Multi-Modal Evaluation Approach for Medical Image Segmentation

TL;DR

This paper introduces a novel multi-modal evaluation approach for medical image segmentation that captures complex prediction properties, improving assessment accuracy across various datasets and making the evaluation process more interpretable.

Contribution

The paper proposes a new multi-modal evaluation method that considers partial correctness and introduces interpretable metrics for medical image segmentation.

Findings

Enhanced evaluation metrics for segmentation quality

Applicability demonstrated on multiple datasets

Open-source implementation available

Abstract

Manual segmentation of medical images (e.g., segmenting tumors in CT scans) is a high-effort task that can be accelerated with machine learning techniques. However, selecting the right segmentation approach depends on the evaluation function, particularly in medical image segmentation where we must deal with dependency between voxels. For instance, in contrast to classical systems where the predictions are either correct or incorrect, predictions in medical image segmentation may be partially correct and incorrect simultaneously. In this paper, we explore this expressiveness to extract the useful properties of these systems and formally define a novel multi-modal evaluation (MME) approach to measure the effectiveness of different segmentation methods. This approach improves the segmentation evaluation by introducing new relevant and interpretable characteristics, including detection property, boundary alignment, uniformity, total volume, and relative volume. Our proposed approach is open-source and publicly available for use. We have conducted several reproducible experiments, including the segmentation of pancreas, liver tumors, and multi-organs datasets, to show the applicability of the proposed approach.