Interactive surface-guided segmentation of brain MRI data

MRI segmentation is a process of deriving semantic information from volume data. For brain MRI data, segmentation is initially performed at a voxel level and then continued at a brain surface level by generating its approximation. While successful most of the time, automated brain segmentation may leave errors which have to be removed interactively by editing individual 2D slices. We propose an approach for correcting these segmentation errors in 3D modeling space. We actively use the brain surface, which is estimated (potentially wrongly) in the automated FreeSurfer segmentation pipeline. It allows us to work with the whole data set at once, utilizing the context information and correcting several slices simultaneously. Proposed heuristic editing support and automatic visual highlighting of potential error locations allow us to substantially reduce the segmentation time. The paper describes the implementation principles of the proposed software tool and illustrates its application.     

A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction

We describe a fully automated method for tissue classification, which is the segmentation into cerebral gray matter (GM), cerebral white matter (WM), and cerebral spinal fluid (CSF), and intensity non-uniformity (INU) correction in brain magnetic resonance imaging (MRI) volumes. It combines supervised MRI modality-specific discriminative modeling and unsupervised statistical expectation maximization (EM) segmentation into an integrated Bayesian framework. While both the parametric observation models and the non-parametrically modeled INUs are estimated via EM during segmentation itself, a Markov random field (MRF) prior model regularizes segmentation and parameter estimation. Firstly, the regularization takes into account knowledge about spatial and appearance-related homogeneity of segments in terms of pairwise clique potentials of adjacent voxels. Secondly and more importantly, patient-specific knowledge about the global spatial distribution of brain tissue is incorporated into the segmentation process via unary clique potentials. They are based on a strong discriminative model provided by a probabilistic boosting tree (PBT) for classifying image voxels. It relies on the surrounding context and alignment-based features derived from a probabilistic anatomical atlas. The context considered is encoded by 3D Haar-like features of reduced INU sensitivity. Alignment is carried out fully automatically by means of an affine registration algorithm minimizing cross-correlation. Both types of features do not immediately use the observed intensities provided by the MRI modality but instead rely on specifically transformed features, which are less sensitive to MRI artifacts. Detailed quantitative evaluations on standard phantom scans and standard real-world data show the accuracy and robustness of the proposed method. They also demonstrate relative superiority in comparison to other state-of-the-art approaches to this kind of computational task: our method achieves average Dice coefficients of 0.93 ± 0.03 (WM) and 0.90 ± 0.05 (GM) on simulated mono-spectral and 0.94 ± 0.02 (WM) and 0.92 ± 0.04 (GM) on simulated multi-spectral data from the BrainWeb repository. The scores are 0.81 ± 0.09 (WM) and 0.82 ± 0.06 (GM) and 0.87 ± 0.05 (WM) and 0.83 ± 0.12 (GM) for the two collections of real-world data sets-consisting of 20 and 18 volumes, respectively-provided by the Internet Brain Segmentation Repository.     

Automated segmentation of human brain MR images using a multi-agent approach

Image interpretation consists in finding a correspondence between radiometric information and symbolic labeling with respect to specific spatial constraints. It is intrinsically a distributed process in terms of goals to be reached, zones in the image to be processed and methods to be applied. To cope the the difficulty inherent in this process, several information processing steps are required to gradually extract information. In this paper we advocate the use of situated cooperative agents as a framework for managing such steps. Dedicated agent behaviors are dynamically adapted depending on their position in the image, of their topographic relationships and of the radiometric information available. The information collected by the agents is gathered, shared via qualitative maps, or used as soon as available by acquaintances. Incremental refinement of interpretation is obtained through a coarse to fine strategy. Our work is essentially focused on radiometry-based tissue interpretation where knowledge is introduced or extracted at several levels to estimate models for tissue-intensity distribution and to cope with noise, intensity non-uniformity and partial volume effect. Several experiments on phantom and real images were performed. A complete volume can be segmented in less than 5 min with about 0.84% accuracy of the segmented reference. Comparison with other techniques demonstrates the potential interest of our approach for magnetic resonance imaging (MRI) brain scan interpretation.     

