A multiscale decomposition approach to detect abnormal vasculature in the optic disc.

A multiscale decomposition approach to detect abnormal vasculature in the optic disc.
复制标题

DOI:
10.1016/j.compmedimag.2015.01.001
复制
发表时间:
2015-07
影响因子:
5.7
通讯作者:
Soliz, Peter
Soliz, Peter
中科院分区:
工程技术2区
文献类型:
--
作者:
Agurto, Carla;Yu, Honggang;Murray, Victor;Pattichis, Marios S.;Nemeth, Sheila;Barriga, Simon;Soliz, Peter

文献摘要

参考文献

相似文献

本文提出了一种使用眼底图像检测视盘(NVD)新生血管的多尺度方法。我们的方法应用于手动选择的包含视盘的感兴趣区域 (ROI)。通过自适应地将对比度增强方法与血管分割技术相结合来分割 ROI 中的所有血管。使用使用多尺度调幅调频、形态粒度测量和分形维数提取的纹理特征。使用线性 SVM 进行分类,并通过 10 倍交叉验证进行测试。使用 300 张图像评估性能,AUC 为 0.93,最大准确度为 88%。
This paper presents a multiscale method to detect neovascularization in the optic disc (NVD) using fundus images. Our method is applied to a manually selected region of interest (ROI) containing the optic disc. All the vessels in the ROI are segmented by adaptively combining contrast enhancement methods with a vessel segmentation technique. Textural features extracted using multiscale amplitude-modulation frequency-modulation, morphological granulometry, and fractal dimension are used. A linear SVM is used to perform the classification, which is tested by means of 10-fold cross-validation. The performance is evaluated using 300 images achieving an AUC of 0.93 with maximum accuracy of 88%.
DOI: 10.1016/0165-1684(89)90090-x
发表时间: 1989-02-01
期刊: SIGNAL PROCESSING
影响因子: 4.4
作者:
PAL, NR;PAL, SK
通讯作者: PAL, SK
DOI: 10.1109/titb.2010.2091279
发表时间: 2011-01-01
影响因子: --
作者:
Loizou, C. P.;Murray, V.;Pattichis, C. S.
通讯作者: Pattichis, C. S.
DOI: 10.1109/tmi.2006.879955
发表时间: 2006-09-01
影响因子: 10.6
作者:
Mendonca, Ana Maria;Campilho, Aurelio
通讯作者: Campilho, Aurelio
DOI: 10.1155/2011/586865
发表时间: 2011-01-01
影响因子: 1.9
作者:
Ramachandran, Janakiramanan;Pattichis, Marios S.;Baba, Justin S.
通讯作者: Baba, Justin S.
DOI: 10.1023/a:1009715923555
发表时间: 1998-06-01
影响因子: 4.8
作者:
Burges, CJC
通讯作者: Burges, CJC