DUTC Net: A novel deep ulcer tissue classification network with stage prediction and treatment plan recommendation

Abstract

Background and objectivesThe Chronic injuries caused by the venous valve called as Varicose ulcers. The pressure in the veins is increased as the valves of the veins allows blood to flow in backward direction. Detecting and segmenting varicose ulcer wound region is a separate step prior to the classification operation. In this work the novel customized Deep Ulcer Tissue Classification Network is proposed and it is named as “DUTC Net”. The goal of the proposed DUTC Net is i) to classify the tissue type by generating tissue map using segmented ulcer wound image ii) to identify the stages of ulcer and iii) Percentage of affected tissues in the wound. MethodsThe dataset contains various stages of varicose ulcer wound images. The first step is to preprocess the ulcer wound image to remove light artifacts and noise. After preprocessing segmentation is done to isolate the region of the varicose ulcer using active contour algorithm. The segmented area can be fed into proposed DUTC Net to get the respective tissue map of the ulcer wound images. The tissue map images are assigned as input to DUTC Net at the phase II. In this phase II, DUTC Net learns the features from the tissue map of the phase I and classifies the stages and percentage of affected tissues in the varicose ulcer wound image. ResultsWhile experimental analysis, the proposed method DUTC Net results sensitivity 97.9%, specificity 98% and accuracy 97.2% for the average of tissue classification and sensitivity 97.1%, specificity 98% and accuracy 97.5% for the average of stage classification. ConclusionThe proposed work is mainly used to classify the varicose ulcer stages, tissues types and affected area using DUTC Net to investigate the patients status and treatment methods.