Jyh-Wen Chai

Quantitative analysis in clinical applications of brain MRI using independent component analysis coupled with support vector machine

To effectively perform quantification of brain normal tissues and pathologies simultaneously, independent component analysis (ICA) coupled with support vector machine (SVM) is investigated and evaluated for effective volumetric measurements of normal and lesion tissues using multispectral MR images.

Neuroimaging in seizure patients associated with nonketotic hyperglycemia.

Nonketotic hyperglycemia (NKH) is a clinical syndrome consisting of hyperglycemia, hyperosmolality and intracellular dehydration but not ketoacidosis. This prospective study evaluated the clinical and magnetic resonance imaging abnormalities in six patients with NKH complicated with simple or complex partial seizures. Subcortical T2 hypointensity rather than hyperintensity together with contrast enhancement was a characteristic feature of seizures associated with NKH. Restricted diffusion on DWI and decreased NAA and/or Choline on MRS studies were also noted.

Robust volume assessment of brain tissues for 3-dimensional fourier transformation MRI via a novel multispectral technique.

A new TRIO algorithm method integrating three different algorithms is proposed to perform brain MRI segmentation in the native coordinate space, with no need of transformation to a standard coordinate space or the probability maps for segmentation. The method is a simple voxel-based algorithm, derived from multispectral remote sensing techniques, and only requires minimal operator input to depict GM, WM, and CSF tissue clusters to complete classification of a 3D high-resolution multislice-multispectral MRI data. Results showed very high accuracy and reproducibility in classification of GM, WM, and CSF in multislice-multispectral synthetic MRI data. The similarity indexes, expressing overlap between classification results and the ground truth, were 0.951, 0.962, and 0.956 for GM, WM, and CSF classifications in the image data with 3% noise level and 0% non-uniformity intensity. The method particularly allows for classification of CSF with 0.994, 0.961 and 0.996 of accuracy, sensitivity and specificity in images data with 3% noise level and 0% non-uniformity intensity, which had seldom performed well in previous studies. As for clinical MRI data, the quantitative data of brain tissue volumes aligned closely with the brain morphometrics in three different study groups of young adults, elderly volunteers, and dementia patients. The results also showed very low rates of the intra- and extra-operator variability in measurements of the absolute volumes and volume fractions of cerebral GM, WM, and CSF in three different study groups. The mean coefficients of variation of GM, WM, and CSF volume measurements were in the range of 0.03% to 0.30% of intra-operator measurements and 0.06% to 0.45% of inter-operator measurements. In conclusion, the TRIO algorithm exhibits a remarkable ability in robust classification of multislice-multispectral brain MR images, which would be potentially applicable for clinical brain volumetric analysis and explicitly promising in cross-sectional and longitudinal studies of different subject groups.

Magnetic resonance brain tissue classification and volume calculation

This study develops a volume sphering analysis (VSA) approach to tissue classification and volume calculation of multispectral magnetic resonance (MR) brain images. It processes all multispectral MR image slices as an image cube while using only one set of training samples obtained from a single multispectral image slice to perform tissue classification as well as to calculate tissue volumes. In order to make a one slice set of training samples fit for all MR image slices a novel multispectral signature-specified extrapolation algorithm is particularly designed for this purpose so that the selected set of training samples can be extrapolated to create new data samples that are also applicable to other MR image slices. As a consequence, it significantly reduces the tremendous burden on radiologists for selection of training samples as well as computational cost. To further resolve instability and inconsistency issues which may be caused by training sample extrapolation, the proposed VSA also includes a support vector machine to refine training samples and develops an iterative Fisher’s linear discriminant analysis (IFLDA) to make VSA robust and insensitive to new generated training samples so as to improve the traditional slice-by-slice MR image classification. Experimental results demonstrate that VSA in conjunction with IFLDA not only performs comparably to approaches using training samples from individual image slices, but also saves significant time in selecting training samples and computational cost.

Classification of Magnetic Resonance brain images by using weighted radial basis function kernels

The paper proposed a weighted Radial basis function kernel (WRBF) approach that can be used to detect and classify anomalies in Magnetic Resonance (MR) images. A weighted Radial basis function kernel (WRBF) approach, despite the fact that the idea of WRBF kernels can be traced back to the work [1], its application to Radial basis function (RBF) kernel is new. It includes the Support Vector Machines (SVMs) using RBF as its special case where the RBF is considered to be uniformly weighted. Methods MR data of abnormal brain data were used to evaluate the accuracy of multiple sclerosis lesions classification by using the proposed method. The data were obtained from the BrainWeb Simulated Brain Database at the McConnell Brain Imaging Centre of the Montreal Neurological Institute (MNI), McGill University. Experimental results via various MR images show that WRBF kernels provide better classification.

