Normative Data and Minimally Detectable Change for Inner Retinal Layer Thicknesses Using a Semi-automated OCT Image Segmentation Pipeline

Motamedi, Seyedamirhosein; Gawlik, K.; Ayadi, Noah; Zimmermann, Hanna; Asseyer, Susanna; Bereuter, Charlotte; Mikolajczak, Janine; Paul, Friedemann; Kadas, Ella-Maria; Brandt, Alexander U.

doi:10.3389/fneur.2019.01117

Cited by 39 publications

(51 citation statements)

References 46 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OCT data are compared with our suggested method in terms of "simplicity and availability", whereas the Livelayer's ability to segment different types of OCTs was argued in the previous sections of this study. OCTMarker [20] is an integrated software package that could only detect up to 3 retinal boundaries automatically. EdgeSelect [16] and SAMIRIX [20] Including an error correction functionality…”

Section: Conclusion and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Livelayer: A Semi-Automatic Software Program for Segmentation of Layers and Diabetic Macular Edema in Optical Coherence Tomography Images

Montazerin

Sajjadifar

Pour

et al. 2021

Preprint

View full text Add to dashboard Cite

Given the capacity of Optical Coherence Tomography (OCT) imaging to display symptoms of a wide variety of eye diseases and neurological disorders, the need for OCT image segmentation and the corresponding data interpretation is latterly felt more than ever before. In this paper, we wish to address this need by designing a semi-automatic software program for applying reliable segmentation of 8 different macular layers as well as outlining retinal pathologies such as diabetic macular edema. The software accommodates a novel graph-based semi-automatic method, called “Livelayer” which is designed for straightforward segmentation of retinal layers and fluids. This method is chiefly based on Dijkstra’s Shortest Path (SPF) algorithm and the Live-wire function together with some preprocessing operations on the to-be-segmented images. The software is indeed suitable for obtaining detailed segmentation of layers, exact localization of clear or unclear fluid objects and the ground truth, demanding far less endeavor in comparison to a common manual segmentation method. It is also valuable as a tool for calculating the irregularity index in deformed OCT images. The amount of time (seconds) that Livelayer required for segmentation of ILM, IPL-INL, OPL-ONL was much less than that for the manual segmentation, 5s for the ILM (minimum) and 15.57s for the OPL-ONL (maximum). The unsigned errors (pixels) between the semi-automatically labeled and gold standard data was on average 2.7, 1.9, 2.1 for ILM, IPL-INL, OPL-ONL, respectively. The Bland-Altman plots indicated perfect concordance between the Livelayer and the manual algorithm and that they could be used interchangeably. The repeatability error was around one pixel for the OPL-ONL and < 1 for the other two. The dice scores for comparing the two algorithms and for obtaining the repeatability on segmentation of fluid objects were at acceptable levels.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

“…OCTMarker [20] is an integrated software package that could only detect up to 3 retinal boundaries automatically. EdgeSelect [16] and SAMIRIX [20] Including an error correction functionality…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Livelayer: A Semi-Automatic Software Program for Segmentation of Layers and Diabetic Macular Edema in Optical Coherence Tomography Images

Montazerin

Sajjadifar

Pour

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“… Flow chart explaining the overall study design and information technology (IT) infrastructure. DCC, Data Coordinating Center; OCT, optical coherence tomography; REDCap, Research Electronic Data Capture; SAMIRIX is a custom-developed intraretinal segmentation pipeline 55 . OSCAR-IB are validated consensus quality criteria for retinal OCT reading 53 .…”

Section: Cohort Descriptionmentioning

confidence: 99%

“…pRNFL segmentation was performed with device-internal algorithms, intraretinal layer segmentation with a device-independent segmentation pipeline. 55 …”

Section: Cohort Descriptionmentioning

confidence: 99%

“… 60 This pipeline is capable of importing and segmenting OCT scans from all devices included in the study and will presumably lead to better comparability of OCT data obtained from different devices. 55 Finally, we modified the widely used OSCAR-IB criteria 53 for assessing OCT image quality to be applicable to macular volume scans and all OCT devices. The modified criteria will be validated using data from our repository.…”

