Name: automated midline shift and intracranial pressure estimation based on brain ct images
Uploaded: 2013-04-13T14:00:00
Description: Watch this Scientific Journal Video about Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images at JoVE.com

该材料是根据工作部分由美国国家科学基金会的支持下批准号：IIS0758410。卡罗来纳医疗保健系统提供的数据。

1。方法概述建议的框架创伤性脑损伤（TBI）患者的脑CT图像进行处理，自动计算在病理情况下，中线移位，使用它，以及其他提取的信息来预测颅内压（ICP）。 图1显示了整个示意图框架。自动化的中线偏移测量可以分为三个步骤。首先，理想的中线的大脑， 也就是受伤前正中线，通过分层搜索根据头骨的对称性和组织功能3。其次，脑室系统分割?...

<ol>
	<li>Langlois, J. A., Rutland-Brown, W., Thomas, K. E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=.">.</a> Traumatic brain injury in the united states: emergency department visits, hospitalizations, and deaths. , (2006).</li><li>Moore, E. E., Feliciano, D. V., Mattox, K. L. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=.">.</a> Trauma. , (2003).</li><li>Chen, W., Smith, R., Ji, S. Y., Ward, K. R., Najarian, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Automated+Ventricular+Systems+Segmentation+in+Brain+CT+Images+by+Combining+Low-level+Segmentation+and+High-level+Template+Matching.">Automated Ventricular Systems Segmentation in Brain CT Images by Combining Low-level Segmentation and High-level Template Matching.</a> BMC Medical Informatics and Decision Making. 9, (2009).</li><li>Chen, W., Najarian, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Segmentation+of+Ventricles+in+Brain+CT+Images+Using+Gaussian+Mixture+Model+Method.">Segmentation of Ventricles in Brain CT Images Using Gaussian Mixture Model Method.</a> , 15-20 (2009).</li><li>Chen, W., Ward, K. R., Najarian, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Actual+Midline+Estimation+from+Brain+CT+Scan+Using+Multiple+Regions+Shape+Matching.">Actual Midline Estimation from Brain CT Scan Using Multiple Regions Shape Matching.</a> , 2552-2555 (2010).</li><li>Chen, W., Cockrell, C., Ward, K. R., Najarian, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Intracranial+Pressure+Level+Prediction+in+Traumatic+Brain+Injury+by+Extracting+Features+from+Multiple+Sources+and+Using+Machine+Learning+Methods.">Intracranial Pressure Level Prediction in Traumatic Brain Injury by Extracting Features from Multiple Sources and Using Machine Learning Methods.</a> , 510-515 (2010).</li><li>Greenspan, H., Ruf, A., Goldberger, J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Constrained+Gaussian+mixture+model+framework+for+automatic+segmentation+of+MR+brain+images.">Constrained Gaussian mixture model framework for automatic segmentation of MR brain images.</a> IEEE Trans. Med. Imaging. 25 (9), 1233-1245 (2006).</li><li>Belongie, S., Malik, J., Puzicha, J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Shape+matching+and+object+recognition+using+shape+contexts.">Shape matching and object recognition using shape contexts.</a> IEEE Trans. Pattern Anal. Mach. Intell. 24, 509-522 (2002).</li><li>Weszaka, J. S., Dyer, C. R., Rosenfeld, A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=A+comparative+study+of+texture+measures+for+terrain+classification.">A comparative study of texture measures for terrain classification.</a> IEEE Trans. on Syst., Man, Cyber. , (1976).</li><li>Kingsbury, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Complex+wavelets+for+shift+invariant+analysis+and+filtering+of+signals.">Complex wavelets for shift invariant analysis and filtering of signals.</a> Applied and Computational Harmonic Analysis. 10 (3), 234-253 (2002).</li><li>Mierswa, I., Wurst, M., Klinkenberg, R., Scholz, M., Euler, T. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=+Yale:+Rapid+prototyping+for+complex+data+mining+tasks."> Yale: Rapid prototyping for complex data mining tasks.</a> , 935-940 (2006).</li></ol>

在这项研究中，直观和灵活的框架建议，以解决具有挑战性的问题：在CT图像的中线移位和ICP预测的基础上提取的特征的估计。评价结果表明，所提出的方法的有效性。据我们所知，这是第一次有系统的研究，解决了这两个问题。我们注意到，总体框架的基础上，有许多潜在的改进，可以实现。例如，在建议的分割，低层次分割和高层次的认知是分开的，目前还没有反馈，从高层次到低层次分割?...

