Hierarchical detection of red lesions in retinal images by multiscale correlation filtering

Bob Zhang; Xiangqian Wu; Jia You; Qin Li; Fakhri Karray

doi:10.1117/12.813913

Hierarchical detection of red lesions in retinal images by multiscale correlation filtering

Bob Zhang, Xiangqian Wu, Jia You, Qin Li, Fakhri Karray

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

31 Citations (Scopus)

Abstract

This paper presents an approach to the computer aided diagnosis (CAD) of diabetic retinopathy (DR)- a common and severe complication of long-term diabetes which damages the retina and cause blindness. Since red lesions are regarded as the first signs of DR, there has been extensive research on effective detection and localization of these abnormalities in retinal images. In contrast to existing algorithms, a new approach based on Multiscale Correlation Filtering (MSCF) and dynamic thresholding is developed. This consists of two levels, Red Lesion Candidate Detection (coarse level) and True Red Lesion Detection (fine level). The approach was evaluated using data from Retinopathy On-line Challenge (ROC) competition website and we conclude our method to be effective and efficient

Original language	English
Title of host publication	Medical Imaging 2009
Subtitle of host publication	Computer-Aided Diagnosis
Volume	7260
DOIs	https://doi.org/10.1117/12.813913
Publication status	Published - 15 Jun 2009
Event	Medical Imaging 2009: Computer-Aided Diagnosis - Lake Buena Vista, FL, United States Duration: 10 Feb 2009 → 12 Feb 2009

Conference

Conference	Medical Imaging 2009: Computer-Aided Diagnosis
Country/Territory	United States
City	Lake Buena Vista, FL
Period	10/02/09 → 12/02/09

Keywords

Computer-aided diagnosis (CAD)
Diabetic Retinopathy (DR)
Multiscale Correlation Filtering
Red lesiondetection

ASJC Scopus subject areas

Atomic and Molecular Physics, and Optics
Electronic, Optical and Magnetic Materials
Biomaterials
Radiology Nuclear Medicine and imaging

UN SDGs

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

More information

10.1117/12.813913

Cite this

@inproceedings{084bcba70f824f60bd5fae908027e03a,

title = "Hierarchical detection of red lesions in retinal images by multiscale correlation filtering",

abstract = "This paper presents an approach to the computer aided diagnosis (CAD) of diabetic retinopathy (DR)- a common and severe complication of long-term diabetes which damages the retina and cause blindness. Since red lesions are regarded as the first signs of DR, there has been extensive research on effective detection and localization of these abnormalities in retinal images. In contrast to existing algorithms, a new approach based on Multiscale Correlation Filtering (MSCF) and dynamic thresholding is developed. This consists of two levels, Red Lesion Candidate Detection (coarse level) and True Red Lesion Detection (fine level). The approach was evaluated using data from Retinopathy On-line Challenge (ROC) competition website and we conclude our method to be effective and efficient",

keywords = "Computer-aided diagnosis (CAD), Diabetic Retinopathy (DR), Multiscale Correlation Filtering, Red lesiondetection",

author = "Bob Zhang and Xiangqian Wu and Jia You and Qin Li and Fakhri Karray",

year = "2009",

month = jun,

day = "15",

doi = "10.1117/12.813913",

language = "English",

isbn = "9780819475114",

volume = "7260",

booktitle = "Medical Imaging 2009",

note = "Medical Imaging 2009: Computer-Aided Diagnosis ; Conference date: 10-02-2009 Through 12-02-2009",

}

TY - GEN

T1 - Hierarchical detection of red lesions in retinal images by multiscale correlation filtering

AU - Zhang, Bob

AU - Wu, Xiangqian

AU - You, Jia

AU - Li, Qin

AU - Karray, Fakhri

PY - 2009/6/15

Y1 - 2009/6/15

N2 - This paper presents an approach to the computer aided diagnosis (CAD) of diabetic retinopathy (DR)- a common and severe complication of long-term diabetes which damages the retina and cause blindness. Since red lesions are regarded as the first signs of DR, there has been extensive research on effective detection and localization of these abnormalities in retinal images. In contrast to existing algorithms, a new approach based on Multiscale Correlation Filtering (MSCF) and dynamic thresholding is developed. This consists of two levels, Red Lesion Candidate Detection (coarse level) and True Red Lesion Detection (fine level). The approach was evaluated using data from Retinopathy On-line Challenge (ROC) competition website and we conclude our method to be effective and efficient

AB - This paper presents an approach to the computer aided diagnosis (CAD) of diabetic retinopathy (DR)- a common and severe complication of long-term diabetes which damages the retina and cause blindness. Since red lesions are regarded as the first signs of DR, there has been extensive research on effective detection and localization of these abnormalities in retinal images. In contrast to existing algorithms, a new approach based on Multiscale Correlation Filtering (MSCF) and dynamic thresholding is developed. This consists of two levels, Red Lesion Candidate Detection (coarse level) and True Red Lesion Detection (fine level). The approach was evaluated using data from Retinopathy On-line Challenge (ROC) competition website and we conclude our method to be effective and efficient

KW - Computer-aided diagnosis (CAD)

KW - Diabetic Retinopathy (DR)

KW - Multiscale Correlation Filtering

KW - Red lesiondetection

UR - http://www.scopus.com/inward/record.url?scp=66749089296&partnerID=8YFLogxK

U2 - 10.1117/12.813913

DO - 10.1117/12.813913

M3 - Conference article published in proceeding or book

SN - 9780819475114

VL - 7260

BT - Medical Imaging 2009

T2 - Medical Imaging 2009: Computer-Aided Diagnosis

Y2 - 10 February 2009 through 12 February 2009

ER -

Hierarchical detection of red lesions in retinal images by multiscale correlation filtering

Abstract

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

More information

Other files and links

Fingerprint

Cite this