CPC G06T 7/11 (2017.01) [G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30088 (2013.01); G06T 2207/30096 (2013.01)] | 16 Claims |
1. A system for determining severity of skin disease, comprising:
a non-transitory computer-readable medium with instructions stored thereon, which when executed by a processor perform steps comprising:
segmenting at least one test image into a set of image regions with a Felzenszwalb segmentation algorithm;
inputting the set of image regions to a trained convolutional neural network;
with the trained neural network, classifying each region of the set of image regions as (a) lesion regions, (b) non-lesion body regions, or (c) non-body regions;
calculating a percentage of body surface area (BSA) covered by lesions by using the combined areas of the lesion regions and the combined areas of the lesion regions and non-lesion body regions.
|