Wound Area Segmentation Using 4-D Probability Map and Superpixel Region Growing

Biswas, Topu; Fauzi, Mohammad Faizal Ahmad; Abas, Fazly Salleh; Logeswaran, Rajasvaran; Nair, Harikrishna K.R.

doi:10.1109/icsipa45851.2019.8977739

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Related Researchmentioning

confidence: 99%

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

Filko

Nyarko

2023

Sensors

View full text Add to dashboard Cite

Chronic wounds, are a worldwide health problem affecting populations and economies as a whole. With the increase in age-related diseases, obesity, and diabetes, the costs of chronic wound healing will further increase. Wound assessment should be fast and accurate in order to reduce possible complications and thus shorten the wound healing process. This paper describes an automatic wound segmentation based on a wound recording system built upon a 7-DoF robot arm with an attached RGB-D camera and high-precision 3D scanner. The developed system represents a novel combination of 2D and 3D segmentation, where the 2D segmentation is based on the MobileNetV2 classifier and the 3D component is based on the active contour model, which works on the 3D mesh to further refine the wound contour. The end output is the 3D model of only the wound surface without the surrounding healthy skin and geometric parameters in the form of perimeter, area, and volume.

show abstract

Section: Related Researchmentioning

confidence: 99%

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

Filko

Nyarko

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Wound area segmentation was performed with an accuracy of 71.98% on ten images. The author's next work described in [6] is based on a superpixel region growing algorithm and formed a 4D probability map which achieved an accuracy of 79.2% on 30 images. Dhane et al [7] used only the S channel from the HSV color space where they converted the image into data points, and with the aid of the Gaussian similarity function, calculated a similarity graph.…”

Section: Related Researchmentioning

confidence: 99%

Wound Detection by Simple Feedforward Neural Network

2022

View full text Add to dashboard Cite

Chronic wounds are a heavy burden on medical facilities, so any help in treating them is most welcome. Current research focuses on wound analysis, especially wound tissue classification, wound measurement, and wound healing prediction to assist medical personnel in wound treatment, with the main goal of reducing wound healing time. The first phase of wound analysis is wound segmentation, where the task is to extract wounds from the healthy tissue and image background. In this work, a standard feedforward neural network was developed for the purpose of wound segmentation using data from the MICCAI 2021 Foot Ulcer Segmentation (FUSeg) Challenge. It proved to be a simple yet efficient method for extracting wounds from images. The proposed algorithm is part of a compact system that analyzes chronic wounds using a robotic manipulator, RGB-D camera and 3D scanner. The feedforward neural network consists of only five fully connected layers, the first four with Rectified Linear Unit (ReLU) activation functions and the last with sigmoid activation functions. Three separate models were trained and tested using images provided as part of the challenge. The predicted images were post-processed and merged to improve the final segmentation performance.The accuracy metrics observed during model training and selection were Precision, Recall and F1 score. The experimental results of the proposed network provided a recall value of 0.77, precision value of 0.72, and an F1 score (Dice score) of 0.74.

show abstract