Unsupervised segmentation of brain tissue in multivariate MRI

Magnetic Resonance imaging is one of the widely used brain imaging modality to visualize and assess the brain anatomy and its function. It provides a much greater contrast between the different soft tissues of the body than computed tomography (CT) does. In this paper an approach for segmentation of brain tissues from T1 – MRI images is proposed. To exemplify the approach, a system is presented which involves image denoising, contrast enhancement and segmentation of brain tissues namely gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF). The segmentation is carried out using combination of Expectation Maximization (EM) and Gaussian Mixture Model (GMM). From the experimental results it is observed that the brain tissue is segmented accurately using EM-GMM.

This paper presents a novel fully automatic unsupervised framework for the segmentation of brain tissues in magnetic resonance (MR) images. The framework is a combination of our proposed Bayesian-based adaptive mean shift (BAMS), a priori spatial tissue probability maps and fuzzy c-means. BAMS is applied to cluster the tissues in the joint spatialintensity feature space and then a fuzzy c-means algorithm is employed with initialization by a priori spatial tissue probability maps to assign the clusters into three tissue types; white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The proposed framework is validated on multimodal synthetic as well as on real T1-weighted MR data with varying noise characteristics and spatial intensity inhomogeneity. The performance of the proposed framework is evaluated relative to our previous method BAMS and other existing adaptive mean shift framework. Both of these are based on the mode pruning and voxel weighted k-means algorithm for classifying the clusters into WM, GM and CSF tissue. The experimental results demonstrate the robustness of the proposed framework to noise and spatial intensity inhomogeneity, and that it exhibits a higher degree of segmentation accuracy in segmenting both synthetic and real MR data compared to competing methods.

Physics in Medicine and Biology, 2013

MRI-based medical image analysis for brain tumor studies is gaining attention in recent times due to an increased need for efficient and objective evaluation of large amounts of data. While the pioneering approaches applying automated methods for analysis of brain tumor images date back almost two decades, the current methods are becoming more mature and coming closer to routine clinical application. This review article aims at providing a comprehensive overview by giving a brief introduction to brain tumors and imaging of brain tumors first. Then we review the state of the art in segmentation, registration and modeling related to tumorbearing brain images with a focus on gliomas. The objective in segmentation is outlining the tumor including its sub-compartments and surrounding tissues, while the main challenge in registration and modeling is the handling of morphological changes caused by the tumor. The qualities of different approaches are discussed with a focus on methods that can be applied on standard clinical imaging protocols. Finally, a critical assessment of the current state is performed and future developments and trends are addressed, giving special attention to recent developments in radiological tumor assessment guidelines.

2018

Amid the variations of the cancer disease, brain tumors account for the majority deaths among young people. To diagnose and treat this deadly disease effectively, analysis of hundreds of medical images such as Magnetic Resonance Imaging (MRI) scans is usually performed. However, the analyses of these scans are still mainly performed manually, making the procedure not only very tedious and time-consuming for doctors, but also error prone and non-repeatable. Attempts have been made to automate this procedure by performing image processing techniques such as thresholding, region-growing, unsupervised learning (e.g. k-means, fuzzy cmeans clustering), and supervised learning (e.g. support vector machines). Some require human interaction. The techniques may be applied on one or more MRI sequence scans. Unfortunately, these automated attempts still result in a high level of error, and more computationally complex algorithms do not guarantee an increase in accuracy. This paper presents a no...

European Journal of Radiology, 2005

Purpose: Manual segmentation of brain tumors from magnetic resonance images is a challenging and time-consuming task. A semi-automated method has been developed for brain tumor and edema segmentation that will provide objective, reproducible segmentations that are close to the manual results. Additionally, the method segments non-enhancing brain tumor and edema from healthy tissues in magnetic resonance images. Methods and materials: In this study, a semi-automated method was developed for brain tumor and edema segmentation and volume measurement using magnetic resonance imaging (MRI). Some novel algorithms for tumor segmentation from MRI were integrated in this medical diagnosis system. We exploit a hybrid level set (HLS) segmentation method driven by region and boundary information simultaneously, region information serves as a propagation force which is robust and boundary information serves as a stopping functional which is accurate. Ten different patients with brain tumors of different size, shape and location were selected, a total of 246 axial tumor-containing slices obtained from 10 patients were used to evaluate the effectiveness of segmentation methods. Results: This method was applied to 10 non-enhancing brain tumors and satisfactory results were achieved. Two quantitative measures for tumor segmentation quality estimation, namely, correspondence ratio (CR) and percent matching (PM), were performed. For the segmentation of brain tumor, the volume total PM varies from 79.12 to 93.25% with the mean of 85.67 ± 4.38% while the volume total CR varies from 0.74 to 0.91 with the mean of 0.84 ± 0.07. For the segmentation of edema, the volume total PM varies from 72.86 to 87.29% with the mean of 79.54 ± 4.18% while the volume total CR varies from 0.69 to 0.85 with the mean of 0.79 ± 0.08. The HLS segmentation method perform better than the classical level sets (LS) segmentation method in PM and CR. Conclusions: The results of this research may have potential applications, both as a staging procedure and a method of evaluating tumor response during treatment, this method can be used as a clinical image analysis tool for doctors or radiologists.

