Cargando…

Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease

PURPOSE: To train and test convolutional neural networks (CNNs) to automate quality assessment of optical coherence tomography (OCT) and OCT angiography (OCTA) images in patients with neurodegenerative disease. METHODS: Patients with neurodegenerative disease were enrolled in the Duke Eye Multimodal...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Terry, Rivera, Alexandra, Brune, Matthew, Kundu, Anita, Haystead, Alice, Winslow, Lauren, Kundu, Raj, Wisely, C. Ellis, Robbins, Cason B., Henao, Ricardo, Grewal, Dilraj S., Fekrat, Sharon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10318591/
https://www.ncbi.nlm.nih.gov/pubmed/37389540
http://dx.doi.org/10.1167/tvst.12.6.30
_version_ 1785068068577214464
author Lee, Terry
Rivera, Alexandra
Brune, Matthew
Kundu, Anita
Haystead, Alice
Winslow, Lauren
Kundu, Raj
Wisely, C. Ellis
Robbins, Cason B.
Henao, Ricardo
Grewal, Dilraj S.
Fekrat, Sharon
author_facet Lee, Terry
Rivera, Alexandra
Brune, Matthew
Kundu, Anita
Haystead, Alice
Winslow, Lauren
Kundu, Raj
Wisely, C. Ellis
Robbins, Cason B.
Henao, Ricardo
Grewal, Dilraj S.
Fekrat, Sharon
author_sort Lee, Terry
collection PubMed
description PURPOSE: To train and test convolutional neural networks (CNNs) to automate quality assessment of optical coherence tomography (OCT) and OCT angiography (OCTA) images in patients with neurodegenerative disease. METHODS: Patients with neurodegenerative disease were enrolled in the Duke Eye Multimodal Imaging in Neurodegenerative Disease Study. Image inputs were ganglion cell–inner plexiform layer (GC-IPL) thickness maps and fovea-centered 6-mm × 6-mm OCTA scans of the superficial capillary plexus (SCP). Two trained graders manually labeled all images for quality (good versus poor). Interrater reliability (IRR) of manual quality assessment was calculated for a subset of each image type. Images were split into train, validation, and test sets in a 70%/15%/15% split. An AlexNet-based CNN was trained using these labels and evaluated with area under the receiver operating characteristic (AUC) and summaries of the confusion matrix. RESULTS: A total of 1465 GC-IPL thickness maps (1217 good and 248 poor quality) and 2689 OCTA scans of the SCP (1797 good and 892 poor quality) served as model inputs. The IRR of quality assessment agreement by two graders was 97% and 90% for the GC-IPL maps and OCTA scans, respectively. The AlexNet-based CNNs trained to assess quality of the GC-IPL images and OCTA scans achieved AUCs of 0.990 and 0.832, respectively. CONCLUSIONS: CNNs can be trained to accurately differentiate good- from poor-quality GC-IPL thickness maps and OCTA scans of the macular SCP. TRANSLATIONAL RELEVANCE: Since good-quality retinal images are critical for the accurate assessment of microvasculature and structure, incorporating an automated image quality sorter may obviate the need for manual image review.
format Online
Article
Text
id pubmed-10318591
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher The Association for Research in Vision and Ophthalmology
record_format MEDLINE/PubMed
spelling pubmed-103185912023-07-05 Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease Lee, Terry Rivera, Alexandra Brune, Matthew Kundu, Anita Haystead, Alice Winslow, Lauren Kundu, Raj Wisely, C. Ellis Robbins, Cason B. Henao, Ricardo Grewal, Dilraj S. Fekrat, Sharon Transl Vis Sci Technol Artificial Intelligence PURPOSE: To train and test convolutional neural networks (CNNs) to automate quality assessment of optical coherence tomography (OCT) and OCT angiography (OCTA) images in patients with neurodegenerative disease. METHODS: Patients with neurodegenerative disease were enrolled in the Duke Eye Multimodal Imaging in Neurodegenerative Disease Study. Image inputs were ganglion cell–inner plexiform layer (GC-IPL) thickness maps and fovea-centered 6-mm × 6-mm OCTA scans of the superficial capillary plexus (SCP). Two trained graders manually labeled all images for quality (good versus poor). Interrater reliability (IRR) of manual quality assessment was calculated for a subset of each image type. Images were split into train, validation, and test sets in a 70%/15%/15% split. An AlexNet-based CNN was trained using these labels and evaluated with area under the receiver operating characteristic (AUC) and summaries of the confusion matrix. RESULTS: A total of 1465 GC-IPL thickness maps (1217 good and 248 poor quality) and 2689 OCTA scans of the SCP (1797 good and 892 poor quality) served as model inputs. The IRR of quality assessment agreement by two graders was 97% and 90% for the GC-IPL maps and OCTA scans, respectively. The AlexNet-based CNNs trained to assess quality of the GC-IPL images and OCTA scans achieved AUCs of 0.990 and 0.832, respectively. CONCLUSIONS: CNNs can be trained to accurately differentiate good- from poor-quality GC-IPL thickness maps and OCTA scans of the macular SCP. TRANSLATIONAL RELEVANCE: Since good-quality retinal images are critical for the accurate assessment of microvasculature and structure, incorporating an automated image quality sorter may obviate the need for manual image review. The Association for Research in Vision and Ophthalmology 2023-06-30 /pmc/articles/PMC10318591/ /pubmed/37389540 http://dx.doi.org/10.1167/tvst.12.6.30 Text en Copyright 2023 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
spellingShingle Artificial Intelligence
Lee, Terry
Rivera, Alexandra
Brune, Matthew
Kundu, Anita
Haystead, Alice
Winslow, Lauren
Kundu, Raj
Wisely, C. Ellis
Robbins, Cason B.
Henao, Ricardo
Grewal, Dilraj S.
Fekrat, Sharon
Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease
title Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease
title_full Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease
title_fullStr Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease
title_full_unstemmed Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease
title_short Convolutional Neural Network–Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease
title_sort convolutional neural network–based automated quality assessment of oct and oct angiography image maps in individuals with neurodegenerative disease
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10318591/
https://www.ncbi.nlm.nih.gov/pubmed/37389540
http://dx.doi.org/10.1167/tvst.12.6.30
work_keys_str_mv AT leeterry convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT riveraalexandra convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT brunematthew convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT kunduanita convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT haysteadalice convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT winslowlauren convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT kunduraj convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT wiselycellis convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT robbinscasonb convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT henaoricardo convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT grewaldilrajs convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease
AT fekratsharon convolutionalneuralnetworkbasedautomatedqualityassessmentofoctandoctangiographyimagemapsinindividualswithneurodegenerativedisease