Vessel enhancement in digital X-ray angiographic sequences by temporal statistical learning

András Lassó; Emanuele Trucco

doi:10.1016/j.compmedimag.2005.02.002

Vessel enhancement in digital X-ray angiographic sequences by temporal statistical learning

András Lassó (Lead / Corresponding author)
, Emanuele Trucco

Computing

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

Abstract

In this paper, we present a vessel enhancement method, SVM temporal filtering (STF), for X-ray angiographic (XA) images using Support Vector Machine (SVM). We show that the linear SVM applied to vessel enhancement can be regarded as a matched linear filter optimizing the contrast-to-noise ratio in XA images. We propose a non-linear kernel function for the SVM leading to good enhancement with noisy, varying grey-level dynamics at vessel pixels. One key advantage over the matched filters is that an optimal filter is learnt from images, not estimated at design stage. Results on clinical XA images show that learning-based enhancement achieves better results compared to simple subtraction and other image stacking methods.

Original language	English
Pages (from-to)	343-355
Number of pages	13
Journal	Computerized Medical Imaging and Graphics
Volume	29
Issue number	5
Early online date	11 May 2005
DOIs	https://doi.org/10.1016/j.compmedimag.2005.02.002
Publication status	Published - Jul 2005

Keywords

Image enhancement
Learning systems
Matched filters
Support vector machines
X-ray angiography

ASJC Scopus subject areas

Radiological and Ultrasound Technology
Radiology Nuclear Medicine and imaging
Computer Vision and Pattern Recognition
Health Informatics
Computer Graphics and Computer-Aided Design

Access to Document

10.1016/j.compmedimag.2005.02.002

Cite this

@article{0161b259e3194a1e98839bbdae0da27b,

title = "Vessel enhancement in digital X-ray angiographic sequences by temporal statistical learning",

abstract = "In this paper, we present a vessel enhancement method, SVM temporal filtering (STF), for X-ray angiographic (XA) images using Support Vector Machine (SVM). We show that the linear SVM applied to vessel enhancement can be regarded as a matched linear filter optimizing the contrast-to-noise ratio in XA images. We propose a non-linear kernel function for the SVM leading to good enhancement with noisy, varying grey-level dynamics at vessel pixels. One key advantage over the matched filters is that an optimal filter is learnt from images, not estimated at design stage. Results on clinical XA images show that learning-based enhancement achieves better results compared to simple subtraction and other image stacking methods.",

keywords = "Image enhancement, Learning systems, Matched filters, Support vector machines, X-ray angiography",

author = "Andr{\'a}s Lass{\'o} and Emanuele Trucco",

year = "2005",

month = jul,

doi = "10.1016/j.compmedimag.2005.02.002",

language = "English",

volume = "29",

pages = "343--355",

journal = "Computerized Medical Imaging and Graphics",

issn = "0895-6111",

publisher = "Elsevier",

number = "5",

}

TY - JOUR

T1 - Vessel enhancement in digital X-ray angiographic sequences by temporal statistical learning

AU - Lassó, András

AU - Trucco, Emanuele

PY - 2005/7

Y1 - 2005/7

N2 - In this paper, we present a vessel enhancement method, SVM temporal filtering (STF), for X-ray angiographic (XA) images using Support Vector Machine (SVM). We show that the linear SVM applied to vessel enhancement can be regarded as a matched linear filter optimizing the contrast-to-noise ratio in XA images. We propose a non-linear kernel function for the SVM leading to good enhancement with noisy, varying grey-level dynamics at vessel pixels. One key advantage over the matched filters is that an optimal filter is learnt from images, not estimated at design stage. Results on clinical XA images show that learning-based enhancement achieves better results compared to simple subtraction and other image stacking methods.

AB - In this paper, we present a vessel enhancement method, SVM temporal filtering (STF), for X-ray angiographic (XA) images using Support Vector Machine (SVM). We show that the linear SVM applied to vessel enhancement can be regarded as a matched linear filter optimizing the contrast-to-noise ratio in XA images. We propose a non-linear kernel function for the SVM leading to good enhancement with noisy, varying grey-level dynamics at vessel pixels. One key advantage over the matched filters is that an optimal filter is learnt from images, not estimated at design stage. Results on clinical XA images show that learning-based enhancement achieves better results compared to simple subtraction and other image stacking methods.

KW - Image enhancement

KW - Learning systems

KW - Matched filters

KW - Support vector machines

KW - X-ray angiography

UR - https://www.scopus.com/pages/publications/19744371376

U2 - 10.1016/j.compmedimag.2005.02.002

DO - 10.1016/j.compmedimag.2005.02.002

M3 - Article

C2 - 15893453

AN - SCOPUS:19744371376

SN - 0895-6111

VL - 29

SP - 343

EP - 355

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

IS - 5

ER -

Vessel enhancement in digital X-ray angiographic sequences by temporal statistical learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this