每年有大约140万相关的创伤性脑损伤（TBI）急诊情况下，在美国，其中，超过50,000名死亡1。通常伴随着严重的脑外伤血肿和脑组织肿胀的症状，如颅内压（ICP）的增加。这些结果在脑灌注压降低，脑血流，脑损伤将额外的风险。严重ICP增长的可能是致命的，所以，监测ICP TBI患者是至关重要的。通常，这要求直接进入大脑的压力进行监测，有风险的程序只能在专门的医疗中心进行的患者的留置导管的位置。该过程还涉及风险，如感染。然而，一些迹象显示，可能是显着升高的ICP医疗成像。特别是，中线移位往往是与增加在ICP和可以捕获从脑吨omography（CT）图像。因此，这些图像提供了一个机会，ICP升高的非侵入性的检测，它可以用来作为一个预检颅环钻步骤之前。 CT成像仍然是TBI评估在所有其他的成像方式， 如 MRI初步的金标准，由于其较高的速度和相对低廉的成本2。此外，CT检查并不需要严格的病人不动，有利于揭示严重的异常如骨骨折和血肿。中线移位而CT通常用于检测的伤害在大脑中，根据目前的技术，还没有自动测量，因此医师必须评估这一重要因素，通过视觉检查。不准确或不一致CT解释往往是与人类视觉系统的性质和结构复杂的大脑。虽然小中线的变化是难以捉摸的，他们往往是非常宝贵的脑损伤评估，在P关节损伤之前，患者的病情在早期阶段会变得更加严重。在光谱的另一端，大中线移位建议高度ICP升高，更严重的TBI。然而，这是一个非常具有挑战性的任务，为人类目视检查CT图像和定量预测水平的ICP。由于在自动计算技术的进步，从CT图像，如中线结构移位，血肿量，脑CT图像和纹理特征提取，可以精确地测量并自动采用先进的图像处理方法。然而，ICP，中线移位以及其他功能，如出血程度之间的关系，从CT图像的质感没有被探索。本文的计算框架被提出来测量中线移位，测量以及其他生理/解剖特征的脑CT图像，然后预测的程度，ICP，非侵入性的使用机器学习技术。

automated midline shift and intracranial pressure estimation based on brain ct images

在本文中，我们提出了一个自动化系统主要基于计算机断层扫描（CT）图像由两个主要部分组成：中线移位估计和颅内压（ICP）的预先筛分系统。估计中线移位，首先的理想中线的对称性颅骨和脑CT扫描的解剖特征的基础上进行估计。然后，分割进行从CT扫描的心室和用作识别的实际中线通过形状匹配的导向。这些过程模仿由医师的测量过程，并已显示出了有前途的结果在评价。在第二部分中，提取相关的ICP更多的功能，如纹理信息，从CT扫描和其他记录的功能，如年龄，损伤严重度评分估计ICP血液量也成立。机器学习技术，包括特征选择和分类，如支持向量机（SVM），使用RapidMiner，建立预测模型。的预测评价显示了潜在的有用的模型。估计理想的中线结构移位及预测ICP水平，可作为一个快速预筛选步骤的医生作出决定，因此，建议或反对侵入颅内压监测。

测试CT数据集提供了卡罗来纳州医疗保健系统（CHS）根据机构审查委员会的批准。所有受试者被诊断为轻度至重度脑外伤时，首先送往医院接受治疗。对于每一个病人，被记录的ICP值每隔一小时，用ICP心室区域内之前和之后得到的CT扫描探针。要关联的的ICP价值与每一个CT扫描，CT扫描的时间平均距离最近的两个测量ICP，这两者都是在一个小时内的CT扫描。然后分配在CT扫描的时间的平均值作为估计?...

