Robust co-teaching learning with consistency-based noisy label correction for medical image classification
Authors:
- 27 November 2022
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 18 (4) , 675-683
Abstract
Purpose Deep neural networks (DNNs) have made great achievements in computer-aided diagnostic systems, but the success highly depends on massive data with high-quality labels. However, for many medical image datasets, a considerable number of noisy labels are introduced by inter- and intra-observer variability, thus hampering DNNs’ performance. To address this problem, a robust noisy label correction method with the co-teaching learning paradigm is proposed. Methods The proposed method aims to reduce the effect of noisy labels by correcting or removing them. It consists of two modules. An adaptive noise rate estimation module is employed to calculate the dataset’s noise rate, which is helpful to detect noisy labels but is usually unavailable in clinical applications. A consistency-based noisy label correction module aims to detect noisy labels and correct them to reduce the disturbance from noisy labels and exploit useful information in data. Results Experiments are conducted on the public skin lesion dataset ISIC-2017, ISIC-2019, and our constructed thyroid ultrasound image dataset. The results demonstrate that the proposed method outperforms other noisy label learning methods in medical image classification tasks. It is also evaluated on the natural image dataset CIFAR-10 to show its generalization. Conclusion This paper proposes a noisy label correction method to handle noisy labels in medical image datasets. Experimental results show that it can self-adapt to different datasets and efficiently correct noisy labels, which is suitable for medical image classification.Keywords
Funding Information
- National Science Fund for Distinguished Young Scholars (62025601)
- National Natural Science Foundation of China (62006164)
- Sichuan University Innovation Spark Project Library (2018SCUH0040)
This publication has 20 references indexed in Scilit:
- The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesionsScientific Data, 2018
- Joint Optimization Framework for Learning with Noisy Labels2018
- Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)2018
- Training a neural network based on unreliable human annotation of medical images2018
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Identity Mappings in Deep Residual Networks2016
- Deep Residual Learning for Image Recognition2016
- Interobserver Variability and Diagnostic Performance in US Assessment of Thyroid Nodule According to SizeUltraschall in der Medizin - European Journal of Ultrasound, 2012
- ImageNet: A large-scale hierarchical image database2009