Automatic Recording of the Target Location During Smooth Pursuit Eye Movement Testing Using Video-Oculography and Deep Learning-Based Object Detection

Eye Tracking in Optometry: A Systematic Review

This systematic review examines the use of eye-tracking devices in optometry, describing their main characteristics, areas of application and metrics used. Using the PRISMA method, a systematic search was performed of three databases. The search strategy identified 141 reports relevant to this topic, indicating the exponential growth over the past ten years of the use of eye trackers in optometry. Eye-tracking technology was applied in at least 12 areas of the field of optometry and rehabilitation, the main ones being optometric device technology, and the assessment, treatment, and analysis of ocular disorders. The main devices reported on were infrared light-based and had an image capture frequency of 60 Hz to 2000 Hz. The main metrics mentioned were fixations, saccadic movements, smooth pursuit, microsaccades, and pupil variables. Study quality was sometimes limited in that incomplete information was provided regarding the devices used, the study design, the methods used, participants' visual function and statistical treatment of data. While there is still a need for more research in this area, eye-tracking devices should be more actively incorporated as a useful tool with both clinical and research applications. This review highlights the robustness this technology offers to obtain objective information about a person's vision in terms of optometry and visual function, with implications for improving visual health services and our understanding of the vision process.

Deep learning for real-time auxiliary diagnosis of pancreatic cancer in endoscopic ultrasonography

In recent year, many deep learning have been playing an important role in the detection of cancers. This study aimed to real-timely differentiate a pancreatic cancer (PC) or a non-pancreatic cancer (NPC) lesion via endoscopic ultrasonography (EUS) image. A total of 1213 EUS images from 157 patients (99 male, 58 female) with pancreatic disease were used for training, validation and test groups. Before model training, regions of interest (ROIs) were manually drawn to mark the PC and NPC lesions using Labelimage software. Yolov5m was used as the algorithm model to automatically distinguish the presence of pancreatic lesion. After training the model based on EUS images using YOLOv5, the parameters achieved convergence within 300 rounds (GIoU Loss: 0.01532, Objectness Loss: 0.01247, precision: 0.713 and recall: 0.825). For the validation group, the mAP0.5 was 0.831, and mAP@.5:.95 was 0.512. In addition, the receiver operating characteristic (ROC) curve analysis showed this model seemed to have a trend of more AUC of 0.85 (0.665 to 0.956) than the area under the curve (AUC) of 0.838 (0.65 to 0.949) generated by physicians using EUS detection without puncture, although pairwise comparison of ROC curves showed that the AUC between the two groups was not significant (z= 0.15, p = 0.8804). This study suggested that the YOLOv5m would generate attractive results and allow for the real-time decision support for distinction of a PC or a NPC lesion.

Analysis of smooth pursuit eye movements in a clinical context by tracking the target and eyes

In the evaluation of smooth pursuit eye movements (SPEMs), recording the stimulus onset time is mandatory. In the laboratory, the stimulus onset time is recorded by electrical signal or programming, and video-oculography (VOG) and the visual stimulus are synchronized. Nevertheless, because the examiner must manually move the fixation target, recording the stimulus onset time is challenging in daily clinical practice. Thus, this study aimed to develop an algorithm for evaluating SPEMs while testing the nine-direction eye movements without recording the stimulus onset time using VOG and deep learning–based object detection (single-shot multibox detector), which can predict the location and types of objects in a single image. The algorithm of peak fitting–based detection correctly classified the directions of target orientation and calculated the latencies and gains within the normal range while testing the nine-direction eye movements in healthy individuals. These findings suggest that the algorithm of peak fitting–based detection has sufficient accuracy for the automatic evaluation of SPEM in clinical settings.