DCMIL: A Progressive Representation Learning of Whole Slide Images for Cancer Prognosis Analysis

2025/10/16 by Chao Tu, Tu, Chao, Kun Huang +8
Biochemistry, Genetics and Molecular Biology · Computer Science · #AI in cancer detection #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2510.14403

openalex publication_date 2025/10/16 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/31

Abstract

The burgeoning discipline of computational pathology shows promise in harnessing whole slide images (WSIs) to quantify morphological heterogeneity and develop objective prognostic modes for human cancers. However, progress is impeded by the computational bottleneck of gigapixel-size inputs and the scarcity of dense manual annotations. Current methods often overlook fine-grained information across multi-magnification WSIs and variations in tumor microenvironments. Here, we propose an easy-to-hard progressive representation learning, termed dual-curriculum contrastive multi-instance learning (DCMIL), to efficiently process WSIs for cancer prognosis. The model does not rely on dense annotations and enables the direct transformation of gigapixel-size WSIs into outcome predictions. Extensive experiments on twelve cancer types (5,954 patients, 12.54 million tiles) demonstrate that DCMIL outperforms standard WSI-based prognostic models. Additionally, DCMIL identifies fine-grained prognosis-salient regions, provides robust instance uncertainty estimation, and captures morphological differences between normal and tumor tissues, with the potential to generate new biological insights. All codes have been made publicly accessible at https://github.com/tuuuc/DCMIL.

Citations

• Multimodal Whole Slide Foundation Model for Pathology
• Multistain Pretraining for Slide Representation Learning in Pathology
• PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology
• Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
• DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification
• Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• A Simple Framework for Contrastive Learning of Visual Representations
• Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology
• Representation Learning with Contrastive Predictive Coding
• Neural Discrete Representation Learning
• Attention Is All You Need
• The Eighth Edition <scp>AJCC</scp> Cancer Staging Manual: Continuing to build a bridge from a population‐based to a more “personalized” approach to cancer staging
• Learning Deep Features for Discriminative Localization
• Estimation of the Youden Index and its Associated Cutoff Point

Related

• nnMIL: A generalizable multiple instance learning framework for computational pathology
• Slide-based Graph Collaborative Training for Histopathology Whole Slide Image Analysis
• MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Images
• MGCT: Mutual-Guided Cross-Modality Transformer for Survival Outcome Prediction using Integrative Histopathology-Genomic Features
• Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images