Automatic Organ and Pan-cancer Segmentation in Abdomen CT: the FLARE 2023 Challenge
This work addresses the need for comprehensive cancer analysis in medical imaging by creating a benchmark for researchers and clinicians, though it is incremental as it builds on existing segmentation methods.
The FLARE 2023 Challenge tackled the problem of organ and pan-cancer segmentation in abdomen CT scans by providing a large-scale dataset of 4650 CT scans, resulting in a winning deep learning framework that achieved average Dice scores of 92.3% for organs and 64.9% for lesions.
Organ and cancer segmentation in abdomen Computed Tomography (CT) scans is the prerequisite for precise cancer diagnosis and treatment. Most existing benchmarks and algorithms are tailored to specific cancer types, limiting their ability to provide comprehensive cancer analysis. This work presents the first international competition on abdominal organ and pan-cancer segmentation by providing a large-scale and diverse dataset, including 4650 CT scans with various cancer types from over 40 medical centers. The winning team established a new state-of-the-art with a deep learning-based cascaded framework, achieving average Dice Similarity Coefficient scores of 92.3% for organs and 64.9% for lesions on the hidden multi-national testing set. The dataset and code of top teams are publicly available, offering a benchmark platform to drive further innovations https://codalab.lisn.upsaclay.fr/competitions/12239.