VISTA3D — CT auto-segmentation (class prompt)

MONAI VISTA3D, Phase 1 auto branch (no point prompts yet). Whole-body CT segmentation with a CLASS prompt — user picks a class name; the model returns a binary mask for that organ/structure. 196 M params, SegResNet encoder + dual decoder + class-embedding matmul head.  ·  custom_ops WebGPU runtime: WGSL conv3d / convT3d(opad) / IN3d / gemm.
✓ Node M1 verification (2026-04-18): per-patch rel_rms 1.5e-6 vs PyTorch, 213×213×163 sliding window rel_rms 4.4e-7, binary agree 100.0000% vs MONAI SlidingWindowInferer. Matches MPS baseline throughput (~5 s/patch on M1).
⚠ Demo scope: ships a pre-canonicalized CT volume (already ScaleIntensityRanged + Spacingd 1.5 mm, shape 213×213×163). Upload-your-own NIfTI flow and the 117-class EVERYTHING_PROMPT one-shot mode are future work.  ·  Download: ~786 MB of weights + 28 MB canonical volume.

Log

Axial slice viewer

CT canonical input
Predicted mask (sigmoid > 0.5)
Overlay