Object recognition supported by user interaction for service robots, 2002

Combining image segmentation based on statistical classification with a geometric prior has been shown to significantly increase robustness and reproducibility. Using a probabilistic geometric model and image registration serves both initialization of probability density functions and definition of spatial constraints. A strong spatial prior, however, prevents segmentation of structures that are not part of the model.

Cancer imaging : the official publication of the International Cancer Imaging Society, 2015

Segmentation of pre-operative low-grade gliomas (LGGs) from magnetic resonance imaging is a crucial step for studying imaging biomarkers. However, segmentation of LGGs is particularly challenging because they rarely enhance after gadolinium administration. Like other gliomas, they have irregular tumor shape, heterogeneous composition, ill-defined tumor boundaries, and limited number of image types. To overcome these challenges we propose a semi-automated segmentation method that relies only on T2-weighted (T2W) and optionally post-contrast T1-weighted (T1W) images. First, the user draws a region-of-interest (ROI) that completely encloses the tumor and some normal tissue. Second, a normal brain atlas and post-contrast T1W images are registered to T2W images. Third, the posterior probability of each pixel/voxel belonging to normal and abnormal tissues is calculated based on information derived from the atlas and ROI. Finally, geodesic active contours use the probability map of the tum...

IEEE Transactions on Medical Imaging, 1995

This paper presents a new method to segment brain parenchyma and cerebrospinal uid spaces automatically in routine axial spin echo multispectral MR images. The algorithm simultaneously incorporates information about anatomical boundaries shape and tissue signature grey scale using a priori knowledge. The head and brain are divided into 4 regions and 7 di erent tissue types. Each tissue type c is modeled by a multivariate Gaussian distribution N c ; c . Each region is associated with a nite mixture density corresponding to its constituent tissue types. Initial estimates of tissue parameters f c ; c g c=1;:::;7 are obtained from k-means clustering of a single slice used for training. The rst algorithmic step uses the EM-algorithm for adjusting the initial tissue parameter estimates to the MR data of new patients. The second step uses a recently developed model of dynamic contours to detect three simply closed, non-intersecting curves in the plane, constituting the arachnoid dura mater boundary of the brain, the border between the subarachnoid space and brain parenchyma, and the inner border of the parenchyma towards the lateral ventricles. The model, which is formulated by energy functions in a Bayesian framework, incorporates a priori knowledge, smoothness constraints and updated tissue type parameters. Satisfactory maximum a posteriori probability estimates of the closed contour curves de ned by the model were found using simulated annealing.

Medical Image Computing and Computer-Assisted Intervention — MICCAI 2002, 2002

Combining image segmentation based on statistical classification with a geometric prior has been shown to significantly increase robustness and reproducibility. Using a probabilistic geometric model of sought structures and image registration serves both initialization of probability density functions and definition of spatial constraints. A strong spatial prior, however, prevents segmentation of structures that are not part of the model. In practical applications, we encounter either the presentation of new objects that cannot be modeled with a spatial prior or regional intensity changes of existing structures not explained by the model. Our driving application is the segmentation of brain tissue and tumors from three-dimensional magnetic resonance imaging (MRI). Our goal is a high-quality segmentation of healthy tissue and a precise delineation of tumor boundaries. We present an extension to an existing expectation maximization (EM) segmentation algorithm that modifies a probabilistic brain atlas with an individual subject's information about tumor location obtained from subtraction of post-and pre-contrast MRI. The new method handles various types of pathology, space-occupying mass tumors and infiltrating changes like edema. Preliminary results on five cases presenting tumor types with very different characteristics demonstrate the potential of the new technique for clinical routine use for planning and monitoring in neurosurgery, radiation oncology, and radiology.

2021

The segmentation of high-grade gliomas (HGG) using magnetic resonance imaging (MRI) data is clinically meaningful in neurosurgical practice, but a challenging task. Currently, most segmentation methods are supervised learning with labeled training sets. Although these methods work well in most cases, they typically require time-consuming manual labeling and pre-trained models. In this work, we propose an automatically unsupervised segmentation toolbox based on the clustering algorithm and morphological processing, named AUCseg. With our toolbox, the whole tumor was first extracted by clustering on T2-FLAIR images. Then, based on the mask acquired with whole tumor segmentation, the enhancing tumor was segmented on the post-contrast T1-weighted images (T1-CE) using clustering methods. Finally, the necrotic regions were segmented by morphological processing or clustering on T2-weighted images. Compared with K-means, Mini-batch K-means, and Fuzzy C Means (FCM), the Gaussian Mixture Mode...