📄 中文摘要
前列腺癌是全球男性中最常见的恶性肿瘤之一。然而，由于肿瘤在前列腺内的多灶性分布，生化复发（BCR）预测在根治性前列腺切除术后仍然具有挑战性。研究提出了一种新颖的AI框架，能够同时处理一系列多切片病理幻灯片，以全面捕捉整个前列腺腺体的肿瘤景观。为开发该预测AI模型，研究团队整理了来自789名患者的23,451张幻灯片的大规模数据集。所提出的框架在1年和2年BCR预测中表现出强大的预测性能，显著优于现有的临床基准。
基于AI的高效多切片全幻灯片图像分析用于前列腺癌生化复发预测
📄 English Summary
Efficient AI-Driven Multi-Section Whole Slide Image Analysis for Biochemical Recurrence Prediction in Prostate Cancer
Prostate cancer is one of the most commonly diagnosed malignancies among men worldwide. However, accurately predicting biochemical recurrence (BCR) after radical prostatectomy remains a challenge due to the multifocal nature of tumors within the prostate gland. A novel AI framework is proposed that simultaneously processes a series of multi-section pathology slides to capture the comprehensive tumor landscape across the entire prostate gland. To develop this predictive AI model, a large-scale dataset comprising 23,451 slides from 789 patients was curated. The proposed framework demonstrated strong predictive performance for 1- and 2-year BCR prediction, significantly outperforming established clinical benchmarks.