mlsanityData to 14 Oct 2026

BaT-SAM: Introducing Inductive Bias into SAM via a Mixture of Convolutional Experts for Brain Tumor Segmentation

arXiv 2610.15330 ↗First posted 11 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis and treatment planning; however, manual delineation is labor-intensive and time-consuming. Existing approaches are either task-specific with limited generalization or rely on user-provided prompts during inference. We present BaT-SAM, a parameter-efficient adaptation framework that enables fully automatic brain tumor segmentation with the Segment Anything Model (SAM). BaT-SAM injects local inductive bias into SAM's frozen Vision Transformer (ViT) encoder via Conv-LoRA, where image features are processed by a sparsely gated mixture of multi-scale convolutional experts. This design compensates for the limited translation-equivariant inductive bias of vanilla ViTs while fine-tuning fewer than 5M parameters (less than 1% of the full model). To remove the need for user prompts, we further introduce a lightweight self-prompting box regressor that is jointly optimized with the adapter using scheduled sampling and predicts tumor locations directly from image embeddings. On the BRISC2025 benchmark, BaT-SAM achieves a weighted mean IoU of 0.832 while outperforming state-of-the-art benchmarks. It further demonstrates strong cross-dataset generalization, achieving Dice scores of 0.702 on Figshare and 0.784 on the LGG MRI Segmentation dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 11 Oct 2026.

Builds on

20 of 32 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Segment Anythingcited by 8,234
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  6. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  7. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
  8. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 214
  9. 2018Pyramid Attention Network for Semantic Segmentationcited by 149
  10. 2023SAM-Med2Dcited by 124
  11. 2019Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithmcited by 77
  12. 2024Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Modelcited by 69
8 more
  1. 2021Boundary-Aware Segmentation Network for Mobile and Web Applicationscited by 42
  2. 2021Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentationcited by 34
  3. 2025BRISC: Annotated Dataset for Brain Tumor Segmentation and Classificationcited by 15
  4. 2024Segmenting Medical Images: From UNet to Res-UNet and nnUNetcited by 7
  5. 2022Towards Complex Backgrounds: A Unified Difference-Aware Decoder for Binary Segmentationcited by 6
  6. 2024Efficient and Accurate Pneumonia Detection Using a Novel Multi-Scale Transformer Approachcited by 6
  7. 2024Adapting Segment Anything Model (SAM) to Experimental Datasets via Fine-Tuning on GAN-based Simulation: A Case Study in Additive Manufacturingcited by 5
  8. 2026XCT-SAM: Sequential Parameter-Efficient Domain Adaptation of SAM for Industrial XCT Defect Segmentationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging
  2. 2024An Ensemble Approach for Brain Tumor Segmentation and Synthesis
  3. 2025VGDM: Vision-Guided Diffusion Model for Brain Tumor Detection and Segmentation
  4. 2026an interpretable vision transformer framework for automated brain tumor classification
  5. 2026Mtextsuperscript4Fuse: Lightweight State-Space MoE with a Cross-Scale Gating Bridge for Brain Tumor Segmentation
  6. 2026Parameter-Efficient Fine-Tuning of Foundation Models for Liver Tumor Segmentation in CT
  7. 2025CLISC: Bridging clip and sam by enhanced cam for unsupervised brain tumor segmentation
  8. 2025NNDM: NN_UNet Diffusion Model for Brain Tumor Segmentation