MORPHA：形态约束训练与低资源疟疾显微镜检查中跨采集迁移的极限
MORPHA: Morphology-Constrained Training and the Limits of Cross-Acquisition Transfer in Low-Resource Malaria Microscopy
- University of Nigeria, Nsukka（尼日利亚大学恩苏卡分校）
- National Hospital Abuja（阿布贾国立医院）
- State University of Medical and Applied Sciences, Igbo-Eno（伊博埃诺州立医学与应用科学大学）
- Veritas University, Abuja（真理大学阿布贾校区）
- Nnamdi Azikiwe University Teaching Hospital, Nnewi（纳姆迪·阿齐基韦大学教学医院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MORPHA利用形态一致性约束改善低资源疟疾显微镜跨采集迁移，减少二分类泛化下降30.8%并降低校准误差49%，同时揭示形态约束的适用边界。
AI中文摘要：
在低资源疟疾显微镜检查中，在一个涂片制备上训练的模型通常会遇到来自另一个涂片的图像，而基于形态的约束如何跨过这一采集差距进行迁移尚不清楚。我们在乌干达的真实非洲现场显微镜数据（Lacuna）上对此进行研究，探讨将测量的寄生虫形态编码为训练约束在哪些方面改善跨采集迁移，以及通用正则化在哪些方面已足够。我们提出MORPHA，一种形态一致性约束，它从带有分期标注的BBBC041数据集中推导出分期条件统计量，并对偏离这些统计量的预测进行惩罚。该约束在二分类、对象级和分期感知模式下统一定义，无需改变架构或推理，在二分类模式下塑造训练过程。检测模式是一个映射边界。在从薄涂片细胞向厚涂片现场图像迁移时，该约束将二分类泛化下降减少了30.8%（F1从0.578提升至0.699），域内代价可忽略不计，并将分布内校准误差降低了49%（ECE从0.0162降至0.0082）。一个无内容对照将相同约束应用于随机统计量，恢复的下降较少（25.3%对30.8%），表明测量的内容而非约束本身对增益有所贡献。两种标准置信度正则化器在原始迁移上超过该约束，定位了形态学增加价值的领域以及通用正则化足够的领域。我们绘制了两个部署相关的边界：薄涂片统计量不能迁移到厚涂片检测（滋养体AP@0.50降至0.000），且跨采集伪标签在过滤应用之前即失败。这些共同产生了一个基于形态的一致性信号，并为低资源环境下的疟疾数据集和模型设计提供了基于证据的指导。
英文摘要：
In low-resource malaria microscopy, a model trained on one smear preparation routinely meets images from another, and how well morphology-based constraints transfer across this acquisition gap is unclear. We study this on real African field microscopy from Uganda (Lacuna), asking where encoding measured parasite morphology as a training constraint improves cross-acquisition transfer and where generic regularisation suffices. We present MORPHA, a morphological consistency constraint that derives stage-conditional statistics from the stage-annotated BBBC041 dataset and penalises predictions that deviate from them. Defined uniformly across binary, object-level, and stage-aware regimes without changing architecture or inference, it shapes training in the binary regime. The detection regime is a mapped boundary. On transfer from thin-smear cells to thick-smear field images, the constraint reduces the binary-classification generalisation drop by 30.8% (F1 0.578 to 0.699) at negligible within-domain cost and lowers in-distribution calibration error by 49% (ECE 0.0162 to 0.0082). A content-free control applying the identical constraint to random statistics recovers less of the drop (25.3% vs 30.8%), indicating the measured content, not constraining alone, contributes to the gain. Two standard confidence regularisers exceed the constraint on raw transfer, locating where morphology adds value and where generic regularisation suffices. We map two deployment-relevant boundaries: thin-smear statistics do not transfer to thick-smear detection (trophozoite AP@0.50 falls to 0.000), and cross-acquisition pseudo-labelling fails before filtering applies. Together these yield a morphology-grounded consistency signal and evidence-based guidance for malaria dataset and model design in low-resource settings.
