Classify Brain Tissue Research Articles

Brain tissues have single-voxel signatures in multi-spectral MRI

Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues – and other tissues – based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.

WITHDRAWN: Multi-Class classification of brain tumor images using data augmentation with deep neural network

Abstract Brain is central to the nervous system (CNS) of the human body, it is a group of white masses of cells. These cells grow abnormally by multiplying rapidly with each other is called a brain tumor, which can lead to the death of an individual if not detected. The most common types of tumors which are occurred in the brain are meningioma, glioma, and pituitary tumors. Manually diagnosing and classifying brain tumors is a big challenge for physicians and clinical professionals, accuracy depends solely on their experience. Therefore, computer-assisted technology must be used to overcome these limitations. With the daily improvement of modern medical standards, artificial intelligence plays an important role in identifying and classifying brain tissues and this is of great interest to researchers. It is currently being developed with various machine learning and DL structures. In the past, several ML algorithms such as SVM, KNN, and CNN have been implemented for tumor identification and tumor binary and multi classification using MR images. But these algorithms are not giving the best results. Therefore, we have proposed a DNN based VGG-16 network to improve the accuracy of multi-classification of brain tumor MR images. Finally, our proposed model gives the best results with 98% accuracy after 20 epochs of model training.

Intraoperative Detection of Pediatric Brain Tumor Margins Using Raman Spectroscopy.

Abstract INTRODUCTION Surgical resection is a mainstay of treatment in patients with brain tumors both for tissue diagnosis and for tumor debulking. While maximal resection of tumors is desired, neurosurgeons can be limited by the challenge of differentiating normal brain from tumor using only microscopic visualization and tactile feedback. Additionally, intraoperative decision-making regarding how aggressively to pursue a gross total resection frequently relies on pathologic preliminary diagnosis using frozen sections which are both time consuming and fallible. Here, we investigate the potential for Raman spectroscopy (RS) to rapidly detect pediatric brain tumor margins and classify brain tissue samples equivalent to histopathology. METHODS Using a first-of-its-kind rapid acquisition RS device we intraoperatively imaged fresh ex vivo pediatric brain tissue samples (2-3 mm × 2-3 mm × 2-3 mm) at the Lucille Packard Children's Hospital. All imaged samples received standard final histopathological analysis, as RS is a nondestructive imaging technique. We curated a labeled dataset of 575 + unique Raman spectra gathered from 160 + brain samples resulting from 23 pediatric patients who underwent brain tissue resection as part of tumor debulking or epilepsy surgery (normal controls). RESULTS To our knowledge we have created the largest labeled Raman spectra dataset of pediatric brain tumors. We are developing an end-to-end machine learning model that can predict final histopathology diagnosis within minutes from Raman spectral data. Our preliminary principle component analyses suggest that RS can be used to classify various brain tumors similar to “frozen” histopathology and can differentiate normal from malignant brain tissue in the context of low-grade glioma resections. CONCLUSION Our work suggests that machine learning approaches can be used to harness the material identification properties of RS for classifying brain tumors and detecting their margins.

Fast and accurate pseudo multispectral technique for whole-brain MRI tissue classification

Numerous strategies have been proposed to classify brain tissues into gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF). However, many of them fail when classifying specific regions with low contrast between tissues. In this work, we propose an alternative pseudo multispectral classification (PMC) technique using CIE LAB spaces instead of gray scale T1-weighted MPRAGE images, combined with a new preprocessing technique for contrast enhancement and an optimized iterative K-means clustering. To improve the accuracy of the classification process, gray scale images were converted to multispectral CIE LAB data by applying several transformation matrices. Thus, the amount of information associated with each image voxel was increased. The image contrast was then enhanced by applying a real time function that separates brain tissue distributions and improve image contrast in certain brain regions. The data were then classified using an optimized iterative and convergent K-means classifier. The performance of the proposed approach was assessed using simulation and in vivo human studies through comparison with three common software packages used for brain MR image segmentation, namely FSL, SPM8 and K-means clustering. In the presence of high SNR, the results showed that the four algorithms achieve a good classification. Conversely, in the presence of low SNR, PMC was shown to outperform the other methods by accurately recovering all tissue volumes. The quantitative assessment of brain tissue classification for simulated studies showed that the PMC algorithm resulted in a mean Jaccard index (JI) of 0.74 compared to 0.75 for FSL, 0.7 for SPM and 0.8 for K-means. The in vivo human studies showed that the PMC algorithm resulted in a mean JI of 0.92, which reflects a good spatial overlap between segmented and actual volumes, compared to 0.84 for FSL, 0.78 for SPM and 0.66 for K-means. The proposed algorithm presents a high potential for improving the accuracy of automatic brain tissues classification and was found to be accurate even in the presence of high noise level.

