Prof. Renjie Zhou, Department of Biomedical Engineering

The world’s first AI-enabled Portable Quantitative Phase Microscope for Blood Testing was one of the five innovative projects showcased at the Hong Kong Electronics Fair (Autumn Edition) 2019 at the Hong Kong Convention and Exhibition Centre. The project provides low-cost, fast and highly efficient blood-testing technology for use in general clinics and underdeveloped areas.

A regular physical check-up typically includes blood testing, which reveals information about a patient’s health, especially in terms of their immune-functioning leukocytes or white blood cells. Unlike red blood cells, there are many types of leukocytes, including monocytes, granulocytes and lymphocytes. Through the classification or counting of the number of leukocytes, to see whether they have increased or decreased, various conditions can be detected, such as inflammation, infectious diseases and leukaemia.

Traditional methods of blood testing include the manual observation of stained smears and fluorescence detection via flow cytometry, but the staining and fluorescent-labelling process is time-consuming and labour-intensive. Quantitative phase microscopy (QPM) is a label-free imaging technology with high imaging sensitivity and speed, but the instruments it requires are bulky and expensive and cannot be moved easily to different laboratories, especially in remote areas. Moreover, all of the above methods need to be carried out by professionals, and the test results can take hours or even days. Therefore, in addition to the high costs of instruments and reagents, labour and time costs also have to be taken into consideration. Even though newer automated instruments are available, these still present the problems of bulk and expense, and they may kill the cells or affect their morphology through staining or labelling. Such cells cannot be reused in other tests that may be able to provide information about a patient’s health. Thus, a blood-testing method that can be performed quickly and efficiently while preserving cell morphology is needed.

In order to provide low-cost and highly efficient blood-testing technology in general clinics and underdeveloped areas, the CUHK team, led by Prof. Zhou Renjie, Department of Biomedical Engineering, developed the AI-enabled Portable Quantitative Phase Microscope for Blood Testing to identify different types of human leukocytes, drawing on quantitative phase imaging and deep learning.

QPM technology has become an important method for quantifying live cell morphology and precision material (e.g. semiconductor) metrology. Professor Zhou’s research team has successfully developed a new, portable and versatile QPM system. By combining the reflection mode and the transmission mode into one system and using a special interferometry technique to greatly reduce noise influence, the system is not only compact and portable but also offers high precision and low cost.

Professor Zhou said, ‘In the past, researchers have tried in vain to combine artificial intelligence with traditional blood-testing methods, because it is difficult to distinguish cell images. Through our high-precision QPM technology, we can effectively combine blood testing with the deep learning technology of artificial intelligence. By learning the morphological features from thousands of cells in two-dimensional quantitative phase images, our learning model can automatically distinguish monocytes, granulocytes, T-cells and B-cells in lymphocytes from healthy volunteers’ blood samples.’

The low-cost AI-enabled Portable Quantitative Phase Microscope for Blood Testing developed by CUHK weighs less than 5kg and is similar in size to a briefcase, meaning that it can be carried and used anywhere. In addition, its label-free feature saves the use of reagents and can avoid the need for a professional to carry out the staining and fluorescent-labelling process and for clinical experts to classify and count cells. The analysis process is completed automatically by a computer, which can obtain the results in a matter of minutes with an accuracy higher than 90%.

The CUHK team has just completed the proof-of-concept study. The researchers are planning to get clinical certification by working with hospitals, which will start in 2020. They expect the low-cost AI-enabled Portable Quantitative Phase Microscope for Blood Testing to be commercialised in three to five years. In future, the researchers plan to develop other artificial intelligence models of this portable quantitative phase microscopy technique that can be used to distinguish red blood cells and all other types of blood cells. They are also working on using their invention to differentiate bacteria and stem cells. Eventually, the team hopes to be able to detect cancer cells in peripheral blood.

References:
[1] https://www.beckmancoulter.com/en/products/hematology/dxh-600?index=0#/d...
[2] Meintker, Lisa, et al. ‘Comparison of automated differential blood cell counts from Abbott Sapphire, Siemens Advia 120, Beckman Coulter DxH 800, and Sysmex XE-2100 in normal and pathologic samples.’ American Journal of Clinical Pathology 139(5) (2013): 641-650.