Fully automatic segmentation of the brain in MRI

Unsupervised model for structure segmentation applied to brain computed tomography

This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity constraints to generate segmentation maps of the anatomical head structures. Specifically designed for real-world datasets, this approach applies a spatial continuity scoring function tailored to the desired number of structures. The primary objective is to assist medical experts in diagnosis by identifying regions with specific abnormalities. Results indicate a simplified and accessible solution, reducing computational effort, training time, and financial costs. Moreover, the method presents potential for expediting the interpretation of abnormal scans, thereby impacting clinical practice. This proposed approach might serve as a practical tool for segmenting brain computed tomography scans, and make a significant contribution to the analysis of medical images in both research and clinical settings.

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.

A New Semantic Segmentation Framework Based on UNet

This paper discusses a semantic segmentation framework and shows its application in agricultural intelligence, such as providing environmental awareness for agricultural robots to work autonomously and efficiently. We propose an ensemble framework based on the bagging strategy and the UNet network, using RGB and HSV color spaces. We evaluated the framework on our self-built dataset (Maize) and a public dataset (Sugar Beets). Then, we compared it with UNet-based methods (single RGB and single HSV), DeepLab V3+, and SegNet. Experimental results show that our ensemble framework can synthesize the advantages of each color space and obtain the best IoUs (0.8276 and 0.6972) on the datasets (Maize and Sugar Beets), respectively. In addition, including our framework, the UNet-based methods have faster speed and a smaller parameter space than DeepLab V3+ and SegNet, which are more suitable for deployment in resource-constrained environments such as mobile robots.

A fast and accurate brain extraction method for CT head images

BACKGROUND

Brain extraction is an essential prerequisite for the automated diagnosis of intracranial lesions and determines, to a certain extent, the accuracy of subsequent lesion recognition, location, and segmentation. Segmentation using a fully convolutional neural network (FCN) yields high accuracy but a relatively slow extraction speed.

METHODS

This paper proposes an integrated algorithm, FABEM, to address the above issues. This method first uses threshold segmentation, closed operation, convolutional neural network (CNN), and image filling to generate a specific mask. Then, it detects the number of connected regions of the mask. If the number of connected regions equals 1, the extraction is done by directly multiplying with the original image. Otherwise, the mask was further segmented using the region growth method for original images with single-region brain distribution. Conversely, for images with multi-region brain distribution, Deeplabv3 + is used to adjust the mask. Finally, the mask is multiplied with the original image to complete the extraction.

RESULTS

The algorithm and 5 FCN models were tested on 24 datasets containing different lesions, and the algorithm's performance showed MPA = 0.9968, MIoU = 0.9936, and MBF = 0.9963, comparable to the Deeplabv3+. Still, its extraction speed is much faster than the Deeplabv3+. It can complete the brain extraction of a head CT image in about 0.43 s, about 3.8 times that of the Deeplabv3+.

CONCLUSION

Thus, this method can achieve accurate brain extraction from head CT images faster, creating a good basis for subsequent brain volume measurement and feature extraction of intracranial lesions.

MDF-Net: A Multi-Scale Dynamic Fusion Network for Breast Tumor Segmentation of Ultrasound Images

Breast tumor segmentation of ultrasound images provides valuable information of tumors for early detection and diagnosis. Accurate segmentation is challenging due to low image contrast between areas of interest; speckle noises, and large inter-subject variations in tumor shape and size. This paper proposes a novel Multi-scale Dynamic Fusion Network (MDF-Net) for breast ultrasound tumor segmentation. It employs a two-stage end-to-end architecture with a trunk sub-network for multiscale feature selection and a structurally optimized refinement sub-network for mitigating impairments such as noise and inter-subject variation via better feature exploration and fusion. The trunk network is extended from UNet++ with a simplified skip pathway structure to connect the features between adjacent scales. Moreover, deep supervision at all scales, instead of at the finest scale in UNet++, is proposed to extract more discriminative features and mitigate errors from speckle noise via a hybrid loss function. Unlike previous works, the first stage is linked to a loss function of the second stage so that both the preliminary segmentations and refinement subnetworks can be refined together at training. The refinement sub-network utilizes a structurally optimized MDF mechanism to integrate preliminary segmentation information (capturing general tumor shape and size) at coarse scales and explores inter-subject variation information at finer scales. Experimental results from two public datasets show that the proposed method achieves better Dice and other scores over state-of-the-art methods. Qualitative analysis also indicates that our proposed network is more robust to tumor size/shapes, speckle noise and heavy posterior shadows along tumor boundaries. An optional post-processing step is also proposed to facilitate users in mitigating segmentation artifacts. The efficiency of the proposed network is also illustrated on the "Electron Microscopy neural structures segmentation dataset". It outperforms a state-of-the-art algorithm based on UNet-2022 with simpler settings. This indicates the advantages of our MDF-Nets in other challenging image segmentation tasks with small to medium data sizes.

Alzheimer Disease Classification through Transfer Learning Approach

Alzheimer's disease (AD) is a slow neurological disorder that destroys the thought process, and consciousness, of a human. It directly affects the development of mental ability and neurocognitive functionality. The number of patients with Alzheimer's disease is increasing day by day, especially in old aged people, who are above 60 years of age, and, gradually, it becomes cause of their death. In this research, we discuss the segmentation and classification of the Magnetic resonance imaging (MRI) of Alzheimer's disease, through the concept of transfer learning and customizing of the convolutional neural network (CNN) by specifically using images that are segmented by the Gray Matter (GM) of the brain. Instead of training and computing the proposed model accuracy from the start, we used a pre-trained deep learning model as our base model, and, after that, transfer learning was applied. The accuracy of the proposed model was tested over a different number of epochs, 10, 25, and 50. The overall accuracy of the proposed model was 97.84%.

