Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm

C. Agurto; S. Barriga; V. Murray; M. Pattichis; P. Soliz

doi:10.1117/12.844431

Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm

C. Agurto
, S. Barriga
, V. Murray
, M. Pattichis
, P. Soliz

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Diabetic retinopathy (DR) is one of the leading causes of blindness among adult Americans. Automatic methods for detection of the disease have been developed in recent years, most of them addressing the segmentation of bright and red lesions. In this paper we present an automatic DR screening system that does approach the problem through the segmentation of features. The algorithm determines non-diseased retinal images from those with pathology based on textural features obtained using multiscale Amplitude Modulation-Frequency Modulation (AM-FM) decompositions. The decomposition is represented as features that are the inputs to a classifier. The algorithm achieves 0.88 area under the ROC curve (AROC) for a set of 280 images from the MESSIDOR database. The algorithm is then used to analyze the effects of image compression and degradation, which will be present in most actual clinical or screening environments. Results show that the algorithm is insensitive to illumination variations, but high rates of compression and large blurring effects degrade its performance.

Original language	English
Title of host publication	Medical Imaging 2010
Subtitle of host publication	Computer-Aided Diagnosis
Editors	Ronald M. Summers, Nico Karssemeijer
Publisher	SPIE
ISBN (Electronic)	9780819480255
DOIs	https://doi.org/10.1117/12.844431
State	Published - 2010
Externally published	Yes
Event	Medical Imaging 2010: Computer-Aided Diagnosis - San Diego, United States Duration: 16 Feb 2010 → 18 Feb 2010

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	7624
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2010: Computer-Aided Diagnosis
Country/Territory	United States
City	San Diego
Period	16/02/10 → 18/02/10

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Diabetic retinopathy
image compression
image degradation
screening algorithm

Access to Document

10.1117/12.844431

Cite this

Agurto, C., Barriga, S., Murray, V., Pattichis, M., & Soliz, P. (2010). Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm. In R. M. Summers, & N. Karssemeijer (Eds.), Medical Imaging 2010: Computer-Aided Diagnosis Article 76240H (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7624). SPIE. https://doi.org/10.1117/12.844431

@inproceedings{a718b0e2562e4735b96016a63848657b,

title = "Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm",

abstract = "Diabetic retinopathy (DR) is one of the leading causes of blindness among adult Americans. Automatic methods for detection of the disease have been developed in recent years, most of them addressing the segmentation of bright and red lesions. In this paper we present an automatic DR screening system that does approach the problem through the segmentation of features. The algorithm determines non-diseased retinal images from those with pathology based on textural features obtained using multiscale Amplitude Modulation-Frequency Modulation (AM-FM) decompositions. The decomposition is represented as features that are the inputs to a classifier. The algorithm achieves 0.88 area under the ROC curve (AROC) for a set of 280 images from the MESSIDOR database. The algorithm is then used to analyze the effects of image compression and degradation, which will be present in most actual clinical or screening environments. Results show that the algorithm is insensitive to illumination variations, but high rates of compression and large blurring effects degrade its performance.",

keywords = "Diabetic retinopathy, image compression, image degradation, screening algorithm",

author = "C. Agurto and S. Barriga and V. Murray and M. Pattichis and P. Soliz",

note = "Publisher Copyright: {\textcopyright} 2010 SPIE.; Medical Imaging 2010: Computer-Aided Diagnosis ; Conference date: 16-02-2010 Through 18-02-2010",

year = "2010",

doi = "10.1117/12.844431",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Summers, \{Ronald M.\} and Nico Karssemeijer",

booktitle = "Medical Imaging 2010",

}

Agurto, C, Barriga, S, Murray, V, Pattichis, M & Soliz, P 2010, Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm. in RM Summers & N Karssemeijer (eds), Medical Imaging 2010: Computer-Aided Diagnosis., 76240H, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 7624, SPIE, Medical Imaging 2010: Computer-Aided Diagnosis, San Diego, United States, 16/02/10. https://doi.org/10.1117/12.844431

Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm. / Agurto, C.; Barriga, S.; Murray, V. et al.
Medical Imaging 2010: Computer-Aided Diagnosis. ed. / Ronald M. Summers; Nico Karssemeijer. SPIE, 2010. 76240H (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7624).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm

AU - Agurto, C.

AU - Barriga, S.

AU - Murray, V.

AU - Pattichis, M.

AU - Soliz, P.

PY - 2010

Y1 - 2010

N2 - Diabetic retinopathy (DR) is one of the leading causes of blindness among adult Americans. Automatic methods for detection of the disease have been developed in recent years, most of them addressing the segmentation of bright and red lesions. In this paper we present an automatic DR screening system that does approach the problem through the segmentation of features. The algorithm determines non-diseased retinal images from those with pathology based on textural features obtained using multiscale Amplitude Modulation-Frequency Modulation (AM-FM) decompositions. The decomposition is represented as features that are the inputs to a classifier. The algorithm achieves 0.88 area under the ROC curve (AROC) for a set of 280 images from the MESSIDOR database. The algorithm is then used to analyze the effects of image compression and degradation, which will be present in most actual clinical or screening environments. Results show that the algorithm is insensitive to illumination variations, but high rates of compression and large blurring effects degrade its performance.

AB - Diabetic retinopathy (DR) is one of the leading causes of blindness among adult Americans. Automatic methods for detection of the disease have been developed in recent years, most of them addressing the segmentation of bright and red lesions. In this paper we present an automatic DR screening system that does approach the problem through the segmentation of features. The algorithm determines non-diseased retinal images from those with pathology based on textural features obtained using multiscale Amplitude Modulation-Frequency Modulation (AM-FM) decompositions. The decomposition is represented as features that are the inputs to a classifier. The algorithm achieves 0.88 area under the ROC curve (AROC) for a set of 280 images from the MESSIDOR database. The algorithm is then used to analyze the effects of image compression and degradation, which will be present in most actual clinical or screening environments. Results show that the algorithm is insensitive to illumination variations, but high rates of compression and large blurring effects degrade its performance.

KW - Diabetic retinopathy

KW - image compression

KW - image degradation

KW - screening algorithm

UR - https://www.scopus.com/pages/publications/79955754320

U2 - 10.1117/12.844431

DO - 10.1117/12.844431

M3 - Conference contribution

AN - SCOPUS:79955754320

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2010

A2 - Summers, Ronald M.

A2 - Karssemeijer, Nico

PB - SPIE

T2 - Medical Imaging 2010: Computer-Aided Diagnosis

Y2 - 16 February 2010 through 18 February 2010

ER -

Effects of image compression and degradation on an automatic diabetic retinopathy screening algorithm

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this