Exigent examiner and mean teacher: an advanced 3D CNN-based semi-supervised brain tumor segmentation framework

Conference item

With the rise of deep learning applications to medical imaging, there has been a growing appetite for large and well-annotated datasets, yet annotation is time-consuming and hard to come by. In this work, we train a 3D semantic segmentation model in an advanced semi-supervised learning fashion. The proposed SSL framework consists of three models: a Student model that learns from annotated data and a large amount of raw data, a Teacher model with the same architecture as the student, updated by self-ensembling and which supervises the student through pseudo-labels, and an Examiner model that assesses the quality of the student’s inferences. All three models are built with 3D convolutional operations. The overall framework mimics a collaboration between a consistency training Student ↔ Teacher module and an adversarial training Examiner ↔ Student module. The proposed method is validated with various evaluation metrics on a public benchmarking 3D MRI brain tumor segmentation dataset. The experimental results of the proposed method outperform pre-existing semi-supervised methods. The source code, baseline methods, and dataset are available at https://github.com/ziyangwang007/CV-SSL-MIS.

Authors: Wang, Z; Voiculescu, ID

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: Medical Image Learning with Limited and Noisy Data. MILLanD 2023
• Pages: 181-190
• Series: Lecture Notes in Computer Science
• Series number: 14307
• Place of publication: Cham, Switzerland
• Publication date: 2023-10-08
• Acceptance date: 2023-07-29
• Event title: 2nd Workshop of Medical Image Learning with Limited & Noisy Data (MILLanD)
• Event location: Vancouver, Canada
• Event website: https://miccaimilland.wixsite.com/milland2023
• Event start date: 2023-10-08
• Event end date: 2023-10-08
• DOI: 10.1007/978-3-031-44917-8_17
• EISSN: 1611-3349
• ISSN: 0302-9743
• EISBN: 9783031449178
• ISBN: 9783031471964
• Language: English
• Keywords: image semantic segmentation; adversarial training; semi-supervised learning; brain tumour segmentation; mean teacher