Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosis

TL;DR

This paper introduces HAICOMM, a novel human-AI collaborative approach that combines multi-modal and multi-rater learning to improve endometriosis diagnosis from MRI images, outperforming clinicians and existing models.

Contribution

The paper presents the first multi-modal, multi-rater learning method that incorporates human-AI collaboration for endometriosis diagnosis from MRI images.

Findings

HAICOMM outperforms clinicians and existing models on the dataset.

Multi-rater learning reduces label noise and improves accuracy.

Human-AI collaboration enhances diagnostic performance.

Abstract

Endometriosis, affecting about 10% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs of the disease using either laparoscopic surgery or the analysis of T1/T2 MRI images, with the latter being quicker and cheaper but less accurate. A key diagnostic sign of endometriosis is the obliteration of the Pouch of Douglas (POD). However, even experienced clinicians struggle with accurately classifying POD obliteration from MRI images, which complicates the training of reliable AI models. In this paper, we introduce the Human-AI Collaborative Multi-modal Multi-rater Learning (HAICOMM) methodology to address the challenge above. HAICOMM is the first method that explores three important aspects of this problem: 1) multi-rater learning to extract a cleaner label from the multiple "noisy" labels available per training sample; 2) multi-modal learning to leverage the presence of T1/T2 MRI images for training and testing; and 3) human-AI collaboration to build a system that leverages the predictions from clinicians and the AI model to provide more accurate classification than standalone clinicians and AI models. Presenting results on the multi-rater T1/T2 MRI endometriosis dataset that we collected to validate our methodology, the proposed HAICOMM model outperforms an ensemble of clinicians, noisy-label learning models, and multi-rater learning methods.