Neurodevelopmental MRI brain templates for children from 2 weeks to 4 years of age

Spatial normalization and segmentation of pediatric brain magnetic resonance images (MRI) data with adult templates may impose biases and limitations in pediatric neuroimaging work. To remedy this issue, we created a single database made up of a series of pediatric, age-specific MRI average brain templates. These average, age-specific templates were constructed from brain scans of individual children obtained from two sources: (1) the NIH MRI Study of Normal Brain Development and (2) MRIs from University of South Carolina's McCausland Brain Imaging Center. Participants included young children enrolled at ages ranging from 8 days through 4.3 years of age. A total of 13 age group cohorts spanning the developmental progression from birth through 4.3 years of age were used to construct age-specific MRI brain templates (2 weeks, 3, 4.5, 6, 7.5, 9, 12, 15, 18 months, 2, 2.5, 3, 4 years). Widely used processing programs (FSL, SPM, and ANTS) extracted the brain and constructed average templates separately for 1.5T and 3T MRI volumes. The resulting age-specific, average templates showed clear changes in head and brain size across ages and between males and females, as well as changes in regional brain structural characteristics (e.g., myelin development). This average brain template database is available via our website (http://jerlab.psych.sc.edu/neurodevelopmentalmridatabase) for use by other researchers. Use of these age-specific, average pediatric brain templates by the research community will enhance our ability to gain a clearer understanding of the early postnatal development of the human brain in health and in disease.     

Developing a virtual patient record using XML and web-based workflow technologies

Virtual patient records (VPR) provide a means for integrated access to patient information that may be scattered around different healthcare settings. Within the boundaries of a health district providing all levels of care, this concept can be implemented in a corporate Intranet environment to support longitudinal patient care activities across the participating healthcare providers. In this context, a VPR implementation enables autonomous healthcare providers to operate in a cooperative working environment and apply continuity of care. Workflow systems bring this collaboration and cooperation into effect by automatically routing the medical information needed by authorised actors in a healthcare process. This paper presents a VPR framework that allows integrating geographically dispersed medical information within a health district and enhancing collaboration and coordination of authorised workgroups by means of a web-based workflow system. An implementation of the proposed framework is also presented.     

一种基于ITK脑部MRI混合分割方法的设计与实现

背景：由于脑部MR图像中信息对比度不高,各种脑部组织的形状复杂等特点,分割方法的选择比较困难,单一的算法很难获得满意的分割结果。 目的：针对脑部MRI的特点综合利用现有的算法开发和定制有效的分割应用算法。 方法：根据邻域连接和Canny水平集分割算法的优缺点,结合图像特征,用邻域连接方法的分割结果作为Canny水平集分割算法的先验分割模型,借以确定出Canny算法的下限阈值,从而完成两种算法的混合分割。 结果与结论：采用实验所用混合方法得到的白质和灰质的分割结果,经与专家手工分割结果对比,证明该方法取得了较好的分割效果,从而证明综合利用现有的算法,不仅避免了重复劳动,还能开发和定制出更加有效的分割应用算法,具备很好的应用潜力。     

A framework for building cooperative software agents in medical applications.

Exploiting the information technology may have a great impact on improving cooperation and interoperability among the different professionals taking part to the process of delivering health care services. New paradigms are therefore being devised considering software systems as autonomous agents able to help professionals in accomplishing their duties. To this aim those systems should encapsulate the skills for solving a given set of tasks and possess the social ability to cooperate in order to fetch the required information and knowledge. This paper illustrates a methodology facilitating the development of interoperable intelligent software agents for medical applications and proposes a generic computational model for implementing them. That model may be specialized in order to support all the different information and knowledge related requirements of a Hospital Information System. The architecture is being tested for implementing a prototype system able to coordinate the joint efforts of the professionals involved in managing patients affected by Acute Myeloid Leukemia.     

神经网络技术在磁共振图像分割中的应用

神经网络具有类似人脑的并行处理结构 ,能够模拟人脑对刺激的反应方式进行工作 ,可以用于解决磁共振图像分割问题。近来 ,涌现出许多神经网络磁共振图像分割方法的应用报道 ,这些神经网络包括传统的确定型神经网络 ,以及结合模糊逻辑、混沌理论或者小波理论等新理论的混合神经网络。本文针对这些磁共振图像分割方法进行综述。     

基于三重注意力的脑肿瘤图像分割网络

脑肿瘤图像分割问题是脑肿瘤临床诊断和治疗脑肿瘤疾病计算机辅助诊断的基础.针对脑肿瘤MRI图像分割网络深度过深和局部与全局特征信息联系匮乏导致图像分割精度降低等问题,提出一种基于三重注意力的脑肿瘤图像分割网络.首先,借鉴残差结构,将原始图像分割网络结构的编码层和解码层中的卷积模块替换为深度残差模块,解决网络加深带来的梯度...     

Statistical morphological skull stripping of adult and infant MRI data

This paper describes a novel automatic statistical morphology skull stripper (SMSS) that uniquely exploits a statistical self-similarity measure and a 2-D brain mask to delineate the brain. The result of applying SMSS to 20 MRI data set volumes, including scans of both adult and infant subjects is also described. Quantitative performance assessment was undertaken with the use of brain masks provided by a brain segmentation expert. The performance is compared with an alternative technique known as brain extraction tool. The results suggest that SMSS is capable of skull-stripping neurological data with small amounts of over- and under-segmentation.     

