基于不确定性校准的玻片级聚合的设备端多物种疟疾检测
On-Device Multi-Species Malaria Detection with Uncertainty-Calibrated Slide-Level Aggregation
浏览论文内容
中文总结 AI 辅助
针对资源有限地区疟疾检测的临床约束，开发基于YOLOv13n的设备端多物种疟疾检测系统，满足多物种鉴别等要求，在2739张图像上实现较高检测精度与聚合性能。
中文摘要 AI 辅助
疟疾仍是资源有限地区的主要致死原因，而这些地区缺乏专业显微镜医师，因此基于显微镜图像的自动诊断具备改善医疗服务的巨大潜力。但算法部署需满足一系列从机器学习（ML）角度看并非显而易见的临床约束条件。为此，我们与一家国家卫生中心密切协作，开发了一套疟疾诊断流水线，该流水线满足了卫生中心列出的、却常被疟疾机器学习文献忽略的关键要求，具体包括：（i）停止准则（减少图像采集量和结果生成时间）；（ii）人在回路功能（用于复核与问责）；（iii）多物种鉴别（因治疗方案随物种而异）；（iv）厚涂片检测（显微镜检查的标准操作）；（v）计算高效的不确定性计算（辅助临床医师复核）；（vi）边缘设备平台（因该服务区域网络不稳定）。该移动系统通过TensorFlow Lite部署YOLOv13n，在设备端完成所有推理，可从吉姆萨染色的厚血涂片图像中检测四种疟原虫物种及白细胞，将单图像检测结果聚合为符合世界卫生组织（WHO）标准的玻片级寄生虫密度。本文重点阐述这些临床约束，并提供应对方法。在涵盖全部四个物种的2739张标注图像上评估，该系统的mAP@0.5达0.863，单图像寄生虫计数相关系数r=0.812，玻片级相关系数r=0.951（软计数，每玻片10张图像），且完全离线运行，单图像流水线耗时为10.27±1.65秒。
英文摘要
Malaria remains a leading cause of mortality in resource-limited settings, where expert microscopists are scarce. Automated diagnosis based on microscopy images thus has strong potential to improve care delivery. But for an algorithm to deploy, a necessary requirement is that it meet a suite of non-obvious (from a machine learning (ML) perspective) clinical constraints. Therefore, in close consultation with a national health center we developed a malaria diagnosis pipeline which addresses key requirements listed by the health care center but typically ignored in the ML malaria literature. In particular, it includes: (i) stopping criteria (to reduce image acquisition and time-to-result); (ii) human-in-the-loop functionality (for review and accountability); (iii) multi-species discrimination (since treatment varies by species); (iv) thick film detection (standard for microscopy); (v) computationally-efficient uncertainty calculations (to aid clinician review); and (vi) an edge device platform (since internet can be spotty in this catchment area). The mobile system performs all inference on-device using YOLOv13n deployed via TensorFlow Lite. It detects four species and white blood cells from Giemsa-stained thick blood smear images, aggregating per-image detections into slide-level parasitemia with World Health Organization (WHO)-standard quantification. This paper highlights these various clinical constraints and offers methods to address them. Evaluated on 2,739 annotated images across all four species, the system achieves mAP@0.5 of 0.863, per-image parasite count correlation of r = 0.812, slide-level r = 0.951 (soft counting, 10 images/slide), and runs entirely offline with a pipeline time of 10.27 +- 1.65 s per image.
发表机构
- Carnegie Mellon University Africa（卡内基梅隆大学非洲分校）
- University of Washington（华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。
