Exigent Examiner and Mean Teacher: An Advanced 3D CNN-Based Semi-Supervised Brain Tumor Segmentation Framework

Ziyang Wang*, Irina Voiculescu

*Corresponding author for this work

Research output: Chapter in Book/Published conference outputConference publication

4 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationMedical Image Learning with Limited and Noisy Data.
Subtitle of host publicationMILLanD 2023. Lecture Notes in Computer Science.
EditorsZhiyun Xue, Sameer Antani, Ghada Zamzmi, Feng Yang, Sivaramakrishnan Rajaraman, Sharon Xiaolei Huang, Marius George Linguraru, Zhaohui Liang
PublisherSpringer
Pages181-190
Number of pages10
Volume14307
ISBN (Electronic)9783031449178
ISBN (Print)9783031471964
DOIs
Publication statusPublished - 8 Oct 2023
Event2nd Workshop on Medical Image Learning with Noisy and Limited Data, MILLanD 2023 - Vancouver, Canada
Duration: 8 Oct 20238 Oct 2023

Publication series

NameLecture Notes in Computer Science (LNCS)
Volume14307
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference2nd Workshop on Medical Image Learning with Noisy and Limited Data, MILLanD 2023
Country/TerritoryCanada
CityVancouver
Period8/10/238/10/23

Keywords

  • Adversarial Training
  • Brain Tumour Segmentation
  • Image Semantic Segmentation
  • Mean Teacher
  • Semi-Supervised Learning

Fingerprint

Dive into the research topics of 'Exigent Examiner and Mean Teacher: An Advanced 3D CNN-Based Semi-Supervised Brain Tumor Segmentation Framework'. Together they form a unique fingerprint.

Cite this