A Comparative Study of Neural Computing Approaches for Semantic Segmentation of Breast Tumors on Ultrasound Images

Luis Eduardo Aguilar-Camacho, Wilfrido Gómez-Flores, Juan Humberto Sossa-Azuela

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

This paper compares two approaches for semantic segmentation of breast tumors on ultrasound. The first approach, called conventional, follows the typical pattern classification process to extract hand-crafted features, followed by pixel classification with a Multilayer Perceptron (MLP) network. The second approach, called convolutional, uses a Convolutional Neural Network (CNN) to learn features automatically. For evaluating both approaches, a breast ultrasound dataset with 1200 images is considered. Experimental results reveal that the CNNs called VGG16 and ResNet50 outperformed the conventional approach in various segmentation quality indices. Thus, extracting hand-crafted discriminant features is challenging since it depends on the problem domain and the designer’s skills. On the other hand, through transfer learning, it is possible to adjust a pre-trained CNN for addressing the problem of tumor segmentation satisfactorily. This performance is because CNN learns general features in its first layers, and more subtle features are activated as depth increases.

Original languageEnglish
Title of host publication27th Brazilian Congress on Biomedical Engineering - Proceedings of CBEB 2020
EditorsTeodiano Freire Bastos-Filho, Eliete Maria de Oliveira Caldeira, Anselmo Frizera-Neto
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1649-1657
Number of pages9
ISBN (Print)9783030706005
DOIs
StatePublished - 2022
Event27th Brazilian Congress on Biomedical Engineering, CBEB 2020 - Vitória, Brazil
Duration: 26 Oct 202030 Oct 2020

Publication series

NameIFMBE Proceedings
Volume83
ISSN (Print)1680-0737
ISSN (Electronic)1433-9277

Conference

Conference27th Brazilian Congress on Biomedical Engineering, CBEB 2020
Country/TerritoryBrazil
CityVitória
Period26/10/2030/10/20

Keywords

  • Artificial neural network
  • Breast ultrasound
  • Convolutional neural network
  • Semantic segmentation

Fingerprint

Dive into the research topics of 'A Comparative Study of Neural Computing Approaches for Semantic Segmentation of Breast Tumors on Ultrasound Images'. Together they form a unique fingerprint.

Cite this