This repository provides the evaluation code of the FLARE Challenges. More details are available on the corresponding websites.
MICCAI FLARE 2021: Fast and Low GPU memory Abdominal oRgan sEgmentation in CT Scans
- 511 cases from 11 medical centers
- Fully supervised setting
- Four segmentation targets: liver, kidney, spleen, and pancreas
- Evaluation metrics: DSC, NSD, Running time, Maximum GPU memory consumption
MICCAI FLARE 2022: Fast and Low-resource semi-supervised Abdominal oRgan sEgmentation in CT Scans
- 2300 CT scans from 50+ medical centers
- Semi-supervised setting
- 13 segmentation targets: liver, spleen, pancreas, right kidney, left kidney, stomach, gallbladder, esophagus, aorta, inferior vena cava, right adrenal gland, left adrenal gland, and duodenum
- Evaluation metrics: DSC, NSD, Running time, Area under GPU memory-time curve and Area under CPU utilization-time curve
MICCAI FLARE 2023: Fast, Low-resource, and Accurate oRgan and Pan-cancer sEgmentation in Abdomen CT
- 4000 CT scans from 50+ medical centers
- Partial-label setting
- 14 segmentation targets: liver, spleen, pancreas, right kidney, left kidney, stomach, gallbladder, esophagus, aorta, inferior vena cava, right adrenal gland, left adrenal gland, duodenum, and tumor
- Evaluation metrics: DSC, NSD, Running time, and Area under GPU memory-time curve