Methods of Brain Extraction from Magnetic Resonance Images of Human Head: A Review

Medical images are providing vital information to aid physicians in diagnosing a disease afflicting the organ of a human body. Magnetic resonance imaging is an important imaging modality in capturing the soft tissues of the brain. Segmenting and extracting the brain is essential in studying the structure and pathological condition of brain. There are several methods that are developed for this purpose. Researchers in brain extraction or segmentation need to know the current status of the work that have been done. Such an information is also important for improving the existing method to get more accurate results or to reduce the complexity of the algorithm. In this paper we review the classical methods and convolutional neural network-based deep learning brain extraction methods.

Sparse Coding for Brain Tumor Segmentation Based on the Non-Linear Features

The main aim of brain Magnetic Resonance Image (MRI) segmentation is to extractthe significant objects like tumors for better diagnosis and proper treatment. As the brain tumors are distinct in the sense of shapes, location, and intensity it is hard to define a general algorithm for the tumor segmentation. Accurate extraction of tumors from the brain MRIs is a challenging task due to the complex anatomical structure of brain tissues in addition to the existence of intensity inhomogeneity, partial volume effects, and noise. In this paper, a method of Sparse coding based on non-linear features is proposed for the tumor segmentation from MR images of the brain. Initially, first and second-order statistical eigenvectors of 3 × 3 size are extracted from the MRIs then the process of Sparse coding is applied to them. The kernel dictionary learning algorithm is employed to obtain the non-linear features from these processed vectors to build two individual adaptive dictionaries for healthy and pathological tissues. This work proposes dictionary learning based kernel clustering algorithm to code the pixels, and then the target pixelsare classified by utilizing the method of linear discrimination. The proposed technique is applied to several tumor MRIs, taken from the BRATS database. This technique overcomes the problem of linear inseparability produced by the high level intensity similarity between the normal and abnormal tissues of the given brain image. All the performance parameters are high for the proposed technique. Comparison of the results with some other existing methods such as Fuzzy – C- Means (FCM), Hybrid k-Mean Graph Cut (HKMGC) and Neutrosophic Set – Expert Maximum Fuzzy Sure Entropy (NS-EMFSE) demonstrates that the proposed sparse coding method is effective in segmenting the brain tumor regions.

Accelerating GluCEST imaging using deep learning for B0 correction

PURPOSE

Glutamate weighted Chemical Exchange Saturation Transfer (GluCEST) MRI is a noninvasive technique for mapping parenchymal glutamate in the brain. Because of the sensitivity to field (B0 ) inhomogeneity, the total acquisition time is prolonged due to the repeated image acquisitions at several saturation offset frequencies, which can cause practical issues such as increased sensitivity to patient motions. Because GluCEST signal is derived from the small z-spectrum difference, it often has a low signal-to-noise-ratio (SNR). We proposed a novel deep learning (DL)-based algorithm armed with wide activation neural network blocks to address both issues.

METHODS

B0 correction based on reduced saturation offset acquisitions was performed for the positive and negative sides of the z-spectrum separately. For each side, a separate deep residual network was trained to learn the nonlinear mapping from few CEST-weighted images acquired at different ppm values to the one at 3 ppm (where GluCEST peaks) in the same side of the z-spectrum.

RESULTS

All DL-based methods outperformed the "traditional" method visually and quantitatively. The wide activation blocks-based method showed the highest performance in terms of Structural Similarity Index (SSIM) and peak signal-to-noise ratio (PSNR), which were 0.84 and 25dB respectively. SNR increases in regions of interest were over 8dB.

CONCLUSION

We demonstrated that the new DL-based method can reduce the entire GluCEST imaging time by ˜50% and yield higher SNR than current state-of-the-art.

State-of-the-Art Traditional to the Machine- and Deep-Learning-Based Skull Stripping Techniques, Models, and Algorithms

Several neuroimaging processing applications consider skull stripping as a crucial pre-processing step. Due to complex anatomical brain structure and intensity variations in brain magnetic resonance imaging (MRI), an appropriate skull stripping is an important part. The process of skull stripping basically deals with the removal of the skull region for clinical analysis in brain segmentation tasks, and its accuracy and efficiency are quite crucial for diagnostic purposes. It requires more accurate and detailed methods for differentiating brain regions and the skull regions and is considered as a challenging task. This paper is focused on the transition of the conventional to the machine- and deep-learning-based automated skull stripping methods for brain MRI images. It is observed in this study that deep learning approaches have outperformed conventional and machine learning techniques in many ways, but they have their limitations. It also includes the comparative analysis of the current state-of-the-art skull stripping methods, a critical discussion of some challenges, model of quantifying parameters, and future work directions.

Effective segmentation and classification of tumor on liver MRI and CT images using multi-kernel K-means clustering

Our proposed research technique intends to provide an effective liver magnetic resonance imaging (MRI) and computed tomography (CT) scan image classification which would play a significant role in medical dataset especially in feature selection and classification. There are a number of existing research works classifying the liver tumor disease. Early detection of liver tumor will help the patients to get cured rapidly. Our proposed research focuses on the classification of medical images with respect to the classification technique artificial neural network (ANN) to classify an image as normal or abnormal. In the pre-processing step, the input image is selected from the database and adaptive median filtering is used for noise removal. For better enhancement, histogram equalization (HE) is done in the noise-removed images. In the pre-processed images, the texture feature such as gray-level co-occurrence matrix (GLCM) and statistical features are extracted. From the extensive feature set, optimal features are selected using the optimal kernel K-means (OKK-means) clustering algorithm along with the oppositional firefly algorithm (OFA). The proposed method obtained 97.5% accuracy in the classification when compared to the existing method.

