Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/31006
Title: A Novel Hierarchical Generative Model for Semi-Supervised Semantic Segmentation of Biomedical Images
Authors: Chai, L
Wang, Z
Shao, Y
Liu, Q
Keywords: generative adversarial network;semi-supervised learning;hierarchical architecture;attention mechanism;biomedical image segmentation
Issue Date: 7-Mar-2025
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Citation: Chai, L. et al. (2025) 'A Novel Hierarchical Generative Model for Semi-Supervised Semantic Segmentation of Biomedical Images', IEEE Transactions on Emerging Topics in Computational Intelligence, 0 (early access), pp. 1 - 13. doi: 10.1109/TETCI.2025.3540418.
Abstract: In biomedical vision research, a significant challenge is the limited availability of pixel-wise labeled data. Data augmentation has been identified as a solution to this issue through generating labeled dummy data. While enhancing model efficacy, semi-supervised learning methodologies have emerged as a promising alternative that allows models to train on a mix of limited labeled and larger unlabeled data sets, potentially marking a significant advancement in biomedical vision research. Drawing from the semi-supervised learning strategy, in this paper, a novel medical image segmentation model is presented that features a hierarchical architecture with an attention mechanism. This model disentangles the synthesis process of biomedical images by employing a tail two-branch generator for semantic mask synthesis, thereby excelling in handling medical images with imbalanced class characteristics. During inference, the k-means clustering algorithm processes feature maps from the generator by using the clustering outcome as the segmentation mask. Experimental results show that this approach preserves biomedical image details more accurately than synthesized semantic masks. Experiments on various datasets, including those for vestibular schwannoma, kidney, and skin cancer, demonstrate the proposed method's superiority over other generative-adversarial-network-based and semi-supervised segmentation methods in both distribution fitting and semantic segmentation performance.
URI: https://bura.brunel.ac.uk/handle/2438/31006
DOI: https://doi.org/10.1109/TETCI.2025.3540418
Other Identifiers: ORCiD: Zidong Wang https://orcid.org/0000-0002-9576-7401
ORCiD: Qinyuan Liu https://orcid.org/0000-0002-0170-3651
Appears in Collections:Dept of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2025 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works ( https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/ ).6.41 MBAdobe PDFView/Open


Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.