Visual interpretation of panoramic radiographs in dental students using eye‐tracking technology

Visual Behaviour During the Interpretation of Cone-Beam Computed Tomography Images of Traumatic Dental Injuries: An Eye-Tracking Study

BACKGROUND

This cross-sectional observational study aimed to investigate the visual attention patterns of postgraduate endodontic residents during the interpretation of cone-beam computed tomography (CBCT) scans for traumatic dental injuries (TDIs) using eye-tracking technology.

METHODS

A cohort of 10 residents who were recruited from King Abdulaziz University Dental Hospital (KAUDH) underwent interpretation of seven CBCT images of TDIs. Eye-tracking metrics, including dwell time, entry time, end time, and the number of revisits, were recorded and analyzed using nonparametric statistical tests.

RESULTS

Eye-tracking data revealed that patients with lateral luxation and extrusive luxation pathologies had the longest mean dwell times (1.82 seconds and 1.50 seconds, respectively). These findings were statistically significant compared to other pathologies (p<0.001). Conversely, horizontal root fractures and periapical radiolucency were identified more quickly by the participants (mean entry times of 6.60 seconds and 8.84 seconds, respectively).

CONCLUSIONS

The findings indicate variability in visual attention metrics depending on the type of TDI, suggesting that certain injuries may require more focused attention for accurate diagnosis. Specifically, lateral and extrusive luxation injuries attracted longer dwell times, possibly due to their unique diagnostic challenges. This research provides a basis for future studies aiming to optimize education and training related to CBCT interpretation of traumatic dental injuries.

Visual interpretation of clinical images among dental students using eye-tracking technology

BACKGROUND

Tele-consultations are increasingly used for screening and diagnosis. Only a few studies have assessed dental students' visual attention to clinical images.

AIM

To (i) determine dental students' gaze behavior, visual fixations, and diagnostic competence while viewing clinical images, and (ii) explore potential opportunities to strengthen the teaching-learning approaches.

DESIGN

Tobii Pro Nano-device captured the eye-tracking data for 65 dental undergraduate students in this cross-sectional study. The predetermined areas of interest (AOI) for all five clinical photographs were uploaded onto Tobii software. All participants used a think-aloud protocol with no restrictions to view time.

RESULTS

A total of 325 clinical pictures were analyzed, and the average view time was 189.25 ± 76.90 s. Most participants started at the center of the image (three frontal photos), spent a significant share of their view time on prominent findings, did not follow a systematic pattern, and exhibited diagnostic incompetence. Also, most participants followed a "Z" viewing pattern (oscillating movement from left to right) for the remaining two pictures.

CONCLUSIONS

Subjects frequently fixated on the prominent AOI, however, failed to make the correct diagnosis. Their view patterns revealed no sequential viewing. Therefore, emphasizing knowledge about common dental abnormalities and focusing on full coverage of clinical pictures can improve dental students' diagnostic competence and view patterns.

Combining public datasets for automated tooth assessment in panoramic radiographs

OBJECTIVE

Panoramic radiographs (PRs) provide a comprehensive view of the oral and maxillofacial region and are used routinely to assess dental and osseous pathologies. Artificial intelligence (AI) can be used to improve the diagnostic accuracy of PRs compared to bitewings and periapical radiographs. This study aimed to evaluate the advantages and challenges of using publicly available datasets in dental AI research, focusing on solving the novel task of predicting tooth segmentations, FDI numbers, and tooth diagnoses, simultaneously.

MATERIALS AND METHODS

Datasets from the OdontoAI platform (tooth instance segmentations) and the DENTEX challenge (tooth bounding boxes with associated diagnoses) were combined to develop a two-stage AI model. The first stage implemented tooth instance segmentation with FDI numbering and extracted regions of interest around each tooth segmentation, whereafter the second stage implemented multi-label classification to detect dental caries, impacted teeth, and periapical lesions in PRs. The performance of the automated tooth segmentation algorithm was evaluated using a free-response receiver-operating-characteristics (FROC) curve and mean average precision (mAP) metrics. The diagnostic accuracy of detection and classification of dental pathology was evaluated with ROC curves and F1 and AUC metrics.