Conventional and Deep Learning Methods for Skull Stripping in Brain MRI

Skull stripping in brain magnetic resonance volume has recently been attracting attention due to an increased demand to develop an efficient, accurate, and general algorithm for diverse datasets of the brain. Accurate skull stripping is a critical step for neuroimaging diagnostic systems because neither the inclusion of non-brain tissues nor removal of brain parts can be corrected in subsequent steps, which results in unfixed error through subsequent analysis. The objective of this review article is to give a comprehensive overview of skull stripping approaches, including recent deep learning-based approaches. In this paper, the current methods of skull stripping have been divided into two distinct groups—conventional or classical approaches, and convolutional neural networks or deep learning approaches. The potentials of several methods are emphasized because they can be applied to standard clinical imaging protocols. Finally, current trends and future developments are addressed giving special attention to recent deep learning algorithms.

Accuracy, uncertainty, and adaptability of automatic myocardial ASL segmentation using deep CNN

PURPOSE

To apply deep convolution neural network to the segmentation task in myocardial arterial spin labeled perfusion imaging and to develop methods that measure uncertainty and that adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff.

METHODS

The Monte Carlo dropout U-Net was trained on data from 22 subjects and tested on data from 6 heart transplant recipients. Manual segmentation and regional myocardial blood flow were available for comparison. We consider 2 global uncertainty measures, named "Dice uncertainty" and "Monte Carlo dropout uncertainty," which were calculated with and without the use of manual segmentation, respectively. Tversky loss function with a hyperparameter β was used to adapt the model to a specific false-positive versus false-negative tradeoff.

RESULTS

The Monte Carlo dropout U-Net achieved a Dice coefficient of 0.91 ± 0.04 on the test set. Myocardial blood flow measured using automatic segmentations was highly correlated to that measured using the manual segmentation (R² = 0.96). Dice uncertainty and Monte Carlo dropout uncertainty were in good agreement (R² = 0.64). As β increased, the false-positive rate systematically decreased and false-negative rate systematically increased.

CONCLUSION

We demonstrate the feasibility of deep convolution neural network for automatic segmentation of myocardial arterial spin labeling, with good accuracy. We also introduce 2 simple methods for assessing model uncertainty. Finally, we demonstrate the ability to adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. These findings are directly relevant to automatic segmentation in quantitative cardiac MRI and are broadly applicable to automatic segmentation problems in diagnostic imaging.

Development of a Stand-Alone Independent Graphical User Interface for Neurological Disease Prediction with Automated Extraction and Segmentation of Gray and White Matter in Brain MRI Images

This research presents an independent stand-alone graphical computational tool which functions as a neurological disease prediction framework for diagnosis of neurological disorders to assist neurologists or researchers in the field to perform automatic segmentation of gray and white matter regions in brain MRI images. The tool was built in collaboration with neurologists and neurosurgeons and many of the features are based on their feedback. This tool provides the user automatized functionality to perform automatic segmentation and extract the gray and white matter regions of patient brain image data using an algorithm called adapted fuzzy c-means (FCM) membership-based clustering with preprocessing using the elliptical Hough transform and postprocessing using connected region analysis. Dice coefficients for several patient brain MRI images were calculated to measure the similarity between the manual tracings by experts and automatic segmentations obtained in this research. The average Dice coefficients are 0.86 for gray matter, 0.88 for white matter, and 0.87 for total cortical matter. Dice coefficients of the proposed algorithm were also the highest when compared with previously published standard state-of-the-art brain MRI segmentation algorithms in terms of accuracy in segmenting the gray matter, white matter, and total cortical matter.

3D U-Net for Skull Stripping in Brain MRI

Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming task. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised and proposed previously. However, there is still no method that solves the entire brain extraction problem satisfactorily for diverse datasets in a generic and robust way. To address these shortcomings of existing methods, we propose the use of a 3D-UNet for skull stripping in brain MRI. The 3D-UNet was recently proposed and has been widely used for volumetric segmentation in medical images due to its outstanding performance. It is an extended version of the previously proposed 2D-UNet, which is based on a deep learning network, specifically, the convolutional neural network. We evaluated 3D-UNet skull-stripping using a publicly available brain MRI dataset and compared the results with three existing methods (BSE, ROBEX, and Kleesiek’s method; BSE and ROBEX are two conventional methods, and Kleesiek’s method is based on deep learning). The 3D-UNet outperforms two typical methods and shows comparable results with the specific deep learning-based algorithm, exhibiting a mean Dice coefficient of 0.9903, a sensitivity of 0.9853, and a specificity of 0.9953.

Semiautomated Assessment of the Anterior Cingulate Cortex in Alzheimer's Disease

BACKGROUND AND PURPOSE

The anterior cingulate cortex (ACC) is involved in several cognitive processes including executive function. Degenerative changes of ACC are consistently seen in Alzheimer's disease (AD). However, volumetric changes specific to the ACC in AD are not clear because of the difficulty in segmenting this region. The objectives of the current study were to develop a precise and high-throughput approach for measuring ACC volumes and to correlate the relationship between ACC volume and cognitive function in AD.

