Performance analysis of cone detection algorithms

Letizia Mariotti; Nicholas Devaney

doi:10.1364/JOSAA.32.000497

Journal of the Optical Society of America A
Vol. 32,
Issue 4,
pp. 497-506
(2015)
•https://doi.org/10.1364/JOSAA.32.000497

Performance analysis of cone detection algorithms

Letizia Mariotti and Nicholas Devaney

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Letizia Mariotti and Nicholas Devaney, "Performance analysis of cone detection algorithms," J. Opt. Soc. Am. A 32, 497-506 (2015)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Related Topics
Table of Contents Category
- Image Processing
Optics & Photonics Topics
?

The topics in this list come from the Optics and Photonics Topics applied to this article.

About this Article
History
- Original Manuscript: October 9, 2014
- Revised Manuscript: January 22, 2015
- Manuscript Accepted: February 1, 2015
- Published: March 4, 2015
Virtual Issues
Virtual Journal for Biomedical Optics Vol. 10, Iss. 5

Abstract

Many algorithms have been proposed to help clinicians evaluate cone density and spacing, as these may be related to the onset of retinal diseases. However, there has been no rigorous comparison of the performance of these algorithms. In addition, the performance of such algorithms is typically determined by comparison with human observers. Here we propose a technique to simulate realistic images of the cone mosaic. We use the simulated images to test the performance of three popular cone detection algorithms, and we introduce an algorithm which is used by astronomers to detect stars in astronomical images. We use Free Response Operating Characteristic (FROC) curves to evaluate and compare the performance of the four algorithms. This allows us to optimize the performance of each algorithm. We observe that performance is significantly enhanced by up-sampling the images. We investigate the effect of noise and image quality on cone mosaic parameters estimated using the different algorithms, finding that the estimated regularity is the most sensitive parameter.

Full Article | PDF Article

More Like This

Hessian-LoG filtering for enhancement and detection of photoreceptor cells in adaptive optics retinal images

Anfisa Lazareva, Panos Liatsis, and Franziska G. Rauscher
J. Opt. Soc. Am. A 33(1) 84-94 (2016)

Semi-automated identification of cones in the human retina using circle Hough transform

Danuta M. Bukowska, Avenell L. Chew, Emily Huynh, Irwin Kashani, Sue Ling Wan, Pak Ming Wan, and Fred K Chen
Biomed. Opt. Express 6(12) 4676-4693 (2015)

Automated segmentation of retinal pigment epithelium cells in fluorescence adaptive optics images

Piero Rangel-Fonseca, Armando Gómez-Vieyra, Daniel Malacara-Hernández, Mario C. Wilson, David R. Williams, and Ethan A. Rossi
J. Opt. Soc. Am. A 30(12) 2595-2604 (2013)

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (7)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (2)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Image	Cone Density ( $cones / {mm}^{2}$ )	Number of Cones (Boundaries Excluded)	Regularity (Percentage of Hexagonal Cells)	Mean NND (μm)
1	25,933	3606	46.03	4.76
2	25,583	3557	47.17	4.82
3	25,691	3576	45.33	4.80
4	25,598	3566	45.54	4.81
5	25,805	3592	47.80	4.79
6	25,825	3596	45.13	4.78
7	25,607	3570	46.44	4.79
8	25,764	3588	48.10	4.80
9	25,663	3576	46.39	4.81
10	25,867	3600	45.14	4.77
Mean $\pm$ St Dev	$25,734 \pm 123$	$3583 \pm 16$	$46.31 \pm 1.09$	$4.79 \pm 0.02$

