Deep learning with noisy labels: exploring techniques and remedies in medical image analysis

By Davood Karimi, Haoran Dou, Simon Keith Warfield, A. Gholipour. Medical Image Anal., 2019

691 citations recorded by the source corpus.

Supervised training of deep learning models requires large labeled datasets. There is a growing interest in obtaining such datasets for medical image analysis applications. However, the impact of label noise has not received sufficient attention. Recent studies have shown that label noise can significantly impact the performance of deep learning models in many machine learning and computer vision applications. This is especially concerning for medical applications, where datasets are typically small, labeling requires domain expertise and suffers from high inter- and intra-observer variability, and erroneous predictions may influence decisions that directly impact human health. In this paper, we first review the state-of-the-art in handling label noise in deep learning. Then, we review studies that have dealt with label noise in deep learning for medical image analysis. Our review shows that recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image analysis community. To help achieve a better understanding of the extent of the problem and its potential remedies, we conducted experiments with three medical imaging datasets with different types of label noise, where we investigated several existing strategies and developed new methods to combat the negative effect of label noise. Based on the results of these experiments and our review of the literature, we have made recommendations on methods that can be used to alleviate the effects of different types of label noise on deep models trained for medical image analysis. We hope that this article helps the medical image analysis researchers and developers in choosing and devising new techniques that effectively handle label noise in deep learning.

Subfields: Artificial Intelligence, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/7e40d5d095db557810ae9560db33a3c2a09e630c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Industrial and Manufacturing Engineering

Mingxia Liu

Citations in the corpus

Part-dependent Label Noise: Towards Instance-dependent Label Noise (2020, background): “The main reason is that it is expensive and sometimes even infeasible to accurately label large-scale datasets [23]; while it is relatively easy to obtain cheap but noisy datasets [77, 62, 65, 71, 19].”
A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images (2020, methodology): “Although learning from noisy labels has been increasing investigated, most existing works focus on image classiﬁcation tasks [13].”
Annotation-efficient deep learning for automatic medical image segmentation (2020, methodology): “Co-teaching was developed based on co-training to specifically address the challenge of NLL by dropping suspected highly noisy samples during network optimization 27,28 .”
Federated learning for medical image analysis: A survey (2023, background): “, learning from noisy labels (Karimi et al., 2020)) in an FL system is worthy of further exploration.”
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation (2019, background): “work of Karimi et al. (2019) that primarily considers label noise in the medical image datasets.”