Deep learning (DL) has revolutionized the field of computer vision and image processing. In medical imaging, algorithmic solutions based on DL have been shown to achieve high performance on tasks that previously required medical experts. However, DL-based solutions for disease detection have been proposed without methods to quantify and control their uncertainty in a decision. In contrast, a physician knows whether she is uncertain about a case and will consult more experienced colleagues if needed. Here we evaluate drop-out based Bayesian uncertainty measures for DL in diagnosing diabetic retinopathy (DR) from fundus images and show that it captures uncertainty better than straightforward alternatives. Furthermore, we show that uncertainty informed decision referral can improve diagnostic performance. Experiments across different networks, tasks and datasets show robust generalization. Depending on network capacity and task/dataset difficulty, we surpass 85% sensitivity and 80% specificity as recommended by the NHS when referring 0−20% of the most uncertain decisions for further inspection. We analyse causes of uncertainty by relating intuitions from 2D visualizations to the high-dimensional image space. While uncertainty is sensitive to clinically relevant cases, sensitivity to unfamiliar data samples is task dependent, but can be rendered more robust.

Visible light synchronizes the human biological clock in the suprachiasmatic nuclei of the hypothalamus to the solar 24‐hour cycle. Short wavelengths, perceived as blue color, are the strongest synchronizing agent for the circadian system that keeps most biological and psychological rhythms internally synchronized. Circadian rhythm is important for optimum function of organisms and circadian sleep–wake disruptions or chronic misalignment often may lead to psychiatric and neurodegenerative illness. The beneficial effect on circadian synchronization, sleep quality, mood, and cognitive performance depends not only on the light spectral composition but also on the timing of exposure and its intensity. Exposure to blue light during the day is important to suppress melatonin secretion, the hormone that is produced by the pineal gland and plays crucial role in circadian rhythm entrainment. While the exposure to blue is important for keeping organism's wellbeing, alertness, and cognitive performance during the day, chronic exposure to low‐intensity blue light directly before bedtime, may have serious implications on sleep quality, circadian phase and cycle durations. This rises inevitably the need for solutions to improve wellbeing, alertness, and cognitive performance in today's modern society where exposure to blue light emitting devices is ever increasing.

In the eye, ultraviolet radiation (UVR) is not known to contribute to visual perception but to mainly damage multiple structures. UVR carries higher energy than visible light and high dose exposure to UVR causes direct cellular damage, which has an important role in the development of cancer. This review provides an overview on the most recent knowledge on the role of UVR in oxidative stress (OS) in relation to noncancer ocular pathologies: various corneal pathologies, cataract, glaucoma and age‐related macular degeneration. Possible OS signaling streams and mechanisms in the aging eye are discussed. Excessive exposure to UVR through live may seriously contribute to increase in OS of various eye tissues and thus lead to the advancement of serious ocular pathologies. Children are especially vulnerable to UVR because of their larger pupils and more transparent ocular media: up to 80% of a person's lifetime exposure to UVR is reached before the age of 18. Therefore, efficient everyday protection of the sensitive tissues of the eye by wearing of sunglasses, clear UVR‐blocking spectacles or contact lenses should be considered from early age on. Many initiatives are taken worldwide to inform and raise the population's awareness about these possible UVR hazards to the eye.

The prevalence of myopia is increasing extensively worldwide. The number of people with myopia in 2020 is predicted to be 2.6 billion globally, which is expected to rise up to 4.9 billion by 2050, unless preventive actions and interventions are taken. The number of individuals with high myopia is also increasing substantially and pathological myopia is predicted to become the most common cause of irreversible vision impairment and blindness worldwide and also in Europe. These prevalence estimates indicate the importance of reducing the burden of myopia by means of myopia control interventions to prevent myopia onset and to slow down myopia progression. Due to the urgency of the situation, the European Society of Ophthalmology decided to publish this update of the current information and guidance on management of myopia. The pathogenesis and genetics of myopia are also summarized and epidemiology, risk factors, preventive and treatment options are discussed in details.

Background: A case study is proposed to empirically test and discuss the eye-tracking status-quo hardware capabilities and limitations of an off-the-shelf virtual reality (VR) headset with embedded eye-tracking for at-home ready-to-go online usability in ophthalmology applications. Methods: The eye-tracking status-quo data quality of the HTC Vive Pro Eye is investigated with novel testing specific to objective online VR perimetry. Testing was done across a wide visual field of the head-mounted-display’s (HMD) screen and in two different moving conditions. A new automatic and low-cost Raspberry Pi system is introduced for VR temporal precision testing for assessing the usability of the HTC Vive Pro Eye as an online assistance tool for visual loss. Results: The target position on the screen and head movement evidenced limitations of the eye-tracker capabilities as a perimetry assessment tool. Temporal precision testing showed the system’s latency of 58.1 milliseconds (ms), evidencing its good potential usage as a ready-to-go online assistance tool for visual loss. Conclusions: The test of the eye-tracking data quality provides novel analysis useful for testing upcoming VR headsets with embedded eye-tracking and opens discussion regarding expanding future introduction of these HMDs into patients’ homes for low-vision clinical usability.

This paper documents the design, implementation and evaluation of the Unfolding Space Glove—an open source sensory substitution device. It transmits the relative position and distance of nearby objects as vibratory stimuli to the back of the hand and thus enables blind people to haptically explore the depth of their surrounding space, assisting with navigation tasks such as object recognition and wayfinding. The prototype requires no external hardware, is highly portable, operates in all lighting conditions, and provides continuous and immediate feedback—all while being visually unobtrusive. Both blind (n = 8) and blindfolded sighted participants (n = 6) completed structured training and obstacle courses with both the prototype and a white long cane to allow performance comparisons to be drawn between them. The subjects quickly learned how to use the glove and successfully completed all of the trials, though still being slower with it than with the cane. Qualitative interviews revealed a high level of usability and user experience. Overall, the results indicate the general processability of spatial information through sensory substitution using haptic, vibrotactile interfaces. Further research would be required to evaluate the prototype’s capabilities after extensive training and to derive a fully functional navigation aid from its features.