Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) has emerged as an effective tool to access tumor vascular characteristics. DCE-MRI can be used to characterize noninvasively, microvasculature providing information about tumor microvessel structure and function (e.g., tumor blood volume, vascular permeability, tumor perfusion). However, pixels of DCE-MRI represent a composite of more than one distinct functional biomarker (e.g., microvessels with fast or slow perfusion) whose spatial distributions are often heterogeneous. Complementary to various existing methods (e.g., compartment modeling, factor analysis), this paper proposes a blind source separation method which allows for a computed simultaneous imaging of multiple biomarkers from composite DCE-MRI sequences. The algorithm is based on a partially-independent component analysis, whose parameters are estimated using a subset of informative pixels defining the independent portion of the observations. We demonstrate the principle of the approach on simulated image data set, and we then apply the method to the tissue heterogeneity characterization of breast tumors where spatial distribution of tumor blood volume, vascular permeability, and tumor perfusion, as well as their time activity curves (TACs) are simultaneously estimated.
Non-rigid image registration is a prerequisite for many medical imaging applications such as change analysis in image-based diagnosis and therapy assessment. Nonlinear interpolation methods may be used to recover the deformation if the correspondence of the extracted feature points is available. However, it may be very difficult to establish such correspondence at an initial stage when confronted with large and complex deformation. In this paper, a mixture of principal axes registration (mPAR) is proposed to tackle the correspondence problem using a neural computation method. The feature is to align two point sets without needing to establish the explicit point correspondence. The mPAR aligns two point sets by minimizing the relative entropy between their probability distributions resulting in a maximum likelihood estimate of the transformation mixture. The neural computation for the mPAR is developed using a committee machine to obtain a mixture of piece-wise rigid registrations. The complete registration process consists of two steps: (1) using the mPAR to establish an improved point correspondence and (2) using a multilayer perceptron (MLP) neural network to recover the nonlinear deformation. The mPAR method has been applied to register a contrast-enhanced magnetic resonance (MR) image sequence. The experimental results show that our method not only improves the point correspondence but also results in a desirable error-resilience property for control point selection errors.
This paper presents the development of a prototype Tactile Mapping Device (TMD) system comprised mainly of a tactile sensor array probe (TSAP), a 3-D camera, and a force/torque sensor, which can provide the means to produce tactile maps of the breast lumps during a breast palpation. Focusing on the key tactile topology features for breast palpation such as spatial location, size/shape of the detected lesion, and the force levels used to demonstrate the palpable abnormalities, these maps can record the results of clinical breast examination with a set of pressure distribution profiles and force sensor measurements due to detected lesion. By combining the knowledge of vision based, neural networks and tactile sensing technology; the TMD is integrated for the investigation of soft tissue interaction with tactile/force sensor, where the hard inclusion (breast cancer) can be characterized through neural network learning capability, instead of using simplified complex biomechanics model with many heuristic assumptions. These maps will serve as an objective documentation of palpable lesions for future comparative examinations. Preliminary results of simulated experiments and limited pre-clinical evaluations of the TMD prototype have tested this hypothesis and provided solid promising data showing the feasibility of the TMD in real clinical applications.
To reveal the spatial pattern of localized prostate cancer distribution, a 3D statistical volumetric model, showing the probability map of prostate cancer distribution, together with the anatomical structure of the prostate, has been developed from 90 digitally-imaged surgical specimens. Through an enhanced virtual environment with various visualization modes, this master model permits for the first time an accurate characterization and understanding of prostate cancer distribution patterns. The construction of the statistical volumetric model is characterized by mapping all of the individual models onto a generic prostate site model, in which a self-organizing scheme is used to decompose a group of contours representing multifold tumors into localized tumor elements. Next crucial step of creating the master model is the development of an accurate multi- object and non-rigid registration/warping scheme incorporating various variations among these individual moles in true 3D. This is achieved with a multi-object based principle-axis alignment followed by an affine transform, and further fine-tuned by a thin-plate spline interpolation driven by the surface based deformable warping dynamics. Based on the accurately mapped tumor distribution, a standard finite normal mixture is used to model the cancer volumetric distribution statistics, whose parameters are estimated using both the K-means and expectation- maximization algorithms under the information theoretic criteria. Given the desired number of tissue samplings, the prostate needle biopsy site selection is optimized through a probabilistic self-organizing map thus achieving a maximum likelihood of cancer detection. We describe the details of our theory and methodology, and report our pilot results and evaluation of the effectiveness of the algorithm in characterizing prostate cancer distributions and optimizing needle biopsy techniques.