mlsanityData to 14 Oct 2026

Shifts in Doctors' Eye Movements Between Real and AI-Generated Medical Images

arXiv 2504.15007 ↗First posted 21 Apr 2025cs.CV cs.HCcited by 1

Not on the map. Why?

Abstract (arXiv)

Eye-tracking analysis plays a vital role in medical imaging, providing key insights into how radiologists visually interpret and diagnose clinical cases. In this work, we first analyze radiologists' attention and agreement by measuring the distribution of various eye-movement patterns, including saccades direction, amplitude, and their joint distribution. These metrics help uncover patterns in attention allocation and diagnostic strategies. Furthermore, we investigate whether and how doctors' gaze behavior shifts when viewing authentic (Real) versus deep-learning-generated (Fake) images. To achieve this, we examine fixation bias maps, focusing on first, last, short, and longest fixations independently, along with detailed saccades patterns, to quantify differences in gaze distribution and visual saliency between authentic and synthetic images.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 47 references that are in the map. First posted on arXiv 21 Apr 2025.

Builds on

13 of 47 references.

References · 13

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2019An Introduction to Variational Autoencoderscited by 1,000
  3. 2022RoentGen: Vision-Language Foundation Model for Chest X-ray Generationcited by 89
  4. 2024Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Modelscited by 69
  5. 2022Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generationcited by 54
  6. 2022Assessing the ability of generative adversarial networks to learn canonical medical image statisticscited by 11
  7. 2023M3Dsynth: A dataset of medical 3D images with AI-generated local manipulationscited by 11
  8. 2021A multi-stage GAN for multi-organ chest X-ray image generation and segmentationcited by 8
  9. 2022A domain adaptive deep learning solution for scanpath prediction of paintingscited by 6
  10. 2023Generative Adversarial Networks for Brain Images Synthesis: A Reviewcited by 4
  11. 2024Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographscited by 3
  12. 2024When Eye-Tracking Meets Machine Learning: A Systematic Review on Applications in Medical Image Analysiscited by 2
1 more
  1. 2024Analysis of Human Perception in Distinguishing Real and AI-Generated Faces: An Eye-Tracking Based Studycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metriccited by 2