Classification of pressure ulcer tissues with 3D convolutional neural network.

https://www.ncbi.nlm.nih.gov/pubmed/29949023

Med Biol Eng Comput. 2018 Jun 15. doi: 10.1007/s11517-018-1835-y. [Epub ahead of print]

Classification of pressure ulcer tissues with 3D convolutional neural network.

García-Zapirain B1, Elmogy M2,3, El-Baz A4, Elmaghraby AS5.

Author information

1

Facultad Ingeniería, Universidad de Deusto, Avda/Universidades 24, 48007, Bilbao, Spain.

2

Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura, 35516, Egypt.

3

Bioengineering Department, University of Louisville, Louisville, KY, 40292, USA.

4

Bioengineering Department, University of Louisville, Louisville, KY, 40292, USA. aselba01@louisville.edu.

5

Department of Computer Engineering and Computer Science, University of Louisville, Louisville, KY, 40292, USA.

Abstract

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. Graphical Abstract The Classification of Pressure Ulcer Tissues Based on 3D Convolutional Neural Network.

KEYWORDS:

3D convolution neural network (CNN); Linear combinations of discrete Gaussians (LCDG); Pressure ulcer; Tissue classification

PMID:

 

29949023

 

DOI:

 

10.1007/s11517-018-1835-y

 

스페인, 미국

압박 궤양

3D CNN

linear combinations of discrete Gaussians (LCDG)

dice similarity coefficient : 92% 

201804 classification of pressure ulcer 3D CNN.pdf