A Computational Method to Assist the Diagnosis of Breast Disease Using Dynamic Thermography.

Thiago Alves Elias Da Silva,Débora Christina Muchaluat-Saade,Aura Conci,Lincoln Faria Da Silva

doi:10.3390/s20143866

Thiago Alves Elias Da Silva, Débora Christina Muchaluat-Saade + Show 2 more

Open Access

https://doi.org/10.3390/s20143866

Copy DOI

Abstract

Breast cancer has been the second leading cause of cancer death among women. New techniques to enhance early diagnosis are very important to improve cure rates. This paper proposes and evaluates an image analysis method to automatically detect patients with breast benign and malignant changes (tumors). Such method explores the difference of Dynamic Infrared Thermography (DIT) patterns observed in patients’ skin. After obtaining the sequential DIT images of each patient, their temperature arrays are computed and new images in gray scale are generated. Then the regions of interest (ROIs) of those images are segmented and, from them, arrays of the ROI temperature are computed. Features are extracted from the arrays, such as the ones based on statistical, clustering, histogram comparison, fractal geometry, diversity indices and spatial statistics. Time series that are broken down into subsets of different cardinalities are generated from such features. Automatic feature selection methods are applied and used in the Support Vector Machine (SVM) classifier. In our tests, using a dataset of 68 images, 100% accuracy was achieved.

Highlights

Breast cancer is the most common type of cancer among women
In order to evaluate the method proposed in this work, some metrics were calculated from the obtained results
The results achieved are discussed and comparisons of the results achieved with the proposed method are made with other related studies of the literature for the diagnosis of breast diseases based on infrared images

Summary

Introduction

Breast cancer is the most common type of cancer among women. The World Health Organization (WHO) states that 2.1 million women are impacted by this disease each year and it causes approximately15% of all deaths among women [1]. Breast cancer is the most common type of cancer among women. The World Health Organization (WHO) states that 2.1 million women are impacted by this disease each year and it causes approximately. 15% of all deaths among women [1]. Some factors related to breast cancer development are well known (aging, women’s reproductive life, family history, alcohol consumption, obesity, physical inactivity and exposure to ionizing radiation). Early-stage disease survival can reach 98% in 5 years. Breast cancer screening aims at detecting asymptomatic tumors in order to reduce mortality from the disease and increase survival chances after diagnosis. Specific questions include determining who should be screened (risk stratification, the age to begin screening and to stop), and which method to use for screening

Objectives

Methods

Results

Discussion

Conclusion