fidoptSynthRAD2023, MR to CT, brain
Brain MR of one patient and the CT to synthesise from it, the CT brought onto the MR's grid by the challenge (SynthRAD2023, Task 1).
Read before comparing (6)
- Case. The challenge's pair as delivered, copied byte for byte from Task1.zip: the MR, the CT the organisers registered onto its grid, and their body mask. The synthetic image is scored inside that mask, as the challenge scores it.
- Registration. What the organisers' registration left misaligned counts as error for every method: it bounds how far even a perfect synthesis can match the CT.
- Baseline. Inside the mask with KonfAI's criteria at CT's range of 4095, a constant at the target's median scores an MAE of 420 HU (298 to 468), a PSNR of 16.5 dB (16.0 to 18.4) and an SSIM of 0.29 (0.05 to 0.41) on the 14 test cases; 415 HU, 16.4 dB and 0.30 on the 12 development cases.
- Held out. SynthRAD_BrainMRCT's patients are left out because their CT, the target here, is that registration set's public fixed image. SynthRAD2023's centre B brain patients carry one number in both tasks: 1BBnnn and 2BBnnn are the same patient with the same CT, correlating at 0.99 after a rigid registration on the eight such pairs the two registration sets hold.
- Overlap. No other descriptor names SynthRAD2023 or its record. The provider says its two tasks 'do not necessarily contain the same patients', so every drawn CT was registered rigidly to every CT of SynthRAD_BrainCBCTCT and SynthRAD_BrainCBCTCT_Syn: at most 0.86 inside the bodies (brain_1BB085 against brain_2BB200, two skulls of different shapes), where one CT on two grids reads 0.98 or more.
- Licence. CC BY-NC 4.0: non-commercial use only.
No method has a result on every case of this dataset yet.
Under a licence that is not open
Methods whose code or weights are released for non-commercial use, or under share-alike or custom terms: shown for reference, ranked nowhere.
| Accuracy | Cost | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| # | Method | MAE | PSNR dB | SSIM | Anatomy Dice | Anatomy HD95 mm | Time s | RAM GB | GPU GB | Machine | Images |
| nnsyn · MR to CT, head and neckGPUapptrained on CC-BY-NC-4.0 dataolder run | 131.8 ±9.2 | 24.18 ±0.55 | 0.716 ±0.019 | 0.562 ±0.085 | 8.96 ±3.78 | 3.8 | 2.5 | Laptop | |||
MAE: mean absolute error of a synthetic image against its target, inside the body, in the image's units. PSNR: the same by signal-to-noise ratio, higher is better. SSIM: the same by structural similarity, 1 is perfect. Anatomy Dice and HD95: TotalSegmentator run on the synthetic and on the target image, the structures compared; shown, not ranked.
Case by case
| MAE | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 |
|---|
Click a score to look at that result: the target image, and over it the method's synthetic image. Underlined scores have their image; for the others you see the case without the result.
About the data
- Test cases
- 14 test patients drawn with seed 2026 by centre (1BA, 1BB, 1BC) in proportion, then 12 development patients, the last of the same seeded order from the centre with the most left. The pool is the 143 of Task 1's 180 brain training patients left once draw.held_out is out: SynthRAD_BrainMRCT's 18 test and 16 development patients, and 1BB059, 1BB095 and 1BB198, whose Task 2 twins are cases of SynthRAD_BrainCBCTCT.
- Truth
- target image as released the patient's CT as the challenge delivers it, registered to the MR by the organisers, in Hounsfield units
- Licence
- CC BY-NC 4.0
12 cases for tuning, never tested
brain_1BC041, brain_1BA116, brain_1BC027, brain_1BA184, brain_1BB083, brain_1BC019, brain_1BA294, brain_1BB082, brain_1BC022, brain_1BA288, brain_1BB034, brain_1BC076