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

2025-07-16

AI Summary

To address the dual bottlenecks of lacking publicly available datasets and 3D modeling capabilities in eye-tracking research on CT imaging, this paper introduces CT-ScanGaze—the first open, clinical CT-based eye-tracking dataset—and proposes CT-Searcher, a novel scan-path prediction model specifically designed for 3D medical volumes. CT-Searcher innovatively integrates 3D convolutional neural networks with oculomotor trajectory modeling, overcoming the limitation of conventional methods that only support 2D inputs. We further design a 2D→3D eye-movement data transformation pipeline to enable efficient pretraining using existing 2D eye-tracking data. Evaluated on CT-ScanGaze, CT-Searcher achieves high-accuracy 3D scan-path prediction, validated through both qualitative and quantitative analyses. Moreover, we establish the first comprehensive evaluation framework for eye-tracking analysis on 3D medical imaging. This work lays a critical foundation for interpretable AI-assisted diagnosis in radiology.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data
• Security and Privacy: Data transparency and provenance

Abstract

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.

Problem

• Lack of public eye-tracking datasets for CT scans
• Difficulty modeling 3D gaze patterns in CT volumes
• Need for pretraining data to improve 3D scanpath prediction

Innovation

• First public CT eye gaze dataset
• 3D scanpath predictor for CT volumes
• Pipeline converts 2D gaze to 3D