An Accurate Automated Local Similarity Factor-Based Neural Tree Approach toward Tissue Segmentation of Newborn Brain MRI.

Segmentation of brain MR images of neonates is a primary step for assessment of brain evolvement. Advanced segmentation techniques used for adult brain MRI are not companionable for neonates, due to extensive dissimilarities in tissue properties and head structure. Existing segmentation methods for neonates utilizes brain atlases or requires manual elucidation, which results into improper and atlas dependent segmentation. The primary objective of this work is to develop fully automatic, atlas free, and robust system to segment and classify brain tissues of newborn infants from magnetic resonance images. In this study, we propose a fully automatic, atlas-free pipeline based Neural Tree approach for segmentation of newborn brain MRI which utilizes resourceful local resemblance factor such as concerning, connectivity, structure, and relative tissue location. Physical collaboration and uses of an atlas are not required in proposed method and at the same time skirting atlas-associated bias which results in improved segmentation. Proposed technique segments and classify brain tissues both at global and tissue level. We examined our results through visual assessment by neonatologists and quantitative comparisons that show first-rate concurrence with proficient manual segmentations. The implementation results of the proposed technique provided a good overall accuracy of 91.82% for the segmentation of brain tissues as compared with other methods. The pipelined-based neural tree approach along with local similarity factor segments and classify brain tissues. The proposed automated system have higher dice similarity coefficient as well as computational speed.

Hemodynamic Segmentation of Brain Perfusion Images with Delay and Dispersion Effects Using an Expectation-Maximization Algorithm

Automatic identification of various perfusion compartments from dynamic susceptibility contrast magnetic resonance brain images can assist in clinical diagnosis and treatment of cerebrovascular diseases. The principle of segmentation methods was based on the clustering of bolus transit-time profiles to discern areas of different tissues. However, the cerebrovascular diseases may result in a delayed and dispersed local perfusion and therefore alter the hemodynamic signal profiles. Assessing the accuracy of the segmentation technique under delayed/dispersed circumstance is critical to accurately evaluate the severity of the vascular disease. In this study, we improved the segmentation method of expectation-maximization algorithm by using the results of hierarchical clustering on whitened perfusion data as initial parameters for a mixture of multivariate Gaussians model. In addition, Monte Carlo simulations were conducted to evaluate the performance of proposed method under different levels of delay, dispersion, and noise of signal profiles in tissue segmentation. The proposed method was used to classify brain tissue types using perfusion data from five normal participants, a patient with unilateral stenosis of the internal carotid artery, and a patient with moyamoya disease. Our results showed that the normal, delayed or dispersed hemodynamics can be well differentiated for patients, and therefore the local arterial input function for impaired tissues can be recognized to minimize the error when estimating the cerebral blood flow. Furthermore, the tissue in the risk of infarct and the tissue with or without the complementary blood supply from the communicating arteries can be identified.

MR∕PET quantification tools: registration, segmentation, classification, and MR-based attenuation correction.

