abstract

• Infrared thermography is a technique that can detect anomalies in temperature patterns which can indicate some breast pathologies including breast cancer. One limitation of the method is the absence of standardised thermography interpretation procedures. Deep learning models have been used for pattern recognition and classification of objects and have been adopted as an adjunct methodology in medical imaging diagnosis. In this paper, the use of a deep convolutional neural network (CNN) with transfer learning is proposed to automatically classify thermograms into two classes (normal and abnormal). A population of 311 female subjects was considered analysing two approaches to test the CNN’s performance: one with a balanced class distribution and the second study in a typical screening cohort, with a low prevalence of abnormal thermograms. Results showed that the transfer-learned ResNet-101 model had a sensitivity of 92.3%25 and a specificity of 53.8%25, while with an unbalanced distribution the values were 84.6%25 and 65.3%25, respectively. These results suggest that the model presented in this work can classify abnormal thermograms with high sensitivity which validates the use of infrared thermography as an adjunct method for breast cancer screening. © 2021 Informa UK Limited, trading as Taylor %26 Francis Group.
• Infrared thermography is a technique that can detect anomalies in temperature patterns which can indicate some breast pathologies including breast cancer. One limitation of the method is the absence of standardised thermography interpretation procedures. Deep learning models have been used for pattern recognition and classification of objects and have been adopted as an adjunct methodology in medical imaging diagnosis. In this paper, the use of a deep convolutional neural network (CNN) with transfer learning is proposed to automatically classify thermograms into two classes (normal and abnormal). A population of 311 female subjects was considered analysing two approaches to test the CNN’s performance: one with a balanced class distribution and the second study in a typical screening cohort, with a low prevalence of abnormal thermograms. Results showed that the transfer-learned ResNet-101 model had a sensitivity of 92.3%25 and a specificity of 53.8%25, while with an unbalanced distribution the values were 84.6%25 and 65.3%25, respectively. These results suggest that the model presented in this work can classify abnormal thermograms with high sensitivity which validates the use of infrared thermography as an adjunct method for breast cancer screening. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

authors

• Flores J.L.
• González Contreras Francisco Javier
• Guevara Codina Edgar
• Kolosovas Machuca Eleazar Samuel
• Torres-Galván J.C.

publication date

• 2021-01-01

published in

• Quantitative InfraRed Thermography Journal  Journal

keywords

• breast cancer screening; Deep convolutional neural networks; infrared thermography; transfer learning Computer aided diagnosis; Convolution; Deep learning; Deep neural networks; Diseases; Medical imaging; Pattern recognition; Temperature measuring instruments; Thermography (imaging); Thermography (temperature measurement); Transfer learning; Breast cancer screening; Breast pathology; Class distributions; High sensitivity; Learning models; Pattern recognition and classification; Temperature patterns; Unbalanced distribution; Convolutional neural networks

Digital Object Identifier (DOI)

• 10.1080/17686733.2021.1918514

PubMed ID

start page

end page

volume

issue