Open AccessClassifications of Multispectral Colorectal Cancer Tissues Using Convolution Neural Network
Author(s) -
Hawraa Haj-Hassan,
Ahmad Chaddad,
Youssef Harkouss,
Christian Desrosiers,
Matthew Toews,
Camel Tanougast
Publication year - 2017
Publication title -
journal of pathology informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.009
H-Index - 17
ISSN - 2153-3539
DOI - 10.4103/jpi.jpi_47_16
Subject(s) - artificial intelligence , computer science , convolutional neural network , pattern recognition (psychology) , convolution (computer science) , colorectal cancer , feature extraction , multispectral image , biopsy , feature (linguistics) , pooling , cancer , artificial neural network , pathology , medicine , linguistics , philosophy
Background: Colorectal cancer (CRC) is the third most common cancer among men and women. Its diagnosis in early stages, typically done through the analysis of colon biopsy images, can greatly improve the chances of a successful treatment. This paper proposes to use convolution neural networks (CNNs) to predict three tissue types related to the progression of CRC: benign hyperplasia (BH), intraepithelial neoplasia (IN), and carcinoma (Ca). Methods: Multispectral biopsy images of thirty CRC patients were retrospectively analyzed. Images of tissue samples were divided into three groups, based on their type (10 BH, 10 IN, and 10 Ca). An active contour model was used to segment image regions containing pathological tissues. Tissue samples were classified using a CNN containing convolution, max-pooling, and fully-connected layers. Available tissue samples were split into a training set, for learning the CNN parameters, and test set, for evaluating its performance. Results: An accuracy of 99.17% was obtained from segmented image regions, outperforming existing approaches based on traditional feature extraction, and classification techniques. Conclusions: Experimental results demonstrate the effectiveness of CNN for the classification of CRC tissue types, in particular when using presegmented regions of interest