Deep Convolutional Neural Networks for left ventricle segmentation.

Left ventricle (LV) segmentation is crucial for quantitative cardiac function analysis. Manual segmentation of the endocardium and epicardium is highly cumbersome; physicians limit delineation to the end-diastolic and end-systolic phases. A fully automated system could provide an analysis of cardiac morphology for all phases in a much shorter time. Most of the current LV segmentation methods are semi-automated and require error prone manual initialization. A fully-automated LV segmentation method would expedite the functional analysis of the LV, reduce subjectivity and improve patient experience. We automatically segment the LV wall in cardiac MRI images with a Deep Convolutional Neural Network (DCNN). This algorithm first calculates the probability of a pixel belonging to the LV wall or background and then generates a label based on those probabilities without manual initialization. We then compare these results to the results obtained with another DCNN initialization method using Gabor filters. With Gabor DCNN we obtain an accuracy of 0.97, specificity of 0.984, sensitivity of 0.841 and mean accuracy of 0.902. This shows that Gabor filters perform better than random filters in the DCNN for LV segmentation.

Molecular Detection of Hepatozoon canis in Dogs of Ardabil Province, Northwest of Iran.

Hepatozoon species are protozoan parasites that infect some animals such as birds, reptiles, amphibians, and carnivores. Previous studies performed on canine hepatozoonosis in Iran have never used molecular techniques for diagnosis of this disease. The main objective of the present study was to detect Hepatozoon canis in the blood of dogs using polymerase chain reaction (PCR) method and sequencing. A total of 104 blood samples were collected from dogs of Meshginshahr County (Ardabil Province), and DNA was extracted from blood samples by dint of DNG-plus Extraction Kit. Then, 18S rRNA gene was amplified by using the conventional PCR methods. PCR products yielded an amplicon of the approximate length of 897 bp for all the positive samples. Twenty-four out of the 104 (23.07%) samples were found to be positive for H. canis. This rate of infection is relatively high among dogs in Ardabil Province. Sequence analysis confirmed the molecular identity of 99% of the samples by comparison with GenBank profiles. This is the first report of molecular detection of H. canis from Iran.