A method for identifying distribution pattern of cone cells in retina image

Ken'ichi Morooka, Yuanting Ji, Oscar Martinez Mozos, Tokuo Tsuji, Ryo Kurazume, Peter K. Ahnelt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a method to identify the spatial distribution patterns of cone cells related with blood vessel in a given retina image. We define three types of the distribution patterns between cones and vessels. Positive correlation distribution (PCD) and negative correlation distribution (NCD) indicate that the cones tend to be close to or far from the vessels. While the cone cells do not have significant correlation with vessels, the cone distribution is regarded as the random distribution (RD). In our method, RD is modeled by many virtual retina images, each of which is generated by the vessels extracted from the original retina image and the virtual cells are selected randomly from the image. Using the virtual images, we estimate the distribution range of RD. When the distribution of the original cells is above the upper limit or below the lower limit of the RD distribution, the cell distribution is NCD or PCD. Otherwise, the cell distribution is regarded as RD.

Original languageEnglish
Title of host publicationWorld Automation Congress Proceedings
PublisherIEEE Computer Society
Pages774-778
Number of pages5
ISBN (Electronic)9781889335490
DOIs
Publication statusPublished - Oct 24 2014
Event2014 World Automation Congress, WAC 2014 - Waikoloa, United States
Duration: Aug 3 2014Aug 7 2014

Publication series

NameWorld Automation Congress Proceedings
ISSN (Print)2154-4824
ISSN (Electronic)2154-4832

Other

Other2014 World Automation Congress, WAC 2014
CountryUnited States
CityWaikoloa
Period8/3/148/7/14

Fingerprint

Cones
Blood vessels
Spatial distribution

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Morooka, K., Ji, Y., Mozos, O. M., Tsuji, T., Kurazume, R., & Ahnelt, P. K. (2014). A method for identifying distribution pattern of cone cells in retina image. In World Automation Congress Proceedings (pp. 774-778). [6936144] (World Automation Congress Proceedings). IEEE Computer Society. https://doi.org/10.1109/WAC.2014.6936144

A method for identifying distribution pattern of cone cells in retina image. / Morooka, Ken'ichi; Ji, Yuanting; Mozos, Oscar Martinez; Tsuji, Tokuo; Kurazume, Ryo; Ahnelt, Peter K.

World Automation Congress Proceedings. IEEE Computer Society, 2014. p. 774-778 6936144 (World Automation Congress Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Morooka, K, Ji, Y, Mozos, OM, Tsuji, T, Kurazume, R & Ahnelt, PK 2014, A method for identifying distribution pattern of cone cells in retina image. in World Automation Congress Proceedings., 6936144, World Automation Congress Proceedings, IEEE Computer Society, pp. 774-778, 2014 World Automation Congress, WAC 2014, Waikoloa, United States, 8/3/14. https://doi.org/10.1109/WAC.2014.6936144
Morooka K, Ji Y, Mozos OM, Tsuji T, Kurazume R, Ahnelt PK. A method for identifying distribution pattern of cone cells in retina image. In World Automation Congress Proceedings. IEEE Computer Society. 2014. p. 774-778. 6936144. (World Automation Congress Proceedings). https://doi.org/10.1109/WAC.2014.6936144
Morooka, Ken'ichi ; Ji, Yuanting ; Mozos, Oscar Martinez ; Tsuji, Tokuo ; Kurazume, Ryo ; Ahnelt, Peter K. / A method for identifying distribution pattern of cone cells in retina image. World Automation Congress Proceedings. IEEE Computer Society, 2014. pp. 774-778 (World Automation Congress Proceedings).
@inproceedings{76d6a277c743436c8030f0403fe294a4,
title = "A method for identifying distribution pattern of cone cells in retina image",
abstract = "This paper proposes a method to identify the spatial distribution patterns of cone cells related with blood vessel in a given retina image. We define three types of the distribution patterns between cones and vessels. Positive correlation distribution (PCD) and negative correlation distribution (NCD) indicate that the cones tend to be close to or far from the vessels. While the cone cells do not have significant correlation with vessels, the cone distribution is regarded as the random distribution (RD). In our method, RD is modeled by many virtual retina images, each of which is generated by the vessels extracted from the original retina image and the virtual cells are selected randomly from the image. Using the virtual images, we estimate the distribution range of RD. When the distribution of the original cells is above the upper limit or below the lower limit of the RD distribution, the cell distribution is NCD or PCD. Otherwise, the cell distribution is regarded as RD.",
author = "Ken'ichi Morooka and Yuanting Ji and Mozos, {Oscar Martinez} and Tokuo Tsuji and Ryo Kurazume and Ahnelt, {Peter K.}",
year = "2014",
month = "10",
day = "24",
doi = "10.1109/WAC.2014.6936144",
language = "English",
series = "World Automation Congress Proceedings",
publisher = "IEEE Computer Society",
pages = "774--778",
booktitle = "World Automation Congress Proceedings",
address = "United States",

}

TY - GEN

T1 - A method for identifying distribution pattern of cone cells in retina image

AU - Morooka, Ken'ichi

AU - Ji, Yuanting

AU - Mozos, Oscar Martinez

AU - Tsuji, Tokuo

AU - Kurazume, Ryo

AU - Ahnelt, Peter K.

PY - 2014/10/24

Y1 - 2014/10/24

N2 - This paper proposes a method to identify the spatial distribution patterns of cone cells related with blood vessel in a given retina image. We define three types of the distribution patterns between cones and vessels. Positive correlation distribution (PCD) and negative correlation distribution (NCD) indicate that the cones tend to be close to or far from the vessels. While the cone cells do not have significant correlation with vessels, the cone distribution is regarded as the random distribution (RD). In our method, RD is modeled by many virtual retina images, each of which is generated by the vessels extracted from the original retina image and the virtual cells are selected randomly from the image. Using the virtual images, we estimate the distribution range of RD. When the distribution of the original cells is above the upper limit or below the lower limit of the RD distribution, the cell distribution is NCD or PCD. Otherwise, the cell distribution is regarded as RD.

AB - This paper proposes a method to identify the spatial distribution patterns of cone cells related with blood vessel in a given retina image. We define three types of the distribution patterns between cones and vessels. Positive correlation distribution (PCD) and negative correlation distribution (NCD) indicate that the cones tend to be close to or far from the vessels. While the cone cells do not have significant correlation with vessels, the cone distribution is regarded as the random distribution (RD). In our method, RD is modeled by many virtual retina images, each of which is generated by the vessels extracted from the original retina image and the virtual cells are selected randomly from the image. Using the virtual images, we estimate the distribution range of RD. When the distribution of the original cells is above the upper limit or below the lower limit of the RD distribution, the cell distribution is NCD or PCD. Otherwise, the cell distribution is regarded as RD.

UR - http://www.scopus.com/inward/record.url?scp=84908876283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908876283&partnerID=8YFLogxK

U2 - 10.1109/WAC.2014.6936144

DO - 10.1109/WAC.2014.6936144

M3 - Conference contribution

AN - SCOPUS:84908876283

T3 - World Automation Congress Proceedings

SP - 774

EP - 778

BT - World Automation Congress Proceedings

PB - IEEE Computer Society

ER -