SGMCE: Segment-Grounded Morphological Concept Explanation for Malaria Parasite Species Identification in Thick Blood Smears
SGMCE:厚血涂片疟原虫物种识别的基于片段的形态学概念解释
机构 * Carnegie Mellon University(卡内基梅隆大学) ; University of Washington(华盛顿大学)
专题命中 视觉定位与Grounding :vision-language model(abstract);分类 cs.CV、cs.LG
AI总结 研究旨在解决厚血涂片疟原虫物种识别中深度学习缺乏形态学证据的问题,提出SGMCE框架,无需额外训练等,通过提取特征、查询GPT-4o生成自然语言解释,经多指标验证,在多种检测中取得较好结果。
Comments Accepted for publication in the 30th Conference on Medical Image Understanding and Analysis (MIUA 2026), Dublin. To appear in Springer Lecture Notes in Computer Science (LNCS)