Normal brain volume measurements using multispectral MRI segmentation

Comparison of Multispectral Image-Processing Methods for Brain Tissue Classification in BrainWeb Synthetic Data and Real MR Images

Accurate quantification of brain tissue is a fundamental and challenging task in neuroimaging. Over the past two decades, statistical parametric mapping (SPM) and FMRIB's Automated Segmentation Tool (FAST) have been widely used to estimate gray matter (GM) and white matter (WM) volumes. However, they cannot reliably estimate cerebrospinal fluid (CSF) volumes. To address this problem, we developed the TRIO algorithm (TRIOA), a new magnetic resonance (MR) multispectral classification method. SPM8, SPM12, FAST, and the TRIOA were evaluated using the BrainWeb database and real magnetic resonance imaging (MRI) data. In this paper, the MR brain images of 140 healthy volunteers (51.5 ± 15.8 y/o) were obtained using a whole-body 1.5 T MRI system (Aera, Siemens, Erlangen, Germany). Before classification, several preprocessing steps were performed, including skull stripping and motion and inhomogeneity correction. After extensive experimentation, the TRIOA was shown to be more effective than SPM and FAST. For real data, all test methods revealed that the participants aged 20–83 years exhibited an age-associated decline in GM and WM volume fractions. However, for CSF volume estimation, SPM8-s and SPM12-m both produced different results, which were also different compared with those obtained by FAST and the TRIOA. Furthermore, the TRIOA performed consistently better than both SPM and FAST for GM, WM, and CSF volume estimation. Compared with SPM and FAST, the proposed TRIOA showed more advantages by providing more accurate MR brain tissue classification and volume measurements, specifically in CSF volume estimation.

Human Brain/Cloud Interface

The Internet comprises a decentralized global system that serves humanity's collective effort to generate, process, and store data, most of which is handled by the rapidly expanding cloud. A stable, secure, real-time system may allow for interfacing the cloud with the human brain. One promising strategy for enabling such a system, denoted here as a "human brain/cloud interface" ("B/CI"), would be based on technologies referred to here as "neuralnanorobotics." Future neuralnanorobotics technologies are anticipated to facilitate accurate diagnoses and eventual cures for the ∼400 conditions that affect the human brain. Neuralnanorobotics may also enable a B/CI with controlled connectivity between neural activity and external data storage and processing, via the direct monitoring of the brain's ∼86 × 109 neurons and ∼2 × 1014 synapses. Subsequent to navigating the human vasculature, three species of neuralnanorobots (endoneurobots, gliabots, and synaptobots) could traverse the blood-brain barrier (BBB), enter the brain parenchyma, ingress into individual human brain cells, and autoposition themselves at the axon initial segments of neurons (endoneurobots), within glial cells (gliabots), and in intimate proximity to synapses (synaptobots). They would then wirelessly transmit up to ∼6 × 1016 bits per second of synaptically processed and encoded human-brain electrical information via auxiliary nanorobotic fiber optics (30 cm3) with the capacity to handle up to 1018 bits/sec and provide rapid data transfer to a cloud based supercomputer for real-time brain-state monitoring and data extraction. A neuralnanorobotically enabled human B/CI might serve as a personalized conduit, allowing persons to obtain direct, instantaneous access to virtually any facet of cumulative human knowledge. Other anticipated applications include myriad opportunities to improve education, intelligence, entertainment, traveling, and other interactive experiences. A specialized application might be the capacity to engage in fully immersive experiential/sensory experiences, including what is referred to here as "transparent shadowing" (TS). Through TS, individuals might experience episodic segments of the lives of other willing participants (locally or remote) to, hopefully, encourage and inspire improved understanding and tolerance among all members of the human family.

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.

