From JAMA Psychiatry — Quantitative Brain Magnetic Resonance Imaging in Attention-Deficit Hyperactivity Disorder

Brain magnetic resonance images (MRI) of 104 healthy children and adolescents, aged 4–18, showed significant effects of age and gender on brain morphometry. Males had larger cerebral (9%) and cerebellar (8%) volumes (P < 0.0001 and P = 0.008. respectively), which remained significant even after correction for height and weight After adjusting for cerebral size, the putamen and globus pallidus remained larger in males, while relative caudate size was larger in females. Neither cerebral nor cerebellar volume changed significantly across this age range. Lateral ventricular volume increased significantly in males (trend for females), with males showing an increase in slope after age 11. In males only, caudate and putamen decreased with age (P = 0.007 and 0.05, respectively). The left lateral ventricles and putamen were significantly greater than the right P = 0.01 and 0.0001, respectively). In contrast, the cerebral hemispheres and caudate showed a highly consistent right greater-than-left asymmetry (P < 0.0001 for both). All volumes demonstrated a high degree of variability. These findings highlight gender-specific maturational changes of the developing brain and the need for large gender-matched samples in pediatric neuropsychiatric studies.

A statistical model is presented that represents the distributions of major tissue classes in single-channel magnetic resonance (MR) cerebral images. Using the model, cerebral images are segmented into gray matter, white matter, and cerebrospinal fluid (CSF). The model accounts for random noise, magnetic field inhomogeneities, and biological variations of the tissues. Intensity measurements are modeled by a finite Gaussian mixture. Smoothness and piecewise contiguous nature of the tissue regions are modeled by a three-dimensional (3-D) Markov random field (MRF). A segmentation algorithm, based on the statistical model, approximately finds the maximum a posteriori (MAP) estimation of the segmentation and estimates the model parameters from the image data. The proposed scheme for segmentation is based on the iterative conditional modes (ICM) algorithm in which measurement model parameters are estimated using local information at each site, and the prior model parameters are estimated using the segmentation after each cycle of iterations. Application of the algorithm to a sample of clinical MR brain scans, comparisons of the algorithm with other statistical methods, and a validation study with a phantom are presented. The algorithm constitutes a significant step toward a complete data driven unsupervised approach to segmentation of MR images in the presence of the random noise and intensity inhomogeneities.

This paper proposes a new feature selection method that uses a backward elimination procedure similar to that implemented in support vector machine recursive feature elimination (SVM-RFE). Unlike the SVM-RFE method, at each step, the proposed approach computes the feature ranking score from a statistical analysis of weight vectors of multiple linear SVMs trained on subsamples of the original training data. We tested the proposed method on four gene expression datasets for cancer classification. The results show that the proposed feature selection method selects better gene subsets than the original SVM-RFE and improves the classification accuracy. A Gene Ontology-based similarity assessment indicates that the selected subsets are functionally diverse, further validating our gene selection method. This investigation also suggests that, for gene expression-based cancer classification, average test error from multiple partitions of training and test sets can be recommended as a reference of performance quality.