awards.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.250164
Charles E Kahn
{"title":"Editor's Recognition Awards.","authors":"Charles E Kahn","doi":"10.1148/ryai.250164","DOIUrl":"https://doi.org/10.1148/ryai.250164","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"7 2","pages":"e250164"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143711539","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
CMRxRecon2024: A Multimodality, Multiview k-Space Dataset Boosting Universal Machine Learning for Accelerated Cardiac MRI.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.240443
Zi Wang, Fanwen Wang, Chen Qin, Jun Lyu, Cheng Ouyang, Shuo Wang, Yan Li, Mengyao Yu, Haoyu Zhang, Kunyuan Guo, Zhang Shi, Qirong Li, Ziqiang Xu, Yajing Zhang, Hao Li, Sha Hua, Binghua Chen, Longyu Sun, Mengting Sun, Qing Li, Ying-Hua Chu, Wenjia Bai, Jing Qin, Xiahai Zhuang, Claudia Prieto, Alistair Young, Michael Markl, He Wang, Lian-Ming Wu, Guang Yang, Xiaobo Qu, Chengyan Wang
{"title":"CMRxRecon2024: A Multimodality, Multiview k-Space Dataset Boosting Universal Machine Learning for Accelerated Cardiac MRI.","authors":"Zi Wang, Fanwen Wang, Chen Qin, Jun Lyu, Cheng Ouyang, Shuo Wang, Yan Li, Mengyao Yu, Haoyu Zhang, Kunyuan Guo, Zhang Shi, Qirong Li, Ziqiang Xu, Yajing Zhang, Hao Li, Sha Hua, Binghua Chen, Longyu Sun, Mengting Sun, Qing Li, Ying-Hua Chu, Wenjia Bai, Jing Qin, Xiahai Zhuang, Claudia Prieto, Alistair Young, Michael Markl, He Wang, Lian-Ming Wu, Guang Yang, Xiaobo Qu, Chengyan Wang","doi":"10.1148/ryai.240443","DOIUrl":"10.1148/ryai.240443","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240443"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143060372","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
Deep Learning-based Brain Age Prediction Using MRI to Identify Fetuses with Cerebral Ventriculomegaly.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.240115
Hyuk Jin Yun, Han-Jui Lee, Sungmin You, Joo Young Lee, Jerjes Aguirre-Chavez, Lana Vasung, Hyun Ju Lee, Tomo Tarui, Henry A Feldman, P Ellen Grant, Kiho Im

Fetal ventriculomegaly (VM) and its severity and associated central nervous system (CNS) abnormalities are important indicators of high risk for impaired neurodevelopmental outcomes. Recently, a novel fetal brain age prediction method using a two-dimensional (2D) single-channel convolutional neural network (CNN) with multiplanar MRI sections showed the potential to detect fetuses with VM. This study examines the diagnostic performance of a deep learning-based fetal brain age prediction model to distinguish fetuses with VM (n = 317) from typically developing fetuses (n = 183), the severity of VM, and the presence of associated CNS abnormalities. The predicted age difference (PAD) was measured by subtracting the predicted brain age from the gestational age in fetuses with VM and typical development. PAD and absolute value of PAD (AAD) were compared between VM and typically developing fetuses. In addition, PAD and AAD were compared between subgroups by VM severity and the presence of associated CNS abnormalities in VM. Fetuses with VM showed significantly larger AAD than typically developing fetuses (P < .001), and fetuses with severe VM showed larger AAD than those with moderate VM (P = .004). Fetuses with VM and associated CNS abnormalities had significantly lower PAD than fetuses with isolated VM (P = .005). These findings suggest that fetal brain age prediction using the 2D single-channel CNN method has the clinical ability to assist in identifying not only the enlargement of the ventricles but also the presence of associated CNS abnormalities. Keywords: MR-Fetal (Fetal MRI), Brain/Brain Stem, Fetus, Supervised Learning, Machine Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms Supplemental material is available for this article. ©RSNA, 2025.

