PulseAugur
中
实时 06:41:40

SAM model shows stable spleen segmentation in CT scans despite domain shifts

作者 PulseAugur 编辑部 · [2 个来源] ·

Researchers evaluated the robustness of the Segment Anything Model (SAM) for spleen segmentation in abdominal CT scans, simulating various domain shifts like noise and resolution changes. The study found that SAM maintained stable performance with minimal degradation in segmentation accuracy across these simulated conditions. These findings suggest SAM's potential as a reliable foundation model for medical imaging applications, including health digital twins, where consistent anatomical modeling is crucial. AI

影响 Suggests SAM's viability for medical imaging, potentially accelerating health digital twin development.

排序理由 Academic paper evaluating an existing model's performance under specific conditions.

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

SAM model shows stable spleen segmentation in CT scans despite domain shifts

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Sanghati Basu ·

    Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deployment

    arXiv:2604.25685v1 Announce Type: cross Abstract: Foundation segmentation models such as the Segment Anything Model (SAM) have demonstrated strong generalization across natural images; however, their robustness under clinically realistic medical imaging domain shifts remains insu…

  2. arXiv cs.CV TIER_1 English(EN) · Sanghati Basu ·

    Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deployment

    Foundation segmentation models such as the Segment Anything Model (SAM) have demonstrated strong generalization across natural images; however, their robustness under clinically realistic medical imaging domain shifts remains insufficiently quantified. We present a systematic sli…

相关实体

相关话题