IDENTIFICATION AND DETECTION OF IMMATURE WHITE BLOOD CELLS THROUGH DEEP LEARNING
Ju‐Huei Chien, Si‐Wa Chan, Shin Cheng, Yen‐Chieh Ouyang · 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech) · 2021
Blood smears have many medical uses, including blood cell sorting, bone marrow examination, and so on. From the examination of the blood film, we can check the blood condition of the patient. In addition, it can also help doctors diagnose the patient's condition and understand the effect of treatment. Blood cell sorting is time consuming particular for immature white blood cells and it requires a lot of manpower. This paper is based on Faster R-CNN and Convolutional Neural Network (CNN) to detect and classify immature white blood cells. The test data set was obtained from Taichung Tzu Chi Hospital. In order to find the best experimental neural network structure, we have tried many different neural network architectures. A graphical user interface was created to help us identify white blood cells. Finally, cross-validation is used to increase the credibility of our experiments with an accuracy rate of nearly 90%.