Authors:
Vitor Fernandes
1
;
Adriano Silva
1
;
Danilo Pereira
1
;
Sérgio Cardoso
2
;
Paulo R. de Faria
3
;
Adriano Loyola
2
;
Thaína Tosta
4
;
Leandro Neves
5
and
Marcelo Z. do Nascimento
1
Affiliations:
1
Faculty of Computer Science, Federal University of Uberlândia, Brazil
;
2
Area of Oral Pathology, School of Dentistry, Federal University of Uberlândia, Brazil
;
3
Department of Histology and Morphology, Institute of Biomedical Science, Federal University of Uberlândia, Brazil
;
4
Science and Technology Institute, Federal University of São Paulo, Brazil
;
5
Department of Computer Science and Statistics (DCCE), São Paulo State University, Brazil
Keyword(s):
Oral Epithelial Dysplasia, Convolutional Neural Network, Tensors, Histological Image, Classifier, Tucker Decomposition.
Abstract:
Cancer in the oral cavity is one of the most common, making it necessary to investigate lesions that could develop into cancer. Initial stage lesions, called dysplasia, can develop into more severe stages of the disease and are characterized by variations in the shape and size of the nucleus of epithelial tissue cells. Due to advances in the areas of digital image processing and artificial intelligence, diagnostic aid systems (CAD) have become a tool to help reduce the difficulties of analyzing and classifying lesions. This paper presents an investigation of the Tucker decomposition in tensors for different CNN models to classify dysplasia in histological images of the oral cavity. In addition to the Tucker decomposition, this study investigates the normalization of H&E dyes on the optimized CNN models to evaluate the behavior of the architectures in the classification stage of dysplasia lesions. The results show that for some of the optimized models, the use of normalization contrib
uted to the performance of the CNNs for classifying dysplasia lesions. However, when the features obtained from the final layers of the CNNs associated with the machine learning algorithms were analyzed, it was noted that the normalization process affected performance during classification.
(More)