itms: accurate prediction of diabetic foot ulcer using convolution neural network

R.Athi vaishnavi,K. Mahalakshmi

Two to ten percent of diabetic patients suffered from diabetic foot ulcer due to poor blood glucose control. The majority of foot and lower leg amputations are performed on patients with diabetic mellitus. Avoiding major amputation is a proper treatment for diabetic foot syndrome. In this DFU (Diabetic foot ulcer) classification problem, we assessed the two classes as normal skin (healthy skin) and abnormal skin (DFU). We used Convolution Neural Networks in DFU Net, with better feature extraction to identify the feature differences between healthy skin and the DFU. In the previous study, expert uses only the foot images for diabetic foot ulcer classification. we use the modalities of plantar studies such as thermal imaging, plantar pressure studies and vibration studies to help in correctly differentiating the region of interest as normal and abnormal. The proposed system,ITMS (Intelligent telemedicine monitoring system) serve as a self-monitoring tool with a mobile app giving diabetic patients the ability to self-check their extremities for any possible ulcer at the pre ulcer stage itself without the need for frequent visits to the diabetic clinic. It is a cost effective, remote and health care monitoring system.

Volume 11 | 08-Special Issue

Pages: 1699-1705