Expert-Adaptive Medical Image Segmentation

TL;DR

This paper introduces an expert-adaptive deep learning approach for medical image segmentation that effectively adapts to new experts with limited training data, addressing variability in expert annotations.

Contribution

The work proposes a multi-expert annotation, multi-task training, and lightweight fine-tuning method to improve model adaptability to new experts in medical image segmentation.

Findings

Effective adaptation to new experts demonstrated on brain MRI segmentation.

Key parameters significantly impact model performance.

Method performs well with limited training data.

Abstract

Medical image segmentation (MIS) plays an instrumental role in medical image analysis, where considerable effort has been devoted to automating the process. Currently, mainstream MIS approaches are based on deep neural networks (DNNs), which are typically trained on a dataset with annotations produced by certain medical experts. In the medical domain, the annotations generated by different experts can be inherently distinct due to complexity of medical images and variations in expertise and post-segmentation missions. Consequently, the DNN model trained on the data annotated by some experts may hardly adapt to a new expert. In this work, we evaluate a customised expert-adaptive method, characterised by multi-expert annotation, multi-task DNN-based model training, and lightweight model fine-tuning, to investigate model's adaptivity to a new expert in the situation where the amount and mobility of training images are limited. Experiments conducted on brain MRI segmentation tasks with limited training data demonstrate its effectiveness and the impact of its key parameters.