S Arndt — Page 9 | Search PubMed

PubMedDate not supplied

Automatic atlas-based volume estimation of human brain regions from MR images.

OBJECTIVE: MRI offers many opportunities for noninvasive in vivo measurement of structure-function relationships in the human brain. Although automated methods are now available for whole-brain measurements, an efficient and valid automatic method for volume estimation of subregions such as the frontal or temporal lobes is still needed. MATERIALS AND METHODS: We adapted the Talairach atlas to the study of brain subregions. We supplemented the atlas with additional boxes to include the cerebellum. We assigned all the boxes to 1 of 12 regions of interest (ROIs) (frontal, parietal, temporal, and occipital lobes, cerebellum, and subcortical regions on right and left sides of the brain). Using T1-weighted MR scans collected with an SPGR sequence (slice thickness = 1.5 mm), we manually traced these ROIs and produced volume estimates. We then transformed the scans into Talairach space and compared the volumes produced by the two methods ("traced" versus "automatic"). The traced measurements were considered to be the "gold standard" against which the automatic measurements were compared. RESULTS: The automatic method was found to produce measurements that were nearly identical to the traced method. We compared absolute measurements of volume produced by the two methods, as well as the sensitivity and specificity of the automatic method. We also compared the measurements of cerebral blood flow obtained through [15O]H2O PET studies in a sample of nine subjects. Absolute measurements of volume produced by the two methods were very similar, and the sensitivity and specificity of the automatic method were found to be high for all regions. The flow values were also found to be very similar by both methods. CONCLUSION: The automatic atlas-based method for measuring the volume of brain subregions produces results that are similar to manual techniques. The method is rapid, efficient, unbiased, and not subject to the problems of rater drift or potentially poor interrater reliability that plague manual methods. Consequently, this method may be very useful for the study of structure-function relationships in the human brain.

Anatomy, Artistic↗

PubMedDate not supplied

Improving tissue classification in MRI: a three-dimensional multispectral discriminant analysis method with automated training class selection.

PURPOSE: To improve the reliability, accuracy, and computational efficiency of tissue classification with multispectral sequences [T1, T2, and proton density (PD)], we developed an automated method for identifying training classes to be used in a discriminant function analysis. We compared it with a supervised operator-dependent method, evaluating its reliability and validity. We also developed a fuzzy (continuous) classification to correct for partial voluming. METHOD: Images were obtained on a 1.5 T GE Signa MR scanner using three pulse sequences that were co-registered. Training classes for the discriminant analysis were obtained in two ways. The operator-dependent method involved defining circular ROIs containing 5-15 voxels that represented "pure" samples of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF), using a total of 150-300 voxels for each tissue type. The automated method involved selecting a large number of samples of brain tissue with sufficiently low variance and randomly placed throughout the brain ("plugs"), partitioning these samples into GM, WM, and CSF, and minimizing the amount of variance within each partition of samples to optimize its "purity." The purity of the plug was estimated by calculating the variance of 8 voxels in all modalities (T1, T2, and PD). We also compared "sharp" (discrete) measurements (which classified tissue only as GM, WM, or CSF) and "fuzzy" (continuous) measurements (which corrected for partial voluming by weighting the classification based on the mixture of tissue types in each voxel). RESULTS: Reliability was compared for the operator-dependent and automated methods as well as for the fuzzy versus sharp classification. The automated sharp classifications consistently had the highest interrater and intrarater reliability. Validity was assessed in three ways: reproducibility of measurements when the same individuals were scanned on multiple occasions, sensitivity of the method to detecting changes associated with aging, and agreement between the automated segmentation values and those produced through expert manual segmentation. The sharp automated classification emerged as slightly superior to the other three methods according to each of these validators. Its reproducibility index (intraclass r) was 0.97, 0.98, and 0.98 for total CSF, total GM, and total WM, respectively. Its correlations with age were 0.54, -0.61, and -0.53, respectively. Its percent agreement with the expert manually segmented tissue for the three tissue types was 93, 90, and 94%, respectively. CONCLUSION: Automated identification of training classes for discriminant analysis was clearly superior to a method that required operator intervention. A sharp (discrete) classification into three tissue types was also slightly superior to one that used "fuzzy" classification to produce continuous measurements to correct for partial voluming. This multispectral automated discriminant analysis method produces a computationally efficient, reliable, and valid method for classifying brain tissue into GM, WM, and CSF. It corrects some of the problems with reliability and computational inefficiency previously observed for operator-dependent approaches to segmentation.

Adult↗