Detail publikačního výsledku

Blind Source Separation of Different Retinal Pulsatile Patterns from Simultaneous Long-term Binocular Ophthalmoscopic Video-records

LABOUNKOVÁ, I.; LABOUNEK, R.; ODSTRČILÍK, J.; HRACHO, M.; NESTRAŠIL, I.; TORNOW, R.; KOLÁŘ, R.

Originální název

Blind Source Separation of Different Retinal Pulsatile Patterns from Simultaneous Long-term Binocular Ophthalmoscopic Video-records

Anglický název

Blind Source Separation of Different Retinal Pulsatile Patterns from Simultaneous Long-term Binocular Ophthalmoscopic Video-records

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

Optical imaging of retinal hemodynamic function is an important part of ophthalmologic research. Development and inventing of imaging devices and data analysis methods are both just in progress. The current study innovatively implements two blind source separation (BSS) techniques (i.e. spatial Principal Component Analysis – sPCA; and spatial Independent Component Analysis – sICA) in application of an automatic detection and segmentation of a distinct Optic Disc (OD) areas with different hemodynamic properties from a simultaneous binocular video-ophthalmoscopic records. Both methods detected 3 different spatial patterns mostly symmetric over both eyes stable and reproducible over investigated participants, i.e. central Spontaneous Vessel Pulsations (SVPs), inner OD intensity pulsations and other OD pulsations. Dynamics of all mentioned patterns has a periodic character with similar main frequency (possibly corresponding to subject-specific heart rate) but shifted phase decreasing patterns’ mutual high crosscorrelations. The sICA estimates a higher rate of phase shifts than sPCA.

Anglický abstrakt

Optical imaging of retinal hemodynamic function is an important part of ophthalmologic research. Development and inventing of imaging devices and data analysis methods are both just in progress. The current study innovatively implements two blind source separation (BSS) techniques (i.e. spatial Principal Component Analysis – sPCA; and spatial Independent Component Analysis – sICA) in application of an automatic detection and segmentation of a distinct Optic Disc (OD) areas with different hemodynamic properties from a simultaneous binocular video-ophthalmoscopic records. Both methods detected 3 different spatial patterns mostly symmetric over both eyes stable and reproducible over investigated participants, i.e. central Spontaneous Vessel Pulsations (SVPs), inner OD intensity pulsations and other OD pulsations. Dynamics of all mentioned patterns has a periodic character with similar main frequency (possibly corresponding to subject-specific heart rate) but shifted phase decreasing patterns’ mutual high crosscorrelations. The sICA estimates a higher rate of phase shifts than sPCA.

Klíčová slova

retinal imaging, spontaneous venous pulsation, principal component analysis, independent component analysis

Klíčová slova v angličtině

retinal imaging, spontaneous venous pulsation, principal component analysis, independent component analysis

Autoři

LABOUNKOVÁ, I.; LABOUNEK, R.; ODSTRČILÍK, J.; HRACHO, M.; NESTRAŠIL, I.; TORNOW, R.; KOLÁŘ, R.

Rok RIV

2020

Vydáno

23.07.2019

Kniha

Proceedings of IEEE Engineering in Medicine and Biology Conference

ISSN

1557-170X

Periodikum

Proceedings IEEE EMBC

Stát

Spojené státy americké

Strany od

4729

Strany do

4732

Strany počet

4

URL

https://ieeexplore.ieee.org/document/8857560

BibTex

@inproceedings{BUT158328,
  author="LABOUNKOVÁ, I. and LABOUNEK, R. and ODSTRČILÍK, J. and HRACHO, M. and NESTRAŠIL, I. and TORNOW, R. and KOLÁŘ, R.",
  title="Blind Source Separation of Different Retinal Pulsatile Patterns from Simultaneous Long-term Binocular Ophthalmoscopic Video-records",
  booktitle="Proceedings of IEEE Engineering in Medicine and Biology Conference",
  year="2019",
  journal="Proceedings IEEE EMBC",
  pages="4729--4732",
  doi="10.1109/EMBC.2019.8857560",
  issn="1557-170X",
  url="https://ieeexplore.ieee.org/document/8857560"
}