{"title":"Deep Learning-based Brain Age Prediction Using MRI to Identify Fetuses with Cerebral Ventriculomegaly.","authors":"Hyuk Jin Yun, Han-Jui Lee, Sungmin You, Joo Young Lee, Jerjes Aguirre-Chavez, Lana Vasung, Hyun Ju Lee, Tomo Tarui, Henry A Feldman, P Ellen Grant, Kiho Im","doi":"10.1148/ryai.240115","DOIUrl":"10.1148/ryai.240115","url":null,"abstract":"<p><p>Fetal ventriculomegaly (VM) and its severity and associated central nervous system (CNS) abnormalities are important indicators of high risk for impaired neurodevelopmental outcomes. Recently, a novel fetal brain age prediction method using a two-dimensional (2D) single-channel convolutional neural network (CNN) with multiplanar MRI sections showed the potential to detect fetuses with VM. This study examines the diagnostic performance of a deep learning-based fetal brain age prediction model to distinguish fetuses with VM (<i>n</i> = 317) from typically developing fetuses (<i>n</i> = 183), the severity of VM, and the presence of associated CNS abnormalities. The predicted age difference (PAD) was measured by subtracting the predicted brain age from the gestational age in fetuses with VM and typical development. PAD and absolute value of PAD (AAD) were compared between VM and typically developing fetuses. In addition, PAD and AAD were compared between subgroups by VM severity and the presence of associated CNS abnormalities in VM. Fetuses with VM showed significantly larger AAD than typically developing fetuses (<i>P</i> < .001), and fetuses with severe VM showed larger AAD than those with moderate VM (<i>P</i> = .004). Fetuses with VM and associated CNS abnormalities had significantly lower PAD than fetuses with isolated VM (<i>P</i> = .005). These findings suggest that fetal brain age prediction using the 2D single-channel CNN method has the clinical ability to assist in identifying not only the enlargement of the ventricles but also the presence of associated CNS abnormalities. <b>Keywords:</b> MR-Fetal (Fetal MRI), Brain/Brain Stem, Fetus, Supervised Learning, Machine Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms <i>Supplemental material is available for this article.</i> ©RSNA, 2025.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240115"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450327","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
Accelerating Complex Tissue Analysis in Prostate MRI: From Hours to Seconds Using Physics-informed Neural Networks.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.250016
Lisa C Adams, Keno K Bressem
{"title":"Accelerating Complex Tissue Analysis in Prostate MRI: From Hours to Seconds Using Physics-informed Neural Networks.","authors":"Lisa C Adams, Keno K Bressem","doi":"10.1148/ryai.250016","DOIUrl":"https://doi.org/10.1148/ryai.250016","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"7 2","pages":"e250016"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143558239","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
Bridging the Trust Gap: Conformal Prediction for AI-based Intracranial Hemorrhage Detection.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.250032
Peter K Ngum, Christopher G Filippi
{"title":"Bridging the Trust Gap: Conformal Prediction for AI-based Intracranial Hemorrhage Detection.","authors":"Peter K Ngum, Christopher G Filippi","doi":"10.1148/ryai.250032","DOIUrl":"https://doi.org/10.1148/ryai.250032","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"7 2","pages":"e250032"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143711519","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
Physics-Informed Autoencoder for Prostate Tissue Microstructure Profiling with Hybrid Multidimensional MRI.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.240167
Batuhan Gundogdu, Aritrick Chatterjee, Milica Medved, Ulas Bagci, Gregory S Karczmar, Aytekin Oto

Purpose To evaluate the performance of Physics-Informed Autoencoder (PIA), a self-supervised deep learning model, in measuring tissue-based biomarkers for prostate cancer (PCa) using hybrid multidimensional MRI. Materials and Methods This retrospective study introduces PIA, an emerging self-supervised deep learning model that integrates a three-compartment diffusion-relaxation model with hybrid multidimensional MRI. PIA was trained to encode the biophysical model into a deep neural network to predict measurements of tissue-specific biomarkers for PCa without extensive training data requirements. Comprehensive in silico and in vivo experiments, using histopathology measurements as the reference standard, were conducted to validate the model's efficacy in comparison to the traditional nonlinear least squares (NLLS) algorithm. PIA's robustness to noise was tested in in silico experiments with varying signal-to-noise ratio (SNR) conditions, and in vivo performance for estimating volume fractions was evaluated in 21 patients (mean age, 60 years ± 6.6 [SD]; all male) with PCa (71 regions of interest). Evaluation metrics included the intraclass correlation coefficient (ICC) and Pearson correlation coefficient. Results PIA predicted the reference standard tissue parameters with high accuracy, outperforming conventional NLLS methods, especially under noisy conditions (rs = 0.80 vs 0.65, P < .001 for epithelium volume at SNR of 20:1). In in vivo validation, PIA's noninvasive volume fraction estimates matched quantitative histology (ICC, 0.94, 0.85, and 0.92 for epithelium, stroma, and lumen compartments, respectively; P < .001 for all). PIA's measurements strongly correlated with PCa aggressiveness (r = 0.75, P < .001). Furthermore, PIA ran 10 000 faster than NLLS (0.18 second vs 40 minutes per image). Conclusion PIA provided accurate prostate tissue biomarker measurements from MRI data with better robustness to noise and computational efficiency compared with the NLLS algorithm. The results demonstrate the potential of PIA as an accurate, noninvasive, and explainable artificial intelligence method for PCa detection. Keywords: Prostate, Stacked Auto-Encoders, Tissue Characterization, MR-Diffusion-weighted Imaging Supplemental material is available for this article. ©RSNA, 2025 See also commentary by Adams and Bressem in this issue.