点对称距离模糊C均值聚类算法在脑部MRI图像分割中的应用

背景：在传统的图像分割方法中,模糊C均值聚类算法应用十分广泛。 目的：将改进的模糊C均值聚类算法应用到MRI图像的分割中,提高MRI图像分割的准确度。 方法：针对传统的基于Minkowski距离的模糊C均值聚类算法,提出了基于点对称距离的模糊C均值聚类算法,并将其运用到了脑部MRI图像分割中。 结果与结论：实验结果表明,与模糊C均值聚类算法相比,点对称距离的模糊C均值聚类算法有明显的优势。     

Age-specific MRI templates for pediatric neuroimaging

This study created a database of pediatric age-specific magnetic resonance imaging (MRI) brain templates for normalization and segmentation. Participants included children from 4.5 through 19.5 years, totaling 823 scans from 494 subjects. Open-source processing programs (FMRIB Software Library, Statistical Parametric Mapping, Advanced Normalization Tools [ANTS]) constructed head, brain, and segmentation templates in 6-month intervals. The tissue classification (white matter [WM], gray matter [GM], cerebrospinal fluid) showed changes over age similar to previous reports. A volumetric analysis of age-related changes in WM and GM based on these templates showed expected increase/decrease pattern in GM and an increase in WM over the sampled ages. This database is available for use for neuroimaging studies (http://jerlab.psych.sc.edu/neurodevelopmentalmridatabase).     

A new segmentation algorithm for knowledge acquisition in tissue-characterizing magnetic resonance imaging

Tissue-characterizing magnetic resonance imaging (MRI) is a new imaging method for differentiation and biochemical characterization of tissue based on multidimensional MR-parameter information. To support knowledge acquisition in tissue-characterizing MRI, a new segmentation algorithm has been developed by using clustering techniques. The visualization of the complex biochemical MR-parameter information is performed by extraction of regions with similar biochemical properties. The clustering algorithm leads to an easy and comfortable handling of the complex tissue-characteristic MR information and supports knowledge acquisition for knowledge-based tissue characterization.     

Artificial intelligence and brain theory: Unities and diversities

This review article synthesizes studies ofartificial intelligence (AI) andbrain theory (BT). In the control ofmovement, AI offers insight into overallplanning of behavior; while control theory enables BT to modelfeedback andfeedforward adjustments by the spinal cord, brainstem, and cerebellum. We stressaction-oriented perception—analyzing perception in terms of preparation for interaction with the world, and offer a new concept of aschema as the internal representation of an “object” in the sense of a domain of interaction. A schema comprises input-matching routines, action routines, and competition and cooperation routines. The internal representation of the world is then given by a “collage” of tuned and activated schemas.Segmentation of input andregion labeling are offered as two mechanisms in the activation of a suitable “collage.” We see a number of studies that offer hope of a unified theory ofcompetition and cooperation within a single subsystem: brain theory models of the reticular formation, of the frog midbrain visual system, and of segmentation on prewired features; and AI models of segmentation on ad hoc features, and of region labeling. We then turn to the modeling of a set of brain regions as acooperative computation system—a distributed structure in which each system has its own “goal structure” for selecting information to act on from its environment, and for transmitting the results to suitable receivers. We use this to describe a few findings ofneurology. We then sample AI studies of computerunderstanding of natural language, ascribing particular significance to a speech understanding system configured as a cooperative computation system. The literatures of AI and BT hardly overlap at all, and differ widely in choice of both problem and method. The aim of this article is to overcome these diversities by extracting contributions from extant AI and BT that can be melded into the creation of atop-down brain theory: the building of a coherent model of cooperative computation within which the computational roles of brain regions, and of neurons within those regions, can be analyzed.     

Pseudo-Label-Assisted Self-Organizing Maps for Brain Tissue Segmentation in Magnetic Resonance Imaging

Brain tissue segmentation in magnetic resonance imaging volumes is an important image processing step for analyzing the human brain. This paper presents a novel approach named Pseudo-Label Assisted Self-Organizing Map (PLA-SOM) that enhances the result produced by a base segmentation method. Using the output of a base method, PLA-SOM calculates pseudo-labels in order to keep inter-class separation and intra-class compactness in the training phase. For the mapping phase, PLA-SOM uses a novel fuzzy function that combines feature space learned by the SOM’s prototypes, topological ordering from the map, and spatial information from a brain atlas. We assessed PLA-SOM performance on synthetic and real MRIs of the brain, obtained from the BrainWeb and the Internet Brain Image Repository datasets. The experimental results showed evidence of segmentation improvement achieved by the proposed method over six different base methods. The best segmentation improvements reported by PLA-SOM on synthetic brain scans are 11%, 6%, and 4% for the tissue classes cerebrospinal fluid, gray matter, and white matter, respectively. On real brain scans, PLA-SOM achieved segmentation enhancements of 15%, 5%, and 12% for cerebrospinal fluid, gray matter, and white matter, respectively.

