文献速递泌尿生殖腹部MR

基于深度迁移学习的3特斯拉多参数MRI前列腺癌分类研究

Deep transfer learning-based prostate cancer classification using 3 Tesla multi-parametric MRI.
PubMed 文献 · Abdom Radiol (NY) · 2019-01-01

本研究纳入140例有3T多参数MRI和全mount病理的患者,提出基于深度迁移学习(DTL)的模型区分惰性与临床显著前列腺癌,并与无迁移学习的深度学习(DL)模型及PI-RADS v2评分≥4分类比较。测试集中DTL模型AUC为0.726,DL模型为0.687,PI-RADS v2≥4为0.711;DeLong检验显示DTL模型与PI-RADS v2评分分类AUC相当(p=0.89)。

要点

  • DTL模型在测试集区分临床显著前列腺癌的AUC为0.726(95%CI 0.575–0.876)。
  • 无迁移学习DL模型AUC为0.687(95%CI 0.532–0.843),PI-RADS v2≥4为0.711(95%CI 0.575–0.847)。
  • DeLong检验示DTL模型与PI-RADS v2评分分类AUC相当(p=0.89)。

核心结论

  • DTL模型在测试集区分惰性与临床显著前列腺癌的AUC高于无迁移学习DL模型和PI-RADS v2≥4分类,但与PI-RADS v2评分分类AUC相当(p=0.89)。

研究设计与样本

  • 经IRB批准,140例有3T mp-MRI和全mount病理的患者组成研究队列;DTL模型在110例任意选择患者的169个病灶上训练,在剩余30例患者的47个病灶上测试;比较DTL模型、相同架构从头训练的DL模型和PI-RADS v2评分阈值4分类,采用准确率、敏感度、特异度和AUC,并用2000次重抽样bootstrap估计AUC的95%CI。

诊断标准与关键数值

  • 测试集中,DTL模型区分惰性与临床显著前列腺癌的AUC为0.726(95%CI 0.575–0.876);无迁移学习DL模型AUC为0.687(95%CI 0.532–0.843);PI-RADS v2评分≥4分类AUC为0.711(95%CI 0.575–0.847)。

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

PURPOSE: The purpose of the study was to propose a deep transfer learning (DTL)-based model to distinguish indolent from clinically significant prostate cancer (PCa) lesions and to compare the DTL-based model with a deep learning (DL) model without transfer learning and PIRADS v2 score on 3 Tesla multi-parametric MRI (3T mp-MRI) with whole-mount histopathology (WMHP) validation.

METHODS: With IRB approval, 140 patients with 3T mp-MRI and WMHP comprised the study cohort. The DTL-based model was trained on 169 lesions in 110 arbitrarily selected patients and tested on the remaining 47 lesions in 30 patients. We compared the DTL-based model with the same DL model architecture trained from scratch and the classification based on PIRADS v2 score with a threshold of 4 using accuracy, sensitivity, specificity, and area under curve (AUC). Bootstrapping with 2000 resamples was performed to estimate the 95% confidence interval (CI) for AUC.

RESULTS: After training on 169 lesions in 110 patients, the AUC of discriminating indolent from clinically significant PCa lesions of the DTL-based model, DL model without transfer learning and PIRADS v2 score ≥ 4 were 0.726 (CI [0.575, 0.876]), 0.687 (CI [0.532, 0.843]), and 0.711 (CI [0.575, 0.847]), respectively, in the testing set. The DTL-based model achieved higher AUC compared to the DL model without transfer learning and PIRADS v2 score ≥ 4 in discriminating clinically significant lesions in the testing set.

CONCLUSION: The DeLong test indicated that the DTL-based model achieved comparable AUC compared to the classification based on PIRADS v2 score (p = 0.89).

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Zhong X, Cao R, Shakeri S, et al. Deep transfer learning-based prostate cancer classification using 3 Tesla multi-parametric MRI. Abdom Radiol (NY). 2019. PMID: 30460529. doi:10.1007/s00261-018-1824-5

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。