Development of computer aided diagnosis system for renal lesions in CT mages

Abstract

Renal or kidney cancer is amid the ten common kinds of malignancies around the world, which is increasing at a rate of 1.6% every year as reported by the National Cancer Institute (NCI) and American Cancer Society (ACS). The early detection and risk assessment is essential for patients suffering from this disease, which also serves as a key element in the timely planning of treatment and follow-up therapies. Moreover, the visual examination using medical images for performing diagnosis is subjective and less accurate in marginal cases. In this regard, Computer-Aided Diagnosis (CAD) systems are being developed and utilized in clinical practice for assisting radiologists. This research work comprehensively scrutinizes the current state-of-the-art techniques utilized in the development of CAD systems for renal cancer. Further, the objective of this study is the development of a CAD system to discriminate among benign (non-cancerous) and malignant (cancerous) renal lesions in CT images. The system comprises of pre-processing, segmentation, feature extraction, feature selection and classification stages. The investigational outcomes recommend that the developed CAD system has a potential for performing automatic diagnosis of renal lesions. The presented research work is likely to contribute significantly in the area of CAD system, and such a system can be utilized for providing medical diagnosis and research purposes. Finally, some suggestions based on the observations and experiments are also mentioned to carry out further research in this area. newline