MOOZY：面向患者优先的计算病理学基础模型

MOOZY: A Patient-First Foundation Model for Computational Pathology

March 27, 2026

作者: Yousef Kotp, Vincent Quoc-Huy Trinh, Christopher Pal, Mahdi S. Hosseini

cs.AI

摘要

計算病理學需要能夠跨越多種臨床任務遷移的全玻片影像基礎模型，然而現有方法仍主要以玻片為中心，通常依賴私有數據和昂貴的配對報告監督，且未顯式建模同一患者多張玻片間的關聯。我們提出MOOZY——一個以患者為先的病理學基礎模型，其核心表徵單元是患者病例而非單張玻片。MOOZY在預訓練階段通過病例轉換器顯式建模同一患者所有玻片間的依賴關係，結合多階段開放式自監督與規模化低成本任務監督。第一階段，我們使用掩碼自蒸餾技術在77,134個公開玻片特徵網格上預訓練純視覺玻片編碼器。第二階段，我們通過病例轉換器將這些表徵與臨床語義對齊，並在來自56個公開數據集的333項任務（包括涵蓋四個終點的205項分類任務和128項生存分析任務）上進行多任務監督。在八項保留任務的五折凍結特徵探針評估中，MOOZY在多數指標上取得最佳或並列最佳性能，加權F1、加權ROC-AUC和平衡準確度的宏觀平均值相較TITAN分別提升+7.37%、+5.50%和+7.83%，相較PRISM分別提升+8.83%、+10.70%和+9.78%。MOOZY僅需8577萬參數，比GigaPath小14倍，具有顯著的參數效率優勢。這些結果表明，開放可重現的患者層級預訓練能夠產生可遷移的表徵嵌入，為構建可擴展的以患者為先的組織病理學基礎模型提供了可行路徑。

English

Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain largely slide-centric, often depend on private data and expensive paired-report supervision, and do not explicitly model relationships among multiple slides from the same patient. We present MOOZY, a patient-first pathology foundation model in which the patient case, not the individual slide, is the core unit of representation. MOOZY explicitly models dependencies across all slides from the same patient via a case transformer during pretraining, combining multi-stage open self-supervision with scaled low-cost task supervision. In Stage 1, we pretrain a vision-only slide encoder on 77,134 public slide feature grids using masked self-distillation. In Stage 2, we align these representations with clinical semantics using a case transformer and multi-task supervision over 333 tasks from 56 public datasets, including 205 classification and 128 survival tasks across four endpoints. Across eight held-out tasks with five-fold frozen-feature probe evaluation, MOOZY achieves best or tied-best performance on most metrics and improves macro averages over TITAN by +7.37%, +5.50%, and +7.83% and over PRISM by +8.83%, +10.70%, and +9.78% for weighted F1, weighted ROC-AUC, and balanced accuracy, respectively. MOOZY is also parameter efficient with 85.77M parameters, 14x smaller than GigaPath. These results demonstrate that open, reproducible patient-level pretraining yields transferable embeddings, providing a practical path toward scalable patient-first histopathology foundation models.