Combined MR∕PET is a relatively new, hybrid imaging modality. A human MR∕PET prototype system consisting of a Siemens 3T Trio MR and brain PET insert was installed and tested at our institution. Its present design does not offer measured attenuation correction (AC) using traditional transmission imaging. This study is the development of quantification tools including MR-based AC for quantification in combined MR∕PET for brain imaging. The developed quantification tools include image registration, segmentation, classification, and MR-based AC. These components were integrated into a single scheme for processing MR∕PET data. The segmentation method is multiscale and based on the Radon transform of brain MR images. It was developed to segment the skull on T1-weighted MR images. A modified fuzzy C-means classification scheme was developed to classify brain tissue into gray matter, white matter, and cerebrospinal fluid. Classified tissue is assigned an attenuation coefficient so that AC factors can be generated. PET emission data are then reconstructed using a three-dimensional ordered sets expectation maximization method with the MR-based AC map. Ten subjects had separate MR and PET scans. The PET with [(11)C]PIB was acquired using a high-resolution research tomography (HRRT) PET. MR-based AC was compared with transmission (TX)-based AC on the HRRT. Seventeen volumes of interest were drawn manually on each subject image to compare the PET activities between the MR-based and TX-based AC methods. For skull segmentation, the overlap ratio between our segmented results and the ground truth is 85.2 ± 2.6%. Attenuation correction results from the ten subjects show that the difference between the MR and TX-based methods was <6.5%. MR-based AC compared favorably with conventional transmission-based AC. Quantitative tools including registration, segmentation, classification, and MR-based AC have been developed for use in combined MR∕PET.

Maximum Evidence Method for classification of brain tissues in MRI

Within the family of statistical image segmentation methods, those based on Bayesian inference have been commonly applied to classify brain tissues as obtained with Magnetic Resonance Imaging (MRI). In this framework we present an unsupervised algorithm to account for the main tissue classes that constitute MR brain volumes. Two models are examined: the Discrete Model (DM), in which every voxel belongs to a single tissue class, and the Partial Volume Model (PVM), where two classes may be present in a single voxel with a certain probability. We make use of the Maximum Evidence (ME) criterion to estimate the most probable parameters describing each model in a separate fashion. Since an exact image inference would be computationally very expensive, we propose an approximate algorithm for model optimization. Such method was tested on a simulated MRI-T1 brain phantom in 3D, as well as on clinical MR images. As a result, we found that the PVM slightly outperforms the DM, both in terms of Evidence and Mean Absolute Error (MAE). We also show that the Evidence is a very useful figure of merit for error prediction as well as a convenient tool to determine the most probable model from measured data.

Improving segmentation accuracy for magnetic resonance imaging using a boosted decision tree

The purpose of this study was to improve the accuracy rate of brain tissue classification in magnetic resonance (MR) imaging using a boosted decision tree segmentation algorithm. Herein, we examined simulated phantom MR (SPMR) images, simulated brain MR (SBMR) images, and a real data. The accuracy rate and k index when classifying brain tissues as gray matter (GM), white matter (WM), or cerebral-spinal fluid (CSF) were better when using the boosted decision tree algorithm combined with a fuzzy threshold than when using a statistical region-growing (SRG) algorithm [Wolf I, Vetter M, Wegner I, Böttger T, Nolden M, Schöbinger M, et al. The medical imaging interaction toolkit. Med Imag Anal 2005;9:594–604] and an adaptive segmentation (AS) algorithm [Wells WM, Grimson WEL, Kikinis R, Jolesz FA. Adaptive segmentation of MRI data. IEEE Trans Med Imag 1996;15:429–42]. The segmentation performance when using this algorithm on real data from brain MR images was also better than those of SRG and AS algorithm. Segmentation of a real data using the boosted decision tree produced particularly clear brain MR imaging and permitted more accurate brain tissue segmentation. In conclusion, a decision tree with appropriate boost trials successfully improved the accuracy rate of MR brain tissue segmentation.

