Mahesh B. Nagarajan

Classification of Small Lesions in Breast MRI: Evaluating The Role of Dynamically Extracted Texture Features Through Feature Selection

Dynamic texture quantification, i.e., extracting texture features from the lesion enhancement pattern in all available post-contrast images, has not been evaluated in terms of its ability to classify small lesions. This study investigates the classification performance achieved with texture features extracted from all five post-contrast images of lesions (mean lesion diameter of 1.1 cm) annotated in dynamic breast magnetic resonance imaging exams. Sixty lesions are characterized dynamically using Haralick texture features. The texture features are then used in a classification task with support vector regression and a fuzzy k-nearest neighbor classifier; free parameters of these classifiers are optimized using random sub-sampling cross-validation. Classifier performance is determined through receiver-operator characteristic (ROC) analysis, specifically through computation of the area under the ROC curve (AUC). Mutual information is used to evaluate the contribution of texture features extracted from different post-contrast stages to classifier performance. Significant improvements (p < 0.05) are observed for six of the thirteen texture features when the lesion enhancement pattern is quantified using the proposed approach of dynamic texture quantification. The highest AUC value observed (0.82) is achieved with texture features responsible for capturing aspects of lesion heterogeneity. Mutual information analysis reveals that texture features extracted from the third and fourth post-contrast images contributed most to the observed improvement in classifier performance. These results show that the performance of automated character classification with small lesions can be significantly improved through dynamic texture quantification of the lesion enhancement pattern.

Prediction of Biomechanical Properties of Trabecular Bone in MR Images With Geometric Features and Support Vector Regression

Whole knee joint MR image datasets were used to compare the performance of geometric trabecular bone features and advanced machine learning techniques in predicting biomechanical strength properties measured on the corresponding ex vivo specimens. Changes of trabecular bone structure throughout the proximal tibia are indicative of several musculoskeletal disorders involving changes in the bone quality and the surrounding soft tissue. Recent studies have shown that MR imaging also allows non-invasive 3-D characterization of bone microstructure. Sophisticated features like the scaling index method (SIM) can estimate local structural and geometric properties of the trabecular bone and may improve the ability of MR imaging to determine local bone quality in vivo. A set of 67 bone cubes was extracted from knee specimens and their biomechanical strength estimated by the yield stress (YS) [in MPa] was determined through mechanical testing. The regional apparent bone volume fraction (BVF) and SIM derived features were calculated for each bone cube. A linear multiregression analysis (MultiReg) and a optimized support vector regression (SVR) algorithm were used to predict the YS from the image features. The prediction accuracy was measured by the root mean square error (RMSE) for each image feature on independent test sets. The best prediction result with the lowest prediction error of RMSE = 1.021 MPa was obtained with a combination of BVF and SIM features and by using SVR. The prediction accuracy with only SIM features and SVR (RMSE = 1.023 MPa) was still significantly better than BVF alone and MultiReg (RMSE = 1.073 MPa). The current study demonstrates that the combination of sophisticated bone structure features and supervised learning techniques can improve MR-based determination of trabecular bone quality.

Computer-Aided Diagnosis in Phase Contrast Imaging X-Ray Computed Tomography for Quantitative Characterization of ex vivo Human Patellar Cartilage

Visualization of ex vivo human patellar cartilage matrix through the phase contrast imaging X-ray computed tomography (PCI-CT) has been previously demonstrated. Such studies revealed osteoarthritis-induced changes to chondrocyte organization in the radial zone. This study investigates the application of texture analysis to characterizing such chondrocyte patterns in the presence and absence of osteoarthritic damage. Texture features derived from Minkowski functionals (MF) and gray-level co-occurrence matrices (GLCM) were extracted from 842 regions of interest (ROI) annotated on PCI-CT images of ex vivo human patellar cartilage specimens. These texture features were subsequently used in a machine learning task with support vector regression to classify ROIs as healthy or osteoarthritic; classification performance was evaluated using the area under the receiver operating characteristic curve (AUC). The best classification performance was observed with the MF features perimeter (AUC: 0.94 ±0.08) and “Euler characteristic” (AUC: 0.94 ± 0.07), and GLCM-derived feature “Correlation” (AUC: 0.93 ± 0.07). These results suggest that such texture features can provide a detailed characterization of the chondrocyte organization in the cartilage matrix, enabling classification of cartilage as healthy or osteoarthritic with high accuracy.

