Retinal fluid segmentation in OCT images using adversarial loss based convolutional neural networks

Tennakoon, R, Khodadadian Gostar, A, Hoseinnezhad, R and Bab-Hadiashar, A 2011, 'Retinal fluid segmentation in OCT images using adversarial loss based convolutional neural networks', in IEEE 15th International Symposium on Biomedical Imaging, Washington, DC, April 4-7th 2018, pp. 1436-1440.


Document type: Conference Paper
Collection: Conference Papers

Title Retinal fluid segmentation in OCT images using adversarial loss based convolutional neural networks
Author(s) Tennakoon, R
Khodadadian Gostar, A
Hoseinnezhad, R
Bab-Hadiashar, A
Year 2011
Conference name IEEE 15th International Symposium on Biomedical Imaging
Conference location Washington, DC
Conference dates April 4-7th 2018
Proceedings title IEEE 15th International Symposium on Biomedical Imaging
Publisher IEEE
Place of publication USA
Start page 1436
End page 1440
Total pages 5
Abstract This paper proposes a novel method in order to obtain voxel-level segmentation for three fluid lesion types (IR-F/SRF/PED) in OCT images provided by the ReTOUCH challenge [1]. The method is based on a deep neural network consisting of encoding and de-coding blocks connected with skip-connections which was trained using a combined cost function comprising of cross-entropy, dice and adversarial loss terms. The segmentation results on a held-out validation set shows that the network architecture and the loss functions used has resulted in improved retinal fluid segmentation. Our method was ranked fourth in the ReTOUCH challenge.
Subjects Computer Vision
Image Processing
Pattern Recognition and Data Mining
DOI - identifier 10.1109/ISBI.2018.8363842
Copyright notice © 2018 IEEE
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 7 Abstract Views  -  Detailed Statistics
Created: Mon, 29 Apr 2019, 13:04:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us