A transfer learning approach to identify Plasmodium in microscopic images.

Plasmodium parasites cause Malaria disease, which remains a significant threat to global health, affecting 200 million people and causing 400,000 deaths yearly. Plasmodium falciparum and Plasmodium vivax remain the two main malaria species affecting humans. Identifying the malaria disease in blood smears requires years of expertise, even for highly trained specialists. Literature studies have been coping with the automatic identification and classification of malaria. However, several points must be addressed and investigated so these automatic methods can be used clinically in a Computer-aided Diagnosis (CAD) scenario. In this work, we assess the transfer learning approach by using well-known pre-trained deep learning architectures. We considered a database with 6222 Region of Interest (ROI), of which 6002 are from the Broad Bioimage Benchmark Collection (BBBC), and 220 were acquired locally by us at Fundação Oswaldo Cruz (FIOCRUZ) in Porto Velho Velho, Rondônia-Brazil, which is part of the legal Amazon. We exhaustively cross-validated the dataset using 100 distinct partitions with 80% train and 20% test for each considering circular ROIs (rough segmentation). Our experimental results show that DenseNet201 has a potential to identify Plasmodium parasites in ROIs (infected or uninfected) of microscopic images, achieving 99.41% AUC with a fast processing time. We further validated our results, showing that DenseNet201 was significantly better (99% confidence interval) than the other networks considered in the experiment. Our results support claiming that transfer learning with texture features potentially differentiates subjects with malaria, spotting those with Plasmodium even in Leukocytes images, which is a challenge. In Future work, we intend scale our approach by adding more data and developing a friendly user interface for CAD use. We aim at aiding the worldwide population and our local natives living nearby the legal Amazon's rivers.

Peripheral arterial disease in heterozygous familial hypercholesterolemia.

BACKGROUND: Familial hypercholesterolemia is characterized by elevated plasma cholesterol and early coronary arterial disease onset. However, few studies investigated the association of heterozygous familial hypercholesterolemia with peripheral arterial disease. METHODS: In a cross sectional study 202 heterozygous familial hypercholesterolemia patients (91% confirmed by molecular diagnosis) were compared to 524 normolipidemic controls. Peripheral arterial disease was diagnosed by ankle-brachial index values ≤0.90. RESULTS: Compared with controls, familial hypercholesterolemia patients were older, more often female, with higher rates of hypertension, diabetes, previous coronary disease and higher total cholesterol levels. Smoking (previous and former) was more common among controls. The prevalence of peripheral arterial disease was 17.3 and 2.3% respectively in familial hypercholesterolemia and controls (p < 0.001). Results persisted after matching familial hypercholesterolemia and controls by a propensity score. Regression analyses demonstrated that age (odds ratio- OR = 1.03 95% CI 1.00-1.05, p = 0.033), previous cardiovascular disease (OR = 3.12 CI 95% 1.56-6.25, p = 0.001) and familial hypercholesterolemia diagnosis (OR = 5.55 CI 95% 2.69-11.44, p< 0.001) were independently associated with peripheral arterial disease. Among familial hypercholesterolemia patients, age (OR 1.05, 95% CI 1.02-1.09, p = 0.005), intermittent claudication (OR 6.32, 95% CI 2.60-15.33, p< 0.001) and smoking (OR 2.44, 95% CI 1.08-5.52, p = 0.032) were associated with peripheral arterial disease. CONCLUSIONS: Peripheral arterial disease is more frequent in familial hypercholesterolemia than in normolipidemic subjects and it should routine screened in these individuals even if asymptomatic. However, its role as predictor of cardiovascular events needs to be ascertained prospectively.