# Optimization of MedSAM model based on bounding box adaptive perturbation algorithm

arXiv: https://arxiv.org/abs/2503.19700 · HTML: https://mlsanity.com/paper/2503.19700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 13 of 13)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [One-Prompt to Segment All Medical Images](https://mlsanity.com/paper/2305.10300/) (2023)
- [Promise:Prompt-driven 3D Medical Image Segmentation Using Pretrained Image Foundation Models](https://mlsanity.com/paper/2310.19721/) (2023)
- [MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM](https://mlsanity.com/paper/2409.00924/) (2024)
- [ProtoSAM: One-Shot Medical Image Segmentation With Foundational Models](https://mlsanity.com/paper/2407.07042/) (2024)
- [De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation](https://mlsanity.com/paper/2407.14153/) (2024)
- [Part-aware Prompted Segment Anything Model for Adaptive Segmentation](https://mlsanity.com/paper/2403.05433/) (2024)
- [Automating MedSAM by Learning Prompts with Weak Few-Shot Supervision](https://mlsanity.com/paper/2409.20293/) (2024)
- [CoSAM: Self-Correcting SAM for Domain Generalization in 2D Medical Image Segmentation](https://mlsanity.com/paper/2411.10136/) (2024)
- [Gaze-Assisted Medical Image Segmentation](https://mlsanity.com/paper/2410.17920/) (2024)
- [Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation](https://mlsanity.com/paper/2404.17033/) (2024)
- [Zero-shot capability of SAM-family models for bone segmentation in CT scans](https://mlsanity.com/paper/2411.08629/) (2024)
- [Point-supervised Brain Tumor Segmentation with Box-prompted MedSAM](https://mlsanity.com/paper/2408.00706/) (2024)

## Abstract (arXiv)

The MedSAM model, built upon the SAM framework, enhances medical image segmentation through generalizable training but still exhibits notable limitations. First, constraints in the perturbation window settings during training can cause MedSAM to incorrectly segment small tissues or organs together with adjacent structures, leading to segmentation errors. Second, when dealing with medical image targets characterized by irregular shapes and complex structures, segmentation often relies on narrowing the bounding box to refine segmentation intent. However, MedSAM's performance under reduced bounding box prompts remains suboptimal. To address these challenges, this study proposes a bounding box adaptive perturbation algorithm to optimize the training process. The proposed approach aims to reduce segmentation errors for small targets and enhance the model's accuracy when processing reduced bounding box prompts, ultimately improving the robustness and reliability of the MedSAM model for complex medical imaging tasks.