Detecting Breast Carcinoma Metastasis on Whole-Slide Images by Partially Subsampled Multiple Instance Learning

2026-04-19

AI Summary

This work addresses the challenge of detecting breast cancer metastases in whole-slide images (WSIs), which is hindered by their massive data volume and tissue heterogeneity. The authors propose a Gaussian mixture model–based multiple instance learning framework that introduces bag-level maximum likelihood estimation (BMLE) and subsampled maximum likelihood estimation (SMLE). These components enhance robustness under model misspecification and improve the sampling of partial positive instances along with their label assignment. The proposed method achieves significant gains in both bag-level and instance-level prediction accuracy, outperforming current state-of-the-art approaches in metastasis detection while maintaining high accuracy and strong robustness.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Computer Vision: Segmentation

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Breast cancer is the most prevalent cancer in women worldwide. Histopathology image analysis serves as the gold standard for cancer diagnosis. In this regard, whole-slide imaging (WSI), a revolutionary technology in digital pathology, allows for ultrahigh-resolution tissue analysis. Despite its promise, WSI analysis faces significant computational challenges due to its massive data size and tissue heterogeneity. To address this issue, we present a Gaussian mixture based multiple instance learning (MIL) framework for WSI analysis with partially subsampled instances. Our approach models a WSI as a bag of instances (i.e., randomly cropped sub-images), leveraging a bag-based maximum likelihood estimator (BMLE) to predict metastases. Furthermore, we introduce a subsampling-based maximum likelihood estimator (SMLE) to refine predictions by selectively labeling a subset of instances. Extensive evaluations of the breast carcinoma metastasis prediction demonstrate that BMLE surpasses state-of-the-art methods, while the SMLE further improves the prediction accuracy at both bag and instance levels. We find that our method is fairly robust against various plausible model mis-specifications. Theoretical analyses and simulation studies validate the performance and robustness of our methods.

Problem

• breast carcinoma metastasis
• whole-slide imaging
• multiple instance learning
• computational pathology
• histopathology image analysis

Innovation

• Multiple Instance Learning
• Whole-Slide Imaging
• Subsampling
• Maximum Likelihood Estimation
• Gaussian Mixture Model