Institute for Urology and Reproductive Health, Sechenov University, Moscow, Russia.
Institute for Clinical Medicine, Sechenov University, Moscow, Russia.
Prostate Cancer Prostatic Dis. 2023 Dec;26(4):681-692. doi: 10.1038/s41391-023-00673-3. Epub 2023 Apr 25.
Artificial intelligence (AI) is a promising tool in pathology, including cancer diagnosis, subtyping, grading, and prognostic prediction.
The aim of the study is to assess AI application in prostate cancer (PCa) histology. We carried out a systematic literature search in 3 databases. Primary outcome was AI accuracy in differentiating between PCa and benign hyperplasia. Secondary outcomes were AI accuracy in determining Gleason grade and agreement among AI and pathologists.
Our final sample consists of 24 studies conducted from 2007 to 2021. They aggregate data from roughly 8000 cases of prostate biopsy and 458 cases of radical prostatectomy (RP). Sensitivity for PCa diagnostic exceeded 90% and ranged from 87% to 100%, and specificity varied from 68% to 99%. Overall accuracy ranged from 83.7% to 98.3% with AUC reaching 0.99. The meta-analysis using the Mantel-Haenszel method showed pooled sensitivity of 0.96 with I = 80.7% and pooled specificity of 0.95 with I = 86.1%. Pooled positive likehood ratio was 15.3 with I = 87.3% and negative - was 0.04 with I = 78.6%. SROC (symmetric receiver operating characteristics) curve represents AUC = 0.99. For grading the accuracy of AI was lower: sensitivity for Gleason grading ranged from 77% to 87%, and specificity from 82% to 90%.
The accuracy of AI for PCa identification and grading is comparable to expert pathologists. This is a promising approach which has several possible clinical applications resulting in expedite and optimize pathology reports. AI introduction into common practice may be limited by difficult and time-consuming convolutional neural network training and tuning.
人工智能（AI）在病理学中具有广阔的应用前景，包括癌症诊断、分型、分级和预后预测。
本研究旨在评估 AI 在前列腺癌（PCa）组织学中的应用。我们在 3 个数据库中进行了系统文献检索。主要结局是 AI 区分 PCa 和良性增生的准确性。次要结局是 AI 确定 Gleason 分级的准确性以及 AI 与病理学家之间的一致性。
我们的最终样本包括 2007 年至 2021 年进行的 24 项研究。这些研究汇总了约 8000 例前列腺活检和 458 例根治性前列腺切除术（RP）的数据。PCa 诊断的敏感性超过 90%，范围为 87%至 100%，特异性为 68%至 99%。总体准确性为 83.7%至 98.3%，AUC 达到 0.99。使用 Mantel-Haenszel 方法进行的荟萃分析显示，合并敏感性为 0.96，I²=80.7%，合并特异性为 0.95，I²=86.1%。合并阳性似然比为 15.3，I²=87.3%，阴性似然比为 0.04，I²=78.6%。SROC（对称接收者操作特征）曲线表示 AUC=0.99。对于分级，AI 的准确性较低：Gleason 分级的敏感性为 77%至 87%，特异性为 82%至 90%。
AI 对 PCa 识别和分级的准确性可与专家病理学家相媲美。这是一种很有前途的方法，具有多种可能的临床应用，可加速和优化病理报告。AI 引入常规实践可能受到卷积神经网络训练和调整困难和耗时的限制。