{"title":"Physics-Informed Autoencoder for Prostate Tissue Microstructure Profiling with Hybrid Multidimensional MRI.","authors":"Batuhan Gundogdu, Aritrick Chatterjee, Milica Medved, Ulas Bagci, Gregory S Karczmar, Aytekin Oto","doi":"10.1148/ryai.240167","DOIUrl":"10.1148/ryai.240167","url":null,"abstract":"<p><p>Purpose To evaluate the performance of Physics-Informed Autoencoder (PIA), a self-supervised deep learning model, in measuring tissue-based biomarkers for prostate cancer (PCa) using hybrid multidimensional MRI. Materials and Methods This retrospective study introduces PIA, an emerging self-supervised deep learning model that integrates a three-compartment diffusion-relaxation model with hybrid multidimensional MRI. PIA was trained to encode the biophysical model into a deep neural network to predict measurements of tissue-specific biomarkers for PCa without extensive training data requirements. Comprehensive in silico and in vivo experiments, using histopathology measurements as the reference standard, were conducted to validate the model's efficacy in comparison to the traditional nonlinear least squares (NLLS) algorithm. PIA's robustness to noise was tested in in silico experiments with varying signal-to-noise ratio (SNR) conditions, and in vivo performance for estimating volume fractions was evaluated in 21 patients (mean age, 60 years ± 6.6 [SD]; all male) with PCa (71 regions of interest). Evaluation metrics included the intraclass correlation coefficient (ICC) and Pearson correlation coefficient. Results PIA predicted the reference standard tissue parameters with high accuracy, outperforming conventional NLLS methods, especially under noisy conditions (<i>r</i><sub>s</sub> = 0.80 vs 0.65, <i>P</i> < .001 for epithelium volume at SNR of 20:1). In in vivo validation, PIA's noninvasive volume fraction estimates matched quantitative histology (ICC, 0.94, 0.85, and 0.92 for epithelium, stroma, and lumen compartments, respectively; <i>P</i> < .001 for all). PIA's measurements strongly correlated with PCa aggressiveness (<i>r</i> = 0.75, <i>P</i> < .001). Furthermore, PIA ran 10 000 faster than NLLS (0.18 second vs 40 minutes per image). Conclusion PIA provided accurate prostate tissue biomarker measurements from MRI data with better robustness to noise and computational efficiency compared with the NLLS algorithm. The results demonstrate the potential of PIA as an accurate, noninvasive, and explainable artificial intelligence method for PCa detection. <b>Keywords:</b> Prostate, Stacked Auto-Encoders, Tissue Characterization, MR-Diffusion-weighted Imaging <i>Supplemental material is available for this article.</i> ©RSNA, 2025 See also commentary by Adams and Bressem in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240167"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190758","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
Bridging Artificial Intelligence Models to Clinical Practice: Challenges in Lung Cancer Prediction.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.250080
Xiaonan Shao, Rong Niu
