Rationale and Objectives We present a new method for automatic brain extraction on structural magnetic resonance images, based on a multi-atlas registration framework. Materials and Methods Our method addresses fundamental challenges of multi-atlas approaches. To overcome the difficulties arising from the variability of imaging characteristics between studies, we propose a study-specific template selection strategy, by which we select a set of templates that best represent the anatomical variations within the data set. Against the difficulties of registering brain images with skull, we use a particularly adapted registration algorithm that is more robust to large variations between images, as it adaptively aligns different regions of the two images based not only on their similarity but also on the reliability of the matching between images. Finally, a spatially adaptive weighted voting strategy, which uses the ranking of Jacobian determinant values to measure the local similarity between the template and the target images, is applied for combining coregistered template masks. Results The method is validated on three different public data sets and obtained a higher accuracy than recent state-of-the-art brain extraction methods. Also, the proposed method is successfully applied on several recent imaging studies, each containing thousands of magnetic resonance images, thus reducing the manual correction time significantly. Conclusions The new method, available as a stand-alone software package for public use, provides a robust and accurate brain extraction tool applicable for both clinical use and large population studies.

Multivariate pattern analysis (MVPA) methods such as support vector machines (SVMs) have been increasingly applied to fMRI and sMRI analyses, enabling the detection of distinctive imaging patterns. However, identifying brain regions that significantly contribute to the classification/group separation requires computationally expensive permutation testing. In this paper we show that the results of SVM-permutation testing can be analytically approximated. This approximation leads to more than a thousand fold speed up of the permutation testing procedure, thereby rendering it feasible to perform such tests on standard computers. The speed up achieved makes SVM based group difference analysis competitive with standard univariate group difference analysis methods.

We present an approach for segmenting low-and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed approach is based on a hybrid generativediscriminative model. Firstly, a generative approach based on an Expectation-Maximization framework that incorporates a glioma growth model is used to segment the brain scans into tumor, as well as healthy tissue labels. Secondly, a gradient boosting multi-class classification scheme is used to refine tumor labels based on information from multiple patients. Lastly, a probabilistic Bayesian strategy is employed to further refine and finalize the tumor segmentation based on patient-specific intensity statistics from the multiple modalities. We evaluated our approach in 186 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2015 challenge and report promising results. During the testing phase, the algorithm was additionally evaluated in 53 unseen cases, achieving the best performance among the competing methods.

The ability to predict response to neoadjuvant chemotherapy for women diagnosed with breast cancer, either before or early on in treatment, is critical to judicious patient selection and tailoring the treatment regimen. In this paper, we investigate the role of contrast agent kinetic heterogeneity features derived from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting treatment response. We propose a set of kinetic statistic descriptors and present preliminary results showing the discriminatory capacity of the proposed descriptors for predicting complete and non-complete responders as assessed from pre-treatment imaging exams. The study population consisted of 15 participants: 8 complete responders and 7 non-complete responders. Using the proposed kinetic features, we trained a leave-one-out logistic regression classifier that performs with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.84 under the ROC. We compare the predictive value of our features against commonly used MRI features including kinetics of the characteristic kinetic curve (CKC), maximum peak enhancement (MPE), hotspot signal enhancement ratio (SER), and longest tumor diameter that give lower AUCs of 0.71, 0.66, 0.64, and 0.54, respectively. Our proposed kinetic statistics thus outperform the conventional kinetic descriptors as well as the classifier using a combination of all the conventional descriptors (i.e., CKC, MPE, SER, and longest diameter), which gives an AUC of 0.74. These findings suggest that heterogeneity-based DCE-MRI kinetic statistics could serve as potential imaging biomarkers for tumor characterization and could be used to improve candidate patient selection even before the start of the neoadjuvant treatment.

Machine learning based classification algorithms like support vector machines (SVMs) have shown great promise for turning a high dimensional neuroimaging data into clinically useful decision criteria. However, tracing imaging based patterns that contribute significantly to classifier decisions remains an open problem. This is an issue of critical importance in imaging studies seeking to determine which anatomical or physiological imaging features contribute to the classifier’s decision, thereby allowing users to critically evaluate the findings of such machine learning methods and to understand disease mechanisms. The majority of published work addresses the question of statistical inference for support vector classification using permutation tests based on SVM weight vectors. Such permutation testing ignores the SVM margin, which is critical in SVM theory. In this work we emphasize the use of a statistic that explicitly accounts for the SVM margin and show that the null distributions associated with this statistic are asymptotically normal. Further, our experiments show that this statistic is a lot less conservative as compared to weight based permutation tests and yet specific enough to tease out multivariate patterns in the data. Thus, we can better understand the multivariate patterns that the SVM uses for neuroimaging based classification.