Correlation of mammographic and histopathological findings in patients submitted to mammotomy / Correlação de achados mamográficos e histopatológicos de pacientes submetidas a mamotomia

Objective: To correlate patients with BI-RADS 4 or 5 mammographic results submitted to mammotomy and compare these findings to histopathological ones. Method: We selected 111 patients with non-palpable breast lesions detected on mammography and who underwent mammotomy at Clínica de Oncologia e Mastologia de Natal. The samples were sent to the laboratory Dr. Getulio Sales, after x-ray of the pieces, and all patients had to use a titanium clip. Results: The prevalent age group was 41-50 years (40.5%); approximately 30.6% had a family history of breast cancer; among the patients selected, 97.3% had a BI-RADS 4 classification and 2.7%, a BI-RADS 5; with microcalcifications being the main reason for mammotomy indication in both cases. The distribution of benign and malignant lesions was 70 and 30%, respectively. The prevalent malignant lesion was ductal carcinoma in situ (58%). Clinical suspicion of malignancy according to BI-RADS 4 and 5 was statistically significant, p=0.018 [95%CI 0.28 (0.209­0.383)]. The degree of association verified through odds ratio showed that the BI-RADS 5 group had 72% less chance of having a benign lesion when compared to the BI-RADS 4 group. There were no reports of complications in patients submitted to mammotomy in the present study. Conclusion: Mammotomy proved to be a safe method to diagnose suspicious lesions (BI-RADS 4 and 5), and its results fit what is observed in the literature.

bjetivo: Correlacionar as pacientes com resultado mamográfico BI-RADS 4 ou 5 submetidas a mamotomia e comparar os achados com os encontrados na histopatologia. Método: Foram selecionadas 111 pacientes as quais apresentavam lesões mamárias não palpáveis detectadas na mamografia e que realizaram mamotomia na Clínica de Oncologia e Mastologia de Natal. As amostras foram enviadas para o laboratório Dr. Getulio Sales, após radiografia das peças, e todas as pacientes tiveram de colocar clipe de titânio. Resultados: A faixa etária predominante foi de 41­50 anos (40,5%); cerca de 30,6% possuía histórico familiar de câncer de mama; entre as selecionadas, 97,3% possuíam classificação 4 do BI-RADS e 2,7% tinham classificação 5, predominando, em ambos os casos, as microcalcificações como indicação de mamotomia. A distribuição entre lesões benignas e malignas foi de 70 e 30%, respectivamente. A prevalência de lesões malignas foi de carcinoma ductal in situ (58%). Houve significância estatística com relação à suspeição de malignidade de acordo com o BI-RADS 4 e 5, p=0,018 [IC95%0,28 (0,209­0,383)]. O grau de associação verificado por meio da odds ratio mostra que o grupo BI-RADS 5 tinha 72% menos chance de ser benigno quando comparado ao grupo BI-RADS 4. Não houve relato de complicações nas pacientes submetidas a mamotomia no presente estudo. Conclusão: A mamotomia mostrou-se um método seguro no diagnóstico de lesões suspeitas (BI-RADS 4 e 5), estando dentro do observado na literatura

Breast cancer diagnosis based on mammary thermography and extreme learning machines

Abstract Introduction Breast cancer is the most common cancer in women and one of the major causes of death from cancer among female around the world. The early detection and treatment are the major way to healing. The use of mammary thermography in Mastology is increasing as a complementary imaging technique to early detect lesions. Its use as a screening exam to identify breast disorders has been investigated. The aim of this study is to investigate the behavior of different classification methods while grouping the thermographic images into specific types of lesions. Methods To evaluate our proposal, we built classifiers based on artificial neural networks, decision trees, Bayesian classifiers, and Haralick and Zernike attributes. The image database is composed by thermographic images acquired at the University Hospital of the Federal University of Pernambuco. These images are clinically classified into the classes cyst, malignant and benign. Moments of Zernike and Haralick were used as attributes. Results Extreme Learning Machines (ELM) and Multilayer Perceptron networks (MLP) proved to be quite efficient classifiers for classification of breast lesions in thermographic images. Using 75% of the database for training, the maximum value obtained for accuracy was 73.38%, with a Kappa index of 0.6007. This result indicated to a sensitivity of 78% and specificity of 88%. The overall efficiency of the system was 83%. Conclusion ELM showed to be a promising classifier to be used in the differentiation of breast lesions in thermographic images, due to its low computational cost and robustness.