{"title":"Bridging Artificial Intelligence Models to Clinical Practice: Challenges in Lung Cancer Prediction.","authors":"Xiaonan Shao, Rong Niu","doi":"10.1148/ryai.250080","DOIUrl":"https://doi.org/10.1148/ryai.250080","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"7 2","pages":"e250080"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143606551","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
Performance of Lung Cancer Prediction Models for Screening-detected, Incidental, and Biopsied Pulmonary Nodules. 肺癌预测模型在筛查发现的肺结节、偶然发现的肺结节和活检肺结节中的表现。
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.230506
Thomas Z Li, Kaiwen Xu, Aravind Krishnan, Riqiang Gao, Michael N Kammer, Sanja Antic, David Xiao, Michael Knight, Yency Martinez, Rafael Paez, Robert J Lentz, Stephen Deppen, Eric L Grogan, Thomas A Lasko, Kim L Sandler, Fabien Maldonado, Bennett A Landman

Purpose To evaluate the performance of eight lung cancer prediction models on patient cohorts with screening-detected, incidentally detected, and bronchoscopically biopsied pulmonary nodules. Materials and Methods This study retrospectively evaluated promising predictive models for lung cancer prediction in three clinical settings: lung cancer screening with low-dose CT, incidentally detected pulmonary nodules, and nodules deemed suspicious enough to warrant a biopsy. The area under the receiver operating characteristic curve of eight validated models, including logistic regressions on clinical variables and radiologist nodule characterizations, artificial intelligence (AI) on chest CT scans, longitudinal imaging AI, and multimodal approaches for prediction of lung cancer risk was assessed in nine cohorts (n = 898, 896, 882, 219, 364, 117, 131, 115, 373) from multiple institutions. Each model was implemented from their published literature, and each cohort was curated from primary data sources collected over periods from 2002 to 2021. Results No single predictive model emerged as the highest-performing model across all cohorts, but certain models performed better in specific clinical contexts. Single-time-point chest CT AI performed well for screening-detected nodules but did not generalize well to other clinical settings. Longitudinal imaging and multimodal models demonstrated comparatively good performance on incidentally detected nodules. When applied to biopsied nodules, all models showed low performance. Conclusion Eight lung cancer prediction models failed to generalize well across clinical settings and sites outside of their training distributions. Keywords: Diagnosis, Classification, Application Domain, Lung Supplemental material is available for this article. © RSNA, 2025 See also commentary by Shao and Niu in this issue.

"刚刚接受 "的论文经过同行评审,已被接受在《放射学》上发表:人工智能》上发表。这篇文章在以最终版本发表之前,还将经过校对、排版和校对审核。请注意,在制作最终校对稿的过程中,可能会发现一些错误,从而影响文章内容。目的 评估八个肺癌预测模型在筛查发现的、偶然发现的和支气管镜活检发现的肺结节患者队列中的表现。材料与方法 本研究回顾性地评估了三种临床环境下肺癌预测模型的预测效果:使用低剂量 CT 进行肺癌筛查、偶然检测到肺结节以及被认为可疑到需要进行活检的结节。在来自多个机构的 9 个队列(n = 898、896、882、219、364、117、131、115、373)中评估了 8 个经过验证的模型的接收器工作特征曲线下面积(AUC),这些模型包括临床变量和放射科医生结节特征的逻辑回归、胸部 CT 人工智能(AI)、纵向成像人工智能以及预测肺癌风险的多模态方法。每个模型都是根据其发表的文献实施的,每个队列都是根据 2002 年至 2021 年期间收集的原始数据来源策划的。结果 在所有队列中,没有一个预测模型是表现最好的模型,但某些模型在特定的临床环境中表现更好。单个时间点胸部 CT AI 在筛查发现的结节方面表现良好,但在其他临床环境中表现不佳。纵向成像和多模态模型在偶然检测到的结节上表现相对较好。当应用于活检结节时,所有模型都表现出较低的性能。结论 八种肺癌预测模型未能在其训练分布以外的临床环境和部位中很好地推广。©RSNA, 2025.
