Image based computer aided diagnosis system for cancer detection

• Studies and compare the recent works in different types of cancer detection.
• Low level features comparison for detecting different cancer types.
• Compare image modalities and associated segmentation algorithms.
• Research extension discussion in intermediate feature analysis and cloud structure for cancer detection.

Cancer is one of the major causes of non-accidental death in human. Early diagnosis of the disease allows clinician to administer suitable treatment, and can improve the patient’s survival rate. Traditional diagnosis involves trained clinicians to visually examine the respective medical images for any signs of nodule development in the body. However due to the large scale of the medical image data, this manual diagnosis is often laborious and can be highly subjective due to inter-observer variability. Inspired by the advanced computing technology which is capable of performing complex image processing and machine learning, researches had been carried out in the past few decades to develop computer aided diagnosis (CAD) systems to assist clinicians detecting different forms of cancer. This paper reviews computer vision techniques adopted in medical image analysis, in particular, for cancer detection. The review focused on the detection of the most common form of cancer types, namely breast cancer, prostate cancer, lung cancer and skin cancer. A recent proposed cloud computing frame work has inspired the researchers to utilize the existing works on image based cancer research and develop a more versatile CAD system for detection.