Classification framework for nailfold capillary microscopy images

Nailfold capillary microscopy examination has been used since late 1950s as a non-invasive in-vivo technique for diagnosing and monitoring connective tissue disease in adults. Disorders such as Raynaud´s phenomenon, progressive systemic sclerosis, and rheumatoid arthritis were detected in more than 80% of adult patients, by analyzing such high resolution images. In this research paper, we propose a framework to classify nailfold capillary microscopy images into SLE (Systemic Lupus Erythematosus) and PSS (Progress Systemic sclerosis) diseases. Based on statistical data collected in Taichung Veteran´s General Hospital (TCVGH), Taiwan, higher percentage of adult patients are find with SLE patients, when compared with PSS. According to ARA (American Rheumatism Association), patients´ outside features are obviously. The PSS patients are the same way to finding the features. And in the same time, we refer from doctor´s idea add other conditions to help judging. In the first step, RP is the most important element. Most of the SLE and PSS features are raised by RP. In the other way, the features can be found in both of SLE and PSS patients. In order to divide the SLE and PSS patients into the correct class, other conditions are existed in necessary.