Publication detail

Non-Rigid Registration of Time Series of Auto-Fluorescent HRA 2D Images

Kubecka L., Jan J., Kolar R., Jirik R.

Original Title

Non-Rigid Registration of Time Series of Auto-Fluorescent HRA 2D Images

Czech Title

Pružná registrace časových řad 2D autofluorescenčních HRA obrazů.

English Title

Non-Rigid Registration of Time Series of Auto-Fluorescent HRA 2D Images

Type

conference paper

Language

en

Original Abstract

According to recent research, auto-fluorescent images taken by means of Heildelberg Retina Angiograph (HRA) have promising value for the diagnosis of glaucoma, especially due to strong correlation between the size of auto-fluorescent zones and glaucoma. With respect to poor signal/noise ratio of this signal, noise is to be suppressed by computation of the average image from the acquired time series. Because of movements of patients during acquisition, it is crucial for good results to perform image registration prior to the image processing. Therefore this contribution deals with the HRA time series non-rigid image registration. The registration is performed by multi-resolutional optimization of the global similarity criterion based on mutual information and consists of two steps. First, both images are registered using affine model of image transformation in order to compensate global mis-registrations. In this step we use a controlled random search optimizer in low-resolution layers of the image pyramid and the Powell optimizer for high-resolution. Further, a B-spline transformation model compensating for local mis-registrations is done making use of limited memory Broyden, Fletcher, Goldfarb and Shannon optimizer (LBFGS). Precision of the algorithm has been evaluated on the HRA images with artificially introduced known mis-registration and finally, the algorithm was tested on a set of 16 real time series each containing 9 images.

Czech abstract

Podle nedávných výzkumů se jako slibná metoda pro diagnostiku glaukomu ukazuje analýza auto-fluorescenčních obrazů sejmutých přístrojem HRA = Heildelberg Retina Tomograph. Zejména je silná korelace mezi výskytem glaukomu a velikostí autoflourescenčbích zón. Vzhledem k nízkému poměru signál/šum je však nutné obrazy před analýzou zbavit šumu pomocí pruměrování časových sérií obrazů. Aby se zabránilo artefaktům vneseným do výsledného obrazu během průměrování z důvodu pohybů pacienta během akvizice, je nutné toto zkreslení kompenzovat pomocí technik registrace obrazů. Tento článek se týká ne-rigidní registrace obrazů za účelem zvýšení poměru signál/šum a zjednodušení náísledného zpracování.

English abstract

According to recent research, auto-fluorescent images taken by means of Heildelberg Retina Angiograph (HRA) have promising value for the diagnosis of glaucoma, especially due to strong correlation between the size of auto-fluorescent zones and glaucoma. With respect to poor signal/noise ratio of this signal, noise is to be suppressed by computation of the average image from the acquired time series. Because of movements of patients during acquisition, it is crucial for good results to perform image registration prior to the image processing. Therefore this contribution deals with the HRA time series non-rigid image registration. The registration is performed by multi-resolutional optimization of the global similarity criterion based on mutual information and consists of two steps. First, both images are registered using affine model of image transformation in order to compensate global mis-registrations. In this step we use a controlled random search optimizer in low-resolution layers of the image pyramid and the Powell optimizer for high-resolution. Further, a B-spline transformation model compensating for local mis-registrations is done making use of limited memory Broyden, Fletcher, Goldfarb and Shannon optimizer (LBFGS). Precision of the algorithm has been evaluated on the HRA images with artificially introduced known mis-registration and finally, the algorithm was tested on a set of 16 real time series each containing 9 images.

Keywords

Image registration, non-rigid transformation, HRA, averaging

RIV year

2005

Released

20.12.2005

Publisher

UTIA, Czech Academy of Sciencies

Location

Praha

Pages from

3

Pages to

3

Pages count

1

URL

BibTex


@inproceedings{BUT16288,
  author="Libor {Kubečka} and Jiří {Jan} and Radim {Kolář} and Radovan {Jiřík}",
  title="Non-Rigid Registration of Time Series of Auto-Fluorescent HRA 2D Images",
  annote="According to recent research, auto-fluorescent images taken by means of Heildelberg Retina Angiograph (HRA) have promising value for the diagnosis of glaucoma, especially due to strong correlation between the size of auto-fluorescent zones and glaucoma. With respect to poor signal/noise ratio of this signal, noise is to be suppressed by computation of the average image from the acquired time series. Because of movements of patients during acquisition, it is crucial for good results to perform image registration prior to the image processing. Therefore this contribution deals with the HRA time series non-rigid image registration. 
The registration is performed by multi-resolutional optimization of the global similarity criterion based on mutual information and consists of two steps. First, both images are registered using affine model of image transformation in order to compensate global mis-registrations. In this step we use a controlled random search optimizer in low-resolution layers of the image pyramid and the Powell optimizer for high-resolution. Further, a B-spline transformation model compensating for local mis-registrations is done making use of limited memory Broyden, Fletcher, Goldfarb and Shannon optimizer (LBFGS). Precision of the algorithm has been evaluated on the HRA images with artificially introduced known mis-registration and finally, the algorithm was tested on a set of 16 real time series each containing 9 images. 
",
  address="UTIA, Czech Academy of Sciencies",
  booktitle="Abstracts of Contributions to International Workshop on Data - Algorithms - Decision Making",
  chapter="16288",
  edition="41",
  institution="UTIA, Czech Academy of Sciencies",
  number="41",
  year="2005",
  month="december",
  pages="3",
  publisher="UTIA, Czech Academy of Sciencies",
  type="conference paper"
}