Deep Learning with Permutation-invariant Operator for Multi-instance Histopathology Classification

TL;DR

This paper introduces a multi-instance learning framework using a permutation-invariant operator for classifying histopathology images, addressing challenges like limited data and large image sizes in medical imaging.

Contribution

The paper proposes a novel deep learning approach that processes images as collections of patches with a permutation-invariant operator for improved classification.

Findings

Effective handling of small datasets and large images in histopathology

Improved classification accuracy over traditional methods

Reduced computational requirements

Abstract

The computer-aided analysis of medical scans is a longstanding goal in the medical imaging field. Currently, deep learning has became a dominant methodology for supporting pathologists and radiologist. Deep learning algorithms have been successfully applied to digital pathology and radiology, nevertheless, there are still practical issues that prevent these tools to be widely used in practice. The main obstacles are low number of available cases and large size of images (a.k.a. the small n, large p problem in machine learning), and a very limited access to annotation at a pixel level that can lead to severe overfitting and large computational requirements. We propose to handle these issues by introducing a framework that processes a medical image as a collection of small patches using a single, shared neural network. The final diagnosis is provided by combining scores of individual patches using a permutation-invariant operator (combination). In machine learning community such approach is called a multi-instance learning (MIL).