arXiv cs.AI· Yesung Cho, Dongmyung Shin, Sujeong Hong, Jooyeon Lee, Seongmin Park, Geongyu Lee, Won Young Park, Bongjin Park, Jongbae Park, Hong Koo Ha·· 13 小时前AI 评分31
高效多切片全切片图像分析框架预测前列腺癌生化复发
A Computationally Efficient Multi-Section Whole Slide Image Analysis for Capturing Prostate Cancer Multifocality in Biochemical Recurrence Prediction
AI 导读
研究提出一种计算高效的多切片全切片图像分析框架，基于789名患者的23,451张切片，通过优化切片与子采样显著降低训练和推理成本，在1年和2年生化复发预测上达到或超过现有临床基准。AI风险评分在多变量Cox分析中为独立预后因素，与临床变量结合可进一步提升预后表现，外部验证提供初步可迁移性证据。注意力分散分析显示模型从多个切片中提取预后信息，与前列腺癌多灶性特征一致。
正文 · 原文
Abstract:Prostate cancer is among the most frequently diagnosed malignancies in men worldwide. However, precise prediction of biochemical recurrence (BCR) after radical prostatectomy remains challenging. Here, we propose a computationally efficient multi section whole slide image analysis framework designed to capture the whole gland tumor landscape. We curated a large scale dataset comprising 23,451 slides from 789 patients and systematically optimized patch and slide sub sampling to substantially reduce the computational cost of training and inference. Under this efficient configuration, the framework achieved strong predictive performance for 1- and 2-year BCR, with discrimination and clinical net benefit comparable to or exceeding those of established clinical benchmarks. In multivariable Cox proportional hazards analysis, the AI derived risk score remained an independent prognostic factor among the covariates examined, and its integration with clinical variables further improved prognostic performance. External validation in an independent cohort provided preliminary evidence of transferability. Finally, attention-dispersion analysis showed that the model drew prognostic information from multiple sections, consistent with the multifocal nature of prostate cancer. Collectively, these findings support the potential of multi section slide analysis as a scalable approach for postoperative BCR risk assessment in prostate cancer.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.20273 [cs.CV] |
| (or arXiv:2603.20273v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2603.20273 arXiv-issued DOI via DataCite |
Submission history
From: Geongyu Lee [view email]
[v1]
Tue, 17 Mar 2026 07:58:02 UTC (1,328 KB)
[v2]
Tue, 27 Oct 2026 06:32:34 UTC (6,013 KB)
来源：arXiv cs.AI · arxiv.org