Conference proceeding
Splat feature classification: Detection of the presence of large retinal hemorrhages
2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp.681-684
03/2011
DOI: 10.1109/ISBI.2011.5872498
PMID: 21797934
Abstract
Reliable detection of large retinal hemorrhages is important in the development of automated screening systems which can be translated into practice. In this study, we propose a novel large retinal hemorrhages detection method based on splat feature classification. Fundus photographs are partitioned into a number of splats covering the entire image. Each splat contains pixels with similar color and close spatial location. A set of distinct features is extracted within each splat. By learning properties of splats formed from blood vessels, a classifier was trained so that it can distinguish blood splats from non-blood splats. Once the blood splats, i.e. vasculature and hemorrhages, are separated from the background, the connected vasculature was removed and the remaining objects considered hemorrhage candidates. Our approach had a satisfactory performance on a test set composed of 1200 images compared to a human expert.
Details
- Title: Subtitle
- Splat feature classification: Detection of the presence of large retinal hemorrhages
- Creators
- Li Tang - Ophthalmology & Visual Sci., Univ. of Iowa Hosp. & Clinics, Iowa City, IA, USAMeindert Niemeijer - Ophthalmology & Visual Sci., Univ. of Iowa Hosp. & Clinics, Iowa City, IA, USAMichael D Abramoff - Ophthalmology & Visual Sci., Univ. of Iowa Hosp. & Clinics, Iowa City, IA, USA
- Resource Type
- Conference proceeding
- Publication Details
- 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp.681-684
- DOI
- 10.1109/ISBI.2011.5872498
- PMID
- 21797934
- NLM abbreviation
- Proc IEEE Int Symp Biomed Imaging
- ISSN
- 1945-7928
- eISSN
- 1945-8452
- Publisher
- IEEE
- Language
- English
- Date published
- 03/2011
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Fraternal Order of Eagles Diabetes Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9984060634902771
Metrics
19 Record Views