Luogang Wei

Multiple sclerosis lesion quantification using fuzzy-connectedness principles

Multiple sclerosis (MS) is a disease of the white matter. Magnetic resonance imaging (MRI) is proven to be a sensitive method of monitoring the progression of this disease and of its changes due to treatment protocols. Quantification of the severity of the disease through estimation of MS lesion volume via MR imaging is vital for understanding and monitoring the disease and its treatment. This paper presents a novel methodology and a system that can be routinely used for segmenting and estimating the volume of MS lesions via dual-echo fast spin-echo MR imagery. A recently developed concept of fuzzy objects forms the basis of this methodology. An operator indicates a few points in the images by pointing to the white matter, the grey matter, and the cerebrospinal fluid (CSF). Each of these objects is then detected as a fuzzy connected set. The holes in the union of these objects correspond to potential lesion sites which are utilized to detect each potential lesion as a three-dimensional (3-D) fuzzy connected object. These objects are presented to the operator who indicates acceptance/rejection through the click of a mouse button. The number and volume of accepted lesions is then computed and output. Based on several evaluation studies, the authors conclude that the methodology is highly reliable and consistent, with a coefficient of variation (due to subjective operator actions) of 0.9% (based on 20 patient studies, three operators, and two trials) for volume and a mean false-negative volume fraction of 1.3%, with a 95% confidence interval of 0%-2.8% (based on ten patient studies).

Correlation of volumetric magnetization transfer imaging with clinical data in MS

We examined the relations between quantitative volumetric estimates of cerebral lesion load based on magnetization transfer imaging (MTI), clinical data, and measures of neuropsychological function in 44 patients with clinically diagnosed MS. In this population we assessed the correlation between several volumetric MTI measures, measures of neurologic function (Kurtzke Expanded Disability Status Scale and Ambulation Index), and disease duration using Spearmans correlation coefficient. Patients were classified on the basis of neuropsychological test performance as severely impaired, moderately impaired, and normal. We assessed differences between these groups with respect to MTI results using the Kruskal-Wallis test. MTI measures corrected for brain volume were found to correlate with disease duration (p < 0.01) and showed suggestive correlations with measures of neurologic impairment (p < 0.05). Individual neuropsychological tests correlated with MTI measures corrected and not corrected for brain volume (p < 0.001). An MTI measure not corrected for brain volume differed (p < 0.05) between severely impaired, moderately impaired, and normal patients. These preliminary results suggest that volumetric MTI analysis provides new measures that reflect more accurately the global lesion load in the brain of MS patients, and they may serve as a method to study the natural course of the disease and as an outcome measure to evaluate the effect of drugs.

Isolated U-fiber involvement in MS : preliminary observations

We studied the frequency and location of isolated U-fiber involvement in MS and correlated these findings exploratively with physical disability and neuropsychological impairment. Fifty-three MS patients were examined. Three-millimeter-thick, fast spin-echo T2-weighted MR images and spin-echo postgadolinium T1-weighted images were obtained. Computer software that which had been validated previously for quantitation of MS lesions was used to detect lesions on the T2-weighted images. The Expanded Disability Status Scale (EDSS), Ambulation Index (AI), and a battery of neurocognitive tests were performed on each patient. Forty-two arcuate hyperintensities along the U-fiber were detected by the software in 28 patients (53%). Twenty-seven lesions (64.3%) were seen in the frontal lobe, eight (19.0%) in the temporal lobe, three (7.1%) in the parietal lobe, three (7.1%) in the occipital lobe, and one (2.4%) in both frontal and parietal lobes. Four lesions (9.5%) showed gadolinium enhancement. Seventeen lesions (40%) were hypointense on the T1-weighted images. Scores of three of the 11 neuropsychological tests reflecting performance in executive control and memory were significantly different at least at the p = 0.05 level between the eight patients with multiple, isolated U-fiber lesions and the 45 patients without any or with only a single U-fiber lesion. No significant difference was noted for EDSS or AI. Isolated U-fiber involvement is an underappreciated MR finding in MS. Our preliminary hypothesis is that U-fiber lesions may contribute to neuropsychological impairment, although our observation requires confirmation.

Detection and quantification of MS lesions using fuzzy topological principles

Quantification of the severity of the multiple sclerosis (MS) disease through estimation of lesion volume via MR imaging is vital for understanding and monitoring the disease and its treatment. This paper presents a novel methodology and a system that can be routinely used for segmenting and estimating the volume of MS lesions via dual-echo spin-echo MR imagery. An operator indicates a few points in the images by pointing to the white matter, the gray matter, and the CSF. Each of these objects is then detected as a fuzzy connected set. The holes in the union of these objects correspond to potential lesion sites which are utilized to detect each potential lesion as a fuzzy connected object. These 3D objects are presented to the operator who indicates acceptance/rejection through the click of a mouse button. The volume of accepted lesions is then computed and output. Based on several evaluation studies and over 300 3D data sets that were processed, we conclude that the methodology is highly reliable and consistent, with a coefficient of variation (due to subjective operator actions) of less than 1.0% for volume.

System for the comprehensive analysis of multiple sclerosis lesion load based on MR imagery

The system is based on the premise that, in the two related tasks required for object definition, namely object recognition and delineation, human operators usually outperform computer algorithms in recognition and it is vice versa for delineation. In our system, some global recognition help is therefore taken from operators, while delineation is done automatically using fuzzy topological algorithms. The lesion quantification methods for the various protocols differ somewhat but follow this general framework. All objects are extracted as 3D fuzzy connected objects. For combining inter- and intra-protocol longitudinal information, fuzzy object registration algorithms are developed and incorporated into the system. A variety of validation studies have been conducted for all protocols to test inter- and intra-operator variations, repeat scan variations, and accuracy in terms of false positive and false negative volume fractions. They all indicate a value of less than 1.5 percent for these factors. THe operator time taken per 3D study varies between 1-20 minutes.