Skip to main content

Research Repository

Advanced Search

CNV-Net: Segmentation, Classification and Activity Score Measurement of Choroidal Neovascularization (CNV) Using Optical Coherence Tomography Angiography (OCTA)

Vali, Mahsa; Nazari, Behzad; Sadri, Saeed; Pour, Elias Khalili; Riazi-Esfahani, Hamid; Faghihi, Hooshang; Ebrahimiadib, Nazanin; Azizkhani, Momeneh; Innes, Will; Steel, David H.; Hurlbert, Anya; Read, Jenny C.A.; Kafieh, Rahele

CNV-Net: Segmentation, Classification and Activity Score Measurement of Choroidal Neovascularization (CNV) Using Optical Coherence Tomography Angiography (OCTA) Thumbnail


Authors

Mahsa Vali

Behzad Nazari

Saeed Sadri

Elias Khalili Pour

Hamid Riazi-Esfahani

Hooshang Faghihi

Nazanin Ebrahimiadib

Momeneh Azizkhani

Will Innes

David H. Steel

Anya Hurlbert

Jenny C.A. Read



Abstract

This paper aims to present an artificial intelligence-based algorithm for the automated segmentation of Choroidal Neovascularization (CNV) areas and to identify the presence or absence of CNV activity criteria (branching, peripheral arcade, dark halo, shape, loop and anastomoses) in OCTA images. Methods: This retrospective and cross-sectional study includes 130 OCTA images from 101 patients with treatment-naïve CNV. At baseline, OCTA volumes of 6 × 6 mm2 were obtained to develop an AI-based algorithm to evaluate the CNV activity based on five activity criteria, including tiny branching vessels, anastomoses and loops, peripheral arcades, and perilesional hypointense halos. The proposed algorithm comprises two steps. The first block includes the pre-processing and segmentation of CNVs in OCTA images using a modified U-Net network. The second block consists of five binary classification networks, each implemented with various models from scratch, and using transfer learning from pre-trained networks. Results: The proposed segmentation network yielded an averaged Dice coefficient of 0.86. The individual classifiers corresponding to the five activity criteria (branch, peripheral arcade, dark halo, shape, loop, and anastomoses) showed accuracies of 0.84, 0.81, 0.86, 0.85, and 0.82, respectively. The AI-based algorithm potentially allows the reliable detection and segmentation of CNV from OCTA alone, without the need for imaging with contrast agents. The evaluation of the activity criteria in CNV lesions obtains acceptable results, and this algorithm could enable the objective, repeatable assessment of CNV features.

Citation

Vali, M., Nazari, B., Sadri, S., Pour, E. K., Riazi-Esfahani, H., Faghihi, H., …Kafieh, R. (2023). CNV-Net: Segmentation, Classification and Activity Score Measurement of Choroidal Neovascularization (CNV) Using Optical Coherence Tomography Angiography (OCTA). Diagnostics, 13(7), Article 1309. https://doi.org/10.3390/diagnostics13071309

Journal Article Type Article
Acceptance Date Mar 24, 2023
Online Publication Date Mar 31, 2023
Publication Date Apr 1, 2023
Deposit Date Apr 5, 2023
Publicly Available Date Mar 28, 2024
Journal Diagnostics
Publisher MDPI
Peer Reviewed Peer Reviewed
Volume 13
Issue 7
Article Number 1309
DOI https://doi.org/10.3390/diagnostics13071309

Files




You might also like



Downloadable Citations