Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation

By Yingda Xia, Dong Yang, Zhiding Yu, Fengze Liu, Jinzheng Cai, Lequan Yu, Zhuotun Zhu, Daguang Xu, Alan L. Yuille, Holger R. Roth. 2020

273 citations recorded by the source corpus.

Although having achieved great success in medical image segmentation, deep learning-based approaches usually require large amounts of well-annotated data, which can be extremely expensive in the field of medical image analysis. Unlabeled data, on the other hand, is much easier to acquire. Semi-supervised learning and unsupervised domain adaptation both take the advantage of unlabeled data, and they are closely related to each other. In this paper, we propose uncertainty-aware multi-view co-training (UMCT), a unified framework that addresses these two tasks for volumetric medical image segmentation. Our framework is capable of efficiently utilizing unlabeled data for better performance. We firstly rotate and permute the 3D volumes into multiple views and train a 3D deep network on each view. We then apply co-training by enforcing multi-view consistency on unlabeled data, where an uncertainty estimation of each view is utilized to achieve accurate labeling. Experiments on the NIH pancreas segmentation dataset and a multi-organ segmentation dataset show state-of-the-art performance of the proposed framework on semi-supervised medical image segmentation. Under unsupervised domain adaptation settings, we validate the effectiveness of this work by adapting our multi-organ segmentation model to two pathological organs from the Medical Segmentation Decathlon Datasets. Additionally, we show that our UMCT-DA model can even effectively handle the challenging situation where labeled source data is inaccessible, demonstrating strong potentials for real-world applications.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

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 Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Annotation-efficient deep learning for automatic medical image segmentation (2020, background): “Only recently has co-training been extended to semi-supervised image segmentation 25 and UDA of segmentation models 26 .”
Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation (2023, unknown): “UMCT [37] used different perspectives of the network to predict the same image of different views.”
Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer (2021, background): “These proprieties can be used to accelerate clinical data annotation, model development, and even reduce the annotation that is often given by radiologists (Luo et al., 2021a,b; Xia et al., 2020; Wang et al., 2021a).”
Mutual consistency learning for semi-supervised medical image segmentation (2021, methodology): “Furthermore, Xia et al. (2020b,a) employed a multi-view co-training strategy to perform ensemble learning for 3D medical image segmentation.”
LViT: Language Meets Vision Transformer in Medical Image Segmentation (2022, background): “Therefore, some approaches [5], [21], [22], [23], [24] have explored the application of semi-supervised learning in different areas.”
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, methodology): “[429] introduced the UMCT model as a semi-supervised framework and tested it on various medical image datasets.”