EUVIMEDOpdag EUVIMED
Crossref

EANet : Multiscale autoencoder based edge attention network for fluid segmentation from SD‐OCT images

Geetha Pavani Pappu, Sreekar Tankala, Krishna Talabhaktula, Birendra Biswal

International Journal of Imaging Systems and Technology · 2023-05 · 33 (3) · 909-927

DOI: 10.1002/ima.22840 ↗

At a glance

Journal article in International Journal of Imaging Systems and Technology, published online on 2022-12-23. Written by Geetha Pavani Pappu and 3 co-authors. Cited 9 times so far (Crossref); 51 references.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Macular edema is a retinal complication that occurs due to the presence of excess fluid between the retinal layers. This might lead to swelling in the retina and cause severe vision impairment if not detected in its early stages. This paper presents a robust Edge Attention network (EANet) for segmenting the different retinal fluids like Intraretinal Fluid (IRF), Subretinal Fluid (SRF), and Pigment Epithelial Detachment (PED) from the Spectral Domain – Optical Coherence Tomography (SD‐OCT) images. The proposed method employs a novel image enhancement technique by filtering OCT images using a BM3D (Block Matching and 3D Filtering) filter followed by Contrast Limited Adaptive Histogram Equalization (CLAHE) and a linear filter based on multivariate Taylor series to acquire the edge maps of the OCT images. A novel autoencoder based multiscale attention mechanism is incorporated with EANet that feeds on both the OCT image and edge‐enhanced OCT image at every level of the encoder. The proposed network, EANet, has been trained and tested for the segmentation of all three types of fluids on the RETOUCH challenge dataset, and the segmentation of the IRF on the OPTIMA challenge and DUKE DME datasets. The average dice coefficient of IRF, SRF, and PED for the RETOUCH dataset is 0.683, 0.873, and 0.756, respectively, whereas it is 0.805, 0.77, and 0.756 for Cirrus, Spectralis, and Topcon vendors, respectively. The proposed method outperformed all the teams that participated in the OPTIMA challenge on all types of vendor images in terms of dice coefficient. The average dice coefficients of IRF on the OPTIMA and DUKE DME datasets are 0.84 and 0.72, respectively.

Cite

APA

Pappu, G. P., Tankala, S., Talabhaktula, K., & Biswal, B. (2023). EANet : Multiscale autoencoder based edge attention network for fluid segmentation from SD‐OCT images. International Journal of Imaging Systems and Technology, 33(3), 909-927. https://doi.org/10.1002/ima.22840

Vancouver

Pappu GP, Tankala S, Talabhaktula K, Biswal B. EANet : Multiscale autoencoder based edge attention network for fluid segmentation from SD‐OCT images. International Journal of Imaging Systems and Technology. 2023;33(3):909-927. doi:10.1002/ima.22840

BibTeX
@article{Pappu2023,
  author = {Pappu, Geetha Pavani and Tankala, Sreekar and Talabhaktula, Krishna and Biswal, Birendra},
  title = {EANet : Multiscale autoencoder based edge attention network for fluid segmentation from SD‐OCT images},
  journal = {International Journal of Imaging Systems and Technology},
  year = {2023},
  volume = {33},
  number = {3},
  pages = {909--927},
  doi = {10.1002/ima.22840}
}
Start for free →