ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts
2026-07-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors developed ALICE, a large AI model for analyzing pathology images, by combining knowledge from eight different expert models into one unified system. They trained ALICE on millions of pathology images and tested it on a wide variety of tasks, including examining tissue samples and interpreting medical images with text descriptions. ALICE performed better on average than other similar models designed for pathology. The authors show that their method of merging multiple models, called agglomerative distillation, helps create a versatile tool for many pathology tasks.
foundation modelcomputational pathologyagglomerative distillationvision-language modelspathology imageswhole-slide imagingmultimodal evaluationpretrainingdeep learningmedical imaging
Authors
Jiawen Li, Tian Guan, Huijuan Shi, Xitong Ling, Mingxi Fu, Anjia Han, Chao He, Yonghong He
Abstract
Foundation models are reshaping computational pathology, yet their capabilities remain shaped by pretraining objectives, data sources, and spatial scales, fragmenting complementary expertise across separate backbones. Here we present ALICE, a unified foundation model trained through multi-stage agglomerative distillation that sequentially distills eight vision-only, vision-language, and slide-level teacher models into dedicated modules of a single backbone. ALICE is pretrained on 24,985,184 tile-level pathology images and 155,604 high-resolution images, and evaluated across 21 task scenarios, 96 downstream tasks, and 48 data sources, spanning region-of-interest tissue analysis, vision-language multimodal evaluation, and whole-slide clinical assessment. In all three evaluation settings, ALICE achieved the best average rank among task-matched pathology foundation models. These results demonstrate that agglomerative distillation can consolidate complementary capabilities from specialized models into a unified backbone for broad computational pathology applications. The model is available at https://github.com/WonderLandxD/ALICE.