Learning from multiple expert annotators for enhancing anomaly detection in medical image analysis

KH Le, TV Tran, HH Pham, HT Nguyen, TT Le… - IEEE …, 2023 - ieeexplore.ieee.org
Recent years have experienced phenomenal growth in computer-aided diagnosis systems
based on machine learning algorithms for anomaly detection tasks in the medical image …

Learning from noisy crowd labels with logics

Z Chen, H Sun, H He, P Chen - 2023 IEEE 39th International …, 2023 - ieeexplore.ieee.org
This paper explores the integration of symbolic logic knowledge into deep neural networks
for learning from noisy crowd labels. We introduce Logic-guided Learning from Noisy Crowd …

Label Filling via Mixed Supervision for Medical Image Segmentation from Noisy Annotations

M Li, W Shen, Q Li, Y Wang - arxiv preprint arxiv:2410.16057, 2024 - arxiv.org
The success of medical image segmentation usually requires a large number of high-quality
labels. But since the labeling process is usually affected by the raters' varying skill levels and …

A Crowdsourcing Truth Inference Algorithm Based on Hypergraph Neural Networks

Z Dong, Y Li, L Gao, Z Zhou - … , Intl Conf on Cloud and Big Data …, 2022 - ieeexplore.ieee.org
Crowdsourcing has become an economical and efficient way to obtain data, but the data
obtained by crowdsourcing is often noisy. Due to concerns about human errors in …