METHODS

Structural T₁ -weighted magnetic resonance images of AD patients (n = 47) and age-matched controls (n = 47) at baseline and at 24 months were obtained from the Alzheimer's disease neuroimaging initiative (ADNI) database and studied using a custom-designed semiautomated segmentation protocol.

RESULTS

ACC volumes obtained using the semiautomated protocol were highly correlated to values obtained from manual segmentation (r = .98) and the semiautomated protocol was considerably faster. When comparing AD and control subjects, no significant differences were observed in baseline ACC volumes or in change in ACC volumes over 24 months using the two segmentation methods. However, a change in ACC volume over 24 months did not correlate with a change in mini-mental state examination scores.

CONCLUSIONS

Our results indicate that the proposed semiautomated segmentation protocol is reliable for determining ACC volume in neurodegenerative conditions including AD.

Reproducibility of 2D GluCEST in healthy human volunteers at 7 T

PURPOSE

To investigate the reproducibility of gray and white matter glutamate contrast of a brain slice among a small group of healthy volunteers by using the 2D single-slice glutamate CEST (GluCEST) imaging technique.

METHODS

Six healthy volunteers were scanned multiple times for within-day and between-day reproducibility. One more volunteer was scanned for within-day reproducibility at 7T MRI. Glutamate CEST contrast measurements were calculated for within subjects and among the subjects and the coefficient of variations are reported.

RESULTS

The GluCEST measurements were highly reproducible in the gray and white matter area of the brain slice, whether it was within-day or between-day with a coefficient of variation of less than 5%.

CONCLUSION

This preliminary study in a small group of healthy volunteers shows a high degree of reproducibility of GluCEST MRI in brain and holds promise for implementation in studying age-dependent changes in the brain.

An accurate and robust skull stripping method for 3-D magnetic resonance brain images

Segmentation of brain region from an MR volume is an essential prerequisite for any automatic medical image processing application as it increases both speed and accuracy of the diagnosis in manifold. Due to material heterogeneity and resolution limitation of imaging devices, the MR image introduces graded intensity of tissues within the brain region. Moreover, it incurs the blurring effect at the brain surface. In spite of these artifacts, all the tissues of brain region of an MR image are perceived to be hanged together within the brain. In this regard, this paper introduces an accurate and robust skull stripping algorithm, termed as ARoSi. It is based on a novel concept, called rough-fuzzy connectedness, introduced in this paper. In the proposed method, the connectedness of a voxel to the brain region is determined by its degree of belongingness to the brain region as well as the degree of adjacency to the brain. Moreover, the proposed ARoSi algorithm considers the local spatial information of the voxel of interest, which reduces the effect of noise, and in turn, helps to improve the performance of the proposed method. Finally, the performance of the proposed ARoSi algorithm, along with a comparison with other state-of-the-art algorithms, is demonstrated on T1-weighted 3-D brain MR volumes obtained from four different data sets. The experiments show that the performance of ARoSi is consistent across all the four data sets, including diseased data sets. The proposed algorithm achieves the highest mean Dice coefficient of value 0.951 for all the volumes of four different data sets, among six existing brain extraction methods.

Radiomic Phenotyping in Brain Cancer to Unravel Hidden Information in Medical Images

Radiomics is a new area of research in the field of imaging with tremendous potential to unravel the hidden information in digital images. The scope of radiology has grown exponentially over the last two decades; since the advent of radiomics, many quantitative imaging features can now be extracted from medical images through high-throughput computing, and these can be converted into mineable data that can help in linking imaging phenotypes with clinical data, genomics, proteomics, and other "omics" information. In cancer, radiomic imaging analysis aims at extracting imaging features embedded in the imaging data, which can act as a guide in the disease or cancer diagnosis, staging and planning interventions for treating patients, monitor patients on therapy, predict treatment response, and determine patient outcomes.

Methods on Skull Stripping of MRI Head Scan Images-a Review

The high resolution magnetic resonance (MR) brain images contain some non-brain tissues such as skin, fat, muscle, neck, and eye balls compared to the functional images namely positron emission tomography (PET), single photon emission computed tomography (SPECT), and functional magnetic resonance imaging (fMRI) which usually contain relatively less non-brain tissues. The presence of these non-brain tissues is considered as a major obstacle for automatic brain image segmentation and analysis techniques. Therefore, quantitative morphometric studies of MR brain images often require a preliminary processing to isolate the brain from extra-cranial or non-brain tissues, commonly referred to as skull stripping. This paper describes the available methods on skull stripping and an exploratory review of recent literature on the existing skull stripping methods.

Histogram analysis with automated extraction of brain-tissue region from whole-brain CT images

To determine whether an automated extraction of the brain-tissue region from CT images is useful for the histogram analysis of the brain-tissue region was studied. We used the CT images of 11 patients. We developed an automatic brain-tissue extraction algorithm. We evaluated the similarity index of this automated extraction method relative to manual extraction, and we compared the mean CT number of all extracted pixels and the kurtosis and skewness of the distribution of CT numbers of all extracted pixels from the automated and manual extractions. The similarity index was 0.93. The mean CT number and the kurtosis and skewness from the automated extraction were 35.0 Hounsfield units, 0.63, and 0.51, respectively, and were equivalent to those from the manual extraction (35.4 Hounsfield units, 0.59, and 0.46, respectively). The automated extraction of the brain-tissue region from whole-brain CT images was useful for histogram analysis of the brain-tissue region.

