Refine
Document Type
Way of publication
- Open Access (2)
Keywords
- Computer vision (1)
- DNA damage response (DDR) (1)
- Digital medicine (1)
- Eye movement disorders (1)
- Nystagmus (1)
- Precision medicine (1)
- Telemedicine (1)
- Videooculography (1)
- bioimage informatics (1)
- double-strand break (DSB) (1)
Institute
Resting in an upright position during daytime decreases downbeat nystagmus (DBN). When measured in brightness only, that is, without intermitting exposure to darkness, it does not make a significant difference whether patients have previously rested in brightness or in darkness. In real-world scenarios, people are often exposed to brightness and darkness intermittently. The aim of this study was to analyze whether resting in brightness or resting in darkness was associated with a lower post-resting DBN after intermitting exposures to brightness and darkness. Eight patients were recorded with three-dimensional video-oculography in brightness and darkness conditions, each following two 2-h resting intervals under either brightness or darkness resting conditions. The dependent variable was DBN intensity, measured in mean slow phase velocity. A repeated measures ANOVA with the factors measurement condition (brightness vs. darkness), resting condition (brightness vs. darkness), and time (after first vs. second resting interval) showed a significant effect for the factor resting condition, where previous resting in darkness was associated with a significantly lower DBN relative to previous resting in brightness (P < 0.01). The clinical relevance is to advise patients with DBN to rest in darkness.
Eye movement abnormalities are commonplace in neurological disorders. However, unaided eye movement assessments lack granularity. Although videooculography (VOG) improves diagnostic accuracy, resource intensiveness precludes its broad use. To bridge this care gap, we here validate a framework for smartphone video-based nystagmography capitalizing on recent computer vision advances.
Methods
A convolutional neural network was fine-tuned for pupil tracking using > 550 annotated frames: ConVNG. In a cross-sectional approach, slow-phase velocity of optokinetic nystagmus was calculated in 10 subjects using ConVNG and VOG. Equivalence of accuracy and precision was assessed using the “two one-sample t-test” (TOST) and Bayesian interval-null approaches. ConVNG was systematically compared to OpenFace and MediaPipe as computer vision (CV) benchmarks for gaze estimation.
Results
ConVNG tracking accuracy reached 9–15% of an average pupil diameter. In a fully independent clinical video dataset, ConVNG robustly detected pupil keypoints (median prediction confidence 0.85). SPV measurement accuracy was equivalent to VOG (TOST p < 0.017; Bayes factors (BF) > 24). ConVNG, but not MediaPipe, achieved equivalence to VOG in all SPV calculations. Median precision was 0.30°/s for ConVNG, 0.7°/s for MediaPipe and 0.12°/s for VOG. ConVNG precision was significantly higher than MediaPipe in vertical planes, but both algorithms’ precision was inferior to VOG.
Conclusions
ConVNG enables offline smartphone video nystagmography with an accuracy comparable to VOG and significantly higher precision than MediaPipe, a benchmark computer vision application for gaze estimation. This serves as a blueprint for highly accessible tools with potential to accelerate progress toward precise and personalized Medicine.
Alley-Cropping - Ein klima-adaptierbares Landnutzungssystem zur nachhaltigen Biomasseproduktion
(2008)
Open source bioimage informatic tools for the analysis of DNA damage and associated biomarkers
(2019)
Land nachhaltig nutzen
(2019)