Oliveira Lia D, Lu Jiayun, Erak Eric, Mendes Adrianna A, Dairo Oluwademilade, Ertunc Onur, Kulac Ibrahim, Baena-Del Valle Javier A, Jones Tracy, Hicks Jessica L, Glavaris Stephanie, Guner Gunes, Vidal Igor D, Trock Bruce J, Joshi Uttara, Kondragunta Chaith, Bonthu Saikiran, Joshu Corinne, Singhal Nitin, De Marzo Angelo M, Lotan Tamara L
Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA.
Eur Urol Oncol. 2025 Feb;8(1):9-13. doi: 10.1016/j.euo.2024.08.004. Epub 2024 Sep 3.
Gleason grade group (GG) is the most powerful prognostic variable in localized prostate cancer; however, interobserver variability remains a challenge. Artificial intelligence algorithms applied to histopathologic images standardize grading, but most have been tested only for agreement with pathologist GG, without assessment of performance with respect to oncologic outcomes. We compared deep learning-based and pathologist-based GGs for an association with metastatic outcome in three surgical cohorts comprising 777 unique patients. A digitized whole slide image of the representative hematoxylin and eosin-stained slide of the dominant tumor nodule was assigned a GG by an artificial intelligence-based grading algorithm and was compared with the GG assigned by a contemporary pathologist or the original pathologist-assigned GG for the entire prostatectomy. Harrell's C-indices based on Cox models for time to metastasis were compared. In a combined analysis of all cohorts, the C-index for the artificial intelligence-assigned GG was 0.77 (95% confidence interval [CI]: 0.73-0.81), compared with 0.77 (95% CI: 0.73-0.81) for the pathologist-assigned GG. By comparison, the original pathologist-assigned GG for the entire case had a C-index of 0.78 (95% CI: 0.73-0.82). PATIENT SUMMARY: Artificial intelligence-enabled prostate cancer grading on a single slide was comparable with pathologist grading for predicting metastatic outcome in men treated by radical prostatectomy, enabling equal access to expert grading in lower resource settings.
Gleason分级组（GG）是局限性前列腺癌中最有力的预后变量；然而，观察者间的变异性仍然是一个挑战。应用于组织病理学图像的人工智能算法使分级标准化，但大多数仅针对与病理学家GG的一致性进行了测试，而未评估其在肿瘤学结果方面的表现。我们在三个包含777例独特患者的手术队列中，比较了基于深度学习的GG和基于病理学家的GG与转移结果的关联。通过基于人工智能的分级算法为优势肿瘤结节的代表性苏木精和伊红染色玻片的数字化全切片图像分配一个GG，并将其与当代病理学家分配的GG或整个前列腺切除术中原病理学家分配的GG进行比较。比较了基于Cox模型的转移时间的Harrell C指数。在所有队列的综合分析中，人工智能分配的GG的C指数为0.77（95%置信区间[CI]：0.73 - 0.81），而病理学家分配的GG的C指数为0.77（95%CI：0.73 - 0.81）。相比之下，整个病例中原病理学家分配的GG的C指数为0.78（95%CI：0.73 - 0.82）。患者总结：在接受根治性前列腺切除术的男性中，基于人工智能的单张玻片前列腺癌分级在预测转移结果方面与病理学家分级相当，从而能够在资源较少的环境中平等获得专家级分级。