A New MRI Masking Technique Based on Multi-Atlas Brain Segmentation in Controls and Schizophrenia: A Rapid and Viable Alternative to Manual Masking

Brain masking of MRI images separates brain from surrounding tissue and its accuracy is important for further imaging analyses. We implemented a new brain masking technique based on multi-atlas brain segmentation (MABS) and compared MABS to masks generated using FreeSurfer (FS; version 5.3), Brain Extraction Tool (BET), and Brainwash, using manually defined masks (MM) as the gold standard. We further determined the effect of different masking techniques on cortical and subcortical volumes generated by FreeSurfer.

METHODS

Images were acquired on a 3-Tesla MR Echospeed system General Electric scanner on five control and five schizophrenia subjects matched on age, sex, and IQ. Automated masks were generated from MABS, FS, BET, and Brainwash, and compared to MM using these metrics: a) volume difference from MM; b) Dice coefficients; and c) intraclass correlation coefficients.

RESULTS

Mean volume difference between MM and MABS masks was significantly less than the difference between MM and FS or BET masks. Dice coefficient between MM and MABS was significantly higher than Dice coefficients between MM and FS, BET, or Brainwash. For subcortical and left cortical regions, MABS volumes were closer to MM volumes than were BET or FS volumes. For right cortical regions, MABS volumes were closer to MM volumes than were BET volumes.

CONCLUSIONS

Brain masks generated using FreeSurfer, BET, and Brainwash are rapidly obtained, but are less accurate than manually defined masks. Masks generated using MABS, in contrast, resemble more closely the gold standard of manual masking, thereby offering a rapid and viable alternative.

Reconstruction of micron resolution mouse brain surface from large-scale imaging dataset using resampling-based variational model

Brain surface profile is essential for brain studies, including registration, segmentation of brain structure and drawing neuronal circuits. Recent advances in high-throughput imaging techniques enable imaging whole mouse brain at micron spatial resolution and provide a basis for more fine quantitative studies in neuroscience. However, reconstructing micron resolution brain surface from newly produced neuronal dataset still faces challenges. Most current methods apply global analysis, which are neither applicable to a large imaging dataset nor to a brain surface with an inhomogeneous signal intensity. Here, we proposed a resampling-based variational model for this purpose. In this model, the movement directions of the initial boundary elements are fixed, the final positions of the initial boundary elements that form the brain surface are determined by the local signal intensity. These features assure an effective reconstruction of the brain surface from a new brain dataset. Compared with conventional typical methods, such as level set based method and active contour method, our method significantly increases the recall and precision rates above 97% and is approximately hundreds-fold faster. We demonstrated a fast reconstruction at micron level of the whole brain surface from a large dataset of hundreds of GB in size within 6 hours.

A Unified Framework for Brain Segmentation in MR Images

Brain MRI segmentation is an important issue for discovering the brain structure and diagnosis of subtle anatomical changes in different brain diseases. However, due to several artifacts brain tissue segmentation remains a challenging task. The aim of this paper is to improve the automatic segmentation of brain into gray matter, white matter, and cerebrospinal fluid in magnetic resonance images (MRI). We proposed an automatic hybrid image segmentation method that integrates the modified statistical expectation-maximization (EM) method and the spatial information combined with support vector machine (SVM). The combined method has more accurate results than what can be achieved with its individual techniques that is demonstrated through experiments on both real data and simulated images. Experiments are carried out on both synthetic and real MRI. The results of proposed technique are evaluated against manual segmentation results and other methods based on real T1-weighted scans from Internet Brain Segmentation Repository (IBSR) and simulated images from BrainWeb. The Kappa index is calculated to assess the performance of the proposed framework relative to the ground truth and expert segmentations. The results demonstrate that the proposed combined method has satisfactory results on both simulated MRI and real brain datasets.

Motion robust GRAPPA for echo-planar imaging

PURPOSE

A readout-segmented method for acquiring robust GRAPPA calibration data for echo-planar imaging (EPI) was proposed and compared with two previous methods, including the gold standard interleaved approach and a single shot method with halved phase encode resolution.

THEORY AND METHODS

The readout-segmented and single shot techniques acquire adjacent phase encode lines in the same shot to obtain the calibration data, rather than interleaving of lines between shots, to decrease sensitivity to motion. Additionally, it uses multiple segments with shortened frequency encode extent to match the phase encode bandwidth to the undersampled data, which decreases sensitivity to B0 inhomogeneity. The three methods were tested using simulations and EPI scans of the brain in healthy volunteers.

RESULTS

The interleaved approach exhibited high sensitivity to motion, while residual undersampling artifacts remained in the single shot method due to mismatch of B0 inhomogeneity between the calibration and undersampled data. The readout segmented method exhibited no such errors, having 30% lower ghosting intensity than the single shot method and 90% lower ghosting intensity than the interleaved approach in moving subjects.

CONCLUSION

Artifacts from B0 inhomogeneity and motion during calibration scans for EPI GRAPPA can be mitigated with a readout segmented calibration scan.

Rough-fuzzy clustering and unsupervised feature selection for wavelet based MR image segmentation

Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis of brain magnetic resonance (MR) images. For many human experts, manual segmentation is a difficult and time consuming task, which makes an automated brain MR image segmentation method desirable. In this regard, this paper presents a new segmentation method for brain MR images, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique. The proposed method assumes that the major brain tissues, namely, gray matter, white matter, and cerebrospinal fluid from the MR images are considered to have different textural properties. The dyadic wavelet analysis is used to extract the scale-space feature vector for each pixel, while the rough-fuzzy clustering is used to address the uncertainty problem of brain MR image segmentation. An unsupervised feature selection method is introduced, based on maximum relevance-maximum significance criterion, to select relevant and significant textural features for segmentation problem, while the mathematical morphology based skull stripping preprocessing step is proposed to remove the non-cerebral tissues like skull. The performance of the proposed method, along with a comparison with related approaches, is demonstrated on a set of synthetic and real brain MR images using standard validity indices.