{"title":"Performance of Lung Cancer Prediction Models for Screening-detected, Incidental, and Biopsied Pulmonary Nodules.","authors":"Thomas Z Li, Kaiwen Xu, Aravind Krishnan, Riqiang Gao, Michael N Kammer, Sanja Antic, David Xiao, Michael Knight, Yency Martinez, Rafael Paez, Robert J Lentz, Stephen Deppen, Eric L Grogan, Thomas A Lasko, Kim L Sandler, Fabien Maldonado, Bennett A Landman","doi":"10.1148/ryai.230506","DOIUrl":"10.1148/ryai.230506","url":null,"abstract":"<p><p>Purpose To evaluate the performance of eight lung cancer prediction models on patient cohorts with screening-detected, incidentally detected, and bronchoscopically biopsied pulmonary nodules. Materials and Methods This study retrospectively evaluated promising predictive models for lung cancer prediction in three clinical settings: lung cancer screening with low-dose CT, incidentally detected pulmonary nodules, and nodules deemed suspicious enough to warrant a biopsy. The area under the receiver operating characteristic curve of eight validated models, including logistic regressions on clinical variables and radiologist nodule characterizations, artificial intelligence (AI) on chest CT scans, longitudinal imaging AI, and multimodal approaches for prediction of lung cancer risk was assessed in nine cohorts (<i>n</i> = 898, 896, 882, 219, 364, 117, 131, 115, 373) from multiple institutions. Each model was implemented from their published literature, and each cohort was curated from primary data sources collected over periods from 2002 to 2021. Results No single predictive model emerged as the highest-performing model across all cohorts, but certain models performed better in specific clinical contexts. Single-time-point chest CT AI performed well for screening-detected nodules but did not generalize well to other clinical settings. Longitudinal imaging and multimodal models demonstrated comparatively good performance on incidentally detected nodules. When applied to biopsied nodules, all models showed low performance. Conclusion Eight lung cancer prediction models failed to generalize well across clinical settings and sites outside of their training distributions. <b>Keywords:</b> Diagnosis, Classification, Application Domain, Lung <i>Supplemental material is available for this article.</i> © RSNA, 2025 See also commentary by Shao and Niu in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e230506"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190741","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
Applying Conformal Prediction to a Deep Learning Model for Intracranial Hemorrhage Detection to Improve Trustworthiness. 在颅内出血检测的深度学习模型中应用共形预测,提高可信度。
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.240032
Cooper Gamble, Shahriar Faghani, Bradley J Erickson

Purpose To apply conformal prediction to a deep learning (DL) model for intracranial hemorrhage (ICH) detection and evaluate model performance in detection as well as model accuracy in identifying challenging cases. Materials and Methods This was a retrospective (November-December 2017) study of 491 noncontrast head CT volumes from the CQ500 dataset, in which three senior radiologists annotated sections containing ICH. The dataset was split into definite and challenging (uncertain) subsets, in which challenging images were defined as those in which there was disagreement among readers. A DL model was trained on patients from the definite data (training dataset) to perform ICH localization and classification into five classes. To develop an uncertainty-aware DL model, 1546 sections of the definite data (calibration dataset) were used for Mondrian conformal prediction (MCP). The uncertainty-aware DL model was tested on 8401 definite and challenging sections to assess its ability to identify challenging sections. The difference in predictive performance (P value) and ability to identify challenging sections (accuracy) were reported. Results The study included 146 patients (mean age, 45.7 years ± 9.9 [SD]; 76 [52.1%] men, 70 [47.9%] women). After the MCP procedure, the model achieved an F1 score of 0.919 for localization and classification. Additionally, it correctly identified patients with challenging cases with 95.3% (143 of 150) accuracy. It did not incorrectly label any definite sections as challenging. Conclusion The uncertainty-aware MCP-augmented DL model achieved high performance in ICH detection and high accuracy in identifying challenging sections, suggesting its usefulness in automated ICH detection and potential to increase trustworthiness of DL models in radiology. Keywords: CT, Head and Neck, Brain, Brain Stem, Hemorrhage, Feature Detection, Diagnosis, Supervised Learning Supplemental material is available for this article. © RSNA, 2025 See also commentary by Ngum and Filippi in this issue.

