Similarity measures are a critical component for iterative registration tasks. In intrinsic 2D/3D registration an initialization close to the solution is usually needed for convergence. Traditional similarity measures are limited in their applicability to perspective projection data. Deep Learning allows us to create similarity measures that encode almost arbitrary non-linear relationships like perspective projection. We apply a siamese network and a 2-channel network to the problem of comparing two perspective maximum intensity projections of medical data. We propose the use of residual units as the building block. A major challenge is to define similarity under perspective projection so that it can be used for training. Extrinsic registration gives us a gold standard of registered examples but we need a way to quantify the dissimilarity of unregistered image pairs for training. We propose the use of disparity as the basis for construction of similarity labels, i.e. labels are based on distances between projected points when viewing the same 3D point through different cameras. The final similarity labels are independent of the choice of camera parametrization and describe the visual similarity of two given views of a common 3D model. We compare our deep similarity metric to traditional similarity measures for a comparative evaluation. Our best configuration has a Pearson correlation coefficient of 0.792 and a Spearman’s rank correlation coefficient of 0.480. The best traditional method is normalized cross correlation with a 5.4% lower Spearman’s rank correlation coefficient.
In dynamic SPECT (dSPECT) images, function of a particular organ may be analyzed by measuring the temporal change of the spatial distribution of radioactive tracer. The organ-specific and location-specific time-activity curves (TAC) of the different heart regions (regions with normal blood circulation and with disturbed blood circulation) are helpful for the diagnosis of heart diseases.A problem of the derivation of the TACs is that the dSPECT images have a poor spatial and temporal resolution and the data is distorted because noise effects, partial volume effects and scatter artifacts. Therefore in a preprocessing step the quality of the data is improved with a nonlinear isotropic diffusion in combination with the principal component analysis. Segmentation according to some homogeneity principle will deliver regions of similar functional behavior but the segmented regions do not directly point to anatomy. For our goal of anatomy specific segmentation information about anatomy is provided a-priori and it must be fitted to the data. For initialization the user have to mark six positions of the left ventricle in the data set which are used to place a super ellipsoid. The parameters of this super ellipsoid are obtained from the computed mean shape of six manual segmented left ventricles in test data sets. A closer fit to the high gradients of the boundaries of the heart wall is achieved using the free form deformation method. For evaluation segmentation results are compared with a manual segmentation. In all test images we could ascertain a good correspondence between the manual and automatic segmentation.
Dynamic SPECT is a novel technique in nuclear medicine imaging. To find coherent structures within the dataset is the most important part of analyzing dSPECT data. Usually the observer focuses on a certain structure or an organ, which is to be identified and outlined. We use a user-guided method where a starting point is interactively selected whcih is also used to identify the object or structure. To find the starting point for segentation we search for the voxel having the maximum intensity in the dataset along the eye beam. In the situation where the data is segmented by region growing, we render both, the segmentation result and the original data in one view. The segmentation result is displayed as a wire mesh and fades over the voluem rendered original data. We use this hybrid rendering method in order to enable the user to validate the correctness of the sementation process. So it is possible to compare the two objects in one rendition.
Segmentation is an essential step in the analysis of medical images. For segmentation of 3-D data sets in clinical practice segmentation methods are necessary which have a small user interaction time and which are highly flexible. For this purpose we propose a two-step segmentation approach. The first step results in a coarse segmentation using the Image Foresting Transformation. In the second step an active surface creates the final segmentation. Our segmentation method was tested for segmentation on real CT images. The performance was compared with the manual segmentation. We found our work method reliable.
In this paper we present a method for interactive analysis of non-segmented medical volume data. We discuss both different rendering methods for visualization and different possibilities for interaction in relation to segmentation results. Furthermore, the adaptive region growing approach is applied to both segmentation of a structure of interest, as well as generation of transfer function for volume rendering of the same structure. The adaptive region growing method is based on the statistical evaluation of 3D-neighbourhood. The method is used for determination of a homogeneity criterion for the structure of interest. Subsequently this criterion is used for segmenting of data and for generating of an initial transfer function for volume rendering. We utilize this for displaying a hybrid 3D-visualization of the segmented structure and the specific gray-value interval of original data. Based on this rendering we discuss possibilities for user-guided validation of segmentation results, based on the variation of several rendering parameters.
