fidoptAbdominal-DIR-QA
10 pairs · ordered on Dice and SDlogJ| # | Method | Dice | Change | SDlogJ |
|---|---|---|---|---|
| 1 | Demons | 0.712 | +0.281 | 0.088 |
| 1 | greedy | 0.744 | +0.313 | 0.055 |
| 3 | NiftyReg | 0.775 | +0.344 | 0.479 |
| 4 | anatomix + ConvexAdam | 0.575 | +0.143 | 0.042 |
| No registration | 0.431 | 0.000 |
Abdomen CT, same patient
3 datasets, 31 test pairs. A method is ranked here when it has a result on every pair of every one of them.
Ranking OfficialResearch
| # | Method | Mean rank | Abdominal-DIR-QA | Liver-DIR-QA | HQColon |
|---|---|---|---|---|---|
| 1 | DemonsCPUapp | 1.671.3–2.0 | 1 | 2 | 1 |
4 methods not ranked here yet: a dataset or some pairs are missing
| # | Method | Mean rank | Abdominal-DIR-QA | Liver-DIR-QA | HQColon |
|---|---|---|---|---|---|
| anatomix + ConvexAdamGPUapp | 3.00 | 4 | |||
| ConvexAdam (MIND)GPUapp | 1.25 | 9/10 | 1 | 6/11 | |
| greedyCPUapp | 2.25 | 1 | |||
| NiftyRegCPUapp | 2.50 | 3 |
1 place in that table, 1 is best2/10 cases done, not ranked yetn/a does not apply not run some cases failed
Under each dataset, the method's place in that dataset's table: 1 is best, the darker the better. The mean rank averages its places over the datasets.
The scores, dataset by dataset
Each score is followed by its change against no registration: green when the method did better, red when it did worse.
Liver-DIR-QA
10 pairs · ordered on Dice and SDlogJ| # | Method | Dice | Change | SDlogJ |
|---|---|---|---|---|
| 1 | ConvexAdam (MIND) | 0.743 | +0.303 | 0.117 |
| 2 | Demons | 0.658 | +0.219 | 0.100 |
| No registration | 0.439 | 0.000 |
HQColon
11 pairs · ordered on Dice and SDlogJ| # | Method | Dice | Change | SDlogJ |
|---|---|---|---|---|
| 1 | Demons | 0.695 | +0.178 | 0.074 |
| No registration | 0.517 | 0.000 |