利用深度学习检测重症疟疾贫血患儿血涂片中红细胞形态学改变
研究提出弱监督多实例学习框架深度学习模型MILISMA,通过识别形态改变的红细胞从外周血涂片分类重症疟疾贫血(SMA),分类准确率83%(ROC-AUC 87%,PR-AUC 76%),并发现SMA相关红细胞描述符的形态学差异有统计学意义(p<0.01)。
要点
- MILISMA模型分类SMA准确率83%,ROC-AUC 87%,PR-AUC 76%。
- 模型可识别SMA相关红细胞描述符的形态学差异(p<0.01)。
- 视觉分析显示SMA相关红细胞具有独特形态学特征。
核心结论
- MILISMA深度学习模型可通过识别形态改变的红细胞对外周血涂片进行分类,辅助检测和表征红细胞改变,可能增进对SMA病理的理解并在规模上改进SMA诊断和预后评估。
研究设计与样本
- 研究提出弱监督多实例学习框架深度学习模型MILISMA,用于从外周血涂片识别形态改变的红细胞以检测SMA。
主要发现
- MILISMA分类准确率为83%,受试者工作特征曲线下面积(AUC)为87%,精确率-召回率AUC为76%。
- MILISMA识别出红细胞描述符中具有统计学意义的形态学差异(p<0.01)。
- 视觉分析强调了SMA相关红细胞与非SMA细胞相比的独特形态学特征。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
In sub-Saharan Africa, acute-onset severe malaria anaemia (SMA) is a critical challenge, particularly affecting children under five. The acute drop in haematocrit in SMA is thought to be driven by an increased phagocytotic pathological process in the spleen, leading to the presence of distinct red blood cells (RBCs) with altered morphological characteristics. We hypothesized that these RBCs could be detected systematically and at scale in peripheral blood films (PBFs) by harnessing the capabilities of deep learning models. Assessment of PBFs by a microscopist does not scale for this task and is subject to variability. Here we introduce a deep learning model, leveraging a weakly supervised Multiple Instance Learning framework, to Identify SMA (MILISMA) through the presence of morphologically changed RBCs. MILISMA achieved a classification accuracy of 83% (receiver operating characteristic area under the curve [AUC] of 87%; precision-recall AUC of 76%). More importantly, MILISMA's capabilities extend to identifying statistically significant morphological distinctions (p < 0.01) in RBCs descriptors. Our findings are enriched by visual analyses, which underscore the unique morphological features of SMA-affected RBCs when compared to non-SMA cells. This model aided detection and characterization of RBC alterations could enhance the understanding of SMA's pathology and refine SMA diagnostic and prognostic evaluation processes at scale.
引用
- Moysis E, Brown BJ, Shokunbi W, et al. Leveraging deep learning for detecting red blood cell morphological changes in blood films from children with severe malaria anaemia. Br J Haematol. 2024. PMID: 38894606. doi:10.1111/bjh.19599
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。