We propose an evaluation process for segmentation which is made up of three different levels. It enables us to carry out the time consuming steps only for those segmentation methods for which a successful segmentation is foreseeable. In the first level the developer of a segmentation method does a coarse analysis of the usefulness of the individual segmentation methods by means of visual assessment of the results for few image examples. Methods which have been judged useful at the first level are investigated in a second evaluation step as to the stability of the segmentation results in case of slight deviations in the images. For the reproduction of the image formation process a multitude of realizations of a given region of interest are produced by means of the bootstrap technique. At the third level of the evaluation process the segmentation methods are tested for segmentation errors. The segmentation methods are judged by means of empirical discrepancy values, and the effectiveness of a method chosen for the respective task is finally estimated.
Successful extraction of small vessels in DSA images requires inclusion of prior knowledge about vessel characteristics. We developed an active double contour (ADC) that uses a vessel template as a model. The template is fitted to the vessel using an adapted ziplock snake approach based on two user-specified end locations. The external energy terms of the ADC describe an ideal vessel with projections changing slowly their course, width and intensity. A backtracking ability was added that enables overturning local decisions that may cause the ziplock snake to be trapped in a local minimum. This is because the optimization of the ADC is carried out locally. If the total energy indicates such case, vessel boundary points are removed and the ziplock process starts again without this location in its actual configuration. The method was tested on artificial data and DSA data. The former showed good agreement between artificial vessel and segmented structure at an SNR as low as 1.5:1. Results from DSA data showed robustness of the method in the presence of noise and its ability to cope with branchings and crossings. The backtracking was found to overcome local minima of the energy function at artefacts, vessel crossings and in regions of low SNR.
KEYWORDS: Image segmentation, Medical imaging, Computed tomography, Image processing algorithms and systems, Image processing, Signal to noise ratio, Magnetic resonance imaging, Abdomen, Data modeling, X-ray computed tomography
Interaction increases flexibility of segmentation but it leads to undesirable behavior of an algorithm if knowledge being requested is inappropriate. In region growing, this is the case for defining the homogeneity criterion as its specification depends also on image formation properties that are not known to the user. We developed a region growing algorithm that learns its homogeneity criterion automatically from characteristics of the region to be segmented. The method is based on a model that describes homogeneity and simple shape properties of the region. Parameters of the homogeneity criterion are estimated from sample locations in the region. These locations are selected sequentially in a random walk starting at the seed point, and the homogeneity criterion is updated continuously. The method was tested for segmentation on test images and of structures in CT images. We found the method to work reliable if the model assumption on homogeneity and region characteristics are true. Furthermore, the model is simple but robust, thus allowing for a certain degree of deviation from model constraints and still delivering the expected segmentation result. This approach was extended to a fully automatic and complete segmentation method by using the pixels with the smallest gradient length in the not yet segmented image region as a seed point.
We present a new method of enhancing cerebral vessels in subtraction angiography that defines shape attributes in terms of pixel features. Vessel knowledge comprises information on the imaging process, e.g., distribution of contrast media, noise characteristics, and morphological information on the vessels. The latter is computed as a fuzzy measure because pixels have not yet been classified into vessel and background pixels. We model our image as result of a process of projecting discrete contrast media voxels on the image plane. The projection is assumed to be distorted by noise. The shape feature is derived from the Karhunen-Loeve transformation (KLT) that is computed at each pixel from the covariance of the contrast distribution in a given neighborhood. Vessel likelihood is computed from local elongatedness. The latter is derived from the variances along the two principal axes and from the first central moment of the contrast distribution. The directional information from the KLT is used for anisotropic diffusion for noise reduction. Results of the enhancement step on angiographic data showed a significant improvement of the contrast while not blurring the image. Closely neighboring vessels could be differentiated if they were one pixel apart and if the SNR were better than 2:1.
In this paper a computer system is presented which is aided to support the physician in the evaluation of muscle ultrasound images. For this purpose a multitude of texture features are calculated for each region of interest (ROl), from which one optimal subset is selected for the different diagnosis problems. The results achieved so far are presented and possibilities for improvement are discussed.
Keywords: texture analysis, tissue characterization, feature extraction, ultrasound, neuromuscular diseases
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.