Header

UZH-Logo

Maintenance Infos

Validation of automated artificial intelligence segmentation of optical coherence tomography images


Maloca, Peter M; Lee, Aaron Y; de Carvalho, Emanuel R; Okada, Mali; Fasler, Katrin; Leung, Irene; Hörmann, Beat; Kaiser, Pascal; Suter, Susanne; Hasler, Pascal W; Zarranz-Ventura, Javier; Egan, Catherine; Heeren, Tjebo F C; Balaskas, Konstantinos; Tufail, Adnan; Scholl, Hendrik P N (2019). Validation of automated artificial intelligence segmentation of optical coherence tomography images. PLoS ONE, 14(8):e0220063.

Abstract

PURPOSE
To benchmark the human and machine performance of spectral-domain (SD) and swept-source (SS) optical coherence tomography (OCT) image segmentation, i.e., pixel-wise classification, for the compartments vitreous, retina, choroid, sclera.

METHODS
A convolutional neural network (CNN) was trained on OCT B-scan images annotated by a senior ground truth expert retina specialist to segment the posterior eye compartments. Independent benchmark data sets (30 SDOCT and 30 SSOCT) were manually segmented by three classes of graders with varying levels of ophthalmic proficiencies. Nine graders contributed to benchmark an additional 60 images in three consecutive runs. Inter-human and intra-human class agreement was measured and compared to the CNN results.

RESULTS
The CNN training data consisted of a total of 6210 manually segmented images derived from 2070 B-scans (1046 SDOCT and 1024 SSOCT; 630 C-Scans). The CNN segmentation revealed a high agreement with all grader groups. For all compartments and groups, the mean Intersection over Union (IOU) score of CNN compartmentalization versus group graders' compartmentalization was higher than the mean score for intra-grader group comparison.

CONCLUSION
The proposed deep learning segmentation algorithm (CNN) for automated eye compartment segmentation in OCT B-scans (SDOCT and SSOCT) is on par with manual segmentations by human graders.

Abstract

PURPOSE
To benchmark the human and machine performance of spectral-domain (SD) and swept-source (SS) optical coherence tomography (OCT) image segmentation, i.e., pixel-wise classification, for the compartments vitreous, retina, choroid, sclera.

METHODS
A convolutional neural network (CNN) was trained on OCT B-scan images annotated by a senior ground truth expert retina specialist to segment the posterior eye compartments. Independent benchmark data sets (30 SDOCT and 30 SSOCT) were manually segmented by three classes of graders with varying levels of ophthalmic proficiencies. Nine graders contributed to benchmark an additional 60 images in three consecutive runs. Inter-human and intra-human class agreement was measured and compared to the CNN results.

RESULTS
The CNN training data consisted of a total of 6210 manually segmented images derived from 2070 B-scans (1046 SDOCT and 1024 SSOCT; 630 C-Scans). The CNN segmentation revealed a high agreement with all grader groups. For all compartments and groups, the mean Intersection over Union (IOU) score of CNN compartmentalization versus group graders' compartmentalization was higher than the mean score for intra-grader group comparison.

CONCLUSION
The proposed deep learning segmentation algorithm (CNN) for automated eye compartment segmentation in OCT B-scans (SDOCT and SSOCT) is on par with manual segmentations by human graders.

Statistics

Citations

Altmetrics

Downloads

8 downloads since deposited on 15 Jan 2020
8 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Ophthalmology Clinic
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:16 August 2019
Deposited On:15 Jan 2020 15:27
Last Modified:01 Feb 2020 17:59
Publisher:Public Library of Science (PLoS)
ISSN:1932-6203
OA Status:Gold
Free access at:PubMed ID. An embargo period may apply.
Publisher DOI:https://doi.org/10.1371/journal.pone.0220063
PubMed ID:31419240

Download

Gold Open Access

Download PDF  'Validation of automated artificial intelligence segmentation of optical coherence tomography images'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 1MB
View at publisher
Licence: Creative Commons: Public Domain Dedication: CC0 1.0 Universal (CC0 1.0)