"刚刚接受 "的论文经过同行评审,已被接受在《放射学》上发表:人工智能》上发表。这篇文章在以最终版本发表之前,还将经过校对、排版和校对审核。请注意,在制作最终校对稿的过程中,可能会发现一些错误,从而影响文章内容。目的 将保形预测应用于颅内出血(ICH)检测的深度学习(DL)模型,并评估模型在检测方面的性能以及模型在识别挑战性病例方面的准确性。材料与方法 这是一项回顾性研究(2017 年 11 月至 2017 年 12 月),研究对象是 CQ500 数据集中的 491 张非对比头部 CT 卷,其中有三位资深放射科医生对含有 ICH 的切片进行了注释。数据集被分成确定和具有挑战性(不确定)的子集,其中具有挑战性的图像被定义为读者之间存在分歧的图像。对明确数据(训练数据集)中的 146 名患者(平均年龄 45.7 岁,女性 70 人,男性 76 人)进行了 DL 模型训练,以进行 ICH 定位并将其分为五类。为了开发不确定性感知 DL 模型,使用了 1,546 个明确数据(校准数据集)进行蒙德里安共形预测 (MCP)。不确定性感知 DL 模型在 8,401 个确定断面和挑战断面上进行了测试,以评估其识别挑战断面的能力。报告了预测性能的差异(P 值)和识别挑战性路段的能力(准确性)。结果 经过 MCP 程序后,该模型在测试数据集上的非物质文化遗产分类 F1 得分为 0.920。此外,在总共 6856 个具有挑战性的部分中,该模型正确识别了 6837 个具有挑战性的部分(准确率为 99.7%)。它没有错误地将任何明确的部分标记为具有挑战性。结论 不确定性感知的 MCP 增强 DL 模型在 ICH 检测中取得了很高的性能,在识别具有挑战性的切片方面也有很高的准确性,这表明它在自动 ICH 检测中非常有用,并有可能提高 DL 模型在放射学中的可信度。©RSNA,2024。
{"title":"Applying Conformal Prediction to a Deep Learning Model for Intracranial Hemorrhage Detection to Improve Trustworthiness.","authors":"Cooper Gamble, Shahriar Faghani, Bradley J Erickson","doi":"10.1148/ryai.240032","DOIUrl":"10.1148/ryai.240032","url":null,"abstract":"<p><p>Purpose To apply conformal prediction to a deep learning (DL) model for intracranial hemorrhage (ICH) detection and evaluate model performance in detection as well as model accuracy in identifying challenging cases. Materials and Methods This was a retrospective (November-December 2017) study of 491 noncontrast head CT volumes from the CQ500 dataset, in which three senior radiologists annotated sections containing ICH. The dataset was split into definite and challenging (uncertain) subsets, in which challenging images were defined as those in which there was disagreement among readers. A DL model was trained on patients from the definite data (training dataset) to perform ICH localization and classification into five classes. To develop an uncertainty-aware DL model, 1546 sections of the definite data (calibration dataset) were used for Mondrian conformal prediction (MCP). The uncertainty-aware DL model was tested on 8401 definite and challenging sections to assess its ability to identify challenging sections. The difference in predictive performance (<i>P</i> value) and ability to identify challenging sections (accuracy) were reported. Results The study included 146 patients (mean age, 45.7 years ± 9.9 [SD]; 76 [52.1%] men, 70 [47.9%] women). After the MCP procedure, the model achieved an F1 score of 0.919 for localization and classification. Additionally, it correctly identified patients with challenging cases with 95.3% (143 of 150) accuracy. It did not incorrectly label any definite sections as challenging. Conclusion The uncertainty-aware MCP-augmented DL model achieved high performance in ICH detection and high accuracy in identifying challenging sections, suggesting its usefulness in automated ICH detection and potential to increase trustworthiness of DL models in radiology. <b>Keywords:</b> CT, Head and Neck, Brain, Brain Stem, Hemorrhage, Feature Detection, Diagnosis, Supervised Learning <i>Supplemental material is available for this article.</i> © RSNA, 2025 See also commentary by Ngum and Filippi in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240032"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142732987","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
2024 Manuscript Reviewers: A Note of Thanks.
IF 8.1 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2025-03-01 DOI: 10.1148/ryai.250163
Umar Mahmood, Charles E Kahn
{"title":"2024 Manuscript Reviewers: A Note of Thanks.","authors":"Umar Mahmood, Charles E Kahn","doi":"10.1148/ryai.250163","DOIUrl":"https://doi.org/10.1148/ryai.250163","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"7 2","pages":"e250163"},"PeriodicalIF":8.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143711428","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
期刊
Radiology-Artificial Intelligence
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