Incorporating a measure of local scale in voxel-based 3-D image registration

Registration of Magnetic Resonance Tomography (MRT) Data with a Low Frequency Adaption of Fourier-Mellin-SOFT (LF-FMS)

Fourier-Mellin-SOFT (FMS) is a rigid 3D registration method, which allows the robust registration of 3 degrees-of-freedom (dof) rotation, 1-dof scale, and 3-dof translation between scans on discrete grids. FMS is based on a spectral decomposition of these 7-dof. This complete spectral representation of the input data enables an adaption to certain frequency ranges. This special property is used here to focus on relevant mutual 3D information between bone structures with a Low Frequency adaptation of FMS (LF-FMS), that is, it is utilized for matching and concurrently determining corresponding transformation parameters. This process is applied on a set of Magnetic Resonance Tomography (MRT) data representing the hand region, in particular the carpal bone area, in a sequence of different hand positions. This data set is available for different probands, which allows a comparison of resulting parameter plots and furthermore matching in between bone structures.

Performance Assessment for Brain MR Imaging Registration Methods

BACKGROUND AND PURPOSE

Clinical brain MR imaging registration algorithms are often made available by commercial vendors without figures of merit. The purpose of this study was to suggest a rational performance comparison methodology for these products.

MATERIALS AND METHODS

Twenty patients were imaged on clinical 3T scanners by using 4 sequences: T2-weighted, FLAIR, susceptibility-weighted angiography, and T1 postcontrast. Fiducial landmark sites (n = 1175) were specified throughout these image volumes to define identical anatomic locations across sequences. Multiple registration algorithms were applied by using the T2 sequence as a fixed reference. Euclidean error was calculated before and after each registration and compared with a criterion standard landmark registration. The Euclidean effectiveness ratio is the fraction of Euclidean error remaining after registration, and the statistical effectiveness ratio is similar, but accounts for dispersion and noise.

RESULTS

Before registration, error values for FLAIR, susceptibility-weighted angiography, and T1 postcontrast were 2.07 ± 0.55 mm, 2.63 ± 0.62 mm, and 3.65 ± 2.00 mm, respectively. Postregistration, the best error values for FLAIR, susceptibility-weighted angiography, and T1 postcontrast were 1.55 ± 0.46 mm, 1.34 ± 0.23 mm, and 1.06 ± 0.16 mm, with Euclidean effectiveness ratio values of 0.493, 0.181, and 0.096 and statistical effectiveness ratio values of 0.573, 0.352, and 0.929 for rigid mutual information, affine mutual information, and a commercial GE registration, respectively.

CONCLUSIONS

We demonstrate a method for comparing the performance of registration algorithms and suggest the Euclidean error, Euclidean effectiveness ratio, and statistical effectiveness ratio as performance metrics for clinical registration algorithms. These figures of merit allow registration algorithms to be rationally compared.

Spectral embedding based active contour (SEAC) for lesion segmentation on breast dynamic contrast enhanced magnetic resonance imaging

PURPOSE

Segmentation of breast lesions on dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) is the first step in lesion diagnosis in a computer-aided diagnosis framework. Because manual segmentation of such lesions is both time consuming and highly susceptible to human error and issues of reproducibility, an automated lesion segmentation method is highly desirable. Traditional automated image segmentation methods such as boundary-based active contour (AC) models require a strong gradient at the lesion boundary. Even when region-based terms are introduced to an AC model, grayscale image intensities often do not allow for clear definition of foreground and background region statistics. Thus, there is a need to find alternative image representations that might provide (1) strong gradients at the margin of the object of interest (OOI); and (2) larger separation between intensity distributions and region statistics for the foreground and background, which are necessary to halt evolution of the AC model upon reaching the border of the OOI.

METHODS

In this paper, the authors introduce a spectral embedding (SE) based AC (SEAC) for lesion segmentation on breast DCE-MRI. SE, a nonlinear dimensionality reduction scheme, is applied to the DCE time series in a voxelwise fashion to reduce several time point images to a single parametric image where every voxel is characterized by the three dominant eigenvectors. This parametric eigenvector image (PrEIm) representation allows for better capture of image region statistics and stronger gradients for use with a hybrid AC model, which is driven by both boundary and region information. They compare SEAC to ACs that employ fuzzy c-means (FCM) and principal component analysis (PCA) as alternative image representations. Segmentation performance was evaluated by boundary and region metrics as well as comparing lesion classification using morphological features from SEAC, PCA+AC, and FCM+AC.