Level set segmentation of breast masses in contrast-enhanced dedicated breast CT and evaluation of stopping criteria

Dedicated breast CT (bCT) produces high-resolution 3D tomographic images of the breast, fully resolving fibroglandular tissue structures within the breast and allowing for breast lesion detection and assessment in 3D. In order to enable quantitative analysis, such as volumetrics, automated lesion segmentation on bCT is highly desirable. In addition, accurate output from CAD (computer-aided detection/diagnosis) methods depends on sufficient segmentation of lesions. Thus, in this study, we present a 3D lesion segmentation method for breast masses in contrast-enhanced bCT images. The segmentation algorithm follows a two-step approach. First, 3D radial-gradient index segmentation is used to obtain a crude initial contour, which is then refined by a 3D level set-based active contour algorithm. The data set included contrast-enhanced bCT images from 33 patients containing 38 masses (25 malignant, 13 benign). The mass centers served as input to the algorithm. In this study, three criteria for stopping the contour evolution were compared, based on (1) the change of region volume, (2) the average intensity in the segmented region increase at each iteration, and (3) the rate of change of the average intensity inside and outside the segmented region. Lesion segmentation was evaluated by computing the overlap ratio between computer segmentations and manually drawn lesion outlines. For each lesion, the overlap ratio was averaged across coronal, sagittal, and axial planes. The average overlap ratios for the three stopping criteria ranged from 0.66 to 0.68 (dice coefficient of 0.80 to 0.81), indicating that the proposed segmentation procedure is promising for use in quantitative dedicated bCT analyses.

Segmentation of intensity inhomogeneous brain MR images using active contours

Segmentation of intensity inhomogeneous regions is a well-known problem in image analysis applications. This paper presents a region-based active contour method for image segmentation, which properly works in the context of intensity inhomogeneity problem. The proposed region-based active contour method embeds both region and gradient information unlike traditional methods. It contains mainly two terms, area and length, in which the area term practices a new region-based signed pressure force (SPF) function, which utilizes mean values from a certain neighborhood using the local binary fitted (LBF) energy model. In turn, the length term uses gradient information. The novelty of our method is to locally compute new SPF function, which uses local mean values and is able to detect boundaries of the homogenous regions. Finally, a truncated Gaussian kernel is used to regularize the level set function, which not only regularizes it but also removes the need of computationally expensive reinitialization. The proposed method targets the segmentation problem of intensity inhomogeneous images and reduces the time complexity among locally computed active contour methods. The experimental results show that the proposed method yields better segmentation result as well as less time complexity compared with the state-of-the-art active contour methods.

Knowledge-guided robust MRI brain extraction for diverse large-scale neuroimaging studies on humans and non-human primates

Accurate and robust brain extraction is a critical step in most neuroimaging analysis pipelines. In particular, for the large-scale multi-site neuroimaging studies involving a significant number of subjects with diverse age and diagnostic groups, accurate and robust extraction of the brain automatically and consistently is highly desirable. In this paper, we introduce population-specific probability maps to guide the brain extraction of diverse subject groups, including both healthy and diseased adult human populations, both developing and aging human populations, as well as non-human primates. Specifically, the proposed method combines an atlas-based approach, for coarse skull-stripping, with a deformable-surface-based approach that is guided by local intensity information and population-specific prior information learned from a set of real brain images for more localized refinement. Comprehensive quantitative evaluations were performed on the diverse large-scale populations of ADNI dataset with over 800 subjects (55∼90 years of age, multi-site, various diagnosis groups), OASIS dataset with over 400 subjects (18∼96 years of age, wide age range, various diagnosis groups), and NIH pediatrics dataset with 150 subjects (5∼18 years of age, multi-site, wide age range as a complementary age group to the adult dataset). The results demonstrate that our method consistently yields the best overall results across almost the entire human life span, with only a single set of parameters. To demonstrate its capability to work on non-human primates, the proposed method is further evaluated using a rhesus macaque dataset with 20 subjects. Quantitative comparisons with popularly used state-of-the-art methods, including BET, Two-pass BET, BET-B, BSE, HWA, ROBEX and AFNI, demonstrate that the proposed method performs favorably with superior performance on all testing datasets, indicating its robustness and effectiveness.

Multiscale segmentation of the skull in MR images for MRI-based attenuation correction of combined MR/PET

BACKGROUND AND OBJECTIVE

Combined magnetic resonance/positron emission tomography (MR/PET) is a relatively new, hybrid imaging modality. MR-based attenuation correction often requires segmentation of the bone on MR images. In this study, we present an automatic segmentation method for the skull on MR images for attenuation correction in brain MR/PET applications.

MATERIALS AND METHODS

Our method transforms T1-weighted MR images to the Radon domain and then detects the features of the skull image. In the Radon domain we use a bilateral filter to construct a multiscale image series. For the repeated convolution we increase the spatial smoothing in each scale and make the width of the spatial and range Gaussian function doubled in each scale. Two filters with different kernels along the vertical direction are applied along the scales from the coarse to fine levels. The results from a coarse scale give a mask for the next fine scale and supervise the segmentation in the next fine scale. The use of the multiscale bilateral filtering scheme is to improve the robustness of the method for noise MR images. After combining the two filtered sinograms, the reciprocal binary sinogram of the skull is obtained for the reconstruction of the skull image.

