Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen’s kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.
Branching morphogenesis generates a diverse array of epithelial patterns, including dichotomous and monopodial geometries. Dichotomous branching can be instructed by concentration gradients of epithelial-derived inhibitory morphogens, including transforming growth factor-β (TGFβ), which is responsible for ramification of the pubertal mammary gland. Here, we investigated the role of autocrine inhibitory morphogens in monopodial branching morphogenesis of the embryonic chicken lung. Computational modeling and experiments using cultured organ explants each separately revealed that monopodial branching patterns cannot be specified by a single epithelial-derived autocrine morphogen gradient. Instead, signaling via TGFβ1 and bone morphogenetic protein-4 (BMP4) differentially affect the rates of branching and growth of the airways. Allometric analysis revealed that development of the epithelial tree obeys power-law dynamics; TGFβ1 and BMP4 have distinct but reversible effects on the scaling coefficient of the power law. These data suggest that although autocrine inhibition cannot specify monopodial branching, inhibitory morphogens define the dynamics of lung morphogenesis.
We showed that both tumor spheres and MSLCs can be isolated from the same PNET specimen. PNET-MSLCs occupied a niche in the vicinity of the vasculature and could be a source of stroma for PNETs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.