Upcoming Talks

CT-ScanGaze: A Dataset and Baselines for 3D Volumetric Scanpath Modeling

Understanding radiologists' eye movement during Computed Tomography (CT) reading is crucial for developing effective interpretable computer-aided diagnosis systems. However, CT research in this area has been limited by the lack of publicly available eye-tracking datasets and the three-dimensional complexity of CT volumes. To address these challenges, we present the first publicly available eye gaze dataset on CT, called CT-ScanGaze. Then, we introduce CT-Searcher, a novel 3D scanpath predictor designed specifically to process CT volumes and generate radiologist-like 3D fixation sequences, overcoming the limitations of current scanpath predictors that only handle 2D inputs. Since deep learning models benefit from a pretraining step, we develop a pipeline that converts existing 2D gaze datasets into 3D gaze data to pretrain CT-Searcher. Through both qualitative and quantitative evaluations on CT-ScanGaze, we demonstrate the effectiveness of our approach and provide a comprehensive assessment framework for 3D scanpath prediction in medical imaging.

Trong Thang Pham is a PhD candidate at the University of Arkansas, Fayetteville, working under the supervision of Dr. Ngan Le. His research focuses on the intersection of expert behavior analysis and deep learning, specifically applying human eye gaze analysis to transform and enhance deep learning models. Prior to his PhD, he was an R&D researcher at AIOZ Singapore, where he developed digital twin technologies, including talking face generation and 3D human models for metaverse applications. His work has resulted in strong publications across premier venues, including top-tier conferences such as CVPR, ICCV, ACM MM, WACV, and ICRA.

Please add your questions to the speaker either to this google form or directly under the YouTube video