Wound Segmentation Network Based on Location Information Enhancement

Abstract

Wound segmentation provides assistance for the diagnosis and treatment of wounds. We find that the wound image has a distinct feature, e.g., the pixel color changes gradually according to its position. Location information is essential to describe this feature. However, the current methods of wound segmentation based on deep learning have not significantly added location information into model training. In order to enhance this information, we propose a deep neural network model based on a location map and location-enhanced convolution kernel. The model effectively encodes the location information to one feature map, which is then concatenated with the inputs of the network and added to the hidden layer of the network after downsampling. Moreover, the model uses a fixed-value initialized convolution kernel to further enhance the location information in the training of the network. At the end of the model, a fixed-value depth-wise convolution layer is added to eliminate minor errors.

A Survey of Wound Image Analysis Using Deep Learning: Classification, Detection, and Segmentation

“…Medetec dataset [24] Mixed -No [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35] BIP_US database [36] Burn 94 Yes [37], [38] FUSeg dataset [28] Diabetic foot ulcer 1210 Yes [29] Sårwebben [39] Mixed -No [40] Chronic wound database [41] Chronic wound 188 Yes [42] AHZ dataset [28] Diabetic foot ulcer 1109 Yes [28] AHZ&UWM dataset [34] Mixed 538 Yes [34] publicly available [44]. Second, the primary job of medical professionals is not data collection, and the acquisition of a batch of images may be done by multiple personnel, which can lead to inconsistent standards of the collected images.…”

“…In a wound image, the pixel color will be a gradient as the wound area extends into a healthy area. Based on this feature, Li et al [27] enhance the location information of the image in a deep neural network. The location map is first obtained through a location encoder, and then input into the DNN together with the original image.…”

2D/3D Wound Segmentation and Measurement Based on a Robot-Driven Reconstruction System

“…Researchers have employed a variety of approaches to perform 2D wound segmentation, including using K-means clustering [ 6 , 7 ], deep neural networks [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 ], support vector machines [ 16 , 17 ], k-nearest neighbors [ 4 ], and simple feedforward networks [ 18 ]. Other approaches include using superpixel region-growing algorithms, color histograms, or combined geometric and visual information of the wound surface to segment wounds.…”

Simultaneous wound border segmentation and tissue classification using a conditional generative adversarial network

“…The model also could not be trained end‐to‐end because of the model complexity. The authors in [27] propose a model for automatic wound region segmentation and wound condition analysis with infection detection and healing progress prediction. This study [27] utilises traditional pre‐ and post‐processing steps to improve segmentation performance and does not have tissue classification.…”

“…The authors in [27] propose a model for automatic wound region segmentation and wound condition analysis with infection detection and healing progress prediction. This study [27] utilises traditional pre‐ and post‐processing steps to improve segmentation performance and does not have tissue classification. The authors in [28] provide a tool for segmenting and locating chronic wounds to facilitate bioprinting treatment using edge detection and segmentation algorithms.…”