Predavanje "Eye-Tracking as a New Frontier for Human-Centered AI in Radiology"

V okviru predmeta Biomedicinska informatika (BMI) na magistrskem študiju Biomedicinska tehnika (BMT) bo v ponedeljek, 22. 12. 2025, ob 12.15 v predavalnici LST-A4 potekalo naslednje vabljeno predavanje v angleškem jeziku.

Naslov: Eye-Tracking as a New Frontier for Human-Centered AI in Radiology

Predavatelj: znan. sod. dr. Bulat Ibragimov (Univerza v Kopenhagnu, Fakulteta za računalništvo & Univerza v Ljubljani, Fakulteta za elektrotehniko)

Povzetek v angleškem jeziku

What if we could teach AI not just to analyze images, but to understand how doctors think? The eyes of radiologists often follow subtle, experience-driven patterns that can reflect attention, uncertainty, fatigue, and even error. Eye-tracking can capture this layer of human cognition and turn it into actionable data. Eye-tracking opens the door to a more human-centered kind of AI in medicine. The possible applications of interest range from predicting when radiologists are likely to make an error, to gaze-guided image annotation, and even controlling medical equipment with gaze. This talk will share how AI-assisted gaze analysis can be used in radiology, including the work conducted at the University of Copenhagen on eye-tracking to detect fatigue in real clinical settings.

As part of the course in Biomedical Informatics (BMI) within the master’s programme in Biomedical Engineering (BME), the following invited lecture in English will take place on Monday, Dec 22, 2025 at 12:15 in lecture room LST-A4.

Title: Eye-Tracking as a New Frontier for Human-Centered AI in Radiology

Lecturer: Assoc. Prof. Bulat Ibragimov, Ph.D. (University of Copenhagen, Department of Computer Science & University of Ljubljana, Faculty of Electrical Engineering)

Abstract

What if we could teach AI not just to analyze images, but to understand how doctors think? The eyes of radiologists often follow subtle, experience-driven patterns that can reflect attention, uncertainty, fatigue, and even error. Eye-tracking can capture this layer of human cognition and turn it into actionable data. Eye-tracking opens the door to a more human-centered kind of AI in medicine. The possible applications of interest range from predicting when radiologists are likely to make an error, to gaze-guided image annotation, and even controlling medical equipment with gaze. This talk will share how AI-assisted gaze analysis can be used in radiology, including the work conducted at the University of Copenhagen on eye-tracking to detect fatigue in real clinical settings.