Texture feature ranking with relevance learning to classify interstitial lung disease patterns

OBJECTIVE The generalized matrix learning vector quantization (GMLVQ) is used to estimate the relevance of texture features in their ability to classify interstitial lung disease patterns in high-resolution computed tomography images. METHODOLOGY After a stochastic gradient descent, the GMLVQ algorithm provides a discriminative distance measure of relevance factors, which can account for pairwise correlations between different texture features and their importance for the classification of healthy and diseased patterns. 65 texture features were extracted from gray-level co-occurrence matrices (GLCMs). These features were ranked and selected according to their relevance obtained by GMLVQ and, for comparison, to a mutual information (MI) criteria. The classification performance for different feature subsets was calculated for a k-nearest-neighbor (kNN) and a random forests classifier (RanForest), and support vector machines with a linear and a radial basis function kernel (SVMlin and SVMrbf). RESULTS For all classifiers, feature sets selected by the relevance ranking assessed by GMLVQ had a significantly better classification performance (p<0.05) for many texture feature sets compared to the MI approach. For kNN, RanForest, and SVMrbf, some of these feature subsets had a significantly better classification performance when compared to the set consisting of all features (p<0.05). CONCLUSION While this approach estimates the relevance of single features, future considerations of GMLVQ should include the pairwise correlation for the feature ranking, e.g. to reduce the redundancy of two equally relevant features.

Computer-Aided Diagnosis for Phase-Contrast X-ray Computed Tomography: Quantitative Characterization of Human Patellar Cartilage with High-Dimensional Geometric Features

Phase-contrast computed tomography (PCI-CT) has shown tremendous potential as an imaging modality for visualizing human cartilage with high spatial resolution. Previous studies have demonstrated the ability of PCI-CT to visualize (1) structural details of the human patellar cartilage matrix and (2) changes to chondrocyte organization induced by osteoarthritis. This study investigates the use of high-dimensional geometric features in characterizing such chondrocyte patterns in the presence or absence of osteoarthritic damage. Geometrical features derived from the scaling index method (SIM) and statistical features derived from gray-level co-occurrence matrices were extracted from 842 regions of interest (ROI) annotated on PCI-CT images of ex vivo human patellar cartilage specimens. These features were subsequently used in a machine learning task with support vector regression to classify ROIs as healthy or osteoarthritic; classification performance was evaluated using the area under the receiver-operating characteristic curve (AUC). SIM-derived geometrical features exhibited the best classification performance (AUC, 0.95 ± 0.06) and were most robust to changes in ROI size. These results suggest that such geometrical features can provide a detailed characterization of the chondrocyte organization in the cartilage matrix in an automated and non-subjective manner, while also enabling classification of cartilage as healthy or osteoarthritic with high accuracy. Such features could potentially serve as imaging markers for evaluating osteoarthritis progression and its response to different therapeutic intervention strategies.

Improving bone strength prediction in human proximal femur specimens through geometrical characterization of trabecular bone microarchitecture and support vector regression

Abstract. We investigate the use of different trabecular bone descriptors and advanced machine learning techniques to complement standard bone mineral density (BMD) measures derived from dual-energy x-ray absorptiometry (DXA) for improving clinical assessment of osteoporotic fracture risk. For this purpose, volumes of interest were extracted from the head, neck, and trochanter of 146 ex vivo proximal femur specimens on multidetector computer tomography. The trabecular bone captured was characterized with (1) statistical moments of the BMD distribution, (2) geometrical features derived from the scaling index method (SIM), and (3) morphometric parameters, such as bone fraction, trabecular thickness, etc. Feature sets comprising DXA BMD and such supplemental features were used to predict the failure load (FL) of the specimens, previously determined through biomechanical testing, with multiregression and support vector regression. Prediction performance was measured by the root mean square error (RMSE); correlation with measured FL was evaluated using the coefficient of determination R2. The best prediction performance was achieved by a combination of DXA BMD and SIM-derived geometric features derived from the femoral head (RMSE: 0.869±0.121, R2: 0.68±0.079), which was significantly better than DXA BMD alone (RMSE: 0.948±0.119, R2: 0.61±0.101) (p<10−4). For multivariate feature sets, SVR outperformed multiregression (p<0.05). These results suggest that supplementing standard DXA BMD measurements with sophisticated femoral trabecular bone characterization and supervised learning techniques can significantly improve biomechanical strength prediction in proximal femur specimens.

Pair-wise clustering of large scale Granger causality index matrices for revealing communities

The analysis of large ensembles of time series is a fundamental challenge in different domains of biomedical image processing applications, specifically in the area of functional MRI data processing. An important aspect of such analysis is the ability to reconstruct community network structures based on interactive behavior between different nodes of the network which are captured in such time series. In this study, we start with a previously proposed novel approach that applies the linear Granger Causality concept to very high-dimensional time series. This approach is based on integrating dimensionality reduction into a multivariate time series model. If residuals of dimensionality reduced models can be transformed back into the original space, prediction errors in the high–dimensional space may be computed, and a large scale Granger Causality Index (lsGCI) is properly defined. The primary goal of this study was then to present an approach for recovering network structure from such lsGCI interactions through the application of pair-wise clustering. We specifically focus on a clustering approach based on topographic mapping of proximity data (TMP) for this purpose. We demonstrate our approach with a simulated network composed of five pair-wise different internal networks with varying strengths of community structure (based on the number of inter-network vertices). Our results suggest that such pair-wise clustering with TMP is capable of reconstructing the structure of the original network from lsGCI matrices that record the interactions between different nodes of the network when there is sufficient disparity between the intra- and inter-network vertices.

