Thermalytix: An Advanced Artificial Intelligence Based Solution for Non-Contact Breast Screening

Authors: S. Sudhakar, Geetha Manjunath, Siva Teja Kakileti, Himanshu Madhu

Abstract:

Diagnosis of breast cancer at early stages has seen better clinical and survival outcomes. Survival rates in developing countries like India are very low due to accessibility and affordability issues of screening tests such as Mammography. In addition, Mammography is not much effective in younger women with dense breasts. This leaves a gap in current screening methods. Thermalytix is a new technique for detecting breast abnormality in a non-contact, non-invasive way. It is an AI-enabled computer-aided diagnosis solution that automates interpretation of high resolution thermal images and identifies potential malignant lesions. The solution is low cost, easy to use, portable and is effective in all age groups.  This paper presents the results of a retrospective comparative analysis of Thermalytix over Mammography and Clinical Breast Examination for breast cancer screening. Thermalytix was found to have better sensitivity than both the tests, with good specificity as well. In addition, Thermalytix identified all malignant patients without palpable lumps.

Keywords: Breast Cancer Screening, Radiology, Thermalytix, Artificial Intelligence, Thermography.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1316566

References:

[1] Gautherie, Michel, and Charles M. Gros. "Breast thermography and cancer risk prediction." Cancer 45.1 (1980): 51-56.
[2] Spitalier, H., Giraud, D., et al: Does Infrared Thermography Truly Have a Role in Present-Day Breast Cancer Management? Biomedical Thermology, Alan R. Liss New York, NY. pp. 269-278, 1982
[3] Report of the working group to review the national cancer institute breast cancer detection demonstration projects. J Natl Cancer Inst 62 (1979):641-709.
[4] Wishart, G. C., et al. "The accuracy of digital infrared imaging for breast cancer detection in women undergoing breast biopsy." European Journal of Surgical Oncology (EJSO) 36.6 (2010):
[5] Himanshu Madhu, Siva Teja Kakileti, Krithika Venkataramani, Sushmija Jabireddy, “Extraction of Medically Interpretable Features for Classification of Malignancy in Breast Thermography”. 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Orlando, USA, on August 17 - 20, 2016.
[6] Siva Teja Kakileti, Geetha Manjunath, Himanshu Madhu and H.V. Ramprakash, Advances in Breast Thermography, Book Chapter in the book "New Perspectives in Breast Imaging" edited by Arshad M. Malik, ISBN 978-953-51-3558-6, Print ISBN 978-953-51-3557-9, InTech, October 10, 2017.
[7] Links to Qualified Thermography Centres, International Academy of Clinical Thermology, http://www.iact-org.org/links.html