	Cone Density	Regularity	Mean NND
Resize x1
Li and Roorda	$- 13.83 \pm 0.92$	$- 10.68 \pm 2.81$	$5.69 \pm 0.53$
Xue et al.	$- 28.00 \pm 3.68$	$- 20.59 \pm 2.50$	$9.32 \pm 2.65$
Chiu et al.	$- 17.09 \pm 0.54$	$- 7.24 \pm 2.48$	$12.75 \pm 0.38$
DAOPHOT	$- 37.41 \pm 2.00$	$- 18.35 \pm 3.10$	$10.80 \pm 1.48$
Resize x2
Li and Roorda	$- 12.88 \pm 0.86$	$- 8.83 \pm 2.19$	$5.60 \pm 0.60$
Xue et al.	$- 11.57 \pm 1.30$	$- 8.71 \pm 2.54$	$7.19 \pm 0.78$
Chiu et al.	$- 2.68 \pm 0.64$	$- 0.58 \pm 1.62$	$4.67 \pm 0.34$
DAOPHOT	$- 2.84 \pm 0.23$	$- 4.08 \pm 2.19$	$- 1.85 \pm 0.35$
Resize x3
Li and Roorda	$- 11.39 \pm 0.66$	$- 8.48 \pm 2.39$	$4.78 \pm 0.49$
Xue et al.	$- 7.32 \pm 0.73$	$- 4.91 \pm 1.64$	$6.36 \pm 0.39$
Chiu et al.	$- 3.19 \pm 1.78$	$- 2.98 \pm 1.85$	$2.03 \pm 0.55$
DAOPHOT	$- 5.18 \pm 0.35$	$- 6.93 \pm 2.42$	$- 2.56 \pm 0.40$

Image	Cone Density ( $cones / {mm}^{2}$ )	Number of Cones (Boundaries Excluded)	Regularity (Percentage of Hexagonal Cells)	Mean NND (μm)
1	25,933	3606	46.03	4.76
2	25,583	3557	47.17	4.82
3	25,691	3576	45.33	4.80
4	25,598	3566	45.54	4.81
5	25,805	3592	47.80	4.79
6	25,825	3596	45.13	4.78
7	25,607	3570	46.44	4.79
8	25,764	3588	48.10	4.80
9	25,663	3576	46.39	4.81
10	25,867	3600	45.14	4.77
Mean $\pm$ St Dev	$25,734 \pm 123$	$3583 \pm 16$	$46.31 \pm 1.09$	$4.79 \pm 0.02$

	Cone Density	Regularity	Mean NND
Resize x1
Li and Roorda	$- 13.83 \pm 0.92$	$- 10.68 \pm 2.81$	$5.69 \pm 0.53$
Xue et al.	$- 28.00 \pm 3.68$	$- 20.59 \pm 2.50$	$9.32 \pm 2.65$
Chiu et al.	$- 17.09 \pm 0.54$	$- 7.24 \pm 2.48$	$12.75 \pm 0.38$
DAOPHOT	$- 37.41 \pm 2.00$	$- 18.35 \pm 3.10$	$10.80 \pm 1.48$
Resize x2
Li and Roorda	$- 12.88 \pm 0.86$	$- 8.83 \pm 2.19$	$5.60 \pm 0.60$
Xue et al.	$- 11.57 \pm 1.30$	$- 8.71 \pm 2.54$	$7.19 \pm 0.78$
Chiu et al.	$- 2.68 \pm 0.64$	$- 0.58 \pm 1.62$	$4.67 \pm 0.34$
DAOPHOT	$- 2.84 \pm 0.23$	$- 4.08 \pm 2.19$	$- 1.85 \pm 0.35$
Resize x3
Li and Roorda	$- 11.39 \pm 0.66$	$- 8.48 \pm 2.39$	$4.78 \pm 0.49$
Xue et al.	$- 7.32 \pm 0.73$	$- 4.91 \pm 1.64$	$6.36 \pm 0.39$
Chiu et al.	$- 3.19 \pm 1.78$	$- 2.98 \pm 1.85$	$2.03 \pm 0.55$
DAOPHOT	$- 5.18 \pm 0.35$	$- 6.93 \pm 2.42$	$- 2.56 \pm 0.40$

Abstract

Cited By

Figures (7)

Tables (2)

Journal of the Optical Society of America A