Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching

Parvathi Chundi, Mahadevan Subramaniam, Keivan Sabet, Eyal Margalit

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

2 Citations (Scopus)

Abstract

Spatial pyramid matching (SPM) has achieved impressive successes in analyzing and classifying images across several domains. SPM computes a similarity measure over images by using bag of words similarity score over different levels of coarseness of the images. In this paper we propose a novel, simple approach based on SPM, differential SPM (DSPM) that incorporates finer differences among images while determining image similarity. The approach propagates the differences seen at fine levels to dampen the similarity observed at the coarser levels, thereby highlighting differences among images at small, localized regions. The resulting similarity scores among images can better separate images that match at coarse levels, but have subtle differences. DSPM integrated with K-nearest neighbor classification approaches was used to identify and analyze retinal Optical Coherence Tomography (OCT) images containing normal retinal scans as well as those from subjects with AMD (age-related macular degeneration) and DME (diabetic macular edema). The proposed approach achieved higher classification accuracy with smaller training overheads in comparison to SPM in all cases in our experiments.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages316-323
Number of pages8
ISBN (Electronic)9781509038336
DOIs
StatePublished - Dec 16 2016
Event16th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2016 - Taichung, Taiwan, Province of China
Duration: Oct 31 2016Nov 2 2016

Publication series

NameProceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016

Other

Other16th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2016
CountryTaiwan, Province of China
CityTaichung
Period10/31/1611/2/16

Fingerprint

Optical tomography
Optical Coherence Tomography
Macular Edema
Macular Degeneration
Experiments

Keywords

  • K-nearest neighbor classification
  • Retinal optical coherence tomogrphy
  • Spatial pyramid matching

ASJC Scopus subject areas

  • Biotechnology
  • Genetics
  • Bioengineering
  • Biomedical Engineering
  • Health Informatics

Cite this

Chundi, P., Subramaniam, M., Sabet, K., & Margalit, E. (2016). Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching. In Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016 (pp. 316-323). [7790003] (Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBE.2016.67

Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching. / Chundi, Parvathi; Subramaniam, Mahadevan; Sabet, Keivan; Margalit, Eyal.

Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 316-323 7790003 (Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016).

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

Chundi, P, Subramaniam, M, Sabet, K & Margalit, E 2016, Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching. in Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016., 7790003, Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016, Institute of Electrical and Electronics Engineers Inc., pp. 316-323, 16th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2016, Taichung, Taiwan, Province of China, 10/31/16. https://doi.org/10.1109/BIBE.2016.67
Chundi P, Subramaniam M, Sabet K, Margalit E. Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching. In Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 316-323. 7790003. (Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016). https://doi.org/10.1109/BIBE.2016.67
Chundi, Parvathi ; Subramaniam, Mahadevan ; Sabet, Keivan ; Margalit, Eyal. / Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching. Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 316-323 (Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016).
@inproceedings{2f41b64528304d6f9d3ad722cc5155e3,
title = "Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching",
abstract = "Spatial pyramid matching (SPM) has achieved impressive successes in analyzing and classifying images across several domains. SPM computes a similarity measure over images by using bag of words similarity score over different levels of coarseness of the images. In this paper we propose a novel, simple approach based on SPM, differential SPM (DSPM) that incorporates finer differences among images while determining image similarity. The approach propagates the differences seen at fine levels to dampen the similarity observed at the coarser levels, thereby highlighting differences among images at small, localized regions. The resulting similarity scores among images can better separate images that match at coarse levels, but have subtle differences. DSPM integrated with K-nearest neighbor classification approaches was used to identify and analyze retinal Optical Coherence Tomography (OCT) images containing normal retinal scans as well as those from subjects with AMD (age-related macular degeneration) and DME (diabetic macular edema). The proposed approach achieved higher classification accuracy with smaller training overheads in comparison to SPM in all cases in our experiments.",
keywords = "K-nearest neighbor classification, Retinal optical coherence tomogrphy, Spatial pyramid matching",
author = "Parvathi Chundi and Mahadevan Subramaniam and Keivan Sabet and Eyal Margalit",
year = "2016",
month = "12",
day = "16",
doi = "10.1109/BIBE.2016.67",
language = "English (US)",
series = "Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "316--323",
booktitle = "Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016",

}

TY - GEN

T1 - Analyzing Retinal Optical Coherence Tomography Images Using Differential Spatial Pyramid Matching

AU - Chundi, Parvathi

AU - Subramaniam, Mahadevan

AU - Sabet, Keivan

AU - Margalit, Eyal

PY - 2016/12/16

Y1 - 2016/12/16

N2 - Spatial pyramid matching (SPM) has achieved impressive successes in analyzing and classifying images across several domains. SPM computes a similarity measure over images by using bag of words similarity score over different levels of coarseness of the images. In this paper we propose a novel, simple approach based on SPM, differential SPM (DSPM) that incorporates finer differences among images while determining image similarity. The approach propagates the differences seen at fine levels to dampen the similarity observed at the coarser levels, thereby highlighting differences among images at small, localized regions. The resulting similarity scores among images can better separate images that match at coarse levels, but have subtle differences. DSPM integrated with K-nearest neighbor classification approaches was used to identify and analyze retinal Optical Coherence Tomography (OCT) images containing normal retinal scans as well as those from subjects with AMD (age-related macular degeneration) and DME (diabetic macular edema). The proposed approach achieved higher classification accuracy with smaller training overheads in comparison to SPM in all cases in our experiments.

AB - Spatial pyramid matching (SPM) has achieved impressive successes in analyzing and classifying images across several domains. SPM computes a similarity measure over images by using bag of words similarity score over different levels of coarseness of the images. In this paper we propose a novel, simple approach based on SPM, differential SPM (DSPM) that incorporates finer differences among images while determining image similarity. The approach propagates the differences seen at fine levels to dampen the similarity observed at the coarser levels, thereby highlighting differences among images at small, localized regions. The resulting similarity scores among images can better separate images that match at coarse levels, but have subtle differences. DSPM integrated with K-nearest neighbor classification approaches was used to identify and analyze retinal Optical Coherence Tomography (OCT) images containing normal retinal scans as well as those from subjects with AMD (age-related macular degeneration) and DME (diabetic macular edema). The proposed approach achieved higher classification accuracy with smaller training overheads in comparison to SPM in all cases in our experiments.

KW - K-nearest neighbor classification

KW - Retinal optical coherence tomogrphy

KW - Spatial pyramid matching

UR - http://www.scopus.com/inward/record.url?scp=85011030475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011030475&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2016.67

DO - 10.1109/BIBE.2016.67

M3 - Conference contribution

T3 - Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016

SP - 316

EP - 323

BT - Proceedings - 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, BIBE 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -