High-throughput, single-cell optofluidic platform for point-of-care diagnosis

随着该项目的完成，产生了两项突破性技术。第一个是智能血小板聚集体分类器（iPAC），它对不同激动剂产生的血小板聚集体进行高通量成像和智能分析，并按激动剂类型对血小板聚集体进行分类。我们发现血小板聚集体可以通过其形态学按激动剂类型分类，这是前所未有的，因为以前从未报道过。关于血小板聚集体形成背后的驱动因素的信息有望导致更好地理解血小板聚集的潜在机制，并打开一个全新的临床诊断，药物计量学和治疗学的窗口。第二种是虚拟光流体时间拉伸定量相位成像，其通过使用用许多对明场和相位图像训练的深度神经网络从其对应的明场图像生成“虚拟”相位图像，并基于其明场和虚拟相位图像从白色血细胞中识别癌细胞。严博士在一个著名的国际会议（澳大利亚和新西兰纳米流体和微流体会议）上介绍了他的工作。同时，该项目产生了3篇稿件。

Two breakthrough technologies are generated with the completion of this project. The first one is intelligent platelet aggregate classifier (iPAC) that performs high-throughput imaging and intelligent analysis of platelet aggregates produced by different agonists and classifies platelet aggregates by agonist type. Our finding that platelet aggregates can be classified by agonist type through their morphology is unprecedented as it has never been reported previously. The information about the driving factors behind the formation of platelet aggregates is expected to lead to a better understanding of the underlying mechanism of platelet aggregation and open a window on an entirely new class of clinical diagnostics, pharmacometrics, and therapeutics. The second one is the virtual optofluidic time-stretch quantitative phase imaging, which generates “virtual” phase images from their corresponding bright-field images by using a deep neural network trained with numerous pairs of bright-field and phase images and identifies cancer cells from white blood cells based on their bright-field and virtual phase images. The fellow, Dr Yan, has presented his work in a prestigious international conference (Australia and New Zealand Nanofluidics and Microfluidics conference). Meanwhile, 3 manuscripts are generated from this project.