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

Building an accurate computer-aided diagnosis system based on data-driven approaches requires a large amount of high-quality labeled data. In medical imaging analysis, multiple expert annotators often produce subjective estimates about "ground truth labels" during the annotation process, d...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-03
Main Authors: Le, Khiem H, Tran, Tuan V, Pham, Hieu H, Nguyen, Hieu T, Le, Tung T, Nguyen, Ha Q
Format: Article
Language:English
Subjects:
Abnormalities
Algorithms
Annotations
Anomalies
Deep learning
Estimates
Human bias
Image analysis
Image enhancement
Machine learning
Medical imaging
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Building an accurate computer-aided diagnosis system based on data-driven approaches requires a large amount of high-quality labeled data. In medical imaging analysis, multiple expert annotators often produce subjective estimates about "ground truth labels" during the annotation process, depending on their expertise and experience. As a result, the labeled data may contain a variety of human biases with a high rate of disagreement among annotators, which significantly affect the performance of supervised machine learning algorithms. To tackle this challenge, we propose a simple yet effective approach to combine annotations from multiple radiology experts for training a deep learning-based detector that aims to detect abnormalities on medical scans. The proposed method first estimates the ground truth annotations and confidence scores of training examples. The estimated annotations and their scores are then used to train a deep learning detector with a re-weighted loss function to localize abnormal findings. We conduct an extensive experimental evaluation of the proposed approach on both simulated and real-world medical imaging datasets. The experimental results show that our approach significantly outperforms baseline approaches that do not consider the disagreements among annotators, including methods in which all of the noisy annotations are treated equally as ground truth and the ensemble of different models trained on different label sets provided separately by annotators.
ISSN:2331-8422