AI Based Digital WSI Scanner for Cancer Detection

Abstract

CancerScopeX is an automated system for identifying malignancy in images of blood slides. The initiative has two major components: video processing and cancer detection. Initially, a digital camera mounted on a microscope is used to capture a video of the blood slide, which is then segmented and stitched together using image stitching algorithms to generate a Whole Slide Image (WSI). The WSI is then preprocessed in preparation for additional analysis. In the second section, a Convolutional Neural Network (CNN) model is trained to detect malignancy (Leukemia) from images of blood slide slides. The dataset used to train the model is comprised of Internet and local hospital images. The system offers an intuitive Graphical User Interface (GUI) for both components of the project. The GUI for video processing displays the merged WSI, whereas the GUI for cancer detection displays the CNN model's results. The CancerScopeX system offers an automated and precise method for detecting cancer in blood slide images, which may aid in the early diagnosis and treatment of cancer.