Scholarlink

<p>The emergence of portable imaging devices improves medical image acquisition efficiency in resource-limited regions, but a shortage of medical personnel still limits timely diagnosis. We propose Embed-MedSAM, a fully automatic segmentation model with low deployment cost. Built on MedSAM, it integrates a lightweight RepViT encoder to reduce computation and applies two-stage distillation on over one million multimodal medical images to preserve the original model’s visual representation. A self-prompting mechanism is also introduced, where the model generates pseudo labels to guide fine-grained segmentation. The training jointly optimizes KL divergence and segmentation losses to improve accuracy under prompt-free conditions. Embed-MedSAM shows excellent performance on 17 benchmark datasets covering 7 imaging modalities. Without external prompts, it improves average Dice score by nearly 16% over the second-best model. It also runs at nearly 30 FPS on iPhone 14, showing strong potential for real-world deployment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Embedded framework for clinical medical image segment anything in resource limited healthcare regions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月24日

查看全文
  • Ying Zhang,
  • Fangdie Ye,
  • Xiaofeng Yu,
  • Xin Lian,
  • Tianlong Jiang,
  • Liyu Yang,
  • Lei Yang

摘要

The emergence of portable imaging devices improves medical image acquisition efficiency in resource-limited regions, but a shortage of medical personnel still limits timely diagnosis. We propose Embed-MedSAM, a fully automatic segmentation model with low deployment cost. Built on MedSAM, it integrates a lightweight RepViT encoder to reduce computation and applies two-stage distillation on over one million multimodal medical images to preserve the original model’s visual representation. A self-prompting mechanism is also introduced, where the model generates pseudo labels to guide fine-grained segmentation. The training jointly optimizes KL divergence and segmentation losses to improve accuracy under prompt-free conditions. Embed-MedSAM shows excellent performance on 17 benchmark datasets covering 7 imaging modalities. Without external prompts, it improves average Dice score by nearly 16% over the second-best model. It also runs at nearly 30 FPS on iPhone 14, showing strong potential for real-world deployment.