发表机构
Radboud University Medical Center; Canisius Wilhelmina Hospital; Oncode Institute; Erasmus University Medical Center; Bydgoszcz University of Science and Technology; Yerevan State Medical University; IMP Diagnostics（拉德堡德大学医学中心; 卡尼修斯威廉明娜医院; Oncode研究所; 伊拉斯姆斯大学医学中心; 比得哥什科技大学; 埃里温国立医科大学; IMP诊断公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究开发首个公开标准化前列腺癌预后多模态基准CHIMERA挑战赛，整合多类数据建立数据集，发现多模态模型在缺失临床变量时更稳健，单模态临床模型性能更高但对变量完整性敏感。
AI 中文摘要
生化复发（BCR）被定义为前列腺切除术后任何可检测到的前列腺特异性抗原水平经确认升高，被广泛用作替代终点，通常通过临床和病理变量进行评估。目前，泌尿系统肿瘤的多模态预后建模尚无标准化基准，部分原因是整理异质多模态数据仍存在挑战。我们开发了CHIMERA挑战赛，这是一个整合了术前多参数磁共振成像（mpMRI）、前列腺切除术后组织病理学、患者特征以及临床医生衍生变量的多模态基准，数据来自两家机构的267名患者。该数据集包含801个MRI序列、每个病例13个临床变量以及942张全视野数字切片（WSI）。训练集（n=95）、验证集（n=23）和测试集（n=149）已建立并托管在Grand Challenge平台上。各拆分集的基线临床和病理特征无显著差异。通过 concordance index（C-index）评估模型预测BCR时间的性能。挑战赛后的分析测试了当临床医生衍生变量被 withheld 或随机化时，每种模型类型的表现。单模态临床模型的测试C指数最高，为0.7402，但对这些变量的完整性敏感，当这些变量被随机化时，性能降至接近随机水平（C约为0.50）。多模态模型在 withheld 这些变量时保持接近基线的性能（delta C最多为0.04），表明它们能够直接从成像数据中恢复预后信号。CHIMERA是首个公开的标准化前列腺癌预后多模态基准。尽管仅使用患者特征和临床医生衍生变量的模型在排行榜上取得了最高性能，但多模态模型在无法保证完整专家注释的临床实际场景中表现出更强的稳健性。
英文摘要
Biochemical recurrence (BCR), defined as any detectable prostate-specific antigen level after prostatectomy with confirmatory elevation, is widely used as a surrogate endpoint and typically assessed using clinical and pathological variables. Currently, no standardized benchmark exists for multimodal prognostic modeling in urological cancers, partly because curating heterogeneous multimodal data remains challenging. We developed the CHIMERA Challenge, a multimodal benchmark integrating preoperative mpMRI, post-prostatectomy histopathology, patient characteristics, and clinician-derived variables from 267 patients across two institutions. The dataset comprises 801 MRI sequences, 13 clinical variables per case, and 942 WSIs. Training (n=95), validation (n=23), and test (n=149) splits were established and hosted on the Grand Challenge platform. Baseline clinical and pathological characteristics did not differ significantly across splits. Models were evaluated on predicting time to BCR using the C-index. Post-challenge analyses tested how each model type performed when clinician-derived variables were withheld or randomized. Unimodal clinical models achieved the highest test C-index of 0.7402 but proved sensitive to the integrity of these variables, with performance collapsing toward chance (C approximately 0.50) when they were randomized. Multimodal models retained near-baseline performance when these variables were withheld (delta C at most 0.04), indicating their ability to recover prognostic signal directly from imaging data. CHIMERA is the first public, standardized multimodal benchmark for prostate cancer prognosis. Although models using only patient characteristics and clinician-derived variables yielded the highest leaderboard performance, multimodal models demonstrated greater robustness in clinically realistic scenarios where complete expert annotation is not guaranteed.
Comments38 pages, 3 figures, 3 supplementary figures. Preprint submitted to Medical Image Analysis. Challenge results presented at the CHIMERA workshop, MICCAI 2025. Challenge website: https://chimera.grand-challenge.org/chimera/