Stable Atlas-based Mapped Prior (STAMP) machine-learning segmentation for multicenter large-scale MRI data

Machine learning (ML)-based segmentation methods are a common technique in the medical image processing field. In spite of numerous research groups that have investigated ML-based segmentation frameworks, there remains unanswered aspects of performance variability for the choice of two key components: ML algorithm and intensity normalization. This investigation reveals that the choice of those elements plays a major part in determining segmentation accuracy and generalizability. The approach we have used in this study aims to evaluate relative benefits of the two elements within a subcortical MRI segmentation framework. Experiments were conducted to contrast eight machine-learning algorithm configurations and 11 normalization strategies for our brain MR segmentation framework. For the intensity normalization, a Stable Atlas-based Mapped Prior (STAMP) was utilized to take better account of contrast along boundaries of structures. Comparing eight machine learning algorithms on down-sampled segmentation MR data, it was obvious that a significant improvement was obtained using ensemble-based ML algorithms (i.e., random forest) or ANN algorithms. Further investigation between these two algorithms also revealed that the random forest results provided exceptionally good agreement with manual delineations by experts. Additional experiments showed that the effect of STAMP-based intensity normalization also improved the robustness of segmentation for multicenter data sets. The constructed framework obtained good multicenter reliability and was successfully applied on a large multicenter MR data set (n>3000). Less than 10% of automated segmentations were recommended for minimal expert intervention. These results demonstrate the feasibility of using the ML-based segmentation tools for processing large amount of multicenter MR images. We demonstrated dramatically different result profiles in segmentation accuracy according to the choice of ML algorithm and intensity normalization chosen.

Unsupervised MRI segmentation of brain tissues using a local linear model and level set

Real-world magnetic resonance imaging of the brain is affected by intensity nonuniformity (INU) phenomena which makes it difficult to fully automate the segmentation process. This difficult task is accomplished in this work by using a new method with two original features: (1) each brain tissue class is locally modeled using a local linear region representative, which allows us to account for the INU in an implicit way and to more accurately position the region's boundaries; and (2) the region models are embedded in the level set framework, so that the spatial coherence of the segmentation can be controlled in a natural way. Our new method has been tested on the ground-truthed Internet Brain Segmentation Repository (IBSR) database and gave promising results, with Tanimoto indexes ranging from 0.61 to 0.79 for the classification of the white matter and from 0.72 to 0.84 for the gray matter. To our knowledge, this is the first time a region-based level set model has been used to perform the segmentation of real-world MRI brain scans with convincing results.

Intensity Standardization Simplifies Brain MR Image Segmentation

Typically, brain MR images present significant intensity variation across patients and scanners. Consequently, training a classifier on a set of images and using it subsequently for brain segmentation may yield poor results. Adaptive iterative methods usually need to be employed to account for the variations of the particular scan. These methods are complicated, difficult to implement and often involve significant computational costs. In this paper, a simple, non-iterative method is proposed for brain MR image segmentation. Two preprocessing techniques, namely intensity inhomogeneity correction, and more importantly MR image intensity standardization, used prior to segmentation, play a vital role in making the MR image intensities have a tissue-specific numeric meaning, which leads us to a very simple brain tissue segmentation strategy.Vectorial scale-based fuzzy connectedness and certain morphological operations are utilized first to generate the brain intracranial mask. The fuzzy membership value of each voxel within the intracranial mask for each brain tissue is then estimated. Finally, a maximum likelihood criterion with spatial constraints taken into account is utilized in classifying all voxels in the intracranial mask into different brain tissue groups. A set of inhomogeneity corrected and intensity standardized images is utilized as a training data set. We introduce two methods to estimate fuzzy membership values. In the first method, called SMG (for simple membership based on a gaussian model), the fuzzy membership value is estimated by fitting a multivariate Gaussian model to the intensity distribution of each brain tissue whose mean intensity vector and covariance matrix are estimated and fixed from the training data sets. The second method, called SMH (for simple membership based on a histogram), estimates fuzzy membership value directly via the intensity distribution of each brain tissue obtained from the training data sets. We present several studies to evaluate the performance of these two methods based on 10 clinical MR images of normal subjects and 10 clinical MR images of Multiple Sclerosis (MS) patients. A quantitative comparison indicates that both methods have overall better accuracy than the k-nearest neighbors (kNN) method, and have much better efficiency than the Finite Mixture (FM) model based Expectation-Maximization (EM) method. Accuracy is similar for our methods and EM method for the normal subject data sets, but much better for our methods for the patient data sets.

