Unsupervised Segmentation of Breast Infrared Images in Lateral View Using Histogram of Oriented Gradients

  • Thays Correa IF Sudeste MG
  • Fabíola de Oliveira IF Sudeste MG
  • Matheus Baffa USP
  • Lucas Lattari IF Sudeste MG

Resumo


Breast cancer is the second most common type of cancer in the world. It is estimated that 29.7% of new cases diagnosed in Brazil occur in any structures of the breasts. However, the disease has a good prognosis if detected early. Thus, the development of new technologies to help doctors to provide an accurate diagnosis is indispensable. The goal of this work is to develop a new method to automate parts of computer-aided diagnosis systems, performing the unsupervised segmentation of the Region of Interest (ROI) of infrared breast images acquired in lateral view. The segmentation proposed in this paper consists of three stages. The first stage pre-processes the infrared images of the lateral region of breasts. Later, features are extracted from a descriptor based on Histogram of Oriented Gradients (HOG). Concluding, a Machine Learning algorithm is used to perform the segmentation of the sample. The current method obtained an average of 89.9% accuracy and 94.3% specificity in our experiments, which is promising compared to other works.

Palavras-chave: breast cancer, histogram of oriented gradients, image segmentation, infrared imaging, computer vision, computeraided diagnosis

Referências

W C Amalu, W B Hobbins, J F Head, and R L Elliot. The biomedical engineering handbook-medical devices ans systems. Infrared The Biomedical Engineering Handbook-Medical devices ans systems, 3, 2006.

Matheus Baffa, Deivison Cheloni, and Lucas Lattari. Segmentação automática de imagens térmicas das mamas utilizando limiarização com refinamento adaptativo. In Anais Principais do XVI Workshop de Informática Médica, pages 39–48. SBC, 2016.

A. Chagpar. An introduction to breast cancer. (11m03s), coursera., 2018. Disponível em: https://www.coursera.org. Acesso em: 10/03/2020.

Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), volume 1, pages 886–893. IEEE, 2005.

Maíra Araújo de Santana et al. Breast cancer diagnosis based on mammary thermography and extreme learning machines. Research on Biomedical Engineering, 34(AHEAD):45–53, 2018.

Hospital do Câncer de Barretos. Informação: Saiba quais são os principais tipos de câncer mais comuns no brasil, 2018. Disponível em: https://www.hcancerbarretos.com.br/82-institucional/noticiasinstitucional/1300-%20informacao-saiba-quais-sao-os-tipos-de-cancermais-comuns-no-brasil. Acesso em: 10/03/2020.

Instituto Nacional do Câncer INCA. Estatísticas de câncer, 2020. Disponível em: https://www.inca.gov.br/numeros-de-cancer. Acesso em: 02/08/2020.

ABC Fonseca, ESRC Rodrigues, MM Nóbrega, JOC Nobre, GJ França, and LP Silva. Estimativa para o câncer de mama feminino: e a assistência de enfermagem na prevenção. Temas em saúde, 16(4):14–30, 2016.

GLOBOCAN. Cancer fact shets: Breast cancer, 2020. Disponível em: http://globocan.iarc.fr/old/FactSheets/cancers/breast-new.asp. Acesso em: 10/03/2020.

Jay P Gore and Lisa X Xu. Thermal imaging for biological and medical diagnostics. In Biomedical Photonics Handbook, pages 540–553. CRC press, 2014.

INCA. Tipos de câncer - câncer de mama, 2020. Disponível em: https://www.inca.gov.br/tipos-de-cancer/cancer-de-mama. Acesso em: 02/08/2020.

Afsaneh Jalalian, Syamsiah Mashohor, Rozi Mahmud, Babak Karasfi, M. Saripan, and Abdul Ramli. Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection. EXCLI Journal, 16:113–137, 02 2017.

J Josephine Selle, A Shenbagavalli, N Sriraam, B Venkatraman, M Jayashree, and M Menaka. Automated recognition of rois for breast thermograms of lateral view-a pilot study. Quantitative InfraRed Thermography Journal, 15(2):194–213, 2018.

Siva Kakileti, Geetha Manjunath, Himanshu Madhu, and Hadonahalli Ramprakash. Advances in Breast Thermography. 10 2017.

Sebastien Mambou, Ondrej Krejcar, Petra Maresova, Ali Selamat, and Kamil Kuca. Breast cancer detection using infrared thermal imaging and a deep learning model. Sensors, 18:2799, 08 2018.

R. Marques. Segmentação automática das mamas em imagens térmicas, 2012.

Antony Morales, E. Kolosovas, Edgar Guevara, Mireya Maruris Reducindo, Alix Hernández, Manuel García, and Francisco Gonzalez. An automated method for the evaluation of breast cancer using infrared thermography. EXCLI Journal, 17:989–998, 10 2018.

L. Motta. Obtenção automática da região de interesse em termogramas frontais da mama para o auxílio à detecção precoce de doenças., 2010. Dissertação de Mestrado, Universidade Federal Fluminense, Instituto de Computação, Niterói, RJ, Brasil.

J. Oliveira. Extração automática de região de interesse em imagens térmicas laterais da mama., 2012. Dissertação de Mestrado, Universidade Federal Fluminense, Instituto de Computação, Niterói, RJ, Brasil.

Proeng. Image processing and image analyses applied to mastology., 2012. Disponível em: http://visual.ic.uff.br/en/proeng/. Acesso em: 10/03/2020.
Publicado
07/10/2020
CORREA, Thays; DE OLIVEIRA, Fabíola; BAFFA, Matheus; LATTARI, Lucas. Unsupervised Segmentation of Breast Infrared Images in Lateral View Using Histogram of Oriented Gradients. In: WORKSHOP DE VISÃO COMPUTACIONAL (WVC), 16. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 18-23. DOI: https://doi.org/10.5753/wvc.2020.13477.

Artigos mais lidos do(s) mesmo(s) autor(es)

Obs.: Esse plugin requer que pelo menos um plugin de estatísticas/relatórios esteja habilitado. Se o seu plugins de estatísticas oferece mais que uma métrica, então, por favor, também selecione uma métrica principal na página de configurações administrativas do site e/ou da revista.