Noninvasive assessment of intracranial elastance and pressure in spontaneous intracranial hypotension by MRI: MR Intracranial Pressure for SIH

Spontaneous intracranial hypotension (SIH) is often misdiagnosed, and can lead to severe complications. Conventional MR sequences show a limited ability to aid in this diagnosis. MR‐based intracranial pressure (MR‐ICP) may be able to detect changes of intracranial elastance and pressure.

Quantitative Measurement of CSF in Patients with Spontaneous Intracranial Hypotension.

BACKGROUND AND PURPOSE: CSF hypovolemia is a core feature of spontaneous intracranial hypotension. Spontaneous intracranial hypotension is characterized by orthostatic headache and radiologic manifestations, including CSF along the neural sleeves, diffuse pachymeningeal enhancement, and/or venous engorgement. However, these characteristics are only qualitative. Quantifying intraspinal CSF volumes could improve spontaneous intracranial hypotension diagnosis and evaluation of hypovolemic statuses in patients with spontaneous intracranial hypotension. The purpose of this study was to compare intraspinal CSF volumes across spontaneous intracranial hypotension stages and to test the clinical applicability of these measures. MATERIALS AND METHODS: A cohort of 23 patients with spontaneous intracranial hypotension and 32 healthy controls was subjected to brain MR imaging and MR myelography with 1.5T imaging. An automatic threshold-based segmentation method was used to calculate intraspinal CSF volumes at initial hospitalization (spontaneous intracranial hypotension-initial), partial improvement (spontaneous intracranial hypotension-intermediate), and complete recovery (spontaneous intracranial hypotension-recovery) stages. RESULTS: The mean intraspinal CSF volumes observed were the following: 95.31 mL for healthy controls, 72.31 mL for spontaneous intracranial hypotension-initial, 81.15 mL for spontaneous intracranial hypotension-intermediate, and 93.74 mL for spontaneous intracranial hypotension-recovery. Increased intraspinal CSF volumes were related to disease recovery (P < .001). The intraspinal CSF volumes of patients before complete recovery were significantly lower than those of healthy controls. With the estimated intradural CSF volumes as a reference, the intraspinal CSF volume percentage was lower in patients with spontaneous intracranial hypotension with venous engorgement than in those without it (P = .058). CONCLUSIONS: With a threshold-based segmentation method, we found that spinal CSF hypovolemia is fundamentally related to spontaneous intracranial hypotension. Intraspinal CSF volumes could be a sensitive parameter for the evaluation of treatment response and follow-up monitoring in patients with spontaneous intracranial hypotension.

Parameter optimization for filtering and segmentation of left ventricular long-axis SPAMM tagged magnetic resonance images

During cardiac muscle contractions, basal descent along the long axis causes the short axis in the MR image to shift, leading to errors in measurement of myocardial function. This study used magnetization vector spatial modulation of magnetization (SPAMM) to tag myocardial motions. After SPAMM image acquisition, a SPAMM image processing algorithm was used to obtain myocardial grid lines. Experience shows that specific internal parameters of the algorithm significantly affect the quality of the grid line output. In this research, grid search enhanced the quality of the grid line output by finding near–optimal combinations within the parameter set. Both geometric and physiological performance metrics were employed. The Hausdorff distance (the geometric metric) improved significantly when the parameters were optimized. Furthermore, the 2-D and 3-D wall thickness discrepancy (the physiological metrics) decreased significantly with the use of optimized parameters.

Characterization of focal brain lesions by gradient-echo arterial spin-tagging perfusion imaging.

A simple gradient-echo arterial spin tagging (GREAST) technique allows for quick assessment of regional tissue perfusion without the need for exogenous contrast agent. The purpose of this prospective study was to validate GREAST imaging in characterizing the regional perfusion status of focal brain lesions by comparing with relative cerebral blood volume (rCBV) maps obtained by using echo-planar imaging (EPI)–based dynamic susceptibility contrast MR imaging. Thirty-two patients whose nonenhanced brain MR images showed 34 focal brain lesions during routine examination were selected to immediately undergo GREAST and dynamic susceptibility contrast MR imaging to evaluate regional perfusion of the lesions. The Pearson correlation coefficient was used to test the relative quantification of local perfusion with the two imaging methods. Qualitative perfusion measurements agreed in 23 (79%) of 29 lesions for which GREAST and dynamic susceptibility contrast MR imaging were successful. On rCBV maps, six focal lesions with local hemorrhage were underestimated. In three patients with metal surgical implants, lesions could not be measured because of susceptibility artifacts and distortion on EPIs. After these lesions were excluded, the Pearson correlation coefficient between relative quantitative perfusion measurements on GREAST images versus rCBV maps was about 0.90 (p value = 0.000). The success rate of GREAST imaging was 94% (30 of 32 patients), higher than that of dynamic susceptibility contrast MR imaging (72%, or 23 of 32 patients). GREAST imaging was comparable to rCBV mapping for the relative quantification of regional perfusion of focal brain lesions. This technique may be useful in routine MR examination for characterizing the regional perfusion of brain focal lesions.