Probabilistic segmentation of brain tissue in MR imaging

A new method has been developed for probabilistic segmentation of five different types of brain structures: white matter, gray matter, cerebro-spinal fluid without ventricles, ventricles and white matter lesion in cranial MR imaging. The algorithm is based on information from T1-weighted (T1-w), inversion recovery (IR), proton density-weighted (PD), T2-weighted (T2-w) and fluid attenuation inversion recovery (FLAIR) scans. It uses the K-Nearest Neighbor classification technique that builds a feature space from spatial information and voxel intensities. The technique generates for each tissue type an image representing the probability per voxel being part of it. By application of thresholds on these probability maps, binary segmentations can be obtained. A similarity index (SI) and a probabilistic SI (PSI) were calculated for quantitative evaluation of the results. The influence of each image type on the performance was investigated by alternately leaving out one of the five scan types. This procedure showed that the incorporation of the T1-w, PD or T2-w did not significantly improve the segmentation results. Further investigation indicated that the combination of IR and FLAIR was optimal for segmentation of the five brain tissue types. Evaluation with respect to the gold standard showed that the SI-values for all tissues exceeded 0.8 and all PSI-values exceeded 0.7, implying an excellent agreement.

Prediction of protein solvent accessibility using fuzzy k-nearest neighbor method

MOTIVATION

The solvent accessibility of amino acid residues plays an important role in tertiary structure prediction, especially in the absence of significant sequence similarity of a query protein to those with known structures. The prediction of solvent accessibility is less accurate than secondary structure prediction in spite of improvements in recent researches. The k-nearest neighbor method, a simple but powerful classification algorithm, has never been applied to the prediction of solvent accessibility, although it has been used frequently for the classification of biological and medical data.

RESULTS

We applied the fuzzy k-nearest neighbor method to the solvent accessibility prediction, using PSI-BLAST profiles as feature vectors, and achieved high prediction accuracies. With leave-one-out cross-validation on the ASTRAL SCOP reference dataset constructed by sequence clustering, our method achieved 64.1% accuracy for a 3-state (buried/intermediate/exposed) prediction (thresholds of 9% for buried/intermediate and 36% for intermediate/exposed) and 86.7, 82.0, 79.0 and 78.5% accuracies for 2-state (buried/exposed) predictions (thresholds of each 0, 5, 16 and 25% for buried/exposed), respectively. Our method also showed slightly better accuracies than other methods by about 2-5% on the RS126 dataset and a benchmarking dataset with 229 proteins.

AVAILABILITY

Program and datasets are available at http://biocom1.ssu.ac.kr/FKNNacc/

CONTACT

jul@ssu.ac.kr.

Multispectral magnetic resonance image analysis using principal component and linear discriminant analysis

PURPOSE

To explore the possibilities of combining multispectral magnetic resonance (MR) images of different patients within one data matrix.

MATERIALS AND METHODS

Principal component and linear discriminant analysis was applied to multispectral MR images of 12 patients with different brain tumors. Each multispectral image consisted of T1-weighted, T2-weighted, proton-density-weighted, and gadolinium-enhanced T1-weighted MR images, and a calculated relative regional cerebral blood volume map.

RESULTS

Similar multispectral image regions were clustered, while dissimilar multispectral image regions were scattered in a single plot. Both principal component and linear discriminant analysis allowed discrimination between healthy and tumor regions on the image. In addition, linear discriminant analysis allowed discrimination between oligodendrogliomas and astrocytomas. However, the discriminant analysis method was partially capable of recognizing the tumor identity in unknown multispectral images.

CONCLUSION

The proposed method may help the radiologist in comparing multispectral MR images of different patients in a more easy and objective way.

