COMPUTER AIDED ANALYSIS OF HISTOPATHOLOGICAL IMAGES FOR FEATURES BASED CANCER DETECTION

Abstract

The present thesis is focused on the development of a computer aided diagnosis (CAD) system to investigate the benign and malignant cells using the haematoxylin and eosin stained histopathological images of cancer. Specific tools were used for the identification of cancer: (1) pre-processing, (2) segmentation, (3) feature extraction and (4) classification of histopathological images. It aims to reduce subjectivity in the diagnostic process and assist in making diagnostic decisions more accurate and consistent. Cancer has turned out to be the leading causes of mortality in the world there by creating the need for more awareness globally. Among the developing countries, India suffers leading cause of death from cancer.