Machine learning and pattern classification in identification of indigenous retinal pathology

Herbert Jelinek, Anderson Rocha, Tiago Carvalho, Siome Goldenstein, Jacques Wainer

Research output: Book chapter/Published conference paperConference paperpeer-review

21 Citations (Scopus)
4 Downloads (Pure)

Abstract

Diabetic retinopathy (DR) is a complication of diabetes, which if untreated leads to blindness. DR early diagnosis and treatment improve outcomes. Automated assessment of single lesions associated with DR has been investigated for sometime. To improve on classification, especially across different ethnic groups, we present an approach using points-of-interest and visual dictionary that contains important features required to identify retinal pathology. Variation in images of the human retina with respect to differences in pigmentation and presence of diverse lesions can be analyzed without the necessity of preprocessing and utilizing different training sets to account for ethnic differences for instance.
Original languageEnglish
Title of host publicationProceedings of the 2011 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages5951-5954
Number of pages4
DOIs
Publication statusPublished - 2011
Event2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Boston Marriott Copley Place Hotel, Boston, United States
Duration: 30 Aug 201103 Sep 2011

Conference

Conference2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Country/TerritoryUnited States
CityBoston
Period30/08/1103/09/11
OtherThe annual conference of EMBS averages 2000 attendees from over 50 countries. The scope of the conference is general in nature to focus on the interdisciplinary fields of biomedical engineering. Themes included but not limited to are: Imaging, Biosignals, Biorobotics, Bioinstrumentation, Neural, Rehabilitation, Bioinformatics, Healthcare IT, Medical Devices, etc.

Fingerprint

Dive into the research topics of 'Machine learning and pattern classification in identification of indigenous retinal pathology'. Together they form a unique fingerprint.

Cite this