Classification of pressure ulcer tissues with 3D convolutional neural network

被引：0
作者：
Begoña García-Zapirain
Mohammed Elmogy
Ayman El-Baz
Adel S. Elmaghraby
机构：
[1] Universidad de Deusto,Facultad Ingeniería
[2] Mansoura University,Information Technology Department, Faculty of Computers and Information
[3] University of Louisville,Bioengineering Department
[4] University of Louisville,Department of Computer Engineering and Computer Science
来源：
Medical & Biological Engineering & Computing | 2018年 / 56卷
关键词：
Pressure ulcer; 3D convolution neural network (CNN); Tissue classification; Linear combinations of discrete Gaussians (LCDG);
D O I：
暂无
中图分类号：
学科分类号：
摘要：
A 3D convolution neural network (CNN) of deep learning architecture is supplied with essential visual features to accurately classify and segment granulation, necrotic eschar, and slough tissues in pressure ulcer color images. After finding a region of interest (ROI), the features are extracted from both the original and convolved with a pre-selected Gaussian kernel 3D HSI images, combined with first-order models of current and prior visual appearance. The models approximate empirical marginal probability distributions of voxel-wise signals with linear combinations of discrete Gaussians (LCDG). The framework was trained and tested on 193 color pressure ulcer images. The classification accuracy and robustness were evaluated using the Dice similarity coefficient (DSC), the percentage area distance (PAD), and the area under the ROC curve (AUC). The obtained preliminary DSC of 92%, PAD of 13%, and AUC of 95% are promising.
引用
收藏
页码：2245 / 2258
页数：13
相关论文
共 80 条
  • [1] Mukherjee R(2014)Automated tissue classification framework for reproducible chronic wound assessment Biomed Res Int 2014 1-9
  • [2] Manohar DD(2015)Computerized segmentation and measurement of chronic wound images Comput Biol Med 60 74-85
  • [3] Das DK(2009)Human skin wounds: a major and snowballing threat to public health and the economy Wound Repair Regen 17 763-771
  • [4] Achar A(2001)Pressure ulcers in america: prevalence, incidence, and implications for the future Adv Skin Wound Care 14 208-215
  • [5] Mitra A(2014)An image mining based approach to detect pressure ulcer stage Pattern Recognit Image Anal 24 292-296
  • [6] Chakraborty C(2016)Inpatient pressure ulcer prevalence in an acute care hospital using evidence-based practice Worldviews Evid-Based Nurs 13 112-117
  • [7] Fauzi MFA(2010)Binary tissue classification on wound images with neural networks and bayesian classifiers IEEE Trans Med Imaging 29 410-427
  • [8] Khansa I(2015)Wound image evaluation with machine learning Neurocomputing 164 112-122
  • [9] Catignani K(2017)Pressure ulcer image segmentation technique through synthetic frequencies generation and contrast variation using toroidal geometry BioMedical Engineering OnLine 16 1-19
  • [10] Gordillo G(2017)Dermatologist-level classification of skin cancer with deep neural networks Nature 542 115-118
12345678