RESULTS

On a cohort of 50 breast DCE-MRI studies, PrEIm yielded overall better region and boundary-based statistics compared to the original DCE-MR image, FCM, and PCA based image representations. Additionally, SEAC outperformed a hybrid AC applied to both PCA and FCM image representations. Mean dice similarity coefficient (DSC) for SEAC was significantly better (DSC = 0.74 ± 0.21) than FCM+AC (DSC = 0.50 ± 0.32) and similar to PCA+AC (DSC = 0.73 ± 0.22). Boundary-based metrics of mean absolute difference and Hausdorff distance followed the same trends. Of the automated segmentation methods, breast lesion classification based on morphologic features derived from SEAC segmentation using a support vector machine classifier also performed better (AUC = 0.67 ± 0.05; p < 0.05) than FCM+AC (AUC = 0.50 ± 0.07), and PCA+AC (AUC = 0.49 ± 0.07).

CONCLUSIONS

In this work, we presented SEAC, an accurate, general purpose AC segmentation tool that could be applied to any imaging domain that employs time series data. SE allows for projection of time series data into a PrEIm representation so that every voxel is characterized by the dominant eigenvectors, capturing the global and local time-intensity curve similarities in the data. This PrEIm allows for the calculation of strong tensor gradients and better region statistics than the original image intensities or alternative image representations such as PCA and FCM. The PrEIm also allows for building a more accurate hybrid AC scheme.

Quantifying local heterogeneity via morphologic scale: Distinguishing tumoral from stromal regions

INTRODUCTION

The notion of local scale was introduced to characterize varying levels of image detail so that localized image processing tasks could be performed while simultaneously yielding a globally optimal result. In this paper, we have presented the methodological framework for a novel locally adaptive scale definition, morphologic scale (MS), which is different from extant local scale definitions in that it attempts to characterize local heterogeneity as opposed to local homogeneity.

METHODS

At every point of interest, the MS is determined as a series of radial paths extending outward in the direction of least resistance, navigating around obstructions. Each pixel can then be directly compared to other points of interest via a rotationally invariant quantitative feature descriptor, determined by the application of Fourier descriptors to the collection of these paths.

RESULTS

OUR GOAL IS TO DISTINGUISH TUMOR AND STROMAL TISSUE CLASSES IN THE CONTEXT OF FOUR DIFFERENT DIGITIZED PATHOLOGY DATASETS: prostate tissue microarrays (TMAs) stained with hematoxylin and eosin (HE) (44 images) and TMAs stained with only hematoxylin (H) (44 images), slide mounts of ovarian H (60 images), and HE breast cancer (51 images) histology images. Classification performance over 50 cross-validation runs using a Bayesian classifier produced mean areas under the curve of 0.88 ± 0.01 (prostate HE), 0.87 ± 0.02 (prostate H), 0.88 ± 0.01 (ovarian H), and 0.80 ± 0.01 (breast HE).

CONCLUSION

For each dataset listed in Table 3, we randomly selected 100 points per image, and using the procedure described in Experiment 1, we attempted to separate them as belonging to stroma or epithelium.

High-frequency oscillations, extent of surgical resection, and surgical outcome in drug-resistant focal epilepsy

PURPOSE

Removal of areas generating high-frequency oscillations (HFOs) recorded from the intracerebral electroencephalography (iEEG) of patients with medically intractable epilepsy has been found to be correlated with improved surgical outcome. However, whether differences exist according to the type of epilepsy is largely unknown. We performed a comparative assessment of the impact of removing HFO-generating tissue on surgical outcome between temporal lobe epilepsy (TLE) and extratemporal lobe epilepsy (ETLE). We also assessed the relationship between the extent of surgical resection and surgical outcome.

METHODS

We studied 30 patients with drug-resistant focal epilepsy, 21 with TLE and 9 with ETLE. Two thirds of the patients were included in a previous report and for these, clinical and imaging data were updated and follow-up was extended. All patients underwent iEEG investigations (500 Hz high-pass filter and 2,000 Hz sampling rate), surgical resection, and postoperative magnetic resonance imaging (MRI). HFOs (ripples, 80-250 Hz; fast ripples, >250 Hz) were identified visually on a 5-10 min interictal iEEG sample. HFO rates inside versus outside the seizure-onset zone (SOZ), in resected versus nonresected tissue, and their association with surgical outcome (ILAE classification) were assessed in the entire cohort, and in the TLE and ETLE subgroups. We also tested the correlation of resected brain hippocampal and amygdala volumes (as measured on postoperative MRIs) with surgical outcome.

KEY FINDINGS

HFO rates were significantly higher inside the SOZ than outside in the entire cohort and TLE subgroup, but not in the ETLE subgroup. In all groups, HFO rates did not differ significantly between resected and nonresected tissue. Surgical outcome was better when higher HFO rates were included in the surgical resection in the entire cohort and TLE subgroup, but not in the ETLE subgroup. Resected brain hippocampal and amygdala volumes were not correlated with surgical outcome.

