The objective of this study is to investigate the use of pattern classification methods for distinguishing different types of brain tumors, such as primary gliomas from metastases, and also for grading of gliomas. The availability of an automated computer analysis tool that is more objective than human readers can potentially lead to more reliable and reproducible brain tumor diagnostic procedures. A computer-assisted classification method combining conventional MRI and perfusion MRI is developed and used for differential diagnosis. The proposed scheme consists of several steps including region-of-interest definition, feature extraction, feature selection, and classification. The extracted features include tumor shape and intensity characteristics, as well as rotation invariant texture features. Feature subset selection is performed using support vector machines with recursive feature elimination. The method was applied on a population of 102 brain tumors histologically diagnosed as metastasis (24), meningiomas (4), gliomas World Health Organization grade II (22), gliomas World Health Organization grade III (18), and glioblastomas (34). The binary support vector machine classification accuracy, sensitivity, and specificity, assessed by leave-one-out cross-validation, were, respectively, 85%, 87%, and 79% for discrimination of metastases from gliomas and 88%, 85%, and 96% for discrimination of high-grade (grades III and IV) from low-grade (grade II) neoplasms. Multiclass classification was also performed via a onevs-all voting scheme.

Written informed consent was obtained prior to all human studies after the institutional review board approved the protocol. A continuous arterial spin-labeling technique with an amplitude-modulated control was implemented by using a single coil at 3.0 T. Adiabatic inversion efficiency at 3.0 T, comparable to that at 1.5 T, was achieved by reducing the amplitude of radiofrequency pulses and gradient strengths appropriately. The amplitude-modulated control provided a good match for the magnetization transfer effect of labeling pulses, allowing multisection perfusion magnetic resonance imaging of the whole brain. Comparison of multisection continuous and pulsed arterial spin-labeling methods at 3.0 T showed a 33% improvement in signal-to-noise ratio by using the former approach.

Background-This study assesses the utility of a hybrid optical instrument for noninvasive transcranial monitoring in the neurointensive care unit. The instrument is based on diffuse correlation spectroscopy (DCS) for measurement of cerebral blood flow (CBF), and near-infrared spectroscopy (NIRS) for measurement of oxy-and deoxy-hemoglobin concentration. DCS/NIRS measurements of CBF and oxygenation from frontal lobes are compared with concurrent xenon-enhanced computed tomography (XeCT) in patients during induced blood pressure changes and carbon dioxide arterial partial pressure variation.

By employing machine learning techniques, we were able to demonstrate that imaging patterns are highly predictive of patient survival. Additionally, we found that GB subtypes have distinctive imaging phenotypes. These results reveal that when imaging markers related to infiltration, cell density, microvascularity, and blood-brain barrier compromise are integrated via advanced pattern analysis methods, they form very accurate predictive biomarkers. These predictive markers used solely preoperative images, hence they can significantly augment diagnosis and treatment of GB patients.