Contrastive Learning Approach to Predict Radiologist's Error Based on Gaze Data
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
The increase in medical imaging and, consequently, the growing workload of radiologists requires workflow optimization. The interaction between radiologists and artificial intelligence is a promising area because it can improve radiologist productivity and reduce diagnostic errors. In this study, we describe an eye-tracking experiment with four practicing radiologists who cumulatively examined 1,000 unique chest X-ray images that included samples with multiple pathologies. We demonstrate the feasibility of a self-supervised approach for gazebased data for problems with a small amount of labeled data. We achieve an accuracy of 64.7% for binary classification of radiologist diagnostic error with 218 samples per label. The proposed approach can be used in the system for assessing the need for a second opinion to improve the quality of diagnostics.
Original language | English |
---|---|
Title of host publication | 2023 IEEE Congress on Evolutionary Computation, CEC 2023 |
Publisher | IEEE |
Publication date | 2023 |
ISBN (Electronic) | 9798350314588 |
DOIs | |
Publication status | Published - 2023 |
Event | 2023 IEEE Congress on Evolutionary Computation, CEC 2023 - Chicago, United States Duration: 1 Jul 2023 → 5 Jul 2023 |
Conference
Conference | 2023 IEEE Congress on Evolutionary Computation, CEC 2023 |
---|---|
Land | United States |
By | Chicago |
Periode | 01/07/2023 → 05/07/2023 |
Bibliographical note
Publisher Copyright:
© 2023 IEEE.
- deep learning, eye-tracking, human-AI interaction, self-supervised
Research areas
ID: 372615699