Classification Models for Skin Tumor Detection Using Texture Analysis in Medical Images.

Medical images have made a great contribution to early diagnosis. In this study, a new strategy is presented for analyzing medical images of skin with melanoma and nevus to model, classify and identify lesions on the skin. Machine learning applied to the data generated by first and second order statistics features, Gray Level Co-occurrence Matrix (GLCM), keypoints and color channel information-Red, Green, Blue and grayscale images of the skin were used to characterize decisive information for the classification of the images. This work proposes a strategy for the analysis of skin images, aiming to choose the best mathematical classifier model, for the identification of melanoma, with the objective of assisting the dermatologist in the identification of melanomas, especially towards an early diagnosis.

Cryptococcal antigenemia prevalence and clinical data in HIV-infected patients from the reference centre at INI-FIOCRUZ, Rio de Janeiro, Southeast of Brazil.

Cryptococcal meningitis is a several disease common in late stage of HIV infection. Detection of cryptococcal antigen (CrAg) is an important for early diagnosis of this invasive mycosis. The pre-emptive treatment for isolated antigenemia prevents the onset of meningoencephalitis. Screening CrAg in patients with low CD4 count is cost-effective in countries with prevalence of antigenemia above 3%. However, in Brazil, the number of prevalence studies on cryptococcosis and HIV is insufficient. The objective of this study is to estimate the prevalence of CrAg and describe clinical characteristics from a cohort of patients followed at a reference center in Brazil. CrAg screening was performed in 89 inpatients with CD4 count ≤200 cells/mm3 or WHO stage III/IV from the National Institute of Infecttious Disease, Rio de Janeiro. Patients with isolated antigenemia received pre-emptive therapy with fluconazole and patients with meningoencephalitis were treated with Amphotericin B. Individuals were followed up for 12 months. Prevalence of serum CrAg was 11.23%, cryptococcal meningoencephalitis 6.74% and isolated antigenemia 4.81%. None of the patients with isolated antigenemia developed meningoencephalitis during the follow up. Signs and symptoms of meningoencephalitis were unspecific or absent. Our study suggests the need of CrAg screening in Brazil and highlights that lumbar puncture is mandatory in all individuals CrAg positive to exclude asymptomatic meningoencephalitis.