Minimally Invasive Urology Institute, The Miriam Hospital, Providence, RI, USA.
Carney Institute for Brain Science, Department of Cognitive, Linguistic & Psychological Sciences, Brown University, Providence, RI, USA.
Eur Urol Focus. 2021 Mar;7(2):347-351. doi: 10.1016/j.euf.2019.11.003. Epub 2019 Nov 22.
The pathologic diagnosis and Gleason grading of prostate cancer are time-consuming, error-prone, and subject to interobserver variability. Machine learning offers opportunities to improve the diagnosis, risk stratification, and prognostication of prostate cancer.
To develop a state-of-the-art deep learning algorithm for the histopathologic diagnosis and Gleason grading of prostate biopsy specimens.
DESIGN, SETTING, AND PARTICIPANTS: A total of 85 prostate core biopsy specimens from 25 patients were digitized at 20× magnification and annotated for Gleason 3, 4, and 5 prostate adenocarcinoma by a urologic pathologist. From these virtual slides, we sampled 14803 image patches of 256×256 pixels, approximately balanced for malignancy.
We trained and tested a deep residual convolutional neural network to classify each patch at two levels: (1) coarse (benign vs malignant) and (2) fine (benign vs Gleason 3 vs 4 vs 5). Model performance was evaluated using fivefold cross-validation. Randomization tests were used for hypothesis testing of model performance versus chance.
The model demonstrated 91.5% accuracy (p<0.001) at coarse-level classification of image patches as benign versus malignant (0.93 sensitivity, 0.90 specificity, and 0.95 average precision). The model demonstrated 85.4% accuracy (p<0.001) at fine-level classification of image patches as benign versus Gleason 3 versus Gleason 4 versus Gleason 5 (0.83 sensitivity, 0.94 specificity, and 0.83 average precision), with the greatest number of confusions in distinguishing between Gleason 3 and 4, and between Gleason 4 and 5. Limitations include the small sample size and the need for external validation.
In this study, a deep learning-based computer vision algorithm demonstrated excellent performance for the histopathologic diagnosis and Gleason grading of prostate cancer.
We developed a deep learning algorithm that demonstrated excellent performance for the diagnosis and grading of prostate cancer.
前列腺癌的病理诊断和 Gleason 分级既耗时，又容易出错，且存在观察者间的变异性。机器学习为改善前列腺癌的诊断、风险分层和预后提供了机会。
开发一种用于前列腺活检组织学诊断和 Gleason 分级的最先进深度学习算法。
设计、设置和参与者：共对 25 名患者的 85 个前列腺核心活检标本进行了 20×放大数字化，并由泌尿科病理学家对 Gleason 3、4 和 5 前列腺腺癌进行了注释。从这些虚拟幻灯片中，我们采集了约 14803 个 256×256 像素的图像斑块，其恶性程度大致平衡。
我们训练并测试了一个深度残差卷积神经网络，以在两个级别上对每个斑块进行分类：（1）粗（良性与恶性）和（2）细（良性与 Gleason 3 与 4 与 5）。使用五重交叉验证评估模型性能。随机化检验用于检验模型性能与随机的假设。
该模型在作为良性与恶性的图像斑块的粗分类水平上表现出 91.5%的准确率（p<0.001）（0.93 的敏感性、0.90 的特异性和 0.95 的平均精度）。该模型在作为良性与 Gleason 3 与 Gleason 4 与 Gleason 5 的图像斑块的细分类水平上表现出 85.4%的准确率（p<0.001）（0.83 的敏感性、0.94 的特异性和 0.83 的平均精度），在区分 Gleason 3 和 4 以及 Gleason 4 和 5 方面的混淆最多。局限性包括样本量小和需要外部验证。
在这项研究中，基于深度学习的计算机视觉算法在前列腺癌的组织病理学诊断和 Gleason 分级方面表现出了优异的性能。
我们开发了一种深度学习算法，该算法在前列腺癌的诊断和分级方面表现出了优异的性能。