Automated segmentation of multispectral brain MR images

This work presents a robust and comprehensive approach for the in vivo automated segmentation and quantitative tissue volume measurement of normal brain composition from multispectral magnetic resonance imaging (MRI) data. Statistical pattern recognition methods based on a finite mixture model are used to partition the intracranial volume into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) spaces. A masking algorithm initially extracts the brain volume from surrounding extrameningeal tissue. Radio frequency (RF) field inhomogeneity effects in the images are then removed using a recursive method that adapts to the intrinsic local tissue contrast. Our technique supports heterogeneous data with multispectral MR images of different contrast and intensity weighting acquired at varying spatial resolution and orientation. The proposed image segmentation methods have been tested using multispectral T1-, proton density-, and T2-weighted MRI data from young and aged non-human primates as well as from human subjects.

Improving image contrast using principal component analysis for subsequent image segmentation

This article presents a technique for improving MR image contrast by linearly combining multiple MR images with different tissue contrast. The weighting coefficients of the linear combination are derived using principal component analysis. The contrast-enhanced composite image is segmented subsequently using gray level-based 1D segmentation methods. The technique reduces a multispectral image set to composite eigenimages and allows application of appropriate 1D segmentation methods that do not have equivalent counterparts in multispectral methods.

Brain volume, intracranial volume, and dementia

RATIONALE AND OBJECTIVES

Using a large magnetic resonance (MR) imaging data set (n = 532), we investigated the utility of total intracranial volume (TICV) as a correction factor for head size variability when assessing total brain volume (TBV) and the subcortical volumes of the temporal horn of the lateral ventricular system and the hippocampus.

METHODS

A uniform tissue segmentation procedure (analyze) was used to calculate volumes. Total brain volume was compared with TICV in 357 control subjects and 175 patients with various dementing and neuropsychiatric disorders (mixed dementia/neuropsychiatric group). These MR-based TBV/TICV relationships were compared with actual postmortem (n = 87) values obtained from a study of neurologically healthy subjects at the time of death. Comparisons were also made in which temporal horn and hippocampal volumes were corrected by TICV and TBV. Lastly, the ability of corrected TBV and temporal horn and hippocampal volumes to distinguish subjects in the mixed dementia/neuropsychiatric group from controls was examined by logistic regression.

RESULTS

In the control sample, brain volume averaged 9% of TICV, regardless of age. In contrast, TBV in the mixed dementia/neuropsychiatric subjects showed, on average, a 22% reduction compared with TICV. By plotting TBV/TICV curves, highly significant but different regression lines emerged, wherein a reduction in brain volume in conditions of mixed dementia/neuropsychiatric disorder showed a distinct separation from the norm. The TBV/TICV regression line generated from MR imaging in controls did not differ from the postmortem TBV/TICV regression line. Logistic regression showed a 96% correct classification of mixed dementia/neuropsychiatric subjects from controls by using the TBV/TICV ratio. This technique has the advantage that each subject serves as his or her own control.

CONCLUSIONS

In cases of dementia and neuropsychiatric disorder in persons 65 and older, TBV corrected by TICV readily differentiated this clinical population from controls. This technique is easy and simple to use and has various clinical applications. For temporal horn and hippocampal volume, corrections with TBV rather than TICV may provide more clinically meaningful corrections.

A modified fuzzy clustering algorithm for operator independent brain tissue classification of dual echo MR images

