Department of Public Health Sciences, Henry Ford Health System, Detroit, Michigan; Center for Bioinformatics, Henry Ford Health System, Detroit, Michigan.
Department of Public Health Sciences, Henry Ford Health System, Detroit, Michigan; Center for Bioinformatics, Henry Ford Health System, Detroit, Michigan.
Mod Pathol. 2023 Jul;36(7):100157. doi: 10.1016/j.modpat.2023.100157. Epub 2023 Mar 15.
Differential classification of prostate cancer grade group (GG) 2 and 3 tumors remains challenging, likely because of the subjective quantification of the percentage of Gleason pattern 4 (%GP4). Artificial intelligence assessment of %GP4 may improve its accuracy and reproducibility and provide information for prognosis prediction. To investigate this potential, a convolutional neural network (CNN) model was trained to objectively identify and quantify Gleason pattern (GP) 3 and 4 areas, estimate %GP4, and assess whether CNN-predicted %GP4 is associated with biochemical recurrence (BCR) risk in intermediate-risk GG 2 and 3 tumors. The study was conducted in a radical prostatectomy cohort (1999-2012) of African American men from the Henry Ford Health System (Detroit, Michigan). A CNN model that could discriminate 4 tissue types (stroma, benign glands, GP3 glands, and GP4 glands) was developed using histopathologic images containing GG 1 (n = 45) and 4 (n = 20) tumor foci. The CNN model was applied to GG 2 (n = 153) and 3 (n = 62) tumors for %GP4 estimation, and Cox proportional hazard modeling was used to assess the association of %GP4 and BCR, accounting for other clinicopathologic features including GG. The CNN model achieved an overall accuracy of 86% in distinguishing the 4 tissue types. Furthermore, CNN-predicted %GP4 was significantly higher in GG 3 than in GG 2 tumors (P = 7.2 × 10). %GP4 was associated with an increased risk of BCR (adjusted hazard ratio, 1.09 per 10% increase in %GP4; P = .010) in GG 2 and 3 tumors. Within GG 2 tumors specifically, %GP4 was more strongly associated with BCR (adjusted hazard ratio, 1.12; P = .006). Our findings demonstrate the feasibility of CNN-predicted %GP4 estimation, which is associated with BCR risk. This objective approach could be added to the standard pathologic assessment for patients with GG 2 and 3 tumors and act as a surrogate for specialist genitourinary pathologist evaluation when such consultation is not available.
前列腺癌分级组（GG）2 和 3 肿瘤的差异分类仍然具有挑战性，可能是因为对 Gleason 模式 4（%GP4）百分比的主观量化。人工评估 %GP4 可能会提高其准确性和可重复性，并为预后预测提供信息。为了研究这种潜力，训练了一个卷积神经网络（CNN）模型，以客观地识别和量化 Gleason 模式（GP）3 和 4 区域，估计 %GP4，并评估 CNN 预测的 %GP4 是否与中危 GG 2 和 3 肿瘤的生化复发（BCR）风险相关。该研究在密歇根州底特律市亨利福特健康系统的非洲裔美国男性根治性前列腺切除术队列（1999-2012 年）中进行。使用包含 GG 1（n=45）和 4（n=20）肿瘤灶的组织病理学图像开发了一种能够区分 4 种组织类型（基质、良性腺体、GP3 腺体和 GP4 腺体）的 CNN 模型。该 CNN 模型应用于 GG 2（n=153）和 3（n=62）肿瘤，以估计 %GP4，并使用 Cox 比例风险模型评估 %GP4 与 BCR 的关联，同时考虑包括 GG 在内的其他临床病理特征。该 CNN 模型在区分 4 种组织类型方面的总体准确率达到 86%。此外，CNN 预测的 %GP4 在 GG 3 肿瘤中明显高于 GG 2 肿瘤（P=7.2×10）。%GP4 与 GG 2 和 3 肿瘤的 BCR 风险增加相关（调整后的危险比，每增加 10%的 %GP4 增加 1.09；P=0.010）。在 GG 2 肿瘤中，%GP4 与 BCR 的相关性更强（调整后的危险比，1.12；P=0.006）。我们的研究结果表明，CNN 预测的 %GP4 估计是可行的，并且与 BCR 风险相关。这种客观方法可以添加到 GG 2 和 3 肿瘤患者的标准病理评估中，并且在无法进行专家泌尿生殖病理学家评估时，可以作为替代方法。
