Applicability of optical coherence tomography angiography (OCTA) imaging in Parkinson’s disease

Lauermann, Jost Lennart; Sochurek, Jan A M; Plöttner, Pauline; Alten, Florian; Kasten, Meike; Prasuhn, Jannik; Brüggemann, Norbert; Ranjbar, Mahdy

doi:10.1038/s41598-021-84862-x

Cited by 14 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning studies usually require manual review and exclusion of poor-quality images and utilize poor signal strength and the presence of artifacts in OCT or OCTA scans as exclusion criteria. 20 , 21 This can be an incredibly time-consuming and labor-intensive process and is prone to human error, which results in a large degree of variability between studies regarding which images are deemed to have acceptable quality for inclusion. To facilitate and streamline the process of image quality assessment, machine-reported signal strength has been proposed as a way of filtering out good- and poor-quality images because signal strength has been shown to impact the accuracy of quantitative measurements derived from OCT 10 , 22 and OCTA images.…”

Section: Discussionmentioning

confidence: 99%

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

Lee,

Rivera,

Brune

et al. 2023

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Lee,

Rivera,

Brune

et al. 2023

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…OCTA images were generated using the OMAG algorithm, and an auxiliary real-time line scan ophthalmoscope (LSO) reduced motion artifacts. Similar to our previous reports, volumetric EDI-OCT (10 × 10 mm 2 ) and OCTA (3 × 3 mm 2 ) scans of the posterior pole of both eyes were captured [ 8 , 11 , 15 ]. As recommended by the guidelines on OCTA imaging, only scans with a signal strength ≥ 8, centered on the fovea, and without motion, segmentation, and projection artifacts were included [ 17 ].…”

Section: Methodsmentioning

confidence: 99%

“…Imaging of the choroidal vasculature during pregnancy has been limited due to concerns regarding the use of mydriatic eye drops and fluorescein dye. However, optical coherence tomography (OCT) and technical upgrades such as enhanced depth imaging (EDI), as well as OCT angiography (OCTA), cleared that obstacle as they are non-invasive and do not require pupillary dilation [ 6 , 7 , 8 ]. OCT- and OCTA-based imaging of the choroid revolutionized our pathophysiological understanding of various diseases, and choroidal metrics such as subfoveal choroidal thickness (SFCT) have been suggested as potential biomarkers in this regard [ 9 , 10 ].…”

Section: Introductionmentioning

confidence: 99%

Vascular Choroidal Alterations in Uncomplicated Third-Trimester Pregnancy

Sochurek¹,

Gembicki

Grisanti

et al. 2022

Tomography

View full text Add to dashboard Cite

(1) Purpose: To evaluate the anatomy and perfusion of choroidal substructures in third-trimester pregnant women using optical coherence tomography (OCT) and OCT angiography (OCTA) imaging. (2) Methods: In this cross-sectional study, women in their third trimester of uncomplicated pregnancy and non-pregnant age-matched women were recruited. Participants underwent enhanced depth imaging (EDI) OCT and OCTA. Subfoveal choroidal thickness (SFCT), as well as choroidal sublayer perfusion, were compared between groups. (3) Results: In total, 26 eyes of 26 pregnant and 26 eyes of 26 non-pregnant women were included. The median age in both groups was 29 years. The median SFCT was 332 (211–469) µm in the pregnant group and 371.5 (224–466) µm in the non-pregnant cohort (p = 0.018). The median choriocapillaris perfusion (CCP) was significantly lower in the pregnant group (46% vs. 48%, p = 0.039). Moreover, Haller’s layer perfusion correlated significantly with mean arterial pressure in non-pregnant women (CC = 0.430, p = 0.028) but not in pregnant ones (CC = 0.054, p = 0.792). (4) Conclusions: SFCT was found to be thinner and CCP was lower in third-trimester pregnant women. Hormonal changes during pregnancy and consecutive impacts on autoregulation of small choroidal vessels might play an important role. Therefore, altered choroidal measurements during third-trimester pregnancy should be carefully evaluated as, to some extent, it could be a normal physiological change.

show abstract

“…Na Newcastle University trwa obecnie (2021) projekt Octahedron (Optical Coherence Tomography Automated Heuristics for Early Diagnosis via Retina in Ophthalmology and Neurology), którego celem jest jak najwcześniejsze wykrycie początkowych objawów chorób neurodegeneracyjnych na podstawie obrazowania siatkówki. Tworzony system wykorzystuje niezwykle szczegółowe dane obrazowe pozyskane techniką OCT (optical coherence tomography) (Lauermann et al, 2021), uwidaczniające poszczególne warstwy komórek nerwowych. Obrazy są następnie analizowane metodami ML.…”

Section: Wybrane Projekty I Narzędziaunclassified

Application of artificial intelligence and machine learning techniques in supporting the diagnosis and treatment of neurological diseases

Belowska-Bień¹,

Bień²

2021

Aktualn Neurol

View full text Add to dashboard Cite

The first two decades of the 21st century have seen great advances in artificial intelligence and machine learning. The techniques have found their way into everyday life, for example in smartphones, search engines, digital customer assistants, motion control systems, and biomedical devices. The aims of this paper are to outline the possibilities for using artificial intelligence and machine learning techniques in supporting the diagnosis and treatment of neurological diseases, and to discuss selected applications of these techniques based on the most recent published reports. First, contemporary definitions of artificial intelligence and machine learning are presented. This is followed by a review of the most important techniques for intelligent data processing: search methods, mathematical logic, probabilistic methods, classifiers, and artificial neural networks (including deep and convolutional networks). Areas of application of these techniques in medicine are identified, including disease diagnosis and support of treatment as well as monitoring and prediction of changes in health status. The role of artificial intelligence and machine learning in neuroscience is presented, together with examples of diagnostic applications based on anatomical, morphological and functional brain connectivity data. Sample applications of intelligent techniques in supporting the treatment (including surgical management) of nervous system diseases are also described. Ambient smart devices monitoring the health status of patients with chronic neurological conditions are discussed, and selected projects based on smart techniques to support early detection of symptoms of neurodegenerative disorders are described. The conclusions highlight the potential of the techniques, as well as the challenges and risks associated with them. A possible synergy between intelligent systems and actions taken by medical staff is outlined as a way to improve the safety and quality of life of patients with acute and chronic neurological diseases.

show abstract

Applicability of optical coherence tomography angiography (OCTA) imaging in Parkinson’s disease

Cited by 14 publications

References 31 publications

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

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

Vascular Choroidal Alterations in Uncomplicated Third-Trimester Pregnancy

Application of artificial intelligence and machine learning techniques in supporting the diagnosis and treatment of neurological diseases

Contact Info

Product

Resources

About