A cellular neural network based method for classification of magnetic resonance images: Towards an automated detection of hippocampal sclerosis

We present a cellular neuronal network (CNN) based approach to classify magnetic resonance images with and without hippocampal or Ammon’s horn sclerosis (AHS) in the medial temporal lobe. A CNN combines the architecture of cellular automata and artificial neural networks and is an array of locally coupled nonlinear electrical circuits or cells, which is capable of processing a large amount of information in parallel and in real time. Using an exemplary database that consists of a large number of volumes of interest extracted from T1-weighted magnetic resonance images from 144 subjects we here demonstrate that the network allows to classify brain tissue with respect to the presence or absence of mesial temporal sclerosis. Results indicate the general feasibility of CNN-based computer-aided systems for diagnosis and classification of images generated by medical imaging systems.

Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification

Conventional k-Nearest-Neighbor (kNN) classification, which has been successfully applied to classify brain tissue in MR data, requires training on manually labeled subjects. This manual labeling is a laborious and time-consuming procedure. In this work, a new fully automated brain tissue classification procedure is presented, in which kNN training is automated. This is achieved by non-rigidly registering the MR data with a tissue probability atlas to automatically select training samples, followed by a post-processing step to keep the most reliable samples. The accuracy of the new method was compared to rigid registration-based training and to conventional kNN-based segmentation using training on manually labeled subjects for segmenting gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) in 12 data sets. Furthermore, for all classification methods, the performance was assessed when varying the free parameters. Finally, the robustness of the fully automated procedure was evaluated on 59 subjects. The automated training method using non-rigid registration with a tissue probability atlas was significantly more accurate than rigid registration. For both automated training using non-rigid registration and for the manually trained kNN classifier, the difference with the manual labeling by observers was not significantly larger than inter-observer variability for all tissue types. From the robustness study, it was clear that, given an appropriate brain atlas and optimal parameters, our new fully automated, non-rigid registration-based method gives accurate and robust segmentation results. A similarity index was used for comparison with manually trained kNN. The similarity indices were 0.93, 0.92 and 0.92, for CSF, GM and WM, respectively. It can be concluded that our fully automated method using non-rigid registration may replace manual segmentation, and thus that automated brain tissue segmentation without laborious manual training is feasible.

Analysis of human brain tissue, brain tumors and tumor cells by infrared spectroscopic mapping.

This study uses infrared (IR) spectroscopic, point detection, mapping procedures to examine tissue samples from normal brain specimens and from astrocytic gliomas, the most frequent human brain tumors. Model systems were derived from cultured glioma cell lines. IR spectra of normal tissue sections distinguished white matter from gray matter by increased spectral contributions from lipids and cholesterol. Qualitatively the same differences were found in IR spectra of low and high grade glioma tissue sections pointing to a significant reduction of brain lipids with increasing malignancy. Whereas spectral contributions of proteins and lipids were similar in IR spectra of glioma cells and tissues, nucleic acid bands were more intense for cells suggesting higher proliferative activities. For statistical analyses of IR spectroscopic maps from 71 samples, a parameter for the lipid to protein ratio was introduced involving the CH(2) symmetric stretch band with lipids as main contributors and the amide I band of proteins. As this parameter correlated with the grade of gliomas obtained from standard histopathological examination, it was applied to classify brain tissue sections based on IR spectroscopic mapping.

Segmentation of magnetic resonance brain images through discriminant analysis

Segmentation (tissue classification) of medical images obtained from a magnetic resonance (MR) system is a primary step in most applications of medical image post-processing. This paper describes nonparametric discriminant analysis methods to segment multispectral MR images of the brain. Starting from routinely available spin-lattice relaxation time, spin–spin relaxation time, and proton density weighted images ( T 1w, T 2w, P Dw), the proposed family of statistical methods is based on: (i) a transform of the images into components that are statistically independent from each other; (ii) a nonparametric estimate of probability density functions of each tissue starting from a training set; (iii) a classic Bayes 0–1 classification rule. Experiments based on a computer built brain phantom ( brainweb) and on eight real patient data sets are shown. A comparison with parametric discriminant analysis is also reported. The capability of nonparametric discriminant analysis in improving brain tissue classification of parametric methods is demonstrated. Finally, an assessment of the role of multispectrality in classifying brain tissues is discussed.

