Computerized Classification of CT Lung Images using CNN with Watershed Segmentation

摘要

Cancer is a major threat to the lives of human beings. Around 74% of the people who get affected by cancer lost their lives. But early detection of cancer cells can prevent death rates. CT(Computerized Tomography) is one of the major used for cancer cell identifications by the oncologist. Computer-aided cancer detection plays a major role in the detection of cancer in an early stage. Classification of CT scan images comes as the first stage for computer-aided detection of cancer cells. CNN(Convolution Neural Network) based classification method along with Gaussian Filtering and Watershed Segmentation is proposed for effective classification of CT Scan Images.500 CT Scan images of Bone, Brain, Lung, Kidney, Neck are collected from the Oncology Department, Manipal Hospitals, Vijayawada. The accuracy rate of 94.5% is achieved with the proposed CNN based classification CT Scan images.