fidoptPOPI
4D chest CT, two respiratory phases of one patient (POPI model).
Read before comparing (2)
- Truth. The board ranks on the manual landmarks. The labels come from a segmentation network and are shown, not ranked: a method that registers on that network's features is scored against its own view of the anatomy.
- Masks. Each image's lung lobes from TotalSegmentator.
No method has a result on every pair of this dataset yet.
| Accuracy | Smoothness | Cost | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| # | Method | TRE mm | Change | Dice * | HD95 mm * | rTRE | SDlogJ | Folds % | Time s | RAM GB | GPU GB | Images |
| No registration | 9.49 ±9.80 | 0.794 ±0.102 | 5.80 ±6.16 | 0.0122 ±0.0128 | 0.000 | 0.00 | ||||||
* shown, not ranked: on this dataset it is checked against the output of a program.
Dice: how much the organ contours overlap, 1 is perfect. HD95: distance between the contours' surfaces. TRE: distance between matching landmarks. rTRE: the TRE over the length of the image's diagonal, to compare datasets of other sizes and units. SDlogJ: how irregular the deformation is, 0 is perfectly smooth. Folds: share of the image where the deformation folds over itself.
Pair by pair
Click a score to look at that result: the fixed image, and over it the moving image after registration, with the annotations. Underlined scores have their image; for the others you see the pair without the result. A green cell gained against no registration on that pair, a red one lost.
About the data
- Test pairs
- Six patients in all, one pair each: three test pairs and three development pairs.
- Truth
- contours by a program landmarks by experts TotalSegmentator (task total) run by us on each image the dataset's manual landmarks
- Licence
- none stated ('for use in your research')
3 pairs for tuning, never tested
bh, bl, dx