Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

When Eye-Tracking Meets Machine Learning: A Systematic Review on Applications in Medical Image Analysis

Sahar Moradizeyveh, Mehnaz Tabassum, Sidong Liu, Robert Ahadizad Newport, Amin Beheshti, Antonio Di Ieva

TL;DR

This systematic review investigates eye-gaze tracking applications and methodologies for enhancing ML/DL algorithms for medical image analysis in depth to improve understanding of human vision, attention, and cognition.

Abstract

Eye-gaze tracking research offers significant promise in enhancing various healthcare-related tasks, above all in medical image analysis and interpretation. Eye tracking, a technology that monitors and records the movement of the eyes, provides valuable insights into human visual attention patterns. This technology can transform how healthcare professionals and medical specialists engage with and analyze diagnostic images, offering a more insightful and efficient approach to medical diagnostics. Hence, extracting meaningful features and insights from medical images by leveraging eye-gaze data improves our understanding of how radiologists and other medical experts monitor, interpret, and understand images for diagnostic purposes. Eye-tracking data, with intricate human visual attention patterns embedded, provides a bridge to integrating artificial intelligence (AI) development and human cognition. This integration allows novel methods to incorporate domain knowledge into machine learning (ML) and deep learning (DL) approaches to enhance their alignment with human-like perception and decision-making. Moreover, extensive collections of eye-tracking data have also enabled novel ML/DL methods to analyze human visual patterns, paving the way to a better understanding of human vision, attention, and cognition. This systematic review investigates eye-gaze tracking applications and methodologies for enhancing ML/DL algorithms for medical image analysis in depth.

When Eye-Tracking Meets Machine Learning: A Systematic Review on Applications in Medical Image Analysis

TL;DR

This systematic review investigates eye-gaze tracking applications and methodologies for enhancing ML/DL algorithms for medical image analysis in depth to improve understanding of human vision, attention, and cognition.

Abstract

Eye-gaze tracking research offers significant promise in enhancing various healthcare-related tasks, above all in medical image analysis and interpretation. Eye tracking, a technology that monitors and records the movement of the eyes, provides valuable insights into human visual attention patterns. This technology can transform how healthcare professionals and medical specialists engage with and analyze diagnostic images, offering a more insightful and efficient approach to medical diagnostics. Hence, extracting meaningful features and insights from medical images by leveraging eye-gaze data improves our understanding of how radiologists and other medical experts monitor, interpret, and understand images for diagnostic purposes. Eye-tracking data, with intricate human visual attention patterns embedded, provides a bridge to integrating artificial intelligence (AI) development and human cognition. This integration allows novel methods to incorporate domain knowledge into machine learning (ML) and deep learning (DL) approaches to enhance their alignment with human-like perception and decision-making. Moreover, extensive collections of eye-tracking data have also enabled novel ML/DL methods to analyze human visual patterns, paving the way to a better understanding of human vision, attention, and cognition. This systematic review investigates eye-gaze tracking applications and methodologies for enhancing ML/DL algorithms for medical image analysis in depth.
Paper Structure (22 sections, 5 figures)

This paper contains 22 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Literature Selection and Search Strategy
  4. Quality Assessment
  5. Characteristics of the studies
  6. Eye-gaze Tracking Datasets and Devices in Medical Imaging
  7. Eye-gaze Tracking Applications in Medical Imaging
  8. Image Classification
  9. Model Interpretability Enhancement
  10. Data Annotation
  11. Pathology Detection and Segmentation
  12. Assess Expertise, Workload and Skills
  13. Visual Attention Learning
  14. Saliency Maps
  15. Class Activation Map (CAM)
  16. ...and 7 more sections

Figures (5)

  • Figure 1: An integrated ML/DL pipeline utilizing eye-gaze tracking data to improve diagnostic accuracy in medical imaging. For example, the input image in this example shows an axial slice of a brain MRI with a skull Meningioma seen by a cohort of neuroradiologists and neurosurgeons (experts’ scan paths and their analysis). In additional steps, features are extracted from the MRI images and scan paths for various tasks.
  • Figure 2: Overview of PRISMA chart in Eye-Gaze Tracking using ML/ DL in Radiological Medical Image Analysis.
  • Figure 3: Summary of QUADAS-2 assessments of included studies.
  • Figure 4: Illustrate the detailed analysis of the various eye-tracking application tasks (A) and distribution of various techniques referenced in the articles under study(B) from 2018 to 2023(C).
  • Figure 6: Human organs and the image modalities featured in eye-gaze datasets from 2018-2023