Toggle Main Menu Toggle Search

Open Access padlockePrints

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

Lookup NU author(s): Dr Will Innes, Professor David SteelORCiD, Professor Anya Hurlbert, Professor Jenny ReadORCiD, Dr Rahele Kafieh

Downloads


Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Abstract

© 2023 by the authors.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.


Publication metadata

Author(s): Vali M, Nazari B, Sadri S, Pour EK, Riazi-Esfahani H, Faghihi H, Ebrahimiadib N, Azizkhani M, Innes W, Steel DH, Hurlbert A, Read JCA, Kafieh R

Publication type: Article

Publication status: Published

Journal: Diagnostics

Year: 2023

Volume: 13

Issue: 7

Print publication date: 01/04/2023

Online publication date: 31/03/2023

Acceptance date: 24/03/2023

Date deposited: 05/05/2023

ISSN (electronic): 2075-4418

Publisher: MDPI

URL: https://doi.org/10.3390/diagnostics13071309

DOI: 10.3390/diagnostics13071309


Altmetrics

Altmetrics provided by Altmetric


Funding

Funder referenceFunder name
AI_AWARD01976

Share