Methods for brain tissue classification or segmentation of structural magnetic resonance imaging (MRI) data should ideally be independent of human operators for reasons of reliability and tractability. An algorithm is described for fully automated segmentation of dual echo, fast spin-echo MRI data. The method is used to assign fuzzy-membership values for each of four tissue classes (gray matter, white matter, cerebrospinal fluid and dura) to each voxel based on partition of a two dimensional feature space. Fuzzy clustering is modified for this application in two ways. First, a two component normal mixture model is initially fitted to the thresholded feature space to identify exemplary gray and white matter voxels. These exemplary data protect subsequently estimated cluster means against the tendency of unmodified fuzzy clustering to equalize the number of voxels in each class. Second, fuzzy clustering is implemented in a moving window scheme that accommodates reduced image contrast at the axial extremes of the transmitting/receiving coil. MRI data acquired from 5 normal volunteers were used to identify stable values for three arbitrary parameters of the algorithm: feature space threshold, relative weight of exemplary gray and white matter voxels, and moving window size. The modified algorithm incorporating these parameter values was then used to classify data from simulated images of the brain, validating the use of fuzzy-membership values as estimates of partial volume. Gray:white matter ratios were estimated from 20 twenty normal volunteers (mean age 32.8 years). Processing time for each three-dimensional image was approximately 30 min on a 170 MHz workstation. Mean cerebral gray and white matter volumes estimated from these automatically segmented images were very similar to comparable results previously obtained by operator dependent methods, but without their inherent unreliability.

Measurement of brain structures with artificial neural networks: two- and three-dimensional applications

PURPOSE

To evaluate the ability of an artificial neural network (ANN) to identify brain structures. This ANN was applied to postprocessed magnetic resonance (MR) images to segment various brain structures in both two- and three-dimensional applications.

MATERIALS AND METHODS

An ANN was designed that learned from experience to define the corpus callosum, whole brain, caudate, and putamen. Manual segmentation was used as a training set for the ANN. The ANN was trained on two-thirds of the manually segmented images and was tested on the remaining one-third. The reliability of the ANN was compared against manual segmentations by two technicians.

RESULTS

The ANN was able to identify the brain structures as readily and as well as did the two technicians. Reliability of the ANN compared with the technicians was 0.96 for the corpus callosum, 0.95 for the whole brain, 0.86 (right) and 0.93 (left) for the caudate, and 0.71 (right) and 0.88 (left) for the putamen.

CONCLUSION

The ANN was able to identify the structures used in this study as well as did the two technicians. The ANN could do this much more rapidly and without rater drift. Several other cortical and subcortical structures could also be readily identified with this method.

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.

Review and evaluation of MRI nonuniformity corrections for brain tumor response measurements

Current MRI nonuniformity correction techniques are reviewed and investigated. Many approaches are used to remedy this artifact, but it is not clear which method is the most appropriate in a given situation, as the applications have been with different MRI coils and different clinical applications. In this work four widely used nonuniformity correction techniques are investigated in order to assess the effect on tumor response measurements (change in tumor volume over time): a phantom correction method, an image smoothing technique, homomorphic filtering, and surface fitting approach. Six brain tumor cases with baseline and follow-up MRIs after treatment with varying degrees of difficulty of segmentation were analyzed without and with each of the nonuniformity corrections. Different methods give significantly different correction images, indicating that rf nonuniformity correction is not yet well understood. No improvement in tumor segmentation or in tumor growth/shrinkage assessment was achieved using any of the evaluated corrections.

Automatic tumor segmentation using knowledge-based techniques

A system that automatically segments and labels glioblastoma-multiforme tumors in magnetic resonance images (MRI's) of the human brain is presented. The MRI's consist of T1-weighted, proton density, and T2-weighted feature images and are processed by a system which integrates knowledge-based (KB) techniques with multispectral analysis. Initial segmentation is performed by an unsupervised clustering algorithm. The segmented image, along with cluster centers for each class are provided to a rule-based expert system which extracts the intracranial region. Multispectral histogram analysis separates suspected tumor from the rest of the intracranial region, with region analysis used in performing the final tumor labeling. This system has been trained on three volume data sets and tested on thirteen unseen volume data sets acquired from a single MRI system. The KB tumor segmentation was compared with supervised, radiologist-labeled "ground truth" tumor volumes and supervised k-nearest neighbors tumor segmentations. The results of this system generally correspond well to ground truth, both on a per slice basis and more importantly in tracking total tumor volume during treatment over time.

