SurgFormer: Scalable Learning of Organ Deformation with Resection Support and Real-Time Inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910043922759680 |
|---|---|
| author | Shahbazi, Ashkan Akbari, Elaheh Pereira, Kyvia Heiselman, Jon S. Benson, Annie C. Johnston, Garrison L. H. Wu, Jie Ying Simaan, Nabil Miga, Michael I. Kolouri, Soheil |
| author_facet | Shahbazi, Ashkan Akbari, Elaheh Pereira, Kyvia Heiselman, Jon S. Benson, Annie C. Johnston, Garrison L. H. Wu, Jie Ying Simaan, Nabil Miga, Michael I. Kolouri, Soheil |
| contents | We introduce SurgFormer, a multiresolution gated transformer for data driven soft tissue simulation on volumetric meshes. High fidelity biomechanical solvers are often too costly for interactive use, so we train SurgFormer on solver generated data to predict nodewise displacement fields at near real time rates. SurgFormer builds a fixed mesh hierarchy and applies repeated multibranch blocks that combine local message passing, coarse global self attention, and pointwise feedforward updates, fused by learned per node, per channel gates to adaptively integrate local and long range information while remaining scalable on large meshes. For cut conditioned simulation, resection information is encoded as a learned cut embedding and provided as an additional input, enabling a unified model for both standard deformation prediction and topology altering cases. We also introduce two surgical simulation datasets generated under a unified protocol with XFEM based supervision: a cholecystectomy resection dataset and an appendectomy manipulation and resection dataset with cut and uncut cases. To our knowledge, this is the first learned volumetric surrogate setting to study XFEM supervised cut conditioned deformation within the same volumetric pipeline as standard deformation prediction. Across diverse baselines, SurgFormer achieves strong accuracy with favorable efficiency, making it a practical backbone for both tasks. {Code, data, and project page: \href{https://mint-vu.github.io/SurgFormer/}{available here}} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06543 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SurgFormer: Scalable Learning of Organ Deformation with Resection Support and Real-Time Inference Shahbazi, Ashkan Akbari, Elaheh Pereira, Kyvia Heiselman, Jon S. Benson, Annie C. Johnston, Garrison L. H. Wu, Jie Ying Simaan, Nabil Miga, Michael I. Kolouri, Soheil Computer Vision and Pattern Recognition We introduce SurgFormer, a multiresolution gated transformer for data driven soft tissue simulation on volumetric meshes. High fidelity biomechanical solvers are often too costly for interactive use, so we train SurgFormer on solver generated data to predict nodewise displacement fields at near real time rates. SurgFormer builds a fixed mesh hierarchy and applies repeated multibranch blocks that combine local message passing, coarse global self attention, and pointwise feedforward updates, fused by learned per node, per channel gates to adaptively integrate local and long range information while remaining scalable on large meshes. For cut conditioned simulation, resection information is encoded as a learned cut embedding and provided as an additional input, enabling a unified model for both standard deformation prediction and topology altering cases. We also introduce two surgical simulation datasets generated under a unified protocol with XFEM based supervision: a cholecystectomy resection dataset and an appendectomy manipulation and resection dataset with cut and uncut cases. To our knowledge, this is the first learned volumetric surrogate setting to study XFEM supervised cut conditioned deformation within the same volumetric pipeline as standard deformation prediction. Across diverse baselines, SurgFormer achieves strong accuracy with favorable efficiency, making it a practical backbone for both tasks. {Code, data, and project page: \href{https://mint-vu.github.io/SurgFormer/}{available here}} |
| title | SurgFormer: Scalable Learning of Organ Deformation with Resection Support and Real-Time Inference |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.06543 |