SIGNIFICANCE

In TLE, removal of HFO-generating areas may lead to improved surgical outcome. Less consistent findings emerge from ETLE, but these may be related to sample size limitations of this study. Size of resection, a factor that was ignored and that could have affected results of earlier studies did not influence results.

Automated segmentation of basal ganglia and deep brain structures in MRI of Parkinson's disease

PURPOSE

Template-based segmentation techniques have been developed to facilitate the accurate targeting of deep brain structures in patients with movement disorders. Three template-based brain MRI segmentation techniques were compared to determine the best strategy for segmenting the deep brain structures of patients with Parkinson's disease.

METHODS

T1-weighted and T2-weighted magnetic resonance (MR) image templates were created by averaging MR images of 57 patients with Parkinson's disease. Twenty-four deep brain structures were manually segmented on the templates. To validate the template-based segmentation, 14 of the 24 deep brain structures from the templates were manually segmented on 10 MR scans of Parkinson's patients as a gold standard. We compared the manual segmentations with three methods of automated segmentation: two registration-based approaches, automatic nonlinear image matching and anatomical labeling (ANIMAL) and symmetric image normalization (SyN), and one patch-label fusion technique. The automated labels were then compared with the manual labels using a Dice-kappa metric and center of gravity. A Friedman test was used to compare the Dice-kappa values and paired t tests for the center of gravity.

RESULTS

The Friedman test showed a significant difference between the three methods for both thalami (p < 0.05) and not for the subthalamic nuclei. Registration with ANIMAL was better than with SyN for the left thalamus and was better than the patch-based method for the right thalamus.

CONCLUSION

Although template-based approaches are the most used techniques to segment basal ganglia by warping onto MR images, we found that the patch-based method provided similar results and was less time-consuming. Patch-based method may be preferable for the subthalamic nucleus segmentation in patients with Parkinson's disease.

Automatic detection and quantification of tree-in-bud (TIB) opacities from CT scans

This study presents a novel computer-assisted detection (CAD) system for automatically detecting and precisely quantifying abnormal nodular branching opacities in chest computed tomography (CT), termed tree-in-bud (TIB) opacities by radiology literature. The developed CAD system in this study is based on 1) fast localization of candidate imaging patterns using local scale information of the images, and 2) Möbius invariant feature extraction method based on learned local shape and texture properties of TIB patterns. For fast localization of candidate imaging patterns, we use ball-scale filtering and, based on the observation of the pattern of interest, a suitable scale selection is used to retain only small size patterns. Once candidate abnormality patterns are identified, we extract proposed shape features from regions where at least one candidate pattern occupies. The comparative evaluation of the proposed method with commonly used CAD methods is presented with a dataset of 60 chest CTs (laboratory confirmed 39 viral bronchiolitis human parainfluenza CTs and 21 normal chest CTs). The quantitative results are presented as the area under the receiver operator characteristics curves and a computer score (volume affected by TIB) provided as an output of the CAD system. In addition, a visual grading scheme is applied to the patient data by three well-trained radiologists. Interobserver and observer-computer agreements are obtained by the relevant statistical methods over different lung zones. Experimental results demonstrate that the proposed CAD system can achieve high detection rates with an overall accuracy of 90.96%. Moreover, correlations of observer-observer (R(2)=0.8848, and observer-CAD agreements (R(2)=0.824, validate the feasibility of the use of the proposed CAD system in detecting and quantifying TIB patterns.

Hierarchical scale-based multiobject recognition of 3-D anatomical structures

Segmentation of anatomical structures from medical images is a challenging problem, which depends on the accurate recognition (localization) of anatomical structures prior to delineation. This study generalizes anatomy segmentation problem via attacking two major challenges: 1) automatically locating anatomical structures without doing search or optimization, and 2) automatically delineating the anatomical structures based on the located model assembly. For 1), we propose intensity weighted ball-scale object extraction concept to build a hierarchical transfer function from image space to object (shape) space such that anatomical structures in 3-D medical images can be recognized without the need to perform search or optimization. For 2), we integrate the graph-cut (GC) segmentation algorithm with prior shape model. This integrated segmentation framework is evaluated on clinical 3-D images consisting of a set of 20 abdominal CT scans. In addition, we use a set of 11 foot MR images to test the generalizability of our method to the different imaging modalities as well as robustness and accuracy of the proposed methodology. Since MR image intensities do not possess a tissue specific numeric meaning, we also explore the effects of intensity nonstandardness on anatomical object recognition. Experimental results indicate that: 1) effective recognition can make the delineation more accurate; 2) incorporating a large number of anatomical structures via a model assembly in the shape model improves the recognition and delineation accuracy dramatically; 3) ball-scale yields useful information about the relationship between the objects and the image; 4) intensity variation among scenes in an ensemble degrades object recognition performance.

