Synthetic liver SBRT · SYN-LIVER-001
50 Gy in 5 fractions·contributed by 이강훈·2026-08-04
This CT was generated by a model. No patient was scanned.
The anatomy is synthetic and the structures come from the generator rather than from a clinician. Treat the Hounsfield units as plausible rather than measured: there is no scanner behind them and so no CT-to-density calibration of yours applies, and because the image has no real counterpart the error in them cannot be quantified at all. It is a planning exercise, and every plan here is scored against the same geometry — but nothing learned from this case is a statement about a real patient.
**This CT was generated by a model. No patient was scanned, and there is no real case behind it.** Produced with NVIDIA MAISI (3D latent diffusion) via MONAI, conditioned on a segmentation from the model's own candidate set, at 512×512×512 and 1 mm isotropic — the combination MAISI's quality check passes. The Hounsfield units are the model's own and have not been replaced; bone above 700 HU was stretched back into a cortical range to undo the training clip at 1000. Treat the HU as plausible rather than measured. There is no scanner behind this image, so no CT-to-density calibration of yours applies to it, and because the volume has no real counterpart the error in its densities cannot be quantified at all. Every plan submitted here is scored against the same geometry, so the ranking compares planners — but nothing learned from this case is a statement about a real patient. Target 16.9 cc in a 1335 cc liver. Liver_GTV is supplied rather than derived by the planner, so every plan is scored on the same denominator. Prescription is 50 Gy in 5 fractions per NRG/RTOG 1112; that trial lowered the dose when the liver mean could not be met, and this challenge does not.
Anatomy
drag to orbit · click a structureBuilding the 3D view…
Leaderboard
Best selected plan per person · unlimited attempts
No scored plans yet.
Nobody has taken this case on yet. The criteria below are what a plan is scored against — they are published before anyone plans, and do not change mid-challenge.
Discussion
Sign in to post →No questions on this case yet. If something about the structure set or the criteria looks wrong, say so here rather than by email — the answer is usually one other people need too.
Guideline
The rules that decide whether a plan counts, before the numbers that score it.
Cover the target while keeping the mean dose to the liver outside it low enough that the organ keeps working. Unlike every other site here, the dose bath falls on the organ the tumour is part of, so coverage and organ sparing are drawn from the same volume.
Based on Constraints follow NRG/RTOG 1112 at the 50 Gy in 5 fractions level. The trial adapted the prescription downward when the liver mean could not be met; a challenge holds the prescription fixed and scores the liver mean instead.
Where the points are
83 points published. The scoring criteria below are what this platform computes automatically.
Allowed
- Technique
- Any — VMAT, IMRT, robotic, helical, particle
- Motion management
- Assume the provided contours; state what you assumed
- Beam arrangement
- Planner's choice, coplanar or not
Not allowed
- Editing the provided contours
- Including Liver_GTV
- Re-deriving Liver_GTV
- It is supplied, so every plan is scored on the same denominator
What disqualifies a plan
A fail removes the plan from the ranking whatever it scored. Some of these are checked from the dose automatically; an edited contour or an undeliverable plan is not, and is enforced by review.
- failPTV V50Gy below 90%
- failLiver−GTV mean above 15 Gy
- failSpinal cord D0.05cc above 28 Gy
- failContours edited from those provided
What to submit
- requiredRTDOSE for the whole course
- optionalRTPLAN
Worth knowing before you start
- Liver−GTV is supplied rather than derived by the planner. Scoring the whole liver would count the tumour's own dose as damage and reward a plan for missing.
- The luminal GI constraints are near-maximum doses to 0.05 cm³, not volumes. On a lesion near the stomach or duodenum they, not the liver, are what limits the plan.
- RTOG 1112 lowered the prescription when the liver mean could not be met. That option is not available here, which makes some geometries genuinely hard rather than merely fiddly — say so in a write-up rather than forcing coverage.
Scoring criteria
88 pointsTarget
| Metric | Minimum | Ideal | Points |
|---|---|---|---|
| PTV V100% | ≥ 95 | ≥ 98 | 12 |
| PTV D95 | ≥ 95 | ≥ 100 | 8 |
| PTV Dmax | ≤ 140 | ≤ 125 | 4 |
Organs at risk
| Metric | Minimum | Ideal | Points |
|---|---|---|---|
| Liver−GTV meanon Liver_GTV | ≤ 13 | ≤ 10 | 16 |
| Stomach D0.05cc | ≤ 30 | ≤ 24 | 9 |
| Duodenum D0.05cc | ≤ 30 | ≤ 24 | 9 |
| Small bowel D0.05ccon SmallBowel | ≤ 30 | ≤ 24 | 7 |
| Spinal cord D0.05ccon SpinalCord | ≤ 25 | ≤ 18 | 8 |
| Kidneys mean | ≤ 10 | ≤ 6 | 5 |
Plan quality
| Metric | Minimum | Ideal | Points |
|---|---|---|---|
| CIon PTV | ≤ 1.4 | ≤ 1.05 | 5 |
| GIon PTV | ≤ 6 | ≤ 3.5 | 5 |
Hard constraints
Breaching any of these removes the plan from the ranking, whatever it scored.
- PTV V50Gy < 90%
- Liver−GTV mean > 15 Gy
- Spinal cord D0.05cc > 28 Gy