Literature DB >> 29650318

Tissue classification and segmentation of pressure injuries using convolutional neural networks.

Sofia Zahia1, Daniel Sierra-Sosa2, Begonya Garcia-Zapirain3, Adel Elmaghraby4.   

Abstract

BACKGROUND AND OBJECTIVES: This paper presents a new approach for automatic tissue classification in pressure injuries. These wounds are localized skin damages which need frequent diagnosis and treatment. Therefore, a reliable and accurate systems for segmentation and tissue type identification are needed in order to achieve better treatment results.
METHODS: Our proposed system is based on a Convolutional Neural Network (CNN) devoted to performing optimized segmentation of the different tissue types present in pressure injuries (granulation, slough, and necrotic tissues). A preprocessing step removes the flash light and creates a set of 5x5 sub-images which are used as input for the CNN network. The network output will classify every sub-image of the validation set into one of the three classes studied.
RESULTS: The metrics used to evaluate our approach show an overall average classification accuracy of 92.01%, an average total weighted Dice Similarity Coefficient of 91.38%, and an average precision per class of 97.31% for granulation tissue, 96.59% for necrotic tissue, and 77.90% for slough tissue.
CONCLUSIONS: Our system has been proven to make recognition of complicated structures in biomedical images feasible.
Copyright © 2018 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Convolutional neural networks; Deep learning; Image segmentation; Pressure injuries; Tissue type classification

Mesh:

Year:  2018        PMID: 29650318     DOI: 10.1016/j.cmpb.2018.02.018

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  8 in total

1.  Fine-grained diabetic wound depth and granulation tissue amount assessment using bilinear convolutional neural network.

Authors:  Xixuan Zhao; Ziyang Liu; Emmanuel Agu; Ameya Wagh; Shubham Jain; Clifford Lindsay; Bengisu Tulu; Diane Strong; Jiangming Kan
Journal:  IEEE Access       Date:  2019-12-12       Impact factor: 3.367

2.  Wound Size Imaging: Ready for Smart Assessment and Monitoring.

Authors:  Yves Lucas; Rania Niri; Sylvie Treuillet; Hassan Douzi; Benjamin Castaneda
Journal:  Adv Wound Care (New Rochelle)       Date:  2020-09-25       Impact factor: 4.730

3.  Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning.

Authors:  Sofia Zahia; Begonya Garcia-Zapirain; Adel Elmaghraby
Journal:  Sensors (Basel)       Date:  2020-05-21       Impact factor: 3.576

Review 4.  Using Machine Learning Technologies in Pressure Injury Management: Systematic Review.

Authors:  Mengyao Jiang; Yuxia Ma; Siyi Guo; Liuqi Jin; Lin Lv; Lin Han; Ning An
Journal:  JMIR Med Inform       Date:  2021-03-10

5.  Deep learning approach based on superpixel segmentation assisted labeling for automatic pressure ulcer diagnosis.

Authors:  Che Wei Chang; Mesakh Christian; Dun Hao Chang; Feipei Lai; Tom J Liu; Yo Shen Chen; Wei Jen Chen
Journal:  PLoS One       Date:  2022-02-17       Impact factor: 3.240

6.  Interactive Medical Image Labeling Tool to Construct a Robust Convolutional Neural Network Training Data Set: Development and Validation Study.

Authors:  David Reifs; Ramon Reig-Bolaño; Marta Casals; Sergi Grau-Carrion
Journal:  JMIR Med Inform       Date:  2022-08-22

7.  Image segmentation using transfer learning and Fast R-CNN for diabetic foot wound treatments.

Authors:  Huang-Nan Huang; Tianyi Zhang; Chao-Tung Yang; Yi-Jing Sheen; Hsian-Min Chen; Chur-Jen Chen; Meng-Wen Tseng
Journal:  Front Public Health       Date:  2022-09-20

8.  Learning Medical Materials From Radiography Images.

Authors:  Carson Molder; Benjamin Lowe; Justin Zhan
Journal:  Front Artif Intell       Date:  2021-06-18
  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.