Contributions in computer assisted diagnosis : breast cancer and autoimmune diseases

Abstract

With the advent of research, it has been established that many leading diseases among women, such as breast cancer, cervical cancer, and autoimmune diseases, can be prevented if diagnosed at initial stage. This research aims at development and analysis of computer assisted systems for accurate diagnosis of such diseases. Among various diseases, this thesis focus upon developing automated systems for screening breast cancer and autoimmune diseases. Significant research efforts are being made to detect breast cancer symptoms on screening mammograms, however, mass detection has been the most challenging task. The complexity of the task is attributed to varying shape and size of masses and presence of artifacts and pectoral muscles. In this research, we pursue the idea of visual saliency and propose a novel framework to detect mass(es) from screening mammogram(s). The concept of visual saliency is based properties of human vision, therefore, it may help in performing the ”intuitive” tasks which human eye perform with ease such as finding the region of interest. We use the saliency algorithm to segment candidate regions which may contain masses. The qualitative analysis shows that saliency algorithm is capable of detecting mass containing regions without any prior segmentation of pectoral muscles. Extensive feature analysis is performed to obtain the optimal set of features to detect masses using Support Vector Machine based classification. Experiments are conducted on publicly available MIAS database using existing protocols. Results from the comparative analysis show that the proposed framework outperforms the state-of-art algorithms. Identification of antigen patterns from HEp-2 cells is crucial for the diagnosis of autoimmune diseases. The manual inspection under microscope as well as computer screens is prone to inter-observer variability and lack of standardization. Therefore, efforts are being made to automate the antigen pattern classification from HEp-2 cell images. In this research, we propose a feature categorization to analyze the existing research associated with HEp-2 cell image classification. We also propose an efficient classification system for antigen pattern identification based on Laws texture features. Experiments are conducted using public datasets and existing protocols. Comparison with state-of-the-art techniques clearly indicate that Laws texture features are more efficient for the given task.