交互式可解释的深度学习模型在加多西酸增强MRI诊断肝细胞癌:一项回顾性,多中心,诊断研究。

IF 5.6 Q1 ONCOLOGY
Mingkai Li, Zhi Zhang, Zebin Chen, Xi Chen, Huaqing Liu, Yuanqiang Xiao, Haimei Chen, Xiaodan Zong, Jingbiao Chen, Jianning Chen, Xinying Wang, Xuehong Xiao, Zhiwei Yang, Lanqing Han, Jin Wang, Bin Wu
{"title":"交互式可解释的深度学习模型在加多西酸增强MRI诊断肝细胞癌:一项回顾性,多中心,诊断研究。","authors":"Mingkai Li, Zhi Zhang, Zebin Chen, Xi Chen, Huaqing Liu, Yuanqiang Xiao, Haimei Chen, Xiaodan Zong, Jingbiao Chen, Jianning Chen, Xinying Wang, Xuehong Xiao, Zhiwei Yang, Lanqing Han, Jin Wang, Bin Wu","doi":"10.1148/rycan.240332","DOIUrl":null,"url":null,"abstract":"<p><p>Purpose To develop an artificial intelligence (AI) model based on gadoxetic acid-enhanced MRI to assist radiologists in hepatocellular carcinoma (HCC) diagnosis. Materials and Methods This retrospective study included patients with focal liver lesions (FLLs) who underwent gadoxetic acid-enhanced MRI between January 2015 and December 2021. All hepatic malignancies were diagnosed pathologically, whereas benign lesions were confirmed with pathologic findings or imaging follow-up. Five manually labeled bounding boxes for each FLL obtained from precontrast T1-weighted, T2-weighted, arterial phase, portal venous phase, and hepatobiliary phase images were included. The lesion classifier component, used to distinguish HCC from non-HCC, was trained and externally tested. The feature classifier, based on a post hoc algorithm, inferred the presence of the Liver Imaging Reporting and Data System (LI-RADS) features by analyzing activation patterns of the pretrained lesion classifier. Two radiologists categorized FLLs in the external testing dataset according to LI-RADS criteria. Diagnostic performance of the AI model and the model's impact on reader accuracy were assessed. Results The study included 839 patients (mean age, 51 years ± 12 [SD]; 681 male) with 1023 FLLs (594 HCCs and 429 non-HCCs). The AI model yielded area under the receiver operating characteristic curves of 0.98 and 0.97 in the training set and external testing set, respectively. Compared with LI-RADS category 5, the AI model showed higher sensitivity (91.6% vs 74.8%; <i>P</i> < .001) and similar specificity (90.7% vs 96.0%; <i>P</i> = .22). The two readers identified more LI-RADS major features and more accurately classified category LR-5 lesions when assisted versus unassisted by AI, with higher sensitivities (reader 1, 85.7% vs 72.3%; <i>P</i> < .001; reader 2, 89.1% vs 74.0%; <i>P</i> < .001) and the same specificities (reader 1, 93.3% vs reader 2, 94.7%; <i>P</i> > .99 for both). Conclusion The AI model accurately diagnosed HCC and improved the radiologists' diagnostic performance. <b>Keywords:</b> Artificial Intelligence, Deep Learning, MRI, Hepatocellular Carcinoma <i>Supplemental material is available for this article.</i> © RSNA, 2025 See also commentary by Singh et al in this issue.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"7 3","pages":"e240332"},"PeriodicalIF":5.6000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12130696/pdf/","citationCount":"0","resultStr":"{\"title\":\"Interactive Explainable Deep Learning Model for Hepatocellular Carcinoma Diagnosis at Gadoxetic Acid-enhanced MRI: A Retrospective, Multicenter, Diagnostic Study.\",\"authors\":\"Mingkai Li, Zhi Zhang, Zebin Chen, Xi Chen, Huaqing Liu, Yuanqiang Xiao, Haimei Chen, Xiaodan Zong, Jingbiao Chen, Jianning Chen, Xinying Wang, Xuehong Xiao, Zhiwei Yang, Lanqing Han, Jin Wang, Bin Wu\",\"doi\":\"10.1148/rycan.240332\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Purpose To develop an artificial intelligence (AI) model based on gadoxetic acid-enhanced MRI to assist radiologists in hepatocellular carcinoma (HCC) diagnosis. Materials and Methods This retrospective study included patients with focal liver lesions (FLLs) who underwent gadoxetic acid-enhanced MRI between January 2015 and December 2021. All hepatic malignancies were diagnosed pathologically, whereas benign lesions were confirmed with pathologic findings or imaging follow-up. Five manually labeled bounding boxes for each FLL obtained from precontrast T1-weighted, T2-weighted, arterial phase, portal venous phase, and hepatobiliary phase images were included. The lesion classifier component, used to distinguish HCC from non-HCC, was trained and externally tested. The feature classifier, based on a post hoc algorithm, inferred the presence of the Liver Imaging Reporting and Data System (LI-RADS) features by analyzing activation patterns of the pretrained lesion classifier. Two radiologists categorized FLLs in the external testing dataset according to LI-RADS criteria. Diagnostic performance of the AI model and the model's impact on reader accuracy were assessed. Results The study included 839 patients (mean age, 51 years ± 12 [SD]; 681 male) with 1023 FLLs (594 HCCs and 429 non-HCCs). The AI model yielded area