Glaucoma is a group of eye diseases which can cause vision loss by damaging the optic nerve. Early glaucoma detection is key to preventing vision loss yet there is a lack of noticeable early symptoms. Colour fundus photography allows the optic disc (OD) to be examined to diagnose glaucoma. Typically, this is done by measuring the vertical cup-to-disc ratio (CDR); however, glaucoma is characterised by thinning of the rim asymmetrically in the inferior-superior-temporal-nasal regions in increasing order. Automatic delineation of the OD features has potential to improve glaucoma management by allowing for this asymmetry to be considered in the measurements. Here, we propose a new deep-learning-based method to segment the OD and optic cup (OC). The core of the proposed method is DenseNet with a fully-convolutional network, whose symmetric U-shaped architecture allows pixel-wise classification. The predicted OD and OC boundaries are then used to estimate the CDR on two axes for glaucoma diagnosis. We assess the proposed method's performance using a large retinal colour fundus dataset, outperforming state-of-the-art segmentation methods. Furthermore, we generalise our method to segment four fundus datasets from different devices without further training, outperforming the state-of-the-art on two and achieving comparable results on the remaining two.
This paper presents a sequence transcription approach for the automatic diacritization of Arabic text. A recurrent neural network is trained to transcribe undiacritized Arabic text with fully diacritized sentences. We use a deep bidirectional long short-term memory network that builds high-level linguistic abstractions of text and exploits longrange context in both input directions. This approach differs from previous approaches in that no lexical, morphological, or syntactical analysis is performed on the data before being processed by the net. Nonetheless, when the network is postprocessed with our error correction techniques, it achieves state-of-the-art performance, yielding an average diacritic and word error rates of 2.09 and 5.82 %, respectively, on samples from 11 books. For the LDC ATB3 benchmark, this approach reduces the diacritic error rate by 25 %, the word error rate by 20 %, and the last-letter diacritization error rate by 33 % over the best published results.
Abstract. Diabetic Macular Edema (DME) is a major cause of vision loss in diabetes. Its early detection and treatment is therefore a vital task in management of diabetic retinopathy. In this paper, we propose a new featurelearning approach for grading the severity of DME using color retinal fundus images. An automated DME diagnosis system based on the proposed featurelearning approach is developed to help early diagnosis of the disease and thus averts (or delays) its progression. It utilizes the convolutional neural networks (CNNs) to identify and extract features of DME automatically without any kind of user intervention. The developed prototype was trained and assessed by using an existing MESSIDOR dataset of 1200 images. The obtained preliminary results showed accuracy of (88.8 %), sensitivity (74.7%) and specificity (96.5 %). These results compare favorably to state-of-the-art findings with the added benefit of an automatic feature-learning approach rather than a time-consuming handcrafted approach.
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.