At-Home Pupillometry using Smartphone Facial Identification Cameras

Abstract

With recent developments in medical and psychiatric research surrounding pupillary response, cheap and accessible pupillometers could enable medical benefits from early neurological disease detection to measurements of cognitive load. In this paper, we introduce a novel smartphone-based pupillometer to allow for future development in clinical research surrounding at-home pupil measurements. Our solution utilizes a NIR front-facing camera for facial recognition paired with the RGB selfie camera to perform tracking of absolute pupil dilation with sub-millimeter accuracy. In comparison to a gold standard pupillometer during a pupillary light reflex test, the smartphone-based system achieves a median MAE of 0.27mm for absolute pupil dilation tracking and a median error of 3.52% for pupil dilation change tracking. Additionally, we remotely deployed the system to older adults as part of a usability study that demonstrates promise for future smartphone deployments to remotely collect data in older, inexperienced adult users operating the system themselves.

Racially Fair Pupillometry Measurements for RGB Smartphone Cameras using the Far Red Spectrum

“…Researchers and clinicians commonly use this test to investigate a number of neurological conditions including traumatic brain injury, cognitive impairment, and substance use. The PLR test within the validation experiment demonstrates functionality across a range of pupil sizes and provides a comparable measurement to prior work 3,14,18 . The experiment and subject recruitment presented here are approved by the UC San Diego internal review board (IRB #200201).…”

“…For example, the current design assumes assisted measurements with one user performing a measurement on a second individual; however, modifications could be made to outfit the scope on to the front facing RGB camera to facilitate self measurements, where a user performs measurements on themselves. Prior works in smartphone pupillometry have demonstrated the usability of smartphone pupillometry in older adult users, suggesting possibilities for this type of technology within at-home deployments 14 .…”

“…One prior work successfully demonstrates accurate pupillometry utilizing the Near Infrared (NIR) Facial recognition cameras included in some smartphones 14 . Unfortunately, this NIR camera was previously only available in expensive phone lines and it is now phased out of most major smartphone brands including Google and Motorolla.…”

“…The key to accurate pupillometry is capturing images in which the pupil can be clearly differentiated from the iris. However, segmenting the pupil and the iris is difficult in visible light, especially for individuals with darker irises 1,14 . The pupil acts like an aperture allowing light to pass through to the back of the eye, where most of the light is absorbed, thus the pupil appears black.…”

“…Currently, the multi-thousand dollar cost of pupillometers restricts the use of pupillometry outside of high resource institutions even though, pupillometry has significant potential beyond clinical laboratories. Prior work demonstrates that pupillometry has potential for prognostic assessments from acute head injuries, at-home cognitive screening in older adults, or opioid testing 4,7,[13][14][15] . However, the lack of pupillometry resources contributes to a lack of research on at-home pupillometry tests, test retest reliability studies of novel pupil biomarkers, and high temporal resolution studies of multi-day or multi-week studies.…”