RESULTS

The two-stage AI model achieved high accuracy in tooth segmentations with a FROC score of 0.988 and a mAP of 0.848. High accuracy was also achieved in the diagnostic classification of impacted teeth (F1 = 0.901, AUC = 0.996), whereas moderate accuracy was achieved in the diagnostic classification of deep caries (F1 = 0.683, AUC = 0.960), early caries (F1 = 0.662, AUC = 0.881), and periapical lesions (F1 = 0.603, AUC = 0.974). The model's performance correlated positively with the quality of annotations in the used public datasets. Selected samples from the DENTEX dataset revealed cases of missing (false-negative) and incorrect (false-positive) diagnoses, which negatively influenced the performance of the AI model.

CONCLUSIONS

The use and pooling of public datasets in dental AI research can significantly accelerate the development of new AI models and enable fast exploration of novel tasks. However, standardized quality assurance is essential before using the datasets to ensure reliable outcomes and limit potential biases.

Eye-Tracking Technology in Dentistry: A Review of Literature

This narrative review explores the integration of eye-tracking technology in dentistry, aiming to provide a comprehensive overview of its current applications and potential benefits. The review begins by elucidating the fundamental principles of eye tracking, encompassing the various eye-tracking methods and devices commonly used in dental research. It then delves into the role of eye tracking in dental education, where the technology offers a unique perspective on students' visual attention during training and skill acquisition. Moreover, the review examines how eye tracking can aid in assessing and improving dental practitioners' clinical performance, shedding light on areas of improvement and expertise. In patient care, the application of eye-tracking technology offers significant potential. By analyzing patients' gaze patterns and visual focus during dental procedures, clinicians can gain valuable insights into their experiences, identifying sources of anxiety and discomfort. This newfound understanding can pave the way for more patient-centric care and optimized treatment plans. The review also explores the application of eye-tracking technology in designing and evaluating dental interfaces and equipment. By assessing visual ergonomics and usability, researchers can develop user-friendly instruments that enhance dental professionals' workflow and efficiency. However, despite its promise, integrating eye tracking in dentistry is not without challenges. Technical limitations, data analysis complexities, and ethical considerations require careful attention to ensure this technology's ethical and responsible use. In conclusion, this narrative review highlights the growing significance of eye-tracking technology in dentistry. Its applications span dental education, clinical practice, and patient care, holding immense potential to revolutionize how dental procedures are conducted, evaluated, and experienced. Nevertheless, further research and collaboration between dental professionals and eye-tracking experts are necessary to unlock the technology's benefits and ensure its seamless integration into dental practices.

Visual Analysis of Panoramic Radiographs among Pediatric Dental Residents Using Eye-Tracking Technology: A Cross-Sectional Study

The aim of this cross-sectional study was to explore the eye tracking (ET) performance of postgraduate pediatric dental students in correctly detecting abnormalities in different sets of panoramic radiographs. This observational study recruited postgraduate pediatric dental students to evaluate seven panoramic radiographs. RED-m® SMI software (Sensomotoric Instruments, Teltow, Germany) was used to track the participants' eye movements as they looked at the radiographs. The data collected for areas of interest (AOIs) included revisit counts, fixation counts, fixation times, entry times, and dwell times. Univariate and bivariate analyses were conducted to summarize the participants' characteristics and ET measures. The overall percentage of correctly located AOIs was 71.7%. The residents had significantly more revisits and fixation counts in AOIs located in one sextant than in multiple sextants (p < 0.001). Similar patterns were observed for fixation and dwell times (p < 0.001), but not for entry time. Heatmaps showed that the highest density of fixations was on the AOIs and the residents fixated more on dentition than on bony structures. In single-sextant radiographs, residents had significantly more revisits and fixation counts for AOIs compared to those of multiple sextants. Residents had slower entry times and dwelled less on AOIs located in multiple sextant(s). The reported findings can direct dental educators to develop a standardized scan scheme of panoramic radiographs to minimize misdiagnosis.