RESUMEN
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.
RESUMEN
The enteric nervous system (ENS) consists of an interconnected meshwork of neurons and glia residing within the wall of the gastrointestinal (GI) tract. While healthy GI function is associated with healthy ENS structure, defined by the normal distribution of neurons within ganglia of the ENS, a comprehensive understanding of normal neuronal distribution and ganglionic organization in the ENS is lacking. Current methodologies for manual enumeration of neurons parse only limited tissue regions and are prone to error, subjective bias, and peer-to-peer discordance. There is accordingly a need for robust, and objective tools that can capture and quantify enteric neurons within multiple ganglia over large areas of tissue. Here, we report on the development of an AI-driven tool, COUNTEN (COUNTing Enteric Neurons), which is capable of accurately identifying and enumerating immunolabeled enteric neurons, and objectively clustering them into ganglia. We tested and found that COUNTEN matches trained humans in its accuracy while taking a fraction of the time to complete the analyses. Finally, we use COUNTEN's accuracy and speed to identify and cluster thousands of ileal myenteric neurons into hundreds of ganglia to compute metrics that help define the normal structure of the ileal myenteric plexus. To facilitate reproducible, robust, and objective measures of ENS structure across mouse models, experiments, and institutions, COUNTEN is freely and openly available to all researchers.
