Análise das imagens termográficas mamárias para detecção de tumores

• Ano de defesa: 2019
• Autor(a) principal: Luz, Thais Gretis Rodrigues da
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Tecnológica Federal do Paraná; Curitiba; Brasil; Programa de Pós-Graduação em Engenharia Biomédica; UTFPR
• Palavras-chave em Português: Termografia médica; Mamas - Câncer - Diagnóstico; Diagnóstico por imagem; Análise de imagem; Mama - Doenças - Diagnóstico; Medical thermography; Breast - Cancer - Diagnosis; Diagnostic imaging; Image analysis; Breast - Diseases - Diagnosis; CNPQ::ENGENHARIAS::ENGENHARIA BIOMEDICA; Engenharia Biomédica
• Link de acesso: http://repositorio.utfpr.edu.br/jspui/handle/1/25011

Early breast cancer detection of plays an important role in improving survival rates. Thermography has been used and have presented promising results in helping the diagnosis of breast neoplasia, mainly because it is a noninvasive, painless, radiation-free or (contraindication) technique. This research aimed to develop an evaluation of breast thermograms in order to analyze the behavior of thermal distribution in tumor areas. Images of volunteers diagnosed with benign and malignant tumors diagnosed in a hospital specialized in the diagnosis and treatment of neoplasms were collected. The data collection environment was maintained with controlled temperature of 22◦C. A thermal camera (Fluke Ti400) was used to monitor and analyze images and temperature extremes in the breast region, in volunteers who presented the diagnosis confirmed by imaging tests (mammography, ultrasound and biopsy), after a cold stress protocol (cooling of the breasts by means of a gel bag with a temperature of 20◦C for 20 seconds), images being recorded for a period of 15 minutes. The analyses consisted of extraction of temperatures in the tumor region and regions symmetrically opposed to the tumor, for analyses of the thermal behavior of tumor tissue and, of healthy tissue around the tumor. Was used the R software. The results indicate that temperatures in tumor regions to have a higher accumulation of hot spots, even when compared to blood irrigation regions. Regarding the classification of malignant and benign tumors, it was observed that the temperatures around the malignant tumor were significantly higher compared to the environment of the benign tumor or healthy tissue.