Automated Quantification of White Blood Cells in Light Microscopic Images of Injured Skeletal Muscle

Muscle regeneration process tracking and analysis aim to monitor the injured muscle tissue section over time and analyze the muscle healing procedure. In this procedure, as one of the most diverse cell types observed, white blood cells (WBCs) exhibit dynamic cellular response and undergo multiple protein expression changes. The characteristics, amount, location, and distribution compose the action of cells which may change over time. Their actions and relationships over the whole healing procedure can be analyzed by processing the microscopic images taken at different time points after injury. The previous studies of muscle regeneration usually employ manual approach or basic intensity process to detect and count WBCs. In comparison, computer vision method is more promising in accuracy, processing speed, and labor cost. Besides, it can extract features like cell/cluster size and eccentricity fast and accurately. In this thesis, we propose an automated quantifying and analysis framework to analyze the WBC in light microscope images of uninjured and injured skeletal muscles. The proposed framework features a hybrid image segmentation method combining the Localized Iterative Otsu’s threshold method assisted by neural networks classifiers and muscle edge detection. In specific, both neural network and convoluted neural network based classifiers are studied and compared. Via this framework, the CD68-positive WBC and 7/4-positive WBC quantification and density distribution results are analyzed for demonstrating the effectiveness of the proposed method