RESULTS

This method has been tested with brain phantom data, simulated brain data, and real MRI data. For real MRI data the Dice overlap ratios are 92.2%±1.9% between our segmentation and manual segmentation.

CONCLUSIONS

The multiscale segmentation method is robust and accurate and can be used for MRI-based attenuation correction in combined MR/PET.

The current situation on vascular cognitive impairment after ischemic stroke in Changsha

The objectives of the study were to explore the prevalence and effects of vascular cognitive impairment (VCI) among ischemic stroke patients and to provide a basis for prevention and treatment strategies. A stratified cluster random sampling method was performed, and 689 ischemic stroke patients (over 40 years of age) were enrolled. All of the patients had received a neuropsychological assessment battery to assess cognitive function and self-designed questionnaires to collect relevant information. According to the cognitive status, the patients were divided into two groups, a case group and a control group. The caregivers of the patients were given a questionnaire concerning the awareness of and attitudes toward VCI. In this study, we determined that the prevalence of VCI was 41.8%. Aging, paraventricular white matter lesion (WML), macroangiopathy, high levels of alcohol, a lack of hobbies, and excessive sleep were risk factors for vascular cognitive impairment no dementia (VCIND). A high level of education, manual-work, low level of alcohol use, regular health checks, a vegetable-based diet, and more fruit and milk were protective factors for VCIND. Living alone, hyperlipidemia, transient ischemic attack, a family history of stroke, and brain atrophy were risk factors of vascular dementia (VD). A high educational level, a vegetable-based diet, and tea were protective factors for VD. The general public awareness of VCI was found to be insufficient, and there was a prejudice toward and lack of funding for the care of VCI patients. The prevalence of VCI is high in ischemic stroke patients, and there are different impact factors at different stages. Despite the high prevalence of VCI, the general public awareness is limited. Appropriate prevention measures should be developed to reduce the prevalence of VCI.

Technical note: Skin thickness measurements using high-resolution flat-panel cone-beam dedicated breast CT

PURPOSE

To determine the mean and range of location-averaged breast skin thickness using high-resolution dedicated breast CT for use in Monte Carlo-based estimation of normalized glandular dose coefficients.

METHODS

This study retrospectively analyzed image data from a clinical study investigating dedicated breast CT. An algorithm similar to that described by Huang et al. ["The effect of skin thickness determined using breast CT on mammographic dosimetry," Med. Phys. 35(4), 1199-1206 (2008)] was used to determine the skin thickness in 137 dedicated breast CT volumes from 136 women. The location-averaged mean breast skin thickness for each breast was estimated and the study population mean and range were determined. Pathology results were available for 132 women, and were used to investigate if the distribution of location-averaged mean breast skin thickness varied with pathology. The effect of surface fitting to account for breast curvature was also studied.

RESULTS

The study mean (± interbreast SD) for breast skin thickness was 1.44 ± 0.25 mm (range: 0.87-2.34 mm), which was in excellent agreement with Huang et al. Based on pathology, pair-wise statistical analysis (Mann-Whitney test) indicated that at the 0.05 significance level, there were no significant difference in the location-averaged mean breast skin thickness distributions between the groups: benign vs malignant (p = 0.223), benign vs hyperplasia (p = 0.651), hyperplasia vs malignant (p = 0.229), and malignant vs nonmalignant (p = 0.172).

CONCLUSIONS

Considering this study used a different clinical prototype system, and the study participants were from a different geographical location, the observed agreement between the two studies suggests that the choice of 1.45 mm thick skin layer comprising the epidermis and the dermis for breast dosimetry is appropriate. While some benign and malignant conditions could cause skin thickening, in this study cohort the location-averaged mean breast skin thickness distributions did not differ significantly with pathology. The study also underscored the importance of considering breast curvature in estimating breast skin thickness.

Automatic MRI 2D brain segmentation using graph searching technique

Accurate and efficient segmentation of the whole brain in magnetic resonance (MR) images is a key task in many neuroscience and medical studies either because the whole brain is the final anatomical structure of interest or because the automatic extraction facilitates further analysis. The problem of segmenting brain MRI images has been extensively addressed by many researchers. Despite the relevant achievements obtained, automated segmentation of brain MRI imagery is still a challenging problem whose solution has to cope with critical aspects such as anatomical variability and pathological deformation. In the present paper, we describe and experimentally evaluate a method for segmenting brain from MRI images basing on two-dimensional graph searching principles for border detection. The segmentation of the whole brain over the entire volume is accomplished slice by slice, automatically detecting frames including eyes. The method is fully automatic and easily reproducible by computing the internal main parameters directly from the image data. The segmentation procedure is conceived as a tool of general applicability, although design requirements are especially commensurate with the accuracy required in clinical tasks such as surgical planning and post-surgical assessment. Several experiments were performed to assess the performance of the algorithm on a varied set of MRI images obtaining good results in terms of accuracy and stability.

Skull stripping of neonatal brain MRI: using prior shape information with graph cuts

In this paper, we propose a novel technique for skull stripping of infant (neonatal) brain magnetic resonance images using prior shape information within a graph cut framework. Skull stripping plays an important role in brain image analysis and is a major challenge for neonatal brain images. Popular methods like the brain surface extractor (BSE) and brain extraction tool (BET) do not produce satisfactory results for neonatal images due to poor tissue contrast, weak boundaries between brain and non-brain regions, and low spatial resolution. Inclusion of prior shape information helps in accurate identification of brain and non-brain tissues. Prior shape information is obtained from a set of labeled training images. The probability of a pixel belonging to the brain is obtained from the prior shape mask and included in the penalty term of the cost function. An extra smoothness term is based on gradient information that helps identify the weak boundaries between the brain and non-brain region. Experimental results on real neonatal brain images show that compared to BET, BSE, and other methods, our method achieves superior segmentation performance for neonatal brain images and comparable performance for adult brain images.

