Study Related to the Identification of Malignancy of Thyroid Nodules by Clinical Data and Infrared Images

• José Ramón González Montero UFF
• Aura Conci UFF

DOI: https://doi.org/10.5753/sbcas_estendido.2024.2247

Abstract

According to experts and medical literature, the thyroid gland, when healthy, and even benign nodules, tend to be less inflamed and active than malignant nodules, and consequently could exhibit different behavior regarding variations in skin surface temperature. This study analyzes parameters influencing the identification of thyroid nodules through infrared images, investigates the essential conditions of termography thyroid exams, and identifies patient and nodule characteristics that may affect their visualization in the infrared spectrum. For this purpose, infrared images, clinical and ultrasonographic data were collected from 151 patients with thyroid nodules, following a protocol developed in conjunction with the UFF Endocrinology Department, approved by the University Hospital Ethics Committee and registered in the Brazil platform of the Ministry of Health. Some of these patients have the malignancy of their nodules confirmed by post operative biopsy. Developments include heat transfer analyses, use of machine learning techniques, and deep learning. The results show the feasibility of using infrared images to assist in the diagnosis of thyroid nodules.

References

Borchartt, T. B., Conci, A., Lima, R. C., Resmini, R., and Sanchez, A. (2013). Breast thermography from an image processing viewpoint: A survey. Signal Processing, 93(10):2785–2803. Signal and Image Processing Techniques for Detection of Breast Diseases.

Comsol (2021). Comsol multiphysics®. Disponível em [link]. Acessado em 20/03/2021.

Damião, C. (2021). Avaliação da importância da termografia no auxílio à investigação diagnóstica de nódulos tireoidianos em pacientes acompanhados no HUAP-UFF. PhD thesis, Faculdade de Medicina / Universidade Federal Fluminense, Teses de Doutorado, Niterói, RJ, Brasil.

Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11(1):10–18.

Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4700–4708.

Weiss, K., Khoshgoftaar, T. M., and Wang, D. (2016). A survey of transfer learning. Journal of Big data, 3:1–40.