A large annotated medical image dataset for the development and evaluation of segmentation algorithms

TL;DR

This paper introduces a large, annotated collection of medical images across various anatomies, designed to support the development, evaluation, and benchmarking of segmentation algorithms, and is openly accessible for research use.

Contribution

It provides a comprehensive, multi-institutional dataset of annotated medical images for segmentation, facilitating objective benchmarking and open research in medical image analysis.

Findings

Created ten annotated datasets for diverse segmentation tasks

Enabled a crowd-sourced challenge to evaluate algorithms

Promoted open access and reproducibility in medical imaging research

Abstract

Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization. The success of semantic segmentation algorithms is contingent on the availability of high-quality imaging data with corresponding labels provided by experts. We sought to create a large collection of annotated medical image datasets of various clinically relevant anatomies available under open source license to facilitate the development of semantic segmentation algorithms. Such a resource would allow: 1) objective assessment of general-purpose segmentation methods through comprehensive benchmarking and 2) open and free access to medical image data for any researcher interested in the problem domain. Through a multi-institutional effort, we generated a large, curated dataset representative of several highly variable segmentation tasks that was used in a crowd-sourced challenge - the Medical Segmentation Decathlon held during the 2018 Medical Image Computing and Computer Aided Interventions Conference in Granada, Spain. Here, we describe these ten labeled image datasets so that these data may be effectively reused by the research community.