Semiautomatic segmentation of ventilated airspaces in healthy and asthmatic subjects using hyperpolarized 3He MRI

A segmentation algorithm to isolate areas of ventilation from hyperpolarized helium-3 magnetic resonance imaging (HP ³He MRI) is described. The algorithm was tested with HP ³He MRI data from four healthy and six asthmatic subjects. Ventilated lung volume (VLV) measured using our semiautomated technique was compared to that obtained from manual outlining of ventilated lung regions and to standard spirometric measurements. VLVs from both approaches were highly correlated (R = 0.99; P < 0.0001) with a mean difference of 3.8 mL and 95% agreement indices of −30.8 mL and 38.4 mL. There was no significant difference between the VLVs obtained through the semiautomatic approach and the manual approach. A Dice coefficient which quantified the intersection of the two datasets was calculated and ranged from 0.95 to 0.97 with a mean of 0.96 ± 0.01 (mean ± SD). VLVs obtained through the semiautomatic algorithm were also highly correlated with measurements of forced expiratory volume in one second (FEV₁) (R = 0.82; P = 0.0035) and forced vital capacity (FVC) (R = 0.95; P < 0.0001). The technique may open new pathways toward advancing more quantitative characterization of ventilation for routine clinical assessment for asthma severity as well as a number of other respiratory diseases.

Automated scan prescription for MR imaging of deformed and normal livers

PURPOSE

We propose an automated scan prescription to assess normal and deformed livers and demonstrate its efficacy in normal volunteers and in simulated deformed livers.

METHODS

Our automated scan prescription can be used to identify the upper and lower edges of the liver enables in commonly used axial slice positioning. The liver's upper edge is detected by template matching and finally identified by applying an active shape model to a sagittal projection image. The lower edge is detected using a maximum a posteriori (MAP) probability estimate that utilizes statistical information from a region of interest (ROI) placed in the liver. This places no restraints on liver shape and is therefore effective in assessing a deformed liver. Following institutional review and approval, we tested our method in 45 healthy volunteers. We also used clinical information to simulate deformed livers and tested our method with those datasets offline.

RESULTS

We could detect the upper edges within an error range of -3 to 6 mm, even without intensity correction for normal volunteers. Similar detection of the lower edges with maximum 21-mm and 7.84-mm standard deviation for normal volunteers confirmed the superior efficacy of our modified approach for deformed livers to that using our previous method. Clinical use required approximately 10 s' computational time on a Core i5 laptop with 2-GB memory.

CONCLUSION

We propose a method for automated scan prescription in magnetic resonance (MR) imaging of the liver and demonstrate the efficacy of our algorithm for evaluating deformed livers within a practical computation time. Detection of liver edges of various shapes by applying the MAP estimate combined with statistical information from the ROI demonstrated the potential clinical utility of this technique.

Dedicated breast CT: fibroglandular volume measurements in a diagnostic population

PURPOSE

To determine the mean and range of volumetric glandular fraction (VGF) of the breast in a diagnostic population using a high-resolution flat-panel cone-beam dedicated breast CT system. This information is important for Monte Carlo-based estimation of normalized glandular dose coefficients and for investigating the dependence of VGF on breast dimensions, race, and pathology.

METHODS

Image data from a clinical trial investigating the role of dedicated breast CT that enrolled 150 women were retrospectively analyzed to determine the VGF. The study was conducted in adherence to a protocol approved by the institutional human subjects review boards and written informed consent was obtained from all study participants. All participants in the study were assigned BI-RADS(®) 4 or 5 as per the American College of Radiology assessment categories after standard diagnostic work-up and underwent dedicated breast CT exam prior to biopsy. A Gaussian-kernel based fuzzy c-means algorithm was used to partition the breast CT images into adipose and fibroglandular tissue after segmenting the skin. Upon determination of the accuracy of the algorithm with a phantom, it was applied to 137 breast CT volumes from 136 women. VGF was determined for each breast and the mean and range were determined. Pathology results with classification as benign, malignant, and hyperplasia were available for 132 women, and were used to investigate if the distributions of VGF varied with pathology.

RESULTS

The algorithm was accurate to within ±1.9% in determining the volume of an irregular shaped phantom. The study mean (± inter-breast SD) for the VGF was 0.172 ± 0.142 (range: 0.012-0.719). VGF was found to be negatively correlated with age, breast dimensions (chest-wall to nipple length, pectoralis to nipple length, and effective diameter at chest-wall), and total breast volume, and positively correlated with fibroglandular volume. Based on pathology, pairwise statistical analysis (Mann-Whitney test) indicated that at the 0.05 significance level, there was no significant difference in distributions of VGF without adjustment for age between malignant and nonmalignant breasts (p = 0.41). Pairwise comparisons of the distributions of VGF in increasing order of mammographic breast density indicated all comparisons were statistically significant (p < 0.002).

CONCLUSIONS

This study used a different clinical prototype breast CT system than that in previous studies to image subjects from a different geographical region, and used a different algorithm for analysis of image data. The mean VGF estimated from this study is within the range reported in previous studies, indicating that the choice of 50% glandular weight fraction to represent an average breast for Monte Carlo-based estimation of normalized glandular dose coefficients in mammography needs revising. In the study, the distributions of VGF did not differ significantly with pathology.