Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images

E. Ataer-Cansizoglu, Y. Taguchi, Jayashree Kalpathy-Cramer, Michael Chiang, D. Erdogmus

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

4 Citations (Scopus)

Abstract

Utilizing priors about the shape of retinal surface is important for accurate reconstruction. We present a detailed analysis of geometrical shape priors in the 3D reconstruction of retina. We first approximate the retinal surface either as a sphere inspired by the actual shape of the eyeball, or as a plane inspired by the 2D mosaicing approaches. Based on this approximation, we perform an initial camera localization with a 2D-to-3D registration procedure. Then, parameters of the surface and the camera poses are refined through a nonlinear least squares optimization using different shape priors. The resulting 3D model and camera poses can be used for intuitively visualizing the retinal images with a model-guided browsing interface.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages1502-1505
Number of pages4
Volume2015-July
ISBN (Print)9781479923748
DOIs
StatePublished - Jul 21 2015
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: Apr 16 2015Apr 19 2015

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period4/16/154/19/15

Fingerprint

Least-Squares Analysis
Retina
Cameras

Keywords

  • 3D reconstruction
  • retinal images
  • visualization

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Ataer-Cansizoglu, E., Taguchi, Y., Kalpathy-Cramer, J., Chiang, M., & Erdogmus, D. (2015). Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images. In Proceedings - International Symposium on Biomedical Imaging (Vol. 2015-July, pp. 1502-1505). [7164162] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7164162

Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images. / Ataer-Cansizoglu, E.; Taguchi, Y.; Kalpathy-Cramer, Jayashree; Chiang, Michael; Erdogmus, D.

Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. p. 1502-1505 7164162.

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

Ataer-Cansizoglu, E, Taguchi, Y, Kalpathy-Cramer, J, Chiang, M & Erdogmus, D 2015, Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images. in Proceedings - International Symposium on Biomedical Imaging. vol. 2015-July, 7164162, IEEE Computer Society, pp. 1502-1505, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 4/16/15. https://doi.org/10.1109/ISBI.2015.7164162
Ataer-Cansizoglu E, Taguchi Y, Kalpathy-Cramer J, Chiang M, Erdogmus D. Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images. In Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July. IEEE Computer Society. 2015. p. 1502-1505. 7164162 https://doi.org/10.1109/ISBI.2015.7164162
Ataer-Cansizoglu, E. ; Taguchi, Y. ; Kalpathy-Cramer, Jayashree ; Chiang, Michael ; Erdogmus, D. / Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images. Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. pp. 1502-1505
@inproceedings{52fdf8ac0f864b2a8d9899c6d4ec8573,
title = "Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images",
abstract = "Utilizing priors about the shape of retinal surface is important for accurate reconstruction. We present a detailed analysis of geometrical shape priors in the 3D reconstruction of retina. We first approximate the retinal surface either as a sphere inspired by the actual shape of the eyeball, or as a plane inspired by the 2D mosaicing approaches. Based on this approximation, we perform an initial camera localization with a 2D-to-3D registration procedure. Then, parameters of the surface and the camera poses are refined through a nonlinear least squares optimization using different shape priors. The resulting 3D model and camera poses can be used for intuitively visualizing the retinal images with a model-guided browsing interface.",
keywords = "3D reconstruction, retinal images, visualization",
author = "E. Ataer-Cansizoglu and Y. Taguchi and Jayashree Kalpathy-Cramer and Michael Chiang and D. Erdogmus",
year = "2015",
month = "7",
day = "21",
doi = "10.1109/ISBI.2015.7164162",
language = "English (US)",
isbn = "9781479923748",
volume = "2015-July",
pages = "1502--1505",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Analysis of shape assumptions in 3D reconstruction of retina from multiple fundus images

AU - Ataer-Cansizoglu, E.

AU - Taguchi, Y.

AU - Kalpathy-Cramer, Jayashree

AU - Chiang, Michael

AU - Erdogmus, D.

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Utilizing priors about the shape of retinal surface is important for accurate reconstruction. We present a detailed analysis of geometrical shape priors in the 3D reconstruction of retina. We first approximate the retinal surface either as a sphere inspired by the actual shape of the eyeball, or as a plane inspired by the 2D mosaicing approaches. Based on this approximation, we perform an initial camera localization with a 2D-to-3D registration procedure. Then, parameters of the surface and the camera poses are refined through a nonlinear least squares optimization using different shape priors. The resulting 3D model and camera poses can be used for intuitively visualizing the retinal images with a model-guided browsing interface.

AB - Utilizing priors about the shape of retinal surface is important for accurate reconstruction. We present a detailed analysis of geometrical shape priors in the 3D reconstruction of retina. We first approximate the retinal surface either as a sphere inspired by the actual shape of the eyeball, or as a plane inspired by the 2D mosaicing approaches. Based on this approximation, we perform an initial camera localization with a 2D-to-3D registration procedure. Then, parameters of the surface and the camera poses are refined through a nonlinear least squares optimization using different shape priors. The resulting 3D model and camera poses can be used for intuitively visualizing the retinal images with a model-guided browsing interface.

KW - 3D reconstruction

KW - retinal images

KW - visualization

UR - http://www.scopus.com/inward/record.url?scp=84944319871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944319871&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7164162

DO - 10.1109/ISBI.2015.7164162

M3 - Conference contribution

AN - SCOPUS:84944319871

SN - 9781479923748

VL - 2015-July

SP - 1502

EP - 1505

BT - Proceedings - International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -