Search

Background: Around 30% of nonexudative macular neovascularizations exudate within 2 years from diagnosis in patients with age-related macular degeneration. The aim of this study is to develop a deep learning classifier based on optical coherence tomography (OCT) and OCT angiography (OCTA) to identify nonexudative macular neovascularizations at risk of exudation., Methods: Patients with age-related macular degeneration showing OCTA and fluorescein angiography-documented nonexudative macular neovascularization with a 2-year minimum imaging follow-up were retrospectively selected. Patients showing OCT B-scan-documented macular neovascularization exudation within the first 2 years formed the EX GROUP while the others formed the QU GROUP. ResNet-101, Inception-ResNet-v2, and DenseNet-201 were independently trained on OCTA and OCT B-scan images. Combinations of the six models were evaluated with major and soft voting techniques., Results: Eighty-nine eyes of 89 patients with a follow-up of 5.7 ± 1.5 years were recruited (35 EX GROUP and 54 QU GROUP). Inception-ResNet-v2 was the best performing among the three single convolutional neural networks. The major voting model resulting from the association of the three different convolutional neural networks resulted in an improvement of performance both for OCTA and OCT B-scan (both significantly higher than human graders' performance). The soft voting model resulting from the combination of OCTA and OCT B-scan-based major voting models showed a testing accuracy of 94.4%. Peripheral arcades and large vessels on OCTA en face imaging were more prevalent in the QU GROUP., Conclusion: Artificial intelligence shows high performances in identifications of nonexudative macular neovascularizations at risk for exudation within the first 2 years of follow-up, allowing better customization of follow-up timing and avoiding treatment delay. Better results are obtained with the combination of OCTA and OCT B-scan image analysis.

Initial stages of Best vitelliform macular dystrophy (BVMD) and adult vitelliform macular dystrophy (AVMD) harbor similar blue autofluorescence (BAF) and optical coherence tomography (OCT) features. Nevertheless, BVMD is characterized by a worse final stage visual acuity (VA) and an earlier onset of critical VA loss. Currently, differential diagnosis requires an invasive and time-consuming process including genetic testing, electrooculography (EOG), full field electroretinogram (ERG), and visual field testing. The aim of our study was to automatically classify OCT and BAF images from stage II BVMD and AVMD eyes using a deep learning algorithm and to identify an image processing method to facilitate human-based clinical diagnosis based on non-invasive tests like BAF and OCT without the use of machine-learning technology. After the application of a customized image processing method, OCT images were characterized by a dark appearance of the vitelliform deposit in the case of BVMD and a lighter inhomogeneous appearance in the case of AVMD. By contrast, a customized method for processing of BAF images revealed that BVMD and AVMD were characterized respectively by the presence or absence of a hypo-autofluorescent region of retina encircling the central hyperautofluorescent foveal lesion. The human-based evaluation of both BAF and OCT images showed significantly higher correspondence to ground truth reference when performed on processed images. The deep learning classifiers based on BAF and OCT images showed around 90% accuracy of classification with both processed and unprocessed images, which was significantly higher than human performance on both processed and unprocessed images. The ability to differentiate between the two entities without recurring to invasive and expensive tests may offer a valuable clinical tool in the management of the two diseases., (© 2022. The Author(s).)

Ancient undeciphered scripts present problems of different nature, not just tied to linguistic identification. The undeciphered Cypro-Minoan script from second millennium BCE Cyprus, for instance, currently does not have a standardized, definitive inventory of signs, and, in addition, stands divided into three separate subgroups (CM1, CM2, CM3), which have also been alleged to record different languages. However, this state of the art is not consensually accepted by the experts. In this article, we aim to apply a method that can aid to shed light on the tripartite division, to assess if it holds up against a multi-pronged, multi-disciplinary approach. This involves considerations linked to paleography (shapes of individual signs) and epigraphy (writing style tied to the support used), and crucially, deep learning-based strategies. These automatic methods, which are widely adopted in many fields such as computer vision and computational linguistics, allow us to look from an innovative perspective at the specific issues presented by ancient, poorly understood scripts in general, and Cypro-Minoan in particular. The usage of a state-of-the-art convolutional neural model that is unsupervised, and therefore does not use any prior knowledge of the script, is still underrepresented in the study of undeciphered writing systems, and helps to investigate the tripartite division from a fresh standpoint. The conclusions we reached show that: 1. the use of different media skews to a large extent the uniformity of the sign shapes; 2. the application of several neural techniques confirm this, since they highlight graphic proximity among signs inscribed on similar supports; 3. multi-stranded approaches prove to be a successful tool to investigate ancient scripts whose language is still unidentified. More crucially, these aspects, together, point in the same direction, namely the validation of a unitary, single Cypro-Minoan script, rather than the current division into three subgroups., Competing Interests: The authors have declared that no competing interests exist.