Randomness-restricted diffusion model for ocular surface structure segmentation

Simple item page
dc.contributor.authorGuo, Xinyu
dc.contributor.authorWen, Han
dc.contributor.authorHao, Huaying
dc.contributor.authorZhao, Yifan
dc.contributor.authorMeng, Yanda
dc.contributor.authorLiu, Jiang
dc.contributor.authorZheng, Yalin
dc.contributor.authorChen, Wei
dc.contributor.authorZhao, Yitian
dc.date.accessioned2025-05-15T11:38:58Z
dc.date.available2025-05-15T11:38:58Z
dc.date.freetoread2024-12-06
dc.date.issued2025-03
dc.date.pubOnline2024-11-11
dc.description.abstractOcular surface diseases affect a significant portion of the population worldwide. Accurate segmentation and quantification of different ocular surface structures are crucial for the understanding of these diseases and clinical decision-making. However, the automated segmentation of the ocular surface structure is relatively unexplored and faces several challenges. Ocular surface structure boundaries are often inconspicuous and obscured by glare from reflections. In addition, the segmentation of different ocular structures always requires training of multiple individual models. Thus, developing a one-model-fits-all segmentation approach is desirable. In this paper, we introduce a randomness-restricted diffusion model for multiple ocular surface structure segmentation. First, a time-controlled fusion-attention module (TFM) is proposed to dynamically adjust the information flow within the diffusion model, based on the temporal relationships between the network’s input and time. TFM enables the network to effectively utilize image features to constrain the randomness of the generation process. We further propose a low-frequency consistency filter and a new loss to alleviate model uncertainty and error accumulation caused by the multi-step denoising process. Extensive experiments have shown that our approach can segment seven different ocular surface structures. Our method performs better than both dedicated ocular surface segmentation methods and general medical image segmentation methods. We further validated the proposed method over two clinical datasets, and the results demonstrated that it is beneficial to clinical applications, such as the meibomian gland dysfunction grading and aqueous deficient dry eye diagnosis.
dc.description.journalNameIEEE Transactions on Medical Imaging
dc.format.extentpp. 1359-1372
dc.format.mediumPrint-Electronic
dc.identifier.citationGuo X, Wen H, Hao H, et al., (2025) Randomness-restricted diffusion model for ocular surface structure segmentation. IEEE Transactions on Medical Imaging, Volume 44, Issue 3, March 2025, pp. 1359-1372en_UK
dc.identifier.eissn1558-254X
dc.identifier.elementsID559374
dc.identifier.issn0278-0062
dc.identifier.issueNo3
dc.identifier.urihttps://doi.org/10.1109/tmi.2024.3494762
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/23887
dc.identifier.volumeNo44
dc.languageeng
dc.language.isoen
dc.publisherIEEEen_UK
dc.publisher.urihttps://ieeexplore.ieee.org/document/10750059
dc.rightsAttribution-NonCommercial 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subjectImage segmentationen_UK
dc.subjectDiffusion models en_UK
dc.subjectSurface structures en_UK
dc.subjectGlands en_UK
dc.subjectSurface morphology en_UK
dc.subjectSurface treatment en_UK
dc.subjectNoise en_UK
dc.subjectPupils en_UK
dc.subjectManuals en_UK
dc.subjectDiseases en_UK
dc.subjectOcular surface en_UK
dc.subjectmedical image segmentation en_UK
dc.subjectdiffusion model en_UK
dc.subject46 Information and Computing Sciences en_UK
dc.subjectEye Disease and Disorders of Vision en_UK
dc.subjectNuclear Medicine & Medical Imaging en_UK
dc.subject40 Engineering en_UK
dc.subject46 Information and computing sciences en_UK
dc.subject.meshHumans en_UK
dc.subject.meshAlgorithms en_UK
dc.subject.meshEye en_UK
dc.subject.meshImage Interpretation, Computer-Assisted en_UK
dc.subject.meshImage Processing, Computer-Assisted en_UK
dc.titleRandomness-restricted diffusion model for ocular surface structure segmentation en_UK
dc.typeArticle
dc.type.subtypeJournal Article
dcterms.dateAccepted2024-11-04

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Randomness-restricted_diffusion_model-2024.pdf
Size:
2.91 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Plain Text
Description:
Download

Collections

Staff publications (SATM)