RESUMO
Thyroid nodules are common, and their investigation is very important to exclude the possibility of cancer. The increase in blood vessels of malignant tumours may be related to local temperature augmentation detectable on the skin surface. The objective of this paper is to evaluate the feasibility of Infrared Thermography for cancer identification. For this purpose, two studies were performed. One used numerical modelling to simulate regional metabolic temperature propagation to evaluate whether a nodule is perceptible on the skin surface. A second study considered thyroid nodule identification by using convolutional neural networks (CNNs). First, variations in nodular size and fat thickness were investigated, showing that the fat layer has an important role in regional heat transfer. In the second study, the training process achieved accuracy of 96% for in-sample and 95% for validation. In the testing phase, 92% accuracy, 100% precision and 80% recall were achieved. Thus, the presented studies suggest the feasibility of using Infrared Thermography with the CNN Artificial Intelligence technique as additional information in the investigation of thyroid nodules for patients without a very thick subcutaneous fat layer.
Assuntos
Termografia/métodos , Nódulo da Glândula Tireoide/diagnóstico , Humanos , Raios Infravermelhos , Modelos Teóricos , Redes Neurais de Computação , Sensibilidade e Especificidade , Condutividade Térmica , Termografia/normasRESUMO
UNLABELLED: This cross-sectional study involves randomly selected men aged 50 to 99 years and postmenopausal women. Either central fat mass or peripheral fat mass were associated to osteoporosis or osteopenia independently from fat-free body mass and other confounding factors. INTRODUCTION: Obesity and osteoporosis are public health problems that probably share common pathophysiological mechanisms. The question if body fat mass, central or peripheral, is protective or harmful for osteoporosis or osteopenia is not completely resolved. This study aims to investigate the association between osteoporosis or osteopenia, and fat body mass (central and peripheral) independently from fat-free body mass, in men aged 50 to 99 years old and postmenopausal women randomly selected in the community. METHODS: This is a cross-sectional investigation with a random sample of registered population in Niterói Family Doctor Program (FDP), State of Rio de Janeiro, Brazil. Bone mineral density (BMD) and fat-free mass were assessed by dual X-ray absorptiometry (DXA). RESULTS: There was statistically significant bivariate association between bone loss with gender, age, skin color, alcohol consumption at risk dose, use of thiazide, fat-free body mass, and fat body mass (central and peripheral). In the multiple analysis of fat-free body mass, central and peripheral fat body mass showed an independent and protective effect on the presence of osteoporosis or osteopenia (p value <0.001). CONCLUSION: Since both obesity and osteoporosis are public health problems worldwide, strategies aimed at preventing both conditions should be encouraged during aging.