Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.06821 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908415332188160 |
|---|---|
| author | Wahd, Assefa Seyoum Felfeliyan, Banafshe Zhou, Yuyue Ghosh, Shrimanti McArthur, Adam Zhang, Jiechen Jaremko, Jacob L. Hareendranathan, Abhilash |
| author_facet | Wahd, Assefa Seyoum Felfeliyan, Banafshe Zhou, Yuyue Ghosh, Shrimanti McArthur, Adam Zhang, Jiechen Jaremko, Jacob L. Hareendranathan, Abhilash |
| contents | Foundation models like the segment anything model require high-quality manual prompts for medical image segmentation, which is time-consuming and requires expertise. SAM and its variants often fail to segment structures in ultrasound (US) images due to domain shift.
We propose Sam2Rad, a prompt learning approach to adapt SAM and its variants for US bone segmentation without human prompts. It introduces a prompt predictor network (PPN) with a cross-attention module to predict prompt embeddings from image encoder features. PPN outputs bounding box and mask prompts, and 256-dimensional embeddings for regions of interest. The framework allows optional manual prompting and can be trained end-to-end using parameter-efficient fine-tuning (PEFT).
Sam2Rad was tested on 3 musculoskeletal US datasets: wrist (3822 images), rotator cuff (1605 images), and hip (4849 images). It improved performance across all datasets without manual prompts, increasing Dice scores by 2-7% for hip/wrist and up to 33% for shoulder data. Sam2Rad can be trained with as few as 10 labeled images and is compatible with any SAM architecture for automatic segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06821 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts Wahd, Assefa Seyoum Felfeliyan, Banafshe Zhou, Yuyue Ghosh, Shrimanti McArthur, Adam Zhang, Jiechen Jaremko, Jacob L. Hareendranathan, Abhilash Computer Vision and Pattern Recognition Foundation models like the segment anything model require high-quality manual prompts for medical image segmentation, which is time-consuming and requires expertise. SAM and its variants often fail to segment structures in ultrasound (US) images due to domain shift. We propose Sam2Rad, a prompt learning approach to adapt SAM and its variants for US bone segmentation without human prompts. It introduces a prompt predictor network (PPN) with a cross-attention module to predict prompt embeddings from image encoder features. PPN outputs bounding box and mask prompts, and 256-dimensional embeddings for regions of interest. The framework allows optional manual prompting and can be trained end-to-end using parameter-efficient fine-tuning (PEFT). Sam2Rad was tested on 3 musculoskeletal US datasets: wrist (3822 images), rotator cuff (1605 images), and hip (4849 images). It improved performance across all datasets without manual prompts, increasing Dice scores by 2-7% for hip/wrist and up to 33% for shoulder data. Sam2Rad can be trained with as few as 10 labeled images and is compatible with any SAM architecture for automatic segmentation. |
| title | Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.06821 |