Premium
Objective evaluation of the visibility of colorectal lesions using eye tracking
Author(s) -
Kumahara Kana,
Ikematsu Hiroaki,
Shinmura Kensuke,
Murano Tatsuro,
Inaba Atsushi,
Okumura Kei,
Nishihara Keiichiro,
Sunakawa Hironori,
Furue Yasuaki,
Ito Renma,
Sato Daiki,
Minamide Tatsunori,
Okamoto Naoki,
Yamamoto Yoichi,
Suyama Masayuki,
Takashima Kenji,
Nakajo Keiichiro,
Yoda Yusuke,
Hori Keisuke,
Oono Yasuhiro,
Yano Tomonori
Publication year - 2019
Publication title -
digestive endoscopy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.5
H-Index - 56
eISSN - 1443-1661
pISSN - 0915-5635
DOI - 10.1111/den.13397
Subject(s) - medicine , visibility , eye tracking , artificial intelligence , optometry , ophthalmology , tracking (education) , computer vision , radiology , optics , computer science , psychology , pedagogy , physics
Background and Aim To assess the visibility of colorectal lesions using blue laser imaging ( BLI )‐bright and linked‐color imaging ( LCI ) with an eye‐tracking system. Methods Eleven endoscopists evaluated 90 images of 30 colorectal lesions. The lesions were randomly selected. Three images of each lesion comprised white light imaging ( WLI ), BLI ‐bright, and LCI in the same position. Participants gazed at the images, and their eye movements were tracked by the eye tracker. We analyzed whether the participants could detect the lesion and how long they took to detect the lesion. We assessed the miss rate and detection time among the imaging modalities. Results One endoscopist was excluded, and 10 endoscopists were assessed. Overall, 12.6% of lesions were missed with WLI , 6.0% with BLI ‐bright, and 4.3% with LCI ; the miss rate of BLI ‐bright and LCI was significantly lower than that of WLI ( P < 0.01), with no significant difference between the former modalities ( P = 0.54). Mean (± SD) detection times were 1.58 ± 1.60 s for WLI , 1.01 ± 1.21 s for BLI ‐bright, and 1.10 ± 1.16 s for LCI . Detection time for BLI ‐bright and LCI was significantly shorter than that for WLI ( P < 0.0001), with no significant difference between the former modalities ( P = 0.34). Regarding the miss rate and detection time between the expert and the non‐experts, there was a significant difference with WLI but not with BLI ‐bright and LCI . Conclusion Blue laser imaging‐bright and LCI improved the detection of colorectal lesions compared with WLI using an eye‐tracking system.