全自动深度学习模型在MRI上检测临床显著性前列腺癌
本研究回顾性纳入单学术机构多院区2017年1月至2019年12月无已知临床显著性前列腺癌(csPCa)患者的MRI数据,训练卷积神经网络仅用患者级标签预测csPCa,并在内部测试集(400例)与外部ProstateX测试集(204例)中与放射科医生比较。内部测试集DL分类器与放射科医生AUC均为0.89(P=0.88),外部测试集分别为0.86与0.84(P=0.68),DL联合放射科医生AUC为0.89(P<0.001)。
要点
- DL模型仅用患者级标签训练即可预测csPCa,内部测试集AUC 0.89与放射科医生相当。
- 外部测试集DL分类器AUC 0.86,放射科医生AUC 0.84,两者差异无统计学意义(P=0.68)。
- Grad-CAM在内部测试集38例真阳性中35例、外部测试集58例真阳性中56例激活于csPCa病灶。
核心结论
- DL模型在MRI检测csPCa方面与放射科医生表现无差异,且Grad-CAM可定位肿瘤。
研究设计与样本
- 回顾性研究,纳入单学术机构多院区2017年1月至2019年12月无已知csPCa患者的MRI检查共5735次(5215例患者,平均年龄66岁±8[SD],均为男性),其中1514次检查(1454例患者)病理诊断为csPCa。训练卷积神经网络基于T2加权图像、扩散加权图像、表观扩散系数图和T1加权对比增强图像预测csPCa,参考标准为病理诊断。
关键影像表现/征象
- Grad-CAM在内部测试集38例真阳性检查中35例、外部测试集58例真阳性检查中56例显示激活位于csPCa病灶上。
诊断标准与关键数值
- csPCa定义为Gleason评分≥7。
- 内部测试集(400次检查):DL分类器AUC 0.89,放射科医生AUC 0.89(P=0.88)。
- 外部测试集(204次检查,ProstateX):DL分类器AUC 0.86,放射科医生AUC 0.84(P=0.68)。
- DL分类器联合放射科医生AUC 0.89(P<0.001)。
临床应用与阅片要点
- 内部测试集放射科医生表现基于放射学报告评估,外部测试集基于4名放射科医生的PI-RADS评分评估。
- DL模型仅使用患者级标签训练,无需肿瘤位置信息。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Background Multiparametric MRI can help identify clinically significant prostate cancer (csPCa) (Gleason score ≥7) but is limited by reader experience and interobserver variability. In contrast, deep learning (DL) produces deterministic outputs. Purpose To develop a DL model to predict the presence of csPCa by using patient-level labels without information about tumor location and to compare its performance with that of radiologists. Materials and Methods Data from patients without known csPCa who underwent MRI from January 2017 to December 2019 at one of multiple sites of a single academic institution were retrospectively reviewed. A convolutional neural network was trained to predict csPCa from T2-weighted images, diffusion-weighted images, apparent diffusion coefficient maps, and T1-weighted contrast-enhanced images. The reference standard was pathologic diagnosis. Radiologist performance was evaluated as follows: Radiology reports were used for the internal test set, and four radiologists' PI-RADS ratings were used for the external (ProstateX) test set. The performance was compared using areas under the receiver operating characteristic curves (AUCs) and the DeLong test. Gradient-weighted class activation maps (Grad-CAMs) were used to show tumor localization. Results Among 5735 examinations in 5215 patients (mean age, 66 years ± 8 [SD]; all male), 1514 examinations (1454 patients) showed csPCa. In the internal test set (400 examinations), the AUC was 0.89 and 0.89 for the DL classifier and radiologists, respectively (P = .88). In the external test set (204 examinations), the AUC was 0.86 and 0.84 for the DL classifier and radiologists, respectively (P = .68). DL classifier plus radiologists had an AUC of 0.89 (P < .001). Grad-CAMs demonstrated activation over the csPCa lesion in 35 of 38 and 56 of 58 true-positive examinations in internal and external test sets, respectively. Conclusion The performance of a DL model was not different from that of radiologists in the detection of csPCa at MRI, and Grad-CAMs localized the tumor. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Johnson and Chandarana in this issue.
引用
- Cai JC, Nakai H, Kuanar S, et al. Fully Automated Deep Learning Model to Detect Clinically Significant Prostate Cancer at MRI. Radiology. 2024. PMID: 39105640. doi:10.1148/radiol.232635
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。