under the receiver operating characteristic curves of 0.98 and 0.97 in the training set and external testing set, respectively. Compared with LI-RADS category 5, the AI model showed higher sensitivity (91.6% vs 74.8%; <i>P</i> < .001) and similar specificity (90.7% vs 96.0%; <i>P</i> = .22). The two readers identified more LI-RADS major features and more accurately classified category LR-5 lesions when assisted versus unassisted by AI, with higher sensitivities (reader 1, 85.7% vs 72.3%; <i>P</i> < .001; reader 2, 89.1% vs 74.0%; <i>P</i> < .001) and the same specificities (reader 1, 93.3% vs reader 2, 94.7%; <i>P</i> > .99 for both). Conclusion The AI model accurately diagnosed HCC and improved the radiologists' diagnostic performance. <b>Keywords:</b> Artificial Intelligence, Deep Learning, MRI, Hepatocellular Carcinoma <i>Supplemental material is available for this article.</i> © RSNA, 2025 See also commentary by Singh et al in this issue.</p>\",\"PeriodicalId\":20786,\"journal\":{\"name\":\"Radiology. Imaging cancer\",\"volume\":\"7 3\",\"pages\":\"e240332\"},\"PeriodicalIF\":5.6000,\"publicationDate\":\"2025-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12130696/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiology. Imaging cancer\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1148/rycan.240332\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology. Imaging cancer","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/rycan.240332","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的建立一种基于加多etic酸增强MRI的人工智能(AI)模型,以辅助放射科医生诊断肝细胞癌(HCC)。材料和方法本回顾性研究纳入了2015年1月至2021年12月期间接受加多etic酸增强MRI检查的局灶性肝病变(fll)患者。所有肝脏恶性肿瘤均经病理诊断,而良性病变均经病理或影像学随访证实。从对比前t1加权、t2加权、动脉期、门静脉期和肝胆期图像中获得的每个FLL,包括5个手动标记的边界框。用于区分HCC和非HCC的病变分类器组件经过训练和外部测试。基于事后算法的特征分类器,通过分析预训练病变分类器的激活模式,推断出肝脏成像报告和数据系统(LI-RADS)特征的存在。两名放射科医生根据LI-RADS标准对外部测试数据集中的fll进行分类。评估了人工智能模型的诊断性能和模型对阅读器准确性的影响。结果纳入839例患者,平均年龄51岁±12岁[SD];681名男性),有1023例fll(594例hcc和429例非hcc)。AI模型在训练集和外部测试集的接收者工作特征曲线下的面积分别为0.98和0.97。与LI-RADS第5类相比,AI模型的灵敏度更高(91.6% vs 74.8%;P < 0.001)和相似的特异性(90.7% vs 96.0%;P = .22)。两种阅读器在人工智能辅助下识别出更多的LI-RADS主要特征,在人工智能辅助下比在无人工智能辅助下更准确地分类出LR-5类病变,灵敏度更高(阅读器1.85.7%比72.3%;P < .001;读者2,89.1% vs . 74.0%;P < 0.001)和相同的特异性(读者1,93.3% vs读者2,94.7%;两者都是0.99英镑)。结论人工智能模型能准确诊断HCC,提高放射科医师的诊断水平。关键词:人工智能,深度学习,核磁共振,肝细胞癌©RSNA, 2025另见Singh等人在本期的评论。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Interactive Explainable Deep Learning Model for Hepatocellular Carcinoma Diagnosis at Gadoxetic Acid-enhanced MRI: A Retrospective, Multicenter, Diagnostic Study.

Purpose To develop an artificial intelligence (AI) model based on gadoxetic acid-enhanced MRI to assist radiologists in hepatocellular carcinoma (HCC) diagnosis. Materials and Methods This retrospective study included patients with focal liver lesions (FLLs) who underwent gadoxetic acid-enhanced MRI between January 2015 and December 2021. All hepatic malignancies were diagnosed pathologically, whereas benign lesions were confirmed with pathologic findings or imaging follow-up. Five manually labeled bounding boxes for each FLL obtained from precontrast T1-weighted, T2-weighted, arterial phase, portal venous phase, and hepatobiliary phase images were included. The lesion classifier component, used to distinguish HCC from non-HCC, was trained and externally tested. The feature classifier, based on a post hoc algorithm, inferred the presence of the Liver Imaging Reporting and Data System (LI-RADS) features by analyzing activation patterns of the pretrained lesion classifier. Two radiologists categorized FLLs in the external testing dataset according to LI-RADS criteria. Diagnostic performance of the AI model and the model's impact on reader accuracy were assessed. Results The study included 839 patients (mean age, 51 years ± 12 [SD]; 681 male) with 1023 FLLs (594 HCCs and 429 non-HCCs). The AI model yielded area under the receiver operating characteristic curves of 0.98 and 0.97 in the training set and external testing set, respectively. Compared with LI-RADS category 5, the AI model showed higher sensitivity (91.6% vs 74.8%; P < .001) and similar specificity (90.7% vs 96.0%; P = .22). The two readers identified more LI-RADS major features and more accurately classified category LR-5 lesions when assisted versus unassisted by AI, with higher sensitivities (reader 1, 85.7% vs 72.3%; P < .001; reader 2, 89.1% vs 74.0%; P < .001) and the same specificities (reader 1, 93.3% vs reader 2, 94.7%; P > .99 for both). Conclusion The AI model accurately diagnosed HCC and improved the radiologists' diagnostic performance. Keywords: Artificial Intelligence, Deep Learning, MRI, Hepatocellular Carcinoma Supplemental material is available for this article. © RSNA, 2025 See also commentary by Singh et al in this issue.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.00
自引率
2.30%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信