TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

Abstract

Multiple instance learning (MIL) is a powerful tool to solve the weakly supervised classification in whole slide image (WSI) based pathology diagnosis. However, the current MIL methods are usually based on independent and identical distribution hypothesis, thus neglect the correlation among different instances. To address this problem, we proposed a new framework, called correlated MIL, and provided a proof for convergence. Based on this framework, we devised a Transformer based MIL (TransMIL), which explored both morphological and spatial information. The proposed TransMIL can effectively deal with unbalanced/balanced and binary/multiple classification with great visualization and interpretability. We conducted various experiments for three different computational pathology problems and achieved better performance and faster convergence compared with state-of-the-art methods. The test AUC for the binary tumor classification can be up to 93.09% over CAMELYON16 dataset. And the AUC over the cancer subtypes classification can be up to 96.03% and 98.82% over TCGA-NSCLC dataset and TCGA-RCC dataset, respectively. Implementation is available at: https://github.com/szc19990412/TransMIL.

Cited by in corpus (15)

• Artificial Intelligence for Digital and Computational Pathology
• Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review
• Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis
• Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images
• Gigapixel Whole-Slide Images Classification using Locally Supervised Learning
• PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioning
• A robust and scalable framework for hallucination detection in virtual tissue staining and digital pathology
• ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classification
• Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labels
• Re-identification from histopathology images
• Joint Stream: Malignant Region Learning for Breast Cancer Diagnosis
• Pretrained Deep 2.5D Models for Efficient Predictive Modeling from Retinal OCT
• SCMIL: Sparse Context-aware Multiple Instance Learning for Predicting Cancer Survival Probability Distribution in Whole Slide Images
• Probabilistic smooth attention for deep multiple instance learning in medical imaging
• Mixing Histopathology Prototypes into Robust Slide-Level Representations for Cancer Subtyping