Nonrigid brain MR image registration using uniform spherical region descriptor

There are two main issues that make nonrigid image registration a challenging task. First, voxel intensity similarity may not be necessarily equivalent to anatomical similarity in the image correspondence searching process. Second, during the imaging process, some interferences such as unexpected rotations of input volumes and monotonic gray-level bias fields can adversely affect the registration quality. In this paper, a new feature-based nonrigid image registration method is proposed. The proposed method is based on a new type of image feature, namely, uniform spherical region descriptor (USRD), as signatures for each voxel. The USRD is rotation and monotonic gray-level transformation invariant and can be efficiently calculated. The registration process is therefore formulated as a feature matching problem. The USRD feature is integrated with the Markov random field labeling framework in which energy function is defined for registration. The energy function is then optimized by the α-expansion algorithm. The proposed method has been compared with five state-of-the-art registration approaches on both the simulated and real 3-D databases obtained from the BrainWeb and Internet Brain Segmentation Repository, respectively. Experimental results demonstrate that the proposed method can achieve high registration accuracy and reliable robustness behavior.

A modified possibilistic fuzzy c-means clustering algorithm for bias field estimation and segmentation of brain MR image

A modified possibilistic fuzzy c-means clustering algorithm is presented for fuzzy segmentation of magnetic resonance (MR) images that have been corrupted by intensity inhomogeneities and noise. By introducing a novel adaptive method to compute the weights of local spatial in the objective function, the new adaptive fuzzy clustering algorithm is capable of utilizing local contextual information to impose local spatial continuity, thus allowing the suppression of noise and helping to resolve classification ambiguity. To estimate the intensity inhomogeneity, the global intensity is introduced into the coherent local intensity clustering algorithm and takes the local and global intensity information into account. The segmentation target therefore is driven by two forces to smooth the derived optimal bias field and improve the accuracy of the segmentation task. The proposed method has been successfully applied to 3 T, 7 T, synthetic and real MR images with desirable results. Comparisons with other approaches demonstrate the superior performance of the proposed algorithm. Moreover, the proposed algorithm is robust to initialization, thereby allowing fully automatic applications.

CAVASS: a computer-assisted visualization and analysis software system

The Medical Image Processing Group at the University of Pennsylvania has been developing (and distributing with source code) medical image analysis and visualization software systems for a long period of time. Our most recent system, 3DVIEWNIX, was first released in 1993. Since that time, a number of significant advancements have taken place with regard to computer platforms and operating systems, networking capability, the rise of parallel processing standards, and the development of open-source toolkits. The development of CAVASS by our group is the next generation of 3DVIEWNIX. CAVASS will be freely available and open source, and it is integrated with toolkits such as Insight Toolkit and Visualization Toolkit. CAVASS runs on Windows, Unix, Linux, and Mac but shares a single code base. Rather than requiring expensive multiprocessor systems, it seamlessly provides for parallel processing via inexpensive clusters of work stations for more time-consuming algorithms. Most importantly, CAVASS is directed at the visualization, processing, and analysis of 3-dimensional and higher-dimensional medical imagery, so support for digital imaging and communication in medicine data and the efficient implementation of algorithms is given paramount importance.

Comparing MR image intensity standardization against tissue characterizability of magnetization transfer ratio imaging

PURPOSE

To evaluate existing methods of standardization by exploiting the well-known tissue characterizing property of magnetization transfer ratio (MTR) values obtained from MT imaging, and compare the tissue characterizability of standardized T2, proton density (PD), and T1 images against the MTR images.

MATERIALS AND METHODS

Image intensity standardization is a postprocessing method that was designed to correct for acquisition-to-acquisition signal intensity variations (nonstandardness) inherent in magnetic resonance (MR) images. The main idea of this technique is to deform the volume image histogram of each study to match a standard histogram, and to utilize the resulting transformations to map the image intensities into a standard scale. The method has been shown to produce a significant gain in similarity of resulting images and to achieve numeric tissue characterization. In this work we compared PD-, T2-, and T1-weighted images before and after standardization with the corresponding MT images for 10 patient MRI studies of the brain, in terms of the normalized median values on the corresponding image histograms.

RESULTS

No statistically significant difference was observed between the standardized PD-, T2-, and T1-weighted images and the corresponding MTR images. However, a statistically significant difference was found between the pre- and poststandardized PD-, T2-, and T1-weighted images, and between the prestandardized PD-, T2-, and T1-weighted images and the corresponding MTR images.

CONCLUSION

These results suggest that standardized T2, PD, and T1 images and their tissue-specific intensity signatures may be useful for characterizing disease.