Semi-supervised Classification of Diagnostic Radiographs with NoTeacher: A Teacher that is Not Mean

Semi-supervised Classification of Diagnostic Radiographs with NoTeacher: A Teacher that is Not Mean
Title:
Semi-supervised Classification of Diagnostic Radiographs with NoTeacher: A Teacher that is Not Mean
Other Titles:
International Conference on Medical Image Computing and Computer-Assisted Intervention
DOI:
10.1007/978-3-030-59710-8_61
Publication Date:
29 September 2020
Citation:
Unnikrishnan B., Nguyen C.M., Balaram S., Foo C.S., Krishnaswamy P. (2020) Semi-supervised Classification of Diagnostic Radiographs with NoTeacher: A Teacher that is Not Mean. In: Martel A.L. et al. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science, vol 12261. Springer, Cham. https://doi.org/10.1007/978-3-030-59710-8_61
Abstract:
Deep learning approaches offer strong performance for radiology image classification, but are bottlenecked by the need for large labeled training datasets. Semi-supervised learning (SSL) methods that can leverage small labeled datasets alongside larger unlabeled datasets offer potential for reducing labeling cost. However, few studies have demonstrated gains of SSL for real-world radiology image classification. Here, we adapt three leading SSL methods (Mean Teacher, Virtual Adversarial Training, Pseudo-labeling) for radiograph classification, and characterize their performance on two public X-Ray and CT classification benchmarks. We observe that Mean Teacher can achieve good performance gains in the low labeled data regime, but is sensitive to hyperparameters and susceptible to confirmation bias. To address these issues, we introduce a novel SSL method named NoTeacher. This method incorporates a probabilistic graphical model to maximize mutual agreement between student networks, thereby eliminating the need for a teacher network. We show that NoTeacher outperforms contemporary SSL baselines by enforcing better consistency regularization, and achieves over 90% of the fully supervised AUROC with less than 5% labeling budget.
License type:
PublisherCopyrights
Funding Info:
CORE (SC20-RD110).
Description:
This is a post-peer-review, pre-copyedit version of an article published in MICCAI 2020: Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-59710-8_61
ISBN:
978-3-030-59709-2
978-3-030-59710-8
Files uploaded:
File Size Format Action
There are no attached files.