Skip to main navigation Skip to search Skip to main content

SwinVFTR: A Novel Volumetric Feature-Learning Transformer for 3D OCT Fluid Segmentation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Accurately segmenting fluid in 3D optical coherence tomography (OCT) images is critical for detecting eye diseases but remains challenging. Traditional autoencoder-based methods struggle with resolution loss and information recovery. While transformer-based models improve segmentation, they aren't optimized for 3D OCT volumes, which vary by vendor and extraction technique. To address this, we propose SwinVFTR, a transformer architecture for precise fluid segmentation in 3D OCT images. SwinVFTR employs channel-wise volumetric sampling and a shifted window transformer block to improve fluid localization. Moreover, a novel volumetric attention block enhances spatial and depth-wise attention. Trained using multiclass dice loss, SwinVFTR outperforms existing models on Spectralis, Cirrus, and Topcon OCT datasets, achieving mean dice scores of 0.72, 0.59, and 0.68, respectively, along with superior performance in mean intersection-over-union (IOU) and structural similarity (SSIM) metrics.

Original languageEnglish (US)
Title of host publicationISBI 2025 - 2025 IEEE 22nd International Symposium on Biomedical Imaging, Proceedings
PublisherIEEE Computer Society
ISBN (Electronic)9798331520526
DOIs
StatePublished - 2025
Externally publishedYes
Event22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025 - Houston, United States
Duration: Apr 14 2025 → Apr 17 2025

Publication series

NameProceedings - International Symposium on Biomedical Imaging
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025
Country/TerritoryUnited States
CityHouston
Period4/14/25 → 4/17/25

Keywords

  • Fluid Segmentation
  • OCT Segmentation
  • Optical Coherence Tomography
  • Swin Transformer

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'SwinVFTR: A Novel Volumetric Feature-Learning Transformer for 3D OCT Fluid Segmentation'. Together they form a unique fingerprint.

Cite this