File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Efficient optic cup detection from intra-image learning with retinal structure priors

TitleEfficient optic cup detection from intra-image learning with retinal structure priors
Authors
Issue Date2012
PublisherSpringer
Citation
15th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2012), Nice, France, 1-5 October 2012. In Ayache, N, Delingette, H, Golland, P, et al. (Eds.), Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part I, p. 58-65. Berlin: Springer, 2012 How to Cite?
AbstractWe present a superpixel based learning framework based on retinal structure priors for glaucoma diagnosis. In digital fundus photographs, our method automatically localizes the optic cup, which is the primary image component clinically used for identifying glaucoma. This method provides three major contributions. First, it proposes processing of the fundus images at the superpixel level, which leads to features more descriptive and effective than those employed by pixel-based techniques, while yielding significant computational savings over methods based on sliding windows. Second, the classifier learning process does not rely on pre-labeled training samples, but rather the training samples are extracted from the test image itself using structural priors on relative cup and disc positions. Third, we present a classification refinement scheme that utilizes both structural priors and local context. Tested on the ORIGA−light clinical dataset comprised of 650 images, the proposed method achieves a 26.7% non-overlap ratio with manually-labeled ground-truth and a 0.081 absolute cup-to-disc ratio (CDR) error, a simple yet widely used diagnostic measure. This level of accuracy is comparable to or higher than the state-of-the-art technique [1], with a speedup factor of tens or hundreds.
Persistent Identifierhttp://hdl.handle.net/10722/321529
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
Series/Report no.Lecture Notes in Computer Science ; 7510
LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics

 

DC FieldValueLanguage
dc.contributor.authorXu, Yanwu-
dc.contributor.authorLiu, Jiang-
dc.contributor.authorLin, Stephen-
dc.contributor.authorXu, Dong-
dc.contributor.authorCheung, Carol Y.-
dc.contributor.authorAung, Tin-
dc.contributor.authorWong, Tien Yin-
dc.date.accessioned2022-11-03T02:19:33Z-
dc.date.available2022-11-03T02:19:33Z-
dc.date.issued2012-
dc.identifier.citation15th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2012), Nice, France, 1-5 October 2012. In Ayache, N, Delingette, H, Golland, P, et al. (Eds.), Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part I, p. 58-65. Berlin: Springer, 2012-
dc.identifier.isbn9783642334146-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/321529-
dc.description.abstractWe present a superpixel based learning framework based on retinal structure priors for glaucoma diagnosis. In digital fundus photographs, our method automatically localizes the optic cup, which is the primary image component clinically used for identifying glaucoma. This method provides three major contributions. First, it proposes processing of the fundus images at the superpixel level, which leads to features more descriptive and effective than those employed by pixel-based techniques, while yielding significant computational savings over methods based on sliding windows. Second, the classifier learning process does not rely on pre-labeled training samples, but rather the training samples are extracted from the test image itself using structural priors on relative cup and disc positions. Third, we present a classification refinement scheme that utilizes both structural priors and local context. Tested on the ORIGA−light clinical dataset comprised of 650 images, the proposed method achieves a 26.7% non-overlap ratio with manually-labeled ground-truth and a 0.081 absolute cup-to-disc ratio (CDR) error, a simple yet widely used diagnostic measure. This level of accuracy is comparable to or higher than the state-of-the-art technique [1], with a speedup factor of tens or hundreds.-
dc.languageeng-
dc.publisherSpringer-
dc.relation.ispartofMedical Image Computing and Computer-Assisted Intervention -- MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part I-
dc.relation.ispartofseriesLecture Notes in Computer Science ; 7510-
dc.relation.ispartofseriesLNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics-
dc.titleEfficient optic cup detection from intra-image learning with retinal structure priors-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-642-33415-3_8-
dc.identifier.pmid23285535-
dc.identifier.scopuseid_2-s2.0-84885897327-
dc.identifier.spage58-
dc.identifier.epage65-
dc.identifier.eissn1611-3349-
dc.publisher.placeBerlin-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats