Entity

Time filter

Source Type

Belfast, United Kingdom

Spiclin Z.,University of Ljubljana | Spiclin Z.,Sensum Inc.
Elektrotehniski Vestnik/Electrotechnical Review | Year: 2015

Technology for spatial co-registration of pre-operative and intra-operative images is a crucial part of surgical image guidance systems. The pre-operative images are usually 3D, i.e. computed tomography, and used for diagnosis and planning, whereas the intra-operative imaging needs to be fast and unobtrusive, which renders the 2D X-ray fluoroscopy as the only suitable technique. The most important properties required for implementation of 3D-2D image registration into image-guidance systems are its computational time and robustness, while the accuracy of spatial alignment should be in the order of the image sampling step. These properties are mainly determined by a similarity measure (SM) between the 3D and 2D images. In this paper, we evaluate a 3D-2D registration method based on matching structural tensors with nine different SMs. The majority of evaluated SMs enable sufficiently accurate 3D-2D registration, while the most robust SMs were Bhattacharrya, Jensen-Bregman divergence, affine invariant and log-Euclidean distance. These four SMs achieved a registration success rate of 85% and capture range from 9 to 10 mm with respect to optimal 3D-2D registration. The first two of the four SMs enabled the fastest registration times around 0.4 seconds. Registration of 3D and 2D images based on these two SMs is accurate, robust and fast and, thus, feasible for implementation into surgical image-guidance systems.


Markelj P.,University of Ljubljana | Likar B.,University of Ljubljana | Likar B.,Sensum Inc. | Pernus F.,University of Ljubljana
Medical Physics | Year: 2010

Purpose: A new image database with a reference-based standardized evaluation methodology for objective evaluation and comparison of three-dimensional/two-dimensional (3D/2D) registration methods has been introduced. Methods: Computed tomography (CT) images of a male and female from the Visible Human Project were used and 16 subvolumes, each containing one of vertebrae T3-T12 and L1-L5 and the pelvis, were defined from the CTs. Six pairs of 2D fluoroscopic x-ray images from different views, showing the thoracic, lumbar, and pelvic regions, were rendered from the CT data using a ray-casting algorithm with an energy conversion function. Furthermore, a single 13-gauge needle was analytically simulated and projected onto the 2D images. By the novel standardized evaluation methodology, a 3D/2D registration method is evaluated by four evaluation criteria: Accuracy, reliability, robustness, and algorithm complexity. Results: To demonstrate the usefulness of the proposed data set and the standardized evaluation methodology, a part of the data set was used in an evaluation study of two gradient-based 3D/2D registration methods. It was shown that the use of a failure criterion to calculate the registration accuracy and reliability is not required, since all the information about a registration method can be determined from the estimated distribution of registration errors. Conclusions: The proposed simulated image data set with quite realistic synthetic 2D images, depicting soft tissues and outliers, is especially suitable for preliminary testing of 3D/2D registration algorithms. Since the aim of this article is to provide objective comparison and unbiased evaluation of 3D/2D registration methods, the standardized evaluation methodology is available upon request from the authors. © 2010 American Association of Physicists in Medicine.


Spiclin Z.,University of Ljubljana | Bukovec M.,University of Ljubljana | Bukovec M.,Sensum Inc. | Pernus F.,University of Ljubljana | Likar B.,University of Ljubljana
Machine Vision and Applications | Year: 2011

Image registration plays a vital role in visual quality inspection of tablets with imprints. In this paper, three registration methods, based on direct matching of pixel intensities, principal axes matching and circular profile matching, were proposed and objectively evaluated on real, large and representative image database (1,634 images) of various types of non-defective and defective tablets. Comparing against a devised "gold standard" registration and considering execution times and different registration tasks, circular profile matching method proved to be a powerful image processing tool for improving visual quality inspection of imprinted tablets in real time. © 2007 Springer-Verlag.


Katrasnik J.,University of Ljubljana | Pernus F.,University of Ljubljana | Pernus F.,Sensum Inc. | Likar B.,University of Ljubljana | Likar B.,Sensum Inc.
Optics Express | Year: 2013

Near-infrared hyperspectral imaging is becoming a popular tool in various fields. In all imaging systems, proper illumination is crucial for attaining optimal image quality that is needed for the best performance of image analysis algorithms. In hyperspectral imaging, the acquired spectral signature has to be representative in all parts of the imaged object. Therefore, the whole object must be equally well illuminated-without shadows or specular reflections. As there are no restrictions imposed on the material and geometry of the object, the desired illumination of the object can only be achieved with completely diffuse illumination. In order to minimize shadows and specular reflections, the light illuminating the object must be spatially, angularly and spectrally uniform. The quality of illumination systems for hyperspectral imaging can therefore be assessed using spatial-intensity, spatial-spectral, angular-intensity and angular-spectral non-uniformity measures that are presented in this paper. Emphasis is given to the angular-intensity and angular-spectral non-uniformity measures, which are the most important contributions of this paper. The measures were defined on images of two reference targets-a flat, white diffuse reflectance target and a sphere grid target-acquired with an acousto-optic tunable filter (AOTF) based hyperspectral imaging system. The proposed measures were tested on a ring light and on a diffuse dome illumination system. © 2013 Optical Society of America.


Burmen M.,University of Ljubljana | Pernus F.,University of Ljubljana | Pernus F.,Sensum Inc. | Likar B.,University of Ljubljana | Likar B.,Sensum Inc.
Applied Spectroscopy | Year: 2011

In this study, we propose and evaluate a method for spectral characterization of acousto-optic tunable filter (AOTF) hyperspectral imaging systems in the near-infrared (NIR) spectral region from 900 nm to 1700 nm. The proposed spectral characterization method is based on the SRM-2035 standard reference material, exhibiting distinct spectral features, which enables robust non-rigid matching of the acquired and reference spectra. The matching is performed by simultaneously optimizing the parameters of the AOTF tuning curve, spectral resolution, baseline, and multiplicative effects. In this way, the tuning curve (frequency-wavelength characteristics) and the corresponding spectral resolution of the AOTF hyperspectral imaging system can be characterized simultaneously. Also, the method enables simple spectral characterization of the entire imaging plane of hyperspectral imaging systems. The results indicate that the method is accurate and efficient and can easily be integrated with systems operating in diffuse reflection or transmission modes. Therefore, the proposed method is suitable for characterization, calibration, or validation of AOTF hyperspectral imaging systems. © 2011 Society for Applied Spectroscopy.

Discover hidden collaborations