Introducing anisotropic Minkowski functionals and quantitative anisotropy measures for local structure analysis in biomedical imaging

The ability of Minkowski Functionals to characterize local structure in different biological tissue types has been demonstrated in a variety of medical image processing tasks. We introduce anisotropic Minkowski Functionals (AMFs) as a novel variant that captures the inherent anisotropy of the underlying gray-level structures. To quantify the anisotropy characterized by our approach, we further introduce a method to compute a quantitative measure motivated by a technique utilized in MR diffusion tensor imaging, namely fractional anisotropy. We showcase the applicability of our method in the research context of characterizing the local structure properties of trabecular bone micro-architecture in the proximal femur as visualized on multi-detector CT. To this end, AMFs were computed locally for each pixel of ROIs extracted from the head, neck and trochanter regions. Fractional anisotropy was then used to quantify the local anisotropy of the trabecular structures found in these ROIs and to compare its distribution in different anatomical regions. Our results suggest a significantly greater concentration of anisotropic trabecular structures in the head and neck regions when compared to the trochanter region (p < 10-4). We also evaluated the ability of such AMFs to predict bone strength in the femoral head of proximal femur specimens obtained from 50 donors. Our results suggest that such AMFs, when used in conjunction with multi-regression models, can outperform more conventional features such as BMD in predicting failure load. We conclude that such anisotropic Minkowski Functionals can capture valuable information regarding directional attributes of local structure, which may be useful in a wide scope of biomedical imaging applications.

Mutual Connectivity Analysis (MCA) Using Generalized Radial Basis Function Neural Networks for Nonlinear Functional Connectivity Network Recovery in Resting-State Functional MRI

We investigate the applicability of a computational framework, called mutual connectivity analysis (MCA), for directed functional connectivity analysis in both synthetic and resting-state functional MRI data. This framework comprises of first evaluating non-linear cross-predictability between every pair of time series prior to recovering the underlying network structure using community detection algorithms. We obtain the non-linear cross-prediction score between time series using Generalized Radial Basis Functions (GRBF) neural networks. These cross-prediction scores characterize the underlying functionally connected networks within the resting brain, which can be extracted using non-metric clustering approaches, such as the Louvain method. We first test our approach on synthetic models with known directional influence and network structure. Our method is able to capture the directional relationships between time series (with an area under the ROC curve = 0.92 ± 0.037) as well as the underlying network structure (Rand index = 0.87 ± 0.063) with high accuracy. Furthermore, we test this method for network recovery on resting-state fMRI data, where results are compared to the motor cortex network recovered from a motor stimulation sequence, resulting in a strong agreement between the two (Dice coefficient = 0.45). We conclude that our MCA approach is effective in analyzing non-linear directed functional connectivity and in revealing underlying functional network structure in complex systems.

Nonlinear functional connectivity network recovery in the human brain with mutual connectivity analysis (MCA): convergent cross-mapping and non-metric clustering

We explore a computational framework for functional connectivity analysis in resting-state functional MRI (fMRI) data acquired from the human brain for recovering the underlying network structure and understanding causality between network components. Termed mutual connectivity analysis (MCA), this framework involves two steps, the first of which is to evaluate the pair-wise cross-prediction performance between fMRI pixel time series within the brain. In a second step, the underlying network structure is subsequently recovered from the affinity matrix using non-metric network clustering approaches, such as the so-called Louvain method. Finally, we use convergent cross-mapping (CCM) to study causality between different network components. We demonstrate our MCA framework in the problem of recovering the motor cortex network associated with hand movement from resting state fMRI data. Results are compared with a ground truth of active motor cortex regions as identified by a task-based fMRI sequence involving a finger-tapping stimulation experiment. Our results regarding causation between regions of the motor cortex revealed a significant directional variability and were not readily interpretable in a consistent manner across subjects. However, our results on whole-slice fMRI analysis demonstrate that MCA-based model-free recovery of regions associated with the primary motor cortex and supplementary motor area are in close agreement with localization of similar regions achieved with a task-based fMRI acquisition. Thus, we conclude that our MCA methodology can extract and visualize valuable information concerning the underlying network structure between different regions of the brain in resting state fMRI.