MRI measurement of brain tumor response: comparison of visual metric and automatic segmentation

An automatic magnetic resonance imaging (MRI) multispectral segmentation method and a visual metric are compared for their effectiveness to measure tumor response to therapy. Automatic response measurements are important for multicenter clinical trials. A visual metric such as the product of the largest diameter and the largest perpendicular diameter of the tumor is a standard approach, and is currently used in the Radiation Treatment Oncology Group (RTOG) and the Eastern Cooperative Oncology Group (EGOG) clinical trials. In the standard approach, the tumor response is based on the percentage change in the visual metric and is categorized into cure, partial response, stable disease, or progression. Both visual and automatic methods are applied to six brain tumor cases (gliomas) of varying levels of segmentation difficulty. The analyzed data were serial multispectral MR images, collected using MR contrast enhancement. A fully automatic knowledge guided method (KG) was applied to the MRI multispectral data, while the visual metric was taken from the MRI films using the T1 gadolinium enhanced image, with repeat measurements done by two radiologists and two residents. Tumor measurements from both visual and automatic methods are compared to "ground truth," (GT) i.e., manually segmented tumor. The KG method was found to slightly overestimate tumor volume, but in a consistent manner, and the estimated tumor response compared very well to hand-drawn ground truth with a correlation coefficient of 0.96. In contrast, the visually estimated metric had a large variation between observers, particularly for difficult cases, where the tumor margins are not well delineated. The inter-observer variation for the measurement of the visual metric was only 16%, i.e., observers generally agreed on the lengths of the diameters. However, in 30% of the studied cases no consensus was found for the categorical tumor response measurement, indicating that the categories are very sensitive to variations in the diameter measurements. Moreover, the method failed to correctly identify the response in half of the cases. The data demonstrate that automatic 3D methods are clearly necessary for objective and clinically meaningful assessment of tumor volume in single or multicenter clinical trials.

A reproducible method for automated extraction of brain volumes from 3D human head MR images

An automated method for extracting brain volumes from three commonly acquired three-dimensional (3D) MR images (proton density, T1 weighted, and T2-weighted) of the human head is described. The procedure is divided into four levels: preprocessing, segmentation, scalp removal, and postprocessing. A user-provided reference point is the sole operator-dependent input required. The method's parameters were first optimized and then fixed and applied to 30 repeat data sets from 15 normal older adult subjects to investigate its reproducibility. Percent differences between total brain volumes (TBVs) for the subjects' repeated data sets ranged from .5% to 2.2%. We conclude that the method is both robust and reproducible and has the potential for wide application.

Monitoring brain tumor response to therapy using MRI segmentation

The performance evaluation of a semi-supervised fuzzy c-means (SFCM) clustering method for monitoring brain tumor volume changes during the course of routine clinical radiation-therapeutic and chemo-therapeutic regimens is presented. The tumor volume determined using the SFCM method was compared with the volume estimates obtained using three other methods: (a) a k nearest neighbor (kNN) classifier, b) a grey level thresholding and seed growing (ISG-SG) method and c) a manual pixel labeling (GT) method for ground truth estimation. The SFCM and kNN methods are applied to the multispectral, contrast enhanced T1, proton density, and T2 weighted, magnetic resonance images (MRI) whereas the ISG-SG and GT methods are applied only to the contrast enhanced T1 weighted image. Estimations of tumor volume were made on eight patient cases with follow-up MRI scans performed over a 32 week interval during treatment. The tumor cases studied include one meningioma, two brain metastases and five gliomas. Comparisons with manually labeled ground truth estimations showed that there is a limited agreement between the segmentation methods for absolute tumor volume measurements when using images of patients after treatment. The average intraobserver reproducibility for the SFCM, kNN and ISG-SG methods was found to be 5.8%, 6.6% and 8.9%, respectively. The average of the interobserver reproducibility of these methods was found to be 5.5%, 6.5% and 11.4%, respectively. For the measurement of relative change of tumor volume as required for the response assessment, the multi-spectral methods kNN and SFCM are therefore preferred over the seedgrowing method.