Scanpath comparison in medical image reading skills of dental students

Castner, Nora; Kasneci, Enkelejda; Kübler, Thomas C.; Scheiter, Katharina; Richter, Juliane; Eder, Thérése; Hüttig, Fabian; Keutel, Constanze

doi:10.1145/3204493.3204550

Cited by 46 publications

(34 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in ScanMatch [Cristino et al 2010], classification of attentional disorder [Galgani et al 2009], multiple scanpath sequence alignment [Burch et al 2018], and expert and novice programmer classification [Busjahn et al 2015]. Castner et al [Castner et al 2018a] found incoming dental students with no prior training in radiograph interpretation could be classified from later semester students with 80% accuracy from Needleman-Wunsch similarity scores.…”

Section: Revisiting Visual Scanpath Comparison 21 Traditional Approamentioning

confidence: 99%

“…Kübler et al [Kübler et al 2014] developed a method -SubsMatchfor sequence comparison without AOI definitions, which uses a bag-of-words model and looks at the transitional behavior of subsequences. Castner et al [Castner et al 2018a] used these subsquence transitions from SubsMatch with an SVM Classifier [Kübler et al 2017] and found comparable results to sequence alignment with grid AOIs.…”

Section: Revisiting Visual Scanpath Comparison 21 Traditional Approamentioning

confidence: 99%

See 1 more Smart Citation

Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewing

Castner

Kuebler

Scheiter

et al. 2020

ACM Symposium on Eye Tracking Research and Applications

Self Cite

View full text Add to dashboard Cite

Modeling eye movement indicative of expertise behavior is decisive in user evaluation. However, it is indisputable that task semantics affect gaze behavior. We present a novel approach to gaze scanpath comparison that incorporates convolutional neural networks (CNN) to process scene information at the fixation level. Image patches linked to respective fixations are used as input for a CNN and the resulting feature vectors provide the temporal and spatial gaze information necessary for scanpath similarity comparison. We evaluated our proposed approach on gaze data from expert and novice dentists interpreting dental radiographs using a local alignment similarity score. Our approach was capable of distinguishing experts from novices with 93% accuracy while incorporating the image semantics. Moreover, our scanpath comparison using image patch features has the potential to incorporate task semantics from a variety of tasks.

show abstract

Section: Revisiting Visual Scanpath Comparison 21 Traditional Approamentioning

confidence: 99%

Section: Revisiting Visual Scanpath Comparison 21 Traditional Approamentioning

confidence: 99%

Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewing

Castner

Kuebler

Scheiter

et al. 2020

ACM Symposium on Eye Tracking Research and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, future research could not only focus on human observers of eye‐movement displays, but also on machine learning techniques (artificial intelligence). With such techniques, eye‐movement measures can be analyzed to identify aspects of performance such as cognitive load or workload (Appel et al, 2019; Halverson, Estepp, Christensen, & Monnin, 2012; Mussgnug, Singer, Lohmeyer, & Meboldt, 2017), performer expertise (Castner et al, 2018), strategic behavior (Eivazi & Bednarik, 2011), or task interest and curiosity (Baranes, Oudeyer, & Gottlieb, 2015). Future studies could investigate whether machine learning techniques are as good or better than humans at analyzing different aspects of performance (e.g., accuracy, confidence, effort) based on eye‐movement measures (or vice versa, whether humans are better than machine learning techniques at interpreting certain aspects of performance).…”

Section: Discussionmentioning

confidence: 99%

Inferring task performance and confidence from displays of eye movements

Emhardt

Wermeskerken

Scheiter

et al. 2020

Applied Cognitive Psychology

Self Cite

View full text Add to dashboard Cite

Eye movements reveal what is at the center of people's attention, which is assumed to coincide with what they are thinking about. Eye-movement displays (visualizations of a person's fixations superimposed onto the stimulus, for example, as dots or circles) might provide useful information for diagnosing that person's performance. However, making inferences about a person's task performance based on eyemovement displays requires substantial interpretation. Using graph-comprehension tasks, we investigated to what extent observers (N = 46) could make accurate inferences about a performer's multiple-choice task performance (i.e., chosen answer), confidence, and competence from displays of that person's eye movements. Observers' accuracy when judging which answer the performer chose was above chance level and was higher for displays reflecting confident performance. Observers were also able to infer performers' confidence from the eye-movement displays; moreover, their own task performance and perceived similarity with the performer affected their judgments of the other's competence.

show abstract

“…Scanpath comparison can be used to understand differences in eye movements between correct and incorrect solvers on physics problems [11]. Also, Novices and experts could be distinguished by the comparison of their scanpath [12] [13]. In addition, the scanpth similarity comparison might clinically help provide evidence diagnosing children with mild or moderate autism spectrum disorder (ASD) [14].…”

Section: Introductionmentioning

confidence: 99%

Detection of Depression and Its High-Risk Group using Scanpath Comparison Based on Semantic Information

Wang

Zheng

Huang

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Depression is a burdensome, recurring mental health disorder with high prevalence. The traditional detection of depression relies on structured interviews and questionnaires, which is labor-intensive and time-consuming. Also, the detection results are affected by subjective factors such as the subject's honesty and the psychologists' experiences. It lacks objective and quantitative metrics.Methods: To solve the above problems, we develop a convenient and objective system to detect depression and its high-risk group using eye-tracking data. In this system, subjects are required to answer the self-rating scale, and their scanpaths are recorded as a series of gaze points and saccades by the eye-tracking technology. Then, the similarity of scanpaths are compared and quantified with the guide of semantic information. Finally, according to the similarity scores of their scanpaths, the subjects are classified into three groups: normal, high-risk group, and depression.Results: The classification accuracy based on each item of the self-rating scale is 86.79% on average, while the detection accuracy is 95.63%.Conclusion: The experimental results show that (1)There are obvious eye movement differences among normal people, high-risk groups of depression, and depression patients while answering the questionnaire. (2)The early screening system for depression provides a novel and efficient solution to detect depression and its high-risk group by integrating traditional scale assessment and quantitative scanpath comparison algorithm.

show abstract

Scanpath comparison in medical image reading skills of dental students

Cited by 46 publications

References 36 publications

Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewing

Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewing

Inferring task performance and confidence from displays of eye movements

Detection of Depression and Its High-Risk Group using Scanpath Comparison Based on Semantic Information

Contact Info

Product

Resources

About