Motion distractors perturb saccade programming later in time than static distractors.

The mechanism that reweights oculomotor vectors based on visual features is unclear. However, the latency of oculomotor visual activations gives insight into their antecedent featural processing. We compared the oculomotor processing time course of grayscale, task-irrelevant static and motion distractors during target selection by continuously measuring a battery of human saccadic behavioral metrics as a function of time after distractor onset. The motion direction was towards or away from the target and the motion speed was fast or slow. We compared static and motion distractors and observed that both distractors elicited curved saccades and shifted endpoints at short latencies (∼25 ms). After 50 ms, saccade trajectory biasing elicited by motion distractors lagged static distractor trajectory biasing by 10 ms. There were no such latency differences between distractor motion directions or motion speeds. This pattern suggests that additional processing of motion stimuli occurred prior to the propagation of visual information into the oculomotor system. We examined the interaction of distractor processing time (DPT) with two additional factors: saccadic reaction time (SRT) and saccadic amplitude. Shorter SRTs were associated with shorter DPT latencies of biased saccade trajectories. Both SRT and saccadic amplitude were associated with the magnitude of saccade trajectory biases.

U-Net-Based Segmentation of Current Imaging Biomarkers in OCT-Scans of Patients with Age Related Macular Degeneration.

Age-related macular degeneration (AMD) is the leading cause of blindness in the Western world. In this work, the non-invasive imaging technique spectral domain optical coherence tomography (SD-OCT) is used to acquire retinal images, which are then analyzed using deep learning techniques. The authors trained a convolutional neural network (CNN) using 1300 SD-OCT scans annotated by trained experts for the presence of different biomarkers associated with AMD. The CNN was able to accurately segment these biomarkers and the performance was further enhanced through transfer learning with weights from a separate classifier, trained on a large external public OCT dataset to distinguish between different types of AMD. Our model is able to accurately detect and segment AMD biomarkers in OCT scans, which suggests that it could be useful for prioritizing patients and reducing ophthalmologists' workloads.

Blood Vessel Segmentation Using U-Net for Glaucoma Diagnosis with Limited Data.

Glaucoma is one of the leading causes of blindness worldwide. Therefore, early detection and diagnosis are key to preserve full vision in patients. As part of the SALUS study, we create a blood vessel segmentation model based on U-Net. We trained U-Net on three different loss functions and used hyperparameter tuning to find their optimal hyperparameters for each loss function. The best models for each of the loss functions achieved an accuracy of over 93%, Dice scores around 83% and Intersection over Union scores over 70%. They each identify large blood vessels reliably and even recognize smaller blood vessels in the retinal fundus images and thus pave the way for improved glaucoma management.