Section: Cohort Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Cohort profile: a collaborative multicentre study of retinal optical coherence tomography in 539 patients with neuromyelitis optica spectrum disorders (CROCTINO)

et al. 2020

Self Cite

View full text Add to dashboard Cite

PurposeOptical coherence tomography (OCT) captures retinal damage in neuromyelitis optica spectrum disorders (NMOSD). Previous studies investigating OCT in NMOSD have been limited by the rareness and heterogeneity of the disease. The goal of this study was to establish an image repository platform, which will facilitate neuroimaging studies in NMOSD. Here we summarise the profile of the Collaborative OCT in NMOSD repository as the initial effort in establishing this platform. This repository should prove invaluable for studies using OCT to investigate NMOSD.ParticipantsThe current cohort includes data from 539 patients with NMOSD and 114 healthy controls. These were collected at 22 participating centres from North and South America, Asia and Europe. The dataset consists of demographic details, diagnosis, antibody status, clinical disability, visual function, history of optic neuritis and other NMOSD defining attacks, and OCT source data from three different OCT devices.Findings to dateThe cohort informs similar demographic and clinical characteristics as those of previously published NMOSD cohorts. The image repository platform and centre network continue to be available for future prospective neuroimaging studies in NMOSD. For the conduct of the study, we have refined OCT image quality criteria and developed a cross-device intraretinal segmentation pipeline.Future plansWe are pursuing several scientific projects based on the repository, such as analysing retinal layer thickness measurements, in this cohort in an attempt to identify differences between distinct disease phenotypes, demographics and ethnicities. The dataset will be available for further projects to interested, qualified parties, such as those using specialised image analysis or artificial intelligence applications.

show abstract

Prior optic neuritis detection on peripapillary ring scans using deep learning

Motamedi

Yadav

Kenney

et al. 2022

Ann Clin Transl Neurol

Self Cite

View full text Add to dashboard Cite

Background: The diagnosis of multiple sclerosis (MS) requires demyelinating events that are disseminated in time and space. Peripapillary retinal nerve fiber layer (pRNFL) thickness as measured by optical coherence tomography (OCT) distinguishes eyes with a prior history of acute optic neuritis (ON) and may provide evidence to support a demyelinating attack. Objective: To investigate whether a deep learning (DL)-based network can distinguish between eyes with prior ON and healthy control (HC) eyes using peripapillary ring scans. Methods: We included 1033 OCT scans from 415 healthy eyes (213 HC subjects) and 510 peripapillary ring scans from 164 eyes with prior acute ON (140 patients with MS). Data were split into 70% training, 15% validation, and 15% test data. We included 102 OCT scans from 80 healthy eyes (40 HC) and 61 scans from 40 ON eyes (31 MS patients) from an independent second center. Receiver operating characteristic curve analyses with area under the curve (AUC) were used to investigate performance. Results: We used a dilated residual convolutional neural network for the classification. The final network had an accuracy of 0.85 and an AUC of 0.86, whereas pRNFL only had an AUC of 0.77 in recognizing ON eyes. Using data from a second center, the network achieved an accuracy of 0.77 and an AUC of 0.90 compared to pRNFL, which had an AUC of 0.84. Interpretation: DL-based disease classification of prior ON is feasible and has the potential to outperform thickness-based classification of eyes with and without history of prior ON.

show abstract

Normative Data and Minimally Detectable Change for Inner Retinal Layer Thicknesses Using a Semi-automated OCT Image Segmentation Pipeline

Cited by 39 publications

References 46 publications

Livelayer: A Semi-Automatic Software Program for Segmentation of Layers and Diabetic Macular Edema in Optical Coherence Tomography Images

Livelayer: A Semi-Automatic Software Program for Segmentation of Layers and Diabetic Macular Edema in Optical Coherence Tomography Images

Cohort profile: a collaborative multicentre study of retinal optical coherence tomography in 539 patients with neuromyelitis optica spectrum disorders (CROCTINO)

Prior optic neuritis detection on peripapillary ring scans using deep learning

Contact Info

Product

Resources

About