Computer Vision for Malaria Microscopy: Automated Detection and Classification of Plasmodium for Basic Science and Pre-Clinical Applications

用于疟疾显微镜的计算机视觉：用于基础科学和临床前应用的疟原虫自动检测和分类

• 批准号: 10576701
• 负责人: Benjamin D Haeffele
• 金额: $ 23.15万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10576701
• 关键词: Acceleration; Address; Africa South of the Sahara; African; Aftercare; Algorithms; Antimalarials; Appearance; Artificial Intelligence; Basic Science; Behavior; Biological; Biology; Biomedical Engineering; Biopsy; Blood; Breeding; Brightfield Microscopy; Cause of Death; Cells; Cessation of life; Child; Classification; Clinic; Clinical; Collaborations; Color; Communicable Diseases; Computer Vision Systems; Computing Methodologies; Consumption; Data; Data Set; Data Sources; Derivation procedure; Detection; Development; Devices; Disease; Drug Exposure; Drug resistance; E-learning; Engineering; Equipment; Erythrocytes; Film; Fingers; Funding Mechanisms; Generations; Genetic Transcription; Grant; Hemolysis; Histologic; Histopathology; Image; Image Analysis; Imaging problem; Immune system; Infection; International; Label; Laboratories; Life Cycle Stages; Liver; Longevity; Machine Learning; Malaria; Manuals; Methods; Microscopy; Modeling; Modernization; Molecular; Monitor; Network-based; Outcome; Parasites; Parasitology; Pathology; Performance; Plasmodium; Plasmodium falciparum; Population; Prediction of Response to Therapy; Predisposition; Preparation; Principal Investigator; Process; Prognosis; Public Health; Reproducibility; Research; Research Institute; Research Personnel; Resolution; Running; Science; Semantics; Sepsis; Site; Slide; Specimen; Spleen; Stains; Surface; Surveys; Techniques; Technology; Time; Tissues; Training; Treatment Efficacy; Universities; Variant; Visual; Work; algorithm training; biomedical imaging; cell injury; cellular pathology; cost; data acquisition; deep learning; deep neural network; design; detection platform; digital; experience; innovation; learning strategy; light microscopy; medical schools; microscopic imaging; miniaturize; neural network; next generation; novel; pre-clinical; preservation; protein expression; protein metabolism; prototype; statistics; success; supervised learning; tool; visual information

PROJECT SUMMARY/ABSTRACT Among the “big three” infectious diseases worldwide, malaria stands out for the complexity of the Plasmodium life-cycle and biology. Malaria parasites breed mainly within red blood cells, and across their lifespan there are dramatic shifts in protein expression and metabolism that alter their appearance, behavior, and susceptibility to clearance by the host immune system or antimalarial drugs. Because it is an infection of the blood, a biopsy can be taken with a simple finger prick, and the ability to derive histopathological information via light microscopy is a critical tool in the study of, and ultimately control and treatment of, malaria. Manual review is painstaking and imperfect. Neural network-based computer vision (CV) approaches can accelerate data acquisition from light microscopy and innovate new methods of extracting data currently only possible through costly, labor-intensive benchtop molecular methods or time-consuming review by a small number of malaria microscopy experts with the necessary training and experience to distinguish subtle differences between parasite forms. This R21 proposal builds on 12 months of preparatory work supported by a pilot grant from The Johns Hopkins University Institute for Data Intensive Engineering and Science, a collaborative pursuit of the Schools of Medicine and Engineering. The co-principal investigators developed a deep learning-based CV algorithm trained on a public dataset of >10,000 images of Plasmodium falciparum ring stage parasites that can detect and quantify parasites with >0.97 accuracy. However, significantly more information is ripe for extraction from malaria smears beyond the simple detection of parasites. We built an early prototype of a 2nd-generation CV algorithm capable of identifying the correct parasite stage to the level of early, middle or late ring stage with >0.80 accuracy, and in this proposal we aim to refine the performance and extend the capabilities of the malaria CV system to wider applications while pioneering new computational methods in multiple domain adaptation and weakly- and semi-supervised learning. The proposed project would result in the development of a next-generation malaria CV system that can derive molecular data from brightfield images for use by investigators at the bench or in the clinic. We will build out the prototype CV system to optimize performance, develop higher-order classifiers (e.g., differentiating viable from nonviable circulating parasites, finding once-infected cells for the prognosis of delayed hemolysis after treatment), and run the algorithm against different tissue backgrounds (e.g., liver, spleen). The product of this work will be a cutting-edge neural network-based malaria CV system that provides a multiplex readout of parasite biological parameters and cellular pathology to help propel the fields of malaria research and biomedical CV analysis forward.

项目概要/摘要 在全球“三大”传染病中，疟疾因其疟原虫的复杂性而脱颖而出 生命周期和生物学。疟疾寄生虫主要在红细胞内繁殖，并且在其整个生命周期中都有。 蛋白质表达和新陈代谢的巨大变化，改变了它们的外观、行为和易感性 通过宿主免疫系统或抗疟药物清除，因为它是血液感染，需要活检。 可以通过简单的手指刺破来获取，并且能够通过光获取组织病理学信息 显微镜检查是研究以及最终控制和治疗疟疾的重要工具。 基于神经网络的计算机视觉（CV）方法可以加速数据。 从光学显微镜中获取数据并创新目前只能通过以下方式提取数据的新方法 昂贵、劳动密集型的台式分子方法或少数疟疾的耗时审查 受过必要培训和经验的显微镜专家可以区分之间的细微差异 寄生虫形式。 这项 R21 提案以 12 个月的准备工作为基础，并得到了约翰斯 (The Johns) 试点拨款的支持 霍普金斯大学数据密集型工程与科学研究所，各学院的合作研究 医学与工程学院的联合首席研究员开发了一种基于深度学习的 CV 算法。 在超过 10,000 张恶性疟原虫环期寄生虫图像的公共数据集上进行训练，可以检测 并以 >0.97 的准确度量化寄生虫。然而，可以从中提取更多信息的时机已经成熟。 疟疾涂片超出了简单检测寄生虫的范围。我们构建了第二代 CV 的早期原型。 能够识别正确的寄生虫阶段到早、中或晚环阶段水平的算法 >0.80 准确度，在本提案中，我们的目标是改进性能并扩展 疟疾CV系统得到更广泛的应用，同时在多个领域开创新的计算方法 适应以及弱监督和半监督学习。 拟议的项目将导致下一代疟疾 CV 系统的开发，该系统可以 从明场图像中获取分子数据，供研究人员在实验室或诊所使用。 开发原型 CV 系统以优化性能，开发高阶分类器（例如，区分 从无法存活的循环寄生虫中存活下来，找到一次感染的细胞以预测延迟性溶血 治疗后），并针对不同的组织背景（例如肝脏、脾脏）运行算法。 这项工作将是一个基于尖端神经网络的疟疾 CV 系统，可提供多重读数 寄生虫生物参数和细胞病理学有助于推动疟疾研究领域的发展 生物医学简历分析向前推进。