fidoptAbdomen CT (Learn2Reg 2021, AbdomenMRCT)
Abdominal CT of one patient with the liver, the spleen and the kidneys labelled (the Learn2Reg 2021 abdomen MR/CT task).
Read before comparing (1)
- Cases. The moving images of L2R_AbdomenMRCT's pairs, the CT images as delivered on the MR's grid: a test pair's image is a test case, a development pair's a development case. The task's validation holds three pairs, so three test images.
| Accuracy | Cost | |||||||
|---|---|---|---|---|---|---|---|---|
| # | Method | Dice | Surface Dice | HD95 mm | Time s | RAM GB | GPU GB | Images |
| 11–4 | KonfAI segmentation app · TotalSegmentator (total), the authors' packageGPUapp | 0.902 ±0.054 | 0.525 ±0.112 | 6.35 ±1.55 | 17.2 | 3.7 | ||
| 21–4 | KonfAI segmentation app · TotalSegmentator (total), KonfAI appGPUapp | 0.900 ±0.057 | 0.521 ±0.125 | 6.45 ±1.44 | 7 | 2.6 | 5.2 | |
| 21–4 | MONAI wholeBody CTGPUapp | 0.902 ±0.052 | 0.518 ±0.118 | 6.46 ±2.10 | 29 | 3.6 | 7.5 | |
| 41–4 | KonfAI segmentation app · MRSegmentator, KonfAI appGPUapp | 0.002 ±0.007 | 0.000 ±0.001 | 160.67 ±24.74 | 2.6 | 4.9 | ||
The order averages each method's ranks on Dice, Surface Dice, HD95 mm, so the first one is not always the best in every column. ± is the 95% interval of the mean over the 3 cases. Two neighbours are tied when a paired Wilcoxon test on the shared cases does not find the upper one better on Dice (5%): the places a method could hold are then shown under its own. The best value of each column is in colour. Click a row to see its images, a column title to sort by it. Time and memory measured on Workstation.
1 result not ranked: an older run, cases still missing, or a failure on every case
| Accuracy | Cost | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| # | Method | Dice | Surface Dice | HD95 mm | Time s | RAM GB | GPU GB | Machine | Images |
| MONAI wholeBody CTGPUappolder run | 0.902 ±0.052 | 0.518 ±0.118 | 6.46 ±2.10 | 10 | 2.4 | 7.3 | Laptop | ||
Dice: how much the organ contours overlap, 1 is perfect. Surface Dice: the share of the contours' surfaces within a tolerance of each other, 1 is perfect. HD95: distance between the contours' surfaces.
Case by case
Click a score to look at that result: the image, the truth in green and the method's map in red. Underlined scores have their image; for the others you see the case without the result.
About the data
- Truth
- contours by experts the challenge's validation labels
- Licence
- CC BY 3.0 (TCIA TCGA CT) and CC BY-NC-SA 4.0 (CHAOS MR)
5 cases for tuning, never tested
case_0001/moving, case_0002/moving, case_0003/moving, case_0005/moving, case_0004/moving