Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

TL;DR

The Touchstone Benchmark provides a large, diverse, and rigorous evaluation platform for AI algorithms in medical segmentation, addressing limitations of existing benchmarks and promoting real-world applicability.

Contribution

It introduces a large-scale, multi-hospital dataset and a third-party evaluation process to improve the assessment of AI algorithms for medical segmentation.

Findings

Enhanced statistical significance of results

Evaluation across out-of-distribution scenarios

Comparison of multiple AI frameworks and algorithms

Abstract

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks--which, differing from algorithms, are more flexible and can support different algorithms--including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.