Evaluation of transfer learning of pre-trained CNNs applied to breast cancer detection on infrared images.

Breast cancer accounts for the highest number of female deaths worldwide. Early detection of the disease is essential to increase the chances of treatment and cure of patients. Infrared thermography has emerged as a promising technique for diagnosis of the disease due to its low cost and that it does not emit harmful radiation, and it gives good results when applied in young women. This work uses convolutional neural networks in a database of 440 infrared images of 88 patients, classifying them into two classes: normal and pathology. During the training of the networks, we use transfer learning of the following convolutional neural network architectures: AlexNet, GoogLeNet, ResNet-18, VGG-16, and VGG-19. Our results show the great potential of using deep learning techniques combined with infrared images in the aid of breast cancer diagnosis.

[1]  Wei Shi,et al.  Truncated-correlation photothermal coherence tomography derivative imaging modality for small animal in vivo early tumor detection. , 2019, Optics letters.

[2]  Gilmar Guimaraes,et al.  Influence analysis of thermophysical properties on temperature profiles on the breast skin surface , 2020 .

[3]  Anjan Gudigar,et al.  Computer-aided diagnosis for the identification of breast cancer using thermogram images: A comprehensive review , 2019, Infrared Physics & Technology.

[4]  Satish G. Kandlikar,et al.  Infrared imaging technology for breast cancer detection – Current status, protocols and new directions , 2017 .

[5]  G. Wishart,et al.  The accuracy of digital infrared imaging for breast cancer detection in women undergoing breast biopsy. , 2010, European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology.

[6]  Syed Muhammad Anwar,et al.  Medical Image Analysis using Convolutional Neural Networks: A Review , 2017, Journal of Medical Systems.

[7]  Aura Conci,et al.  A New Database for Breast Research with Infrared Image , 2014 .

[8]  Maurício Marengoni,et al.  Applying Artificial Neural Network for the Classification of Breast Cancer Using Infrared Thermographic Images , 2016, ICCVG.

[9]  J. V. Vargas,et al.  An infrared image based methodology for breast lesions screening , 2016 .

[10]  Saiful Islam,et al.  Cancer diagnosis in histopathological image: CNN based approach , 2019, Informatics in Medicine Unlocked.

[11]  Phoebe E. Freer,et al.  Mammographic breast density: impact on breast cancer risk and implications for screening. , 2015, Radiographics : a review publication of the Radiological Society of North America, Inc.

[12]  Sami Ekici,et al.  Breast cancer diagnosis using thermography and convolutional neural networks. , 2019, Medical hypotheses.

[13]  Khairul Munadi,et al.  A Study of Fine-Tuning CNN Models Based on Thermal Imaging for Breast Cancer Classification , 2019, 2019 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom).

[14]  A. Figueiredo,et al.  Estimation of thermal properties using only one surface by means of infrared thermography , 2019, Applied Thermal Engineering.

[15]  E. Y.-K. Ng,et al.  A review of thermography as promising non-invasive detection modality for breast tumor , 2009 .

[16]  Gilmar Guimaraes,et al.  Breast tumor localization using skin surface temperatures from a 2D anatomic model without knowledge of the thermophysical properties , 2019, Comput. Methods Programs Biomed..