SlimFormer++
Lightweight (5.98M-parameter) 3D segmentation network packaged as an nnU-Net v2 trainer, with pretrained weights for ACDC (cardiac MRI), AbdomenCT-1K and AMOS2022 CT and a 3D Slicer extension for 15 abdominal organs in CT
- What it is
- Segmentation (Segmentation & frameworks)
- Modality
- Radiology: 3D CT, MRI, ultrasound
- Maintainer
- Hong, Zhang, Liu, Mo, Ye (University of Exeter)
- License
- SlimFormer++ Noncommercial Research License 1.0
- Commercial use
- Non-commercial
- Access
- Free, public source repository (see links below)
- Last update
- 2026-10-24 (last repository push, UTC; Maintained)
- Last checked
- 2026-11-16
- Limitations
- Listed for research and development reference. Hounsfield Lab has not tested its clinical performance; check the project’s own documentation for intended use and regulatory status.
Links
- github.com/WHHHHHY822/SlimFormerPlusPlus
- github.com/WHHHHHY822/SlicerSlimFormerPlusPlus
- huggingface.co/Yang0822/SlimFormerPlusPlus-AMOS2022-CT
License review: Repo LICENSE permits noncommercial scientific research only; commercial use, including products and paid consulting, needs separate written permission. Third-party parts stay Apache-2.0. The Slicer extension code (WHHHHHY822/SlicerSlimFormerPlusPlus) is Apache-2.0 but its model weights follow the noncommercial license. Requires Linux, an NVIDIA GPU and CUDA 12.6 to build. Paper: arXiv 2610.25488.
Commercial use: read the project’s license (and any model-weight terms) yourself before relying on it. This isn’t legal advice.
Related tools in Segmentation & frameworks
- MONAI: PyTorch-based AI toolkit for healthcare imaging
- MONAI Label: AI-assisted image labeling and active learning; integrates with 3D Slicer and OHIF
- nnU-Net: Self-configuring segmentation framework
- TotalSegmentator: Segments more than 100 anatomical structures in CT and MR
- TotalSpineSeg: Two-stage nnU-Net tool that segments and individually labels every vertebra and intervertebral disc plus the spinal cord and canal, using an odd/even vertebra scheme and landmark discs (C2-C3, C7-T1, T12-L1, L5-S) to avoid fused or split vertebrae; works on localizers and short-FOV scans; peer-reviewed in European Radiology (Nov 7, 2026)
- CXAS: Chest X-ray anatomy segmentation (Mask2Former models: 187 frontal and 177 lateral classes) plus 132 named landmarks and landmark-based measurements such as cardiothoracic ratio, costophrenic angle, Cobb angle and the Haller index, in mm for DICOM input; cxas_idc writes one multi-segment DICOM SEG and a TID 1500 SR per radiograph; trained on PAXRay++ CT-projected radiographs