This paper presents extensions which improve the performance of the shape-based deformable active contour model presented earlier in [9]. In contrast to that work, the segmentation framework that we present in this paper allows multiple shapes to be segmented simultaneously in a seamless fashion. To achieve this, multiple signed distance functions are employed as the implicit representations of the multiple shape classes within the image. A parametric model for this new representation is derived by applying principal component analysis to the collection of these multiple signed distance functions. By deriving a parametric model in this manner, we obtain a coupling between the multiple shapes within the image and hence effectively capture the co-variations among the different shapes. The parameters of the multi-shape model are then calculated to minimize a single mutual information-based cost functional for image segmentation. The use of a single cost criterion further enhances the coupling between the multiple shapes as the deformation of any given shape depends, at all times, upon every other shape, regardless of their proximity. We demonstrate the utility of this algorithm to the segmentation of the prostate gland, the rectum, and the internal obturator muscles for MR-guided prostate brachytherapy.

We propose a novel bias correction method for magnetic resonance (MR) imaging that uses complementary body coil and surface coil images. The former are spatially homogeneous but have low signal intensity; the latter provide excellent signal response but have large bias fields. We present a variational framework where we optimize an energy functional to estimate the bias field and the underlying image using both observed images. The energy functional contains smoothness-enforcing regularization for both the image and the bias field. We present extensions of our basic framework to a variety of imaging protocols. We solve the optimization problem using a computationally efficient numerical algorithm based on coordinate descent, preconditioned conjugate gradient, half-quadratic regularization, and multigrid techniques. We show qualitative and quantitative results demonstrating the effectiveness of the proposed method in producing debiased and denoised MR images.

In progressive neurological disorders, such as multiple sclerosis (MS), magnetic resonance imaging (MRI) follow-up is used to monitor disease activity and progression and to understand the underlying pathogenic mechanisms. This article presents image postprocessing methods and validation for integrating multiple serial MRI scans into a spatiotemporal volume for direct quantitative evaluation of the temporal intensity profiles. This temporal intensity signal and its dynamics have thus far not been exploited in the study of MS pathogenesis and the search for MRI surrogates of disease activity and progression. The integration into a four-dimensional data set comprises stages of tissue classification, followed by spatial and intensity normalization and partial volume filtering. Spatial normalization corrects for variations in head positioning and distortion artifacts via fully automated intensity-based registration algorithms, both rigid and nonrigid. Intensity normalization includes separate stages of correcting intra- and interscan variations based on the prior tissue class segmentation. Different approaches to image registration, partial volume correction, and intensity normalization were validated and compared. Validation included a scan-rescan experiment as well as a natural-history study on MS patients, imaged in weekly to monthly intervals over a 1-year follow-up. Significant error reduction was observed by applying tissue-specific intensity normalization and partial volume filtering. Example temporal profiles within evolving multiple sclerosis lesions are presented. An overall residual signal variance of 1.4% +/- 0.5% was observed across multiple subjects and time points, indicating an overall sensitivity of 3% (for axial dual echo images with 3-mm slice thickness) for longitudinal study of signal dynamics from serial brain MRI.

PURPOSE: To suggest a quantitative method for assessing the temporal changes in the geometry of individual multiple sclerosis (MS) lesions in follow-up studies of MS patients. MATERIALS AND METHODS: Computer simulated and in vivo magnetic resonance (MR) imaged MS lesions were studied. Ten in vivo MS lesions were identified from sets of axial MR images acquired from a patient scanned consecutively for 24 times during a one-year period. Each of the lesions was segmented and its three-dimensional surface approximated using spherical harmonics (SH). From the obtained SH polynomial coefficients, indices of shape were defined, and analysis of the temporal changes in each lesion s geometry throughout the year was performed by determining the mean discrete total variation of the shape indices. RESULTS: The results demonstrate that most of the studied lesions undergo notable geometrical changes with time. These changes are not necessarily associated with similar changes in size/volume. Furthermore, it was found that indices corresponding to changes in lesion shape could be 1.4 to 8.0 times higher than those corresponding to changes in the lesion size/volume. CONCLUSION: Quantitative three-dimensional shape analysis can serve as a new tool for monitoring MS lesion activity and study patterns of MS lesion evolution over time.

RATIONALE AND OBJECTIVES: The accuracy of diagnostic test and imaging segmentation is important in clinical practice because it has a direct impact on therapeutic planning. Statistical validations of classification accuracy was conducted based on parametric receiver operating characteristic analysis, illustrated on three radiologic examples, MATERIALS AND METHODS: Two parametric models were developed for diagnostic or imaging data. Example 1: A semi-automated fractional segmentation algorithm was applied to magnetic resonance imaging of nine cases of brain tumors. The tumor and background pixel data were assumed to have bi-beta distributions. Fractional segmentation was validated against an estimated composite pixel-wise gold standard based on multi-reader manual segmentations. Example 2: The predictive value of 100 cases of spiral computed tomography of ureteral stone sizes, distributed as bi-normal after a non-linear transformation, under two treatment options received. Example 3: One hundred eighty cases had prostate-specific antigen levels measured in a prospective clinical trial. Radical prostatectomy was performed in all to provide a binary gold standard of local and advanced cancer stages. Prostate-specific antigen level was transformed and modeled by bi-normal distributions. In all examples, areas under the receiver operating characteristic curves were computed. RESULTS. The areas under the receiver operating characteristic curves were: Example 1: Fractional segmentation of magnetic resonance imaging of brain tumors: meningiomas (0.924-0.984); astrocytomas (0.786-0.986); and other low-grade gliomas (0.896-0.983). Example 3: Ureteral stone size for treatment planning (0.813). Example 2: Prostate-specific antigen for staging prostate cancer (0.768). CONCLUSION: All clinical examples yielded fair to excellent accuracy. The validation metric area under the receiver operating characteristic curves may be generalized to evaluating the performances of several continuous classifiers related to imaging.