Learning from Multiple Expert Annotators for Enhancing Anomaly Detection in Medical Image Analysis

The proposed method uses Weighted Boxes Fusion (WBF) algorithm to obtain the aggregated annotations with the implicit annotators' agreement as confidence scores. The estimated annotations are then used to train a deep learning detector with a re-weighted loss function that incorporates the confidence scores to localize abnormal findings.

Data and Resources

Cite this as

Khiem H. Le, Tuan V. Tran, Hieu H. Pham, Hieu T. Nguyen, Tung T. Le, Ha Q. Nguyen, D. Q. Tran, D. B. Nguyen, C. M. Pham, H. T. Tong, D. H. Dinh (2025). Dataset: Learning from Multiple Expert Annotators for Enhancing Anomaly Detection in Medical Image Analysis. https://doi.org/10.57702/4gst46z5

DOI retrieved: January 2, 2025

Additional Info

Field Value
Created January 2, 2025
Last update January 2, 2025
Defined In https://doi.org/10.48550/arXiv.2203.10611
Author Khiem H. Le
More Authors
Tuan V. Tran
Hieu H. Pham
Hieu T. Nguyen
Tung T. Le
Ha Q. Nguyen
D. Q. Tran
D. B. Nguyen
C. M. Pham
H. T. Tong
D. H. Dinh
Homepage https://github.com/huyhieupham/learning-from-multiple-annotators