Tissues Classification for Pressure Ulcer Images Based on 3D Convolutional Neural Network

Abstract

Pressure ulcer (PU) is a type of chronic wounds (CWs), which is remaining unhealed for a period longer than six weeks. PU results from applying pressure and friction on the skin of the patient for a long time. It has a complex structure as it has different kinds of tissues. Reliable assessment of PU is essential to the success of the treatment and care decision. In this paper, we propose a tissue classification system for PU based on 3D convolutional neural network (CNN). The main idea of the proposed system is to provide a 3D CNN network with five different models of the colored PU RGB images to accurately segment slough, granulation, and necrotic eschar tissues. Each model of the PU RGB image is provided to the CNN as an independent pathway. The first and second models are the original RGB PU images and its equivalent HSV images. The third model is the smoothed image by convolving the original image with a preselected Gaussian kernel. The last two models are the first-order models of the current and prior visual appearance. The models approximate empirical marginal probability distributions of voxel-wise signals with linear combinations of discrete Gaussians (LCDG). The proposed system was trained and tested on 193 color PU images. The proposed tissue segmentation system is evaluated by using three various metrics, which are the area under the ROC curve (AUC), the Dice similarity coefficient (DSC), and the percentage area distance (PAD). The system achieved an average AUC equals to 95%, DSC equals to 92%, and PAD equals to 10%, which are a promising result.