TY - JOUR
T1 - aEYE
T2 - A deep learning system for video nystagmus detection
AU - Wagle, Narayani
AU - Morkos, John
AU - Liu, Jingyan
AU - Reith, Henry
AU - Greenstein, Joseph
AU - Gong, Kirby
AU - Gangan, Indranuj
AU - Pakhomov, Daniil
AU - Hira, Sanchit
AU - Komogortsev, Oleg V.
AU - Newman-Toker, David E.
AU - Winslow, Raimond
AU - Zee, David S.
AU - Otero-Millan, Jorge
AU - Green, Kemar E.
N1 - Publisher Copyright:
Copyright © 2022 Wagle, Morkos, Liu, Reith, Greenstein, Gong, Gangan, Pakhomov, Hira, Komogortsev, Newman-Toker, Winslow, Zee, Otero-Millan and Green.
PY - 2022/8/11
Y1 - 2022/8/11
N2 - Background: Nystagmus identification and interpretation is challenging for non-experts who lack specific training in neuro-ophthalmology or neuro-otology. This challenge is magnified when the task is performed via telemedicine. Deep learning models have not been heavily studied in video-based eye movement detection. Methods: We developed, trained, and validated a deep-learning system (aEYE) to classify video recordings as normal or bearing at least two consecutive beats of nystagmus. The videos were retrospectively collected from a subset of the monocular (right eye) video-oculography (VOG) recording used in the Acute Video-oculography for Vertigo in Emergency Rooms for Rapid Triage (AVERT) clinical trial (#NCT02483429). Our model was derived from a preliminary dataset representing about 10% of the total AVERT videos (n = 435). The videos were trimmed into 10-sec clips sampled at 60 Hz with a resolution of 240 × 320 pixels. We then created 8 variations of the videos by altering the sampling rates (i.e., 30 Hz and 15 Hz) and image resolution (i.e., 60 × 80 pixels and 15 × 20 pixels). The dataset was labeled as “nystagmus” or “no nystagmus” by one expert provider. We then used a filtered image-based motion classification approach to develop aEYE. The model's performance at detecting nystagmus was calculated by using the area under the receiver-operating characteristic curve (AUROC), sensitivity, specificity, and accuracy. Results: An ensemble between the ResNet-soft voting and the VGG-hard voting models had the best performing metrics. The AUROC, sensitivity, specificity, and accuracy were 0.86, 88.4, 74.2, and 82.7%, respectively. Our validated folds had an average AUROC, sensitivity, specificity, and accuracy of 0.86, 80.3, 80.9, and 80.4%, respectively. Models created from the compressed videos decreased in accuracy as image sampling rate decreased from 60 Hz to 15 Hz. There was only minimal change in the accuracy of nystagmus detection when decreasing image resolution and keeping sampling rate constant. Conclusion: Deep learning is useful in detecting nystagmus in 60 Hz video recordings as well as videos with lower image resolutions and sampling rates, making it a potentially useful tool to aid future automated eye-movement enabled neurologic diagnosis.
AB - Background: Nystagmus identification and interpretation is challenging for non-experts who lack specific training in neuro-ophthalmology or neuro-otology. This challenge is magnified when the task is performed via telemedicine. Deep learning models have not been heavily studied in video-based eye movement detection. Methods: We developed, trained, and validated a deep-learning system (aEYE) to classify video recordings as normal or bearing at least two consecutive beats of nystagmus. The videos were retrospectively collected from a subset of the monocular (right eye) video-oculography (VOG) recording used in the Acute Video-oculography for Vertigo in Emergency Rooms for Rapid Triage (AVERT) clinical trial (#NCT02483429). Our model was derived from a preliminary dataset representing about 10% of the total AVERT videos (n = 435). The videos were trimmed into 10-sec clips sampled at 60 Hz with a resolution of 240 × 320 pixels. We then created 8 variations of the videos by altering the sampling rates (i.e., 30 Hz and 15 Hz) and image resolution (i.e., 60 × 80 pixels and 15 × 20 pixels). The dataset was labeled as “nystagmus” or “no nystagmus” by one expert provider. We then used a filtered image-based motion classification approach to develop aEYE. The model's performance at detecting nystagmus was calculated by using the area under the receiver-operating characteristic curve (AUROC), sensitivity, specificity, and accuracy. Results: An ensemble between the ResNet-soft voting and the VGG-hard voting models had the best performing metrics. The AUROC, sensitivity, specificity, and accuracy were 0.86, 88.4, 74.2, and 82.7%, respectively. Our validated folds had an average AUROC, sensitivity, specificity, and accuracy of 0.86, 80.3, 80.9, and 80.4%, respectively. Models created from the compressed videos decreased in accuracy as image sampling rate decreased from 60 Hz to 15 Hz. There was only minimal change in the accuracy of nystagmus detection when decreasing image resolution and keeping sampling rate constant. Conclusion: Deep learning is useful in detecting nystagmus in 60 Hz video recordings as well as videos with lower image resolutions and sampling rates, making it a potentially useful tool to aid future automated eye-movement enabled neurologic diagnosis.
KW - artificial intelligence
KW - deep learning
KW - dizziness
KW - eye movements
KW - machine learning
KW - nystagmus
KW - telemedicine
KW - vertigo
UR - http://www.scopus.com/inward/record.url?scp=85136924507&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136924507&partnerID=8YFLogxK
U2 - 10.3389/fneur.2022.963968
DO - 10.3389/fneur.2022.963968
M3 - Article
C2 - 36034311
AN - SCOPUS:85136924507
SN - 1664-2295
VL - 13
JO - Frontiers in Neurology
JF - Frontiers in Neurology
M1 - 963968
ER -