Artificial Intelligence for the Analysis of Workload-Related Changes in Radiologists' Gaze Patterns
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Artificial Intelligence for the Analysis of Workload-Related Changes in Radiologists' Gaze Patterns. / Pershin, Ilya; Kholiavchenko, Maksim; Maksudov, Bulat; Mustafaev, Tamerlan; Ibragimova, Dilyara; Ibragimov, Bulat.
In: IEEE Journal of Biomedical and Health Informatics, Vol. 26, No. 9, 2022, p. 4541-4550.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Artificial Intelligence for the Analysis of Workload-Related Changes in Radiologists' Gaze Patterns
AU - Pershin, Ilya
AU - Kholiavchenko, Maksim
AU - Maksudov, Bulat
AU - Mustafaev, Tamerlan
AU - Ibragimova, Dilyara
AU - Ibragimov, Bulat
N1 - Publisher Copyright: © 2013 IEEE.
PY - 2022
Y1 - 2022
N2 - Around 60-80% of radiological errors are attributed to overlooked abnormalities, the rate of which increases at the end of work shifts. In this study, we run an experiment to investigate if artificial intelligence (AI) can assist in detecting radiologists' gaze patterns that correlate with fatigue. A retrospective database of lung X-ray images with the reference diagnoses was used. The X-ray images were acquired from 400 subjects with a mean age of 49 ± 17, and 61% men. Four practicing radiologists read these images while their eye movements were recorded. The radiologists passed a series of concentration tests at prearranged breaks of the experiment. A U-Net neural network was adapted to annotate lung anatomy on X-rays and calculate coverage and information gain features from the radiologists' eye movements over lung fields. The lung coverage, information gain, and eye tracker-based features were compared with the cumulative work done (CDW) label for each radiologist. The gaze-traveled distance, X-ray coverage, and lung coverage statistically significantly (p < 0.01) deteriorated with cumulative work done (CWD) for three out of four radiologists. The reading time and information gain over lungs statistically significantly deteriorated for all four radiologists. We discovered a novel AI-based metric blending reading time, speed, and organ coverage, which can be used to predict changes in the fatigue-related image reading patterns.
AB - Around 60-80% of radiological errors are attributed to overlooked abnormalities, the rate of which increases at the end of work shifts. In this study, we run an experiment to investigate if artificial intelligence (AI) can assist in detecting radiologists' gaze patterns that correlate with fatigue. A retrospective database of lung X-ray images with the reference diagnoses was used. The X-ray images were acquired from 400 subjects with a mean age of 49 ± 17, and 61% men. Four practicing radiologists read these images while their eye movements were recorded. The radiologists passed a series of concentration tests at prearranged breaks of the experiment. A U-Net neural network was adapted to annotate lung anatomy on X-rays and calculate coverage and information gain features from the radiologists' eye movements over lung fields. The lung coverage, information gain, and eye tracker-based features were compared with the cumulative work done (CDW) label for each radiologist. The gaze-traveled distance, X-ray coverage, and lung coverage statistically significantly (p < 0.01) deteriorated with cumulative work done (CWD) for three out of four radiologists. The reading time and information gain over lungs statistically significantly deteriorated for all four radiologists. We discovered a novel AI-based metric blending reading time, speed, and organ coverage, which can be used to predict changes in the fatigue-related image reading patterns.
KW - artificial intelligence
KW - chest X-ray
KW - Eye-tracking
KW - image segmentation
KW - lung fields
KW - unet
U2 - 10.1109/JBHI.2022.3183299
DO - 10.1109/JBHI.2022.3183299
M3 - Journal article
C2 - 35704540
AN - SCOPUS:85132767344
VL - 26
SP - 4541
EP - 4550
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
SN - 2168-2194
IS - 9
ER -
ID: 344439469