前列腺MRI上的癌症分类:深度学习与临床PI-RADS评估的比较
回顾性纳入2015至2016年间在单一3.0-T MRI系统连续检查的312名疑似临床显著前列腺癌男性,比较U-Net深度学习系统与PI-RADS临床评估在病灶检测和分割中的表现。测试集中PI-RADS≥3与≥4的敏感度分别为96%与88%、特异度分别为22%与50%;U-Net阈值≥0.22与≥0.33的敏感度分别为96%与92%、特异度分别为31%与47%,与PI-RADS无统计学差异。PI-RADS≥4与U-Net病灶(阈值≥0.33) coincidence使阳性预测值从48%升至67%(P=0.01),阴性预测值不变(83% vs 83%,P>0.99)。
要点
- U-Net前列腺癌概率图经校准后,其敏感度和特异度与PI-RADS临床评估无统计学差异。
- PI-RADS≥4与U-Net病灶(阈值≥0.33)联合可将阳性预测值从48%(28/58)提升至67%(24/36)(P=0.01),阴性预测值不变(83%[25/30] vs 83%[43/52],P>0.99)。
- 前列腺分割Dice系数为0.89,MRI病灶分割Dice系数为0.35。
核心结论
- 以T2加权和扩散MRI训练的U-Net分割系统在前列腺癌检测和分割中达到与临床PI-RADS评估相似的性能。
研究设计与样本
- 回顾性研究,连续纳入312名疑似临床显著前列腺癌男性(中位年龄64岁,IQR 58-71岁),使用单一3.0-T MRI系统于2015至2016年间行T2加权和扩散前列腺MRI;训练集250人(中位年龄64岁,IQR 58-71岁),测试集62人(中位年龄64岁,IQR 60-69岁);参考标准为靶向联合扩展系统MRI-经直肠超声融合活检,临床显著前列腺癌定义为国际泌尿病理学会Gleason分级组≥2;采用分割样本验证,U-Net在训练集(80%数据)通过交叉验证内部验证,并在测试集(20%数据)外部验证。
诊断标准与关键数值
- 测试集按患者分析:PI-RADS≥3 vs ≥4的敏感度为96%(25/26)vs 88%(23/26),特异度为22%(8/36)vs 50%(18/36);U-Net概率阈值≥0.22 vs ≥0.33的敏感度为96%(25/26)vs 92%(24/26)(均P>.99),特异度为31%(11/36)vs 47%(17/36)(均P>.99),与PI-RADS无统计学差异;Dice系数前列腺为0.89,MRI病灶为0.35;测试集中PI-RADS≥4与U-Net病灶(阈值≥0.33)coincidence使阳性预测值从48%(28/58)升至67%(24/36)(P=.01),阴性预测值不变(83%[25/30] vs 83%[43/52];P>.99)。
临床应用与阅片要点
- U-Net概率图经校准后可用于辅助PI-RADS评估,其与PI-RADS≥4联合可提高阳性预测值;病灶分割Dice系数0.35提示分割精度有限,阅片时仍需以临床PI-RADS评估为准。
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 Men suspected of having clinically significant prostate cancer (sPC) increasingly undergo prostate MRI. The potential of deep learning to provide diagnostic support for human interpretation requires further evaluation. Purpose To compare the performance of clinical assessment to a deep learning system optimized for segmentation trained with T2-weighted and diffusion MRI in the task of detection and segmentation of lesions suspicious for sPC. Materials and Methods In this retrospective study, T2-weighted and diffusion prostate MRI sequences from consecutive men examined with a single 3.0-T MRI system between 2015 and 2016 were manually segmented. Ground truth was provided by combined targeted and extended systematic MRI-transrectal US fusion biopsy, with sPC defined as International Society of Urological Pathology Gleason grade group greater than or equal to 2. By using split-sample validation, U-Net was internally validated on the training set (80% of the data) through cross validation and subsequently externally validated on the test set (20% of the data). U-Net-derived sPC probability maps were calibrated by matching sextant-based cross-validation performance to clinical performance of Prostate Imaging Reporting and Data System (PI-RADS). Performance of PI-RADS and U-Net were compared by using sensitivities, specificities, predictive values, and Dice coefficient. Results A total of 312 men (median age, 64 years; interquartile range [IQR], 58-71 years) were evaluated. The training set consisted of 250 men (median age, 64 years; IQR, 58-71 years) and the test set of 62 men (median age, 64 years; IQR, 60-69 years). In the test set, PI-RADS cutoffs greater than or equal to 3 versus cutoffs greater than or equal to 4 on a per-patient basis had sensitivity of 96% (25 of 26) versus 88% (23 of 26) at specificity of 22% (eight of 36) versus 50% (18 of 36). U-Net at probability thresholds of greater than or equal to 0.22 versus greater than or equal to 0.33 had sensitivity of 96% (25 of 26) versus 92% (24 of 26) (both P > .99) with specificity of 31% (11 of 36) versus 47% (17 of 36) (both P > .99), not statistically different from PI-RADS. Dice coefficients were 0.89 for prostate and 0.35 for MRI lesion segmentation. In the test set, coincidence of PI-RADS greater than or equal to 4 with U-Net lesions improved the positive predictive value from 48% (28 of 58) to 67% (24 of 36) for U-Net probability thresholds greater than or equal to 0.33 (P = .01), while the negative predictive value remained unchanged (83% [25 of 30] vs 83% [43 of 52]; P > .99). Conclusion U-Net trained with T2-weighted and diffusion MRI achieves similar performance to clinical Prostate Imaging Reporting and Data System assessment. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Padhani and Turkbey in this issue.
引用
- Schelb P, Kohl S, Radtke JP, et al. Classification of Cancer at Prostate MRI: Deep Learning versus Clinical PI-RADS Assessment. Radiology. 2019. PMID: 31592731. doi:10.1148/radiol.2019190938
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。