Method for determining severity of skin disease based on percentage of body surface area covered by lesions

A computerized method for determining severity of skin disease based on percentage of body surface area (BSA) that is covered by lesions, the method comprising:

• (a) performing image segmentation on a plurality of training set images of BSA's using a segmentation algorithm, wherein each of the plurality of training set images of BSA's include skin disease, the image segmentation performed using the segmentation algorithm outputting proposed regions in each of the plurality of training set images;
• (b) classifying each of the proposed regions as being a lesion or a non-lesion;
• (c) training a neural network using the classified proposed regions in each of the plurality of training setimages;
• (d) performing image segmentation on a test image of a BSA that includes skin disease using the segmentation algorithm, the image segmentation performed using the segmentation algorithm outputting regions in the test image of the BSA;
• (e) inputting the regions of the test image into the trained neural network;
• (f) using the trained neural network to identify and filter out non-lesion regions from the test image, wherein the remaining regions of the test image are classified as lesion regions;
• and
• (g) calculating a percentage of BSA in the test image that is covered by lesions using areas of the classified lesion regions of the test image, and the areas of identified non-lesion regions of the test image.