Radiologists' Gaze Characterization During Lung Nodule Search in Thoracic CT

Machado, Marlene; Aresta, Guilherme; Leitão, Patrícia; Carvalho, A.; Rodrigues, Márcio; Ramos, Isabel; Cunha, António; Campilho, Aurélio

doi:10.1109/itcgi.2018.8602697

Cited by 5 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In CXR, experts viewed images in long sweeps with greater average fixation distance 16 . This was similar in CT viewing where experts demonstrated fewer analysis patterns and fixation clusters 21,31 . In CT, experts exhibited driller (observers that focus on one region of the lung at a time while scrolling through image stacks) characteristics while novice readers were typically scanners (scanning across one slice of a CT before moving on to the next slice) 22 .…”

Section: Thematic Findingsmentioning

confidence: 91%

“…16 This was similar in CT viewing where experts demonstrated fewer analysis patterns and fixation clusters. 21,31 In CT, experts exhibited driller (observers that focus on one region of the lung at a time while scrolling through image stacks) characteristics while novice readers were typically scanners (scanning across one slice of a CT before moving on to the next slice). 22 Drillers had on average more experience in CT chest viewing of around 45 cases per week compared to scanners who averaged 20 cases per week.…”

Section: Thematic Findings Functional Visual Field and The Satisfacti...mentioning

confidence: 99%

“…22 Experts' had greater distance between fixations and made 5% fewer search errors. 22,27 In addition, experts had faster viewing times, larger sweeps of visual search 16 and focused on the lung apices 31 while na€ ıve and non-expert viewers searched regions of the lungs with low probability of containing a lung nodule. 27 Although the viewing style demonstrated by experts is beneficial to the efficient detection of a nodule it does not aid in satisfaction of search and the identification of other comorbidities that could be present in CXRs.…”

Section: Thematic Findings Functional Visual Field and The Satisfacti...mentioning

confidence: 99%

See 2 more Smart Citations

The cognitive and perceptual processes that affect observer performance in lung cancer detection: a scoping review

Luecht

Reed

2021

J of Medical Radiation Sci

View full text Add to dashboard Cite

Introduction: Early detection of malignant pulmonary nodules through screening has been shown to reduce lung cancer-related mortality by 20%. However, perceptual and cognitive factors that affect nodule detection are poorly understood. This review examines the cognitive and visual processes of various observers, with a particular focus on radiologists, during lung nodule detection. Methods: Four databases (Medline, Embase, Scopus and PubMed) were searched to extract studies on eye-tracking in pulmonary nodule detection. Studies were included if they used eye-tracking to assess the search and detection of lung nodules in computed tomography or 2D radiographic imaging. Data were charted according to identified themes and synthesised using a thematic narrative approach. Results: The literature search yielded 25 articles and five themes were discovered: 1functional visual field and satisfaction of search, 2expert search patterns, 3error classification through dwell time, 4the impact of the viewing environment and 5the effect of prevalence expectation on search. Functional visual field reduced to 2.7°in 3D imaging compared to 5°in 2D radiographs. Although greater visual coverage improved nodule detection, incomplete search was not responsible for missed nodules. Most radiological errors during lung nodule detection were decisionmaking errors (30%-45%). Dwell times associated with false-positive (FP) decisions informed feedback systems to improve diagnosis. Interruptions did not influence diagnostic performance; however, it increased viewing time by 8% and produced a 23.1% search continuation accuracy. Comparative scanning was found to increase the detection of low contrast nodules. Prevalence expectation did not directly affect diagnostic accuracy; however, decisionmaking time increased by 2.32 seconds with high prevalence expectations. Conclusion:Visual and cognitive factors influence pulmonary nodule detection. Insights gained from eye-tracking can inform advancements in lung screening. Further exploration of eye-tracking in lung screening, particularly with lowdose computed tomography (LDCT), will benefit the future of lung cancer screening.

show abstract

Section: Thematic Findingsmentioning

confidence: 91%

Section: Thematic Findings Functional Visual Field and The Satisfacti...mentioning

confidence: 99%

Section: Thematic Findings Functional Visual Field and The Satisfacti...mentioning

confidence: 99%

See 1 more Smart Citation

The cognitive and perceptual processes that affect observer performance in lung cancer detection: a scoping review

Luecht

Reed

2021

J of Medical Radiation Sci

View full text Add to dashboard Cite

show abstract

“…Eyetracking was performed during manual annotation to record the radiologists' gaze [16]. The screen coordinates of the radiologists' gaze were recorded at a frequency of 90Hz together with the display settings of the graphical interface.…”

Section: B Manual Annotation Processmentioning

confidence: 99%

LNDb: A Lung Nodule Database on Computed Tomography

Pedrosa¹,

Aresta²,

Ferreira³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Lung cancer is the deadliest type of cancer worldwide and late detection is the major factor for the low survival rate of patients. Low dose computed tomography has been suggested as a potential screening tool but manual screening is costly, time-consuming and prone to variability. This has fuelled the development of automatic methods for the detection, segmentation and characterisation of pulmonary nodules but its application to clinical routine is challenging. In this study, a new database for the development and testing of pulmonary nodule computer-aided strategies is presented which intends to complement current databases by giving additional focus to radiologist variability and local clinical reality. Stateof-the-art nodule detection, segmentation and characterization methods are tested and compared to manual annotations as well as collaborative strategies combining multiple radiologists and radiologists and computer-aided systems. It is shown that state-of-the-art methodologies can determine a patient's followup recommendation as accurately as a radiologist, though the nodule detection method used shows decreased performance in this database.

show abstract