A Two-Level Food Classification System For People With Diabetes Mellitus Using Convolutional Neural Networks.

Accurate estimation of food's macronutrient content for people with Diabetes Mellitus (DM) is of great importance, as it determines postprandial insulin dosage. This paper introduces a classification system for food images that is adjusted to the nutritional needs of people with DM. A two-level image classification scheme, exploiting Convolutional Neural Networks (CNNs), is proposed, in order to classify an image in one of eight broad food categories with similar macronutrient content and then assign it to a specific food within that category. To this end, a visual dataset, namely NTUA-Food 2017, has been designed, consisting of 3248 images organized in eight broad food categories of totally 82 different foods. Moreover, a novel evaluation metric is proposed, which penalizes classification errors proportionally to the discrepancy in postprandial blood sugar levels between the actual and predicted class. The proposed system achieves 84.18% and 85.94% classification accuracy at the first and second level of classification, respectively, on the NTUA-Food 2017 dataset. The algorithm developed for the first level of classification on the NTUA-Food 2017 dataset improves classification accuracy on the benchmark Food Image Dataset (FID) to 97.08% outperforming previous approaches. The algorithm's mean error in terms of carbohydrate content estimation on the NTUA-Food 2017 dataset is less than 2 g per food serving.

Cirrhosis but not neutropenia is associated with the development of infection in patients with chronic hepatitis C undergoing treatment with pegylated interferon-alpha and ribavirin.

Peginterferon-alpha (PegIFNa) frequently causes neutropenia, mainly due to bone marrow suppression. The aim of this study was to explore factors that are associated with infections during antiviral treatment. We analysed data from 275 chronic hepatitis C (CHC) patients with compensated liver disease who underwent 318 courses of PegIFNa and ribavirin. Neutropenia was defined as neutrophils <1000 cells/µL. Mean leucocytes count significantly decreased from baseline to treatment nadir (7081 ± 2182 vs 3293 ± 1331 cells/µL, P < 0.001), while neutropenia was observed in 32% during treatment. Thirty-one infections were observed. The incidence rate for infection was assessed at 1.46 infections per 100 person-months of therapy. The hazard rate for infection did not correlate with the neutrophils' nadir or the decrease in white blood cells. In multivariate Cox's regression analysis, cirrhosis was the only factor that was significantly associated with the occurrence of infection. Our data show that the development of bacterial infections during treatment with PegIFNa and ribavirin in patients with compensated CHC is not associated with reduction or the nadir of white cells or neutrophil counts. Baseline cirrhosis is the only factor related with infection during treatment. The common practice of dose adjustment or discontinuation of interferon should be revised; careful assessment of liver damage before therapy and close monitoring during therapy are essential in all patients receiving interferon-based regimes, to minimize the detrimental consequences of infections.