     

Automatic Organ Segmentation for CT Scans Based on Super-Pixel and Convolutional Neural Networks

Accurate segmentation of specific organ from computed tomography (CT) scans is a basic and crucial task for accurate diagnosis and treatment. To avoid time-consuming manual optimization and to help physicians distinguish diseases, an automatic organ segmentation framework is presented. The framework utilized convolution neural networks (CNN) to classify pixels. To reduce the redundant inputs, the simple linear iterative clustering (SLIC) of super-pixels and the support vector machine (SVM) classifier are introduced. To establish the perfect boundary of organs in one-pixel-level, the pixels need to be classified step-by-step. First, the SLIC is used to cut an image into grids and extract respective digital signatures. Next, the signature is classified by the SVM, and the rough edges are acquired. Finally, a precise boundary is obtained by the CNN, which is based on patches around each pixel-point. The framework is applied to abdominal CT scans of livers and high-resolution computed tomography (HRCT) scans of lungs. The experimental CT scans are derived from two public datasets (Sliver 07 and a Chinese local dataset). Experimental results show that the proposed method can precisely and efficiently detect the organs. This method consumes 38 s/slice for liver segmentation. The Dice coefficient of the liver segmentation results reaches to 97.43%. For lung segmentation, the Dice coefficient is 97.93%. This finding demonstrates that the proposed framework is a favorable method for lung segmentation of HRCT scans.     

3D asymmetric expectation-maximization attention network for brain tumor segmentation

Automatic brain tumor segmentation on MRI is a prerequisite to provide a quantitative and intuitive assistance for clinical diagnosis and treatment. Meanwhile, 3D deep neural network related brain tumor segmentation models have demonstrated considerable accuracy improvement over corresponding 2D methodologies. However, 3D brain tumor segmentation models generally suffer from high computation cost. Motivated by a recently proposed 3D dilated multi-fiber network (DMF-Net) architecture that pays more attention to reduction of computation cost, we present in this work a novel encoder-decoder neural network, ie a 3D asymmetric expectation-maximization attention network (AEMA-Net), to automatically segment brain tumors. We modify DMF-Net by introducing an asymmetric convolution block into a multi-fiber unit and a dilated multi-fiber unit to capture more powerful deep features for the brain tumor segmentation. In addition, AEMA-Net further incorporates an expectation-maximization attention (EMA) module into the DMF-Net by embedding the EMA block in the third stage of skip connection, which focuses on capturing the long-range dependence of context. We extensively evaluate AEMA-Net on three MRI brain tumor segmentation benchmarks of BraTS 2018, 2019 and 2020 datasets. Experimental results demonstrate that AEMA-Net outperforms both 3D U-Net and DMF-Net, and it achieves competitive performance compared with the state-of-the-art brain tumor segmentation methods.     

Age-Specific MRI Templates for Pediatric Neuroimaging

This study created a database of pediatric age-specific magnetic resonance imaging (MRI) brain templates for normalization and segmentation. Participants included children from 4.5 through 19.5 years, totaling 823 scans from 494 subjects. Open-source processing programs (FMRIB Software Library, Statistical Parametric Mapping, Advanced Normalization Tools [ANTS]) constructed head, brain, and segmentation templates in 6-month intervals. The tissue classification (white matter [WM], gray matter [GM], cerebrospinal fluid) showed changes over age similar to previous reports. A volumetric analysis of age-related changes in WM and GM based on these templates showed expected increase/decrease pattern in GM and an increase in WM over the sampled ages. This database is available for use for neuroimaging studies (http://jerlab.psych.sc.edu/neurodevelopmentalmridatabase).     

An Artificial Immune-Activated Neural Network Applied to Brain 3D MRI Segmentation

In this paper, a new neural network model inspired by the biological immune system functions is presented. The model, termed Artificial Immune-Activated Neural Network (AIANN), extracts classification knowledge from a training data set, which is then used to classify input patterns or vectors. The AIANN is based on a neuron activation function whose behavior is conceptually modeled after the chemical bonds between the receptors and epitopes in the biological immune system. The bonding is controlled through an energy measure to ensure accurate recognition. The AIANN model was applied to the segmentation of 3-dimensional magnetic resonance imaging (MRI) data of the brain and a contextual basis was developed for the segmentation problem. Evaluation of the segmentation results was performed using both real MRI data obtained from the Center for Morphometric Analysis at Massachusetts General Hospital and simulated MRI data generated using the McGill University BrainWeb MRI simulator. Experimental results demonstrated that the AIANN model attained higher average results than those obtained using published methods for real MRI data and simulated MRI data, especially at low levels of noise.