Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets.
IF 8.1
Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Hao Li, Han Liu, Heinrich von Busch, Robert Grimm, Henkjan Huisman, Angela Tong, David Winkel, Tobias Penzkofer, Ivan Shabunin, Moon Hyung Choi, Qingsong Yang, Dieter Szolar, Steven Shea, Fergus Coakley, Mukesh Harisinghani, Ipek Oguz, Dorin Comaniciu, Ali Kamen, Bin Lou
下载PDF
{"title":"Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets.","authors":"Hao Li, Han Liu, Heinrich von Busch, Robert Grimm, Henkjan Huisman, Angela Tong, David Winkel, Tobias Penzkofer, Ivan Shabunin, Moon Hyung Choi, Qingsong Yang, Dieter Szolar, Steven Shea, Fergus Coakley, Mukesh Harisinghani, Ipek Oguz, Dorin Comaniciu, Ali Kamen, Bin Lou","doi":"10.1148/ryai.230521","DOIUrl":null,"url":null,"abstract":"<p><p>Purpose To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. Materials and Methods This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various <i>b</i> values, to align with the style of images acquired using <i>b</i> values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. Results For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (<i>P</i> < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (<i>P</i> < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (<i>P</i> < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (<i>P</i> < .001) for lesions with PI-RADS scores of 4 or greater. Conclusion UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various <i>b</i> values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high <i>b</i> value). <b>Keywords:</b> Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, <i>b</i> Value <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e230521"},"PeriodicalIF":8.1000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11449150/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology-Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/ryai.230521","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
引用
批量引用
Abstract
Purpose To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. Materials and Methods This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. Results For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. Conclusion UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024.
利用多部位双参数磁共振成像数据集,通过统一模型进行前列腺病变检测的基于深度学习的无监督领域适应。
"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,可能会发现影响文章内容的错误。目的 确定使用生成图像的无监督领域适应(UDA)方法是否能提高使用多部位 bp-MRI 数据集进行前列腺癌(PCa)检测的监督学习(SL)模型的性能。材料与方法 这项回顾性研究包括九个不同成像中心收集的 5,150 名患者(14,191 个样本)的数据。研究人员使用统一生成模型开发了一种新型 UDA 方法,用于使用多部位 bp-MRI 数据集检测 PCa。该方法将扩散加权成像(DWI)采集数据(包括表观扩散系数(ADC)和使用不同 b 值采集的单个 DW 图像)转换为前列腺成像报告和数据系统(PI-RADS)指南推荐的 b 值采集图像样式。生成的 ADC 和 DW 图像取代了用于 PCa 检测的原始图像。评估使用了一组独立的 1,692 个测试案例(2,393 个样本)。接收者操作特征曲线下面积(AUC)被用作主要指标,统计分析通过引导法进行。结果 在所有测试病例中,对于 PI-RADS ≥ 3 的 PCa 病变,基线 SL 和 UDA 方法的 AUC 值分别为 0.73 和 0.79(P < .001);对于 PI-RADS ≥ 4 的 PCa 病变,基线 SL 和 UDA 方法的 AUC 值分别为 0.77 和 0.80(P < .001)。在最不利的图像采集设置下的 361 个测试病例中,基线 SL 和 UDA 的 AUC 值分别为:PI-RADS ≥ 3 为 0.49 和 0.76(P < .001),PI-RADS ≥ 4 PCa 病变为 0.50 和 0.77(P < .001)。结论 使用生成图像的 UDA 提高了 SL 方法在不同 b 值的多部位数据集上检测 PCa 病灶的性能,尤其是在采集的图像明显偏离 PI-RADS 推荐的 DWI 方案(如具有极高 b 值)时。©RSNA,2024。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
来源期刊
期刊介绍:
Radiology: Artificial Intelligence is a bi-monthly publication that focuses on the emerging applications of machine learning and artificial intelligence in the field of imaging across various disciplines. This journal is available online and accepts multiple manuscript types, including Original Research, Technical Developments, Data Resources, Review articles, Editorials, Letters to the Editor and Replies, Special Reports, and AI in Brief.