Magnetic Resonance Image Tissue Classification Using a Partial Volume Model

We describe a sequence of low-level operations to isolate and classify brain tissue within T1-weighted magnetic resonance images (MRI). Our method first removes nonbrain tissue using a combination of anisotropic diffusion filtering, edge detection, and mathematical morphology. We compensate for image nonuniformities due to magnetic field inhomogeneities by fitting a tricubic B-spline gain field to local estimates of the image nonuniformity spaced throughout the MRI volume. The local estimates are computed by fitting a partial volume tissue measurement model to histograms of neighborhoods about each estimate point. The measurement model uses mean tissue intensity and noise variance values computed from the global image and a multiplicative bias parameter that is estimated for each region during the histogram fit. Voxels in the intensity-normalized image are then classified into six tissue types using a maximum a posteriori classifier. This classifier combines the partial volume tissue measurement model with a Gibbs prior that models the spatial properties of the brain. We validate each stage of our algorithm on real and phantom data. Using data from the 20 normal MRI brain data sets of the Internet Brain Segmentation Repository, our method achieved average κ indices of κ = 0.746 ± 0.114 for gray matter (GM) and κ = 0.798 ± 0.089 for white matter (WM) compared to expert labeled data. Our method achieved average κ indices κ = 0.893 ± 0.041 for GM and κ = 0.928 ± 0.039 for WM compared to the ground truth labeling on 12 volumes from the Montreal Neurological Institute's BrainWeb phantom.

Some aspects of Dempster-Shafer evidence theory for classification of multi-modality medical images taking partial volume effect into account

This paper points out some key features of Dempster-Shafer evidence theory for data fusion in medical imaging. Examples are provided to show its ability to take into account a large variety of situations, which actually often occur and are not always well managed by classical approaches nor by previous applications of Dempster-Shafer theory in medical imaging. The modelization of both uncertainty and imprecision, the introduction of possible partial or global ignorance, the computation of conflict between images, the possible introduction of a priori information are all powerful aspects of this theory, which deserve to be more exploited in medical image processing. They may be of great influence on the final decision. They are illustrated on a simple example for classifying brain tissues in pathological dual echo MR images. In particular, partial volume effect can be properly managed by this approach.

Automated segmentation of brain MR images

A simple, robust and efficient image segmentation algorithm for classifying brain tissues from dual echo Magnetic Resonance (MR) images is presented. The algorithm consists of a sequence of adaptive histogram analysis, morphological operations and knowledge based rules to accurately classify various regions such as the brain matter and the cerebrospinal fluid, and detect if there are any abnormal regions. It can be completely automated and has been tested on over hundred images from several patient studies. Experimental results are provided.

Schizophrenic thought disorder: MRI correlates

The purpose of this study was to improve the accuracy rate of brain tissue classification in magnetic resonance (MR) imaging using a boosted decision tree segmentation algorithm. Herein, we examined simulated phantom MR (SPMR) images, simulated brain MR (SBMR) images, and a real data. The accuracy rate and k index when classifying brain tissues as gray matter (GM), white matter (WM), or cerebral-spinal fluid (CSF) were better when using the boosted decision tree algorithm combined with a fuzzy threshold than when using a statistical region-growing (SRG) algorithm [Wolf I, Vetter M, Wegner I, Böttger T, Nolden M, Schöbinger M, et al. The medical imaging interaction toolkit. Med Imag Anal 2005;9:594–604] and an adaptive segmentation (AS) algorithm [Wells WM, Grimson WEL, Kikinis R, Jolesz FA. Adaptive segmentation of MRI data. IEEE Trans Med Imag 1996;15:429–42]. The segmentation performance when using this algorithm on real data from brain MR images was also better than those of SRG and AS algorithm. Segmentation of a real data using the boosted decision tree produced particularly clear brain MR imaging and permitted more accurate brain tissue segmentation. In conclusion, a decision tree with appropriate boost trials successfully improved the accuracy rate of MR brain tissue segmentation.