Multitask Learning for Activity Detection in Neovascular Age-Related Macular Degeneration.

Purpose: The purpose of this study was to provide a comparison of performance and explainability of a multitask convolutional deep neuronal network to single-task networks for activity detection in neovascular age-related macular degeneration (nAMD).

Methods: From 70 patients (46 women and 24 men) who attended the University Eye Hospital Tübingen, 3762 optical coherence tomography B-scans (right eye = 2011 and left eye = 1751) were acquired with Heidelberg Spectralis, Heidelberg, Germany. B-scans were graded by a retina specialist and an ophthalmology resident, and then used to develop a multitask deep learning model to predict disease activity in neovascular age-related macular degeneration along with the presence of sub- and intraretinal fluid.

Clinical validation of saliency maps for understanding deep neural networks in ophthalmology.

Deep neural networks (DNNs) have achieved physician-level accuracy on many imaging-based medical diagnostic tasks, for example classification of retinal images in ophthalmology. However, their decision mechanisms are often considered impenetrable leading to a lack of trust by clinicians and patients. To alleviate this issue, a range of explanation methods have been proposed to expose the inner workings of DNNs leading to their decisions.

Expert-validated estimation of diagnostic uncertainty for deep neural networks in diabetic retinopathy detection.

Deep learning-based systems can achieve a diagnostic performance comparable to physicians in a variety of medical use cases including the diagnosis of diabetic retinopathy. To be useful in clinical practice, it is necessary to have well calibrated measures of the uncertainty with which these systems report their decisions. However, deep neural networks (DNNs) are being often overconfident in their predictions, and are not amenable to a straightforward probabilistic treatment.

Photodynamic therapy with double duration for circumscribed choroidal haemangioma: functional and anatomical results based on initial parameters.

Importance: Pre-treatment symptoms longer than 12 months and foveal cystoid changes are indicators for poor anatomical and functional outcome after photodynamic therapy (PDT).

Background: To evaluate the prognostic factors on the effectiveness of PDT with double duration for treatment of exudative circumscribed choroidal haemangioma.

Design: Retrospective study.

[Chronic central serous chorioretinopathy (cCSC): differential diagnosis to choroidal neovascularisation (CNV) secondary to age-related macular degeneration (AMD)].

Central neurosensory detachments (NSD) with time-dependent height constitute a disease called central serous chorioretinopathy (CSC), if not arising from uveitis, choroidal neovascularisations (CNV) or leaking retinal vessels. In 10 % of these patients, CSC develops into a chronic disease with recurrent NSD, atrophy of photoreceptors and severe drop in visual acuity. This review article summarises recent progress in understanding this disease and its appearance in funduscopy, FLA, ICG, OCT, autofluorescence as well as its progress, therapy and possible development into secondary CNV.