Watch this Scientific Journal Video about Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images at JoVE.com

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

一个自动化的中线移位估计和颅内压（ICP）计算机断层扫描（CT）图像与创伤性脑损伤（TBI）患者的预先筛分系统的基础上，提出一种利用图像处理和机器学习技术。

根据脑CT图像的自动中线移位和颅内压的估计

In this paper we present an automated system based mainly on the computed tomography (CT) images consisting of two main components: the midline shift ...

Research

JoVE Journal

Medicine

Epidural Intracranial Pressure Measurement in Rats Using a Fiber-optic Pressure Transducer

硬膜外颅内压测量中使用的光纤压力传感器的大鼠

Elevated intracranial pressure (ICP) is a significant problem in several forms of ischemic brain injury including stroke, traumatic brain injury and ...

科研

医学

A Novel High-resolution In vivo Imaging Technique to Study the Dynamic Response of Intracranial Structures to Tumor Growth and Therapeutics

A Novel High-resolution In vivo Imaging Technique to Study the Dynamic Response of Intracranial Structures to Tumor Growth and Therapeutics

一种新型的高分辨率<em&gt;在体内</em&gt;成像技术研究肿瘤生长及治疗颅内结构的动态响应

We have successfully integrated previously established Intracranial window (ICW) technology 1-4 with intravital 2-photon confocal microscopy to develop a ...

Creating Anatomically Accurate and Reproducible Intracranial Xenografts of Human Brain Tumors

创建精确的解剖学和人脑肿瘤的重现性颅内移植瘤

Orthotopic tumor models are currently the best way to study the characteristics of a tumor type, with and without intervention, in the context of a live ...

Assessing Cortical Cerebral Microinfarcts on High Resolution MR Images

评估皮层脑Microinfarcts高分辨率核磁共振图像

Cerebral microinfarcts are frequent findings in the post-mortem human brain, and are related to cognitive decline and dementia. Due to their small sizes ...

Proximal Cadaveric Femur Preparation for Fracture Strength Testing and Quantitative CT-based Finite Element Analysis

近端股骨尸制备基于CT的断裂强度测试和定量的有限元分析

Cadaveric fracture testing is routinely used to understand factors that affect proximal femur strength.  Because ex vivo biological tissues are prone to ...

Determining Glucose Metabolism Kinetics Using 18F-FDG Micro-PET/CT

Determining Glucose Metabolism Kinetics Using 18F-FDG Micro-PET/CT

确定葡萄糖代谢动力学研究<sup&gt; 18</sup&gt; F-FDG微PET / CT

This paper describes the use of 18F-FDG and micro-PET/CT imaging to determine in vivo glucose metabolism kinetics in mice (and is transferable to rats). ...

Improved Method for the Establishment of an In Vitro Blood-Brain Barrier Model Based on Porcine Brain Endothelial Cells

Improved Method for the Establishment of an In Vitro Blood-Brain Barrier Model Based on Porcine Brain Endothelial Cells

一种基于猪脑内皮细胞的体外血脑屏障模型的改进方法

The aim of this protocol presents an optimized procedure for the purification and cultivation of pBECs and to establish in vitro blood-brain barrier (BBB) ...

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT

胃癌腹膜转移的基因调控及靶向治疗: 双能量 ct 与 PET/ct 的影像学研究

Gastric cancer remains fourth in cancer incidence worldwide with a five-year survival of only 20%-30%. Peritoneal metastasis is the most frequent type of ...

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

基于Swin变压器的超声图像甲状腺结节检测模型

In recent years, the incidence of thyroid cancer has been increasing. Thyroid nodule detection is critical for both the detection and treatment of thyroid ...

Automated Processor for Clinical-Scale CAR-T Cell Manufacturing

Chimeric Antigen Receptor T Cell Manufacturing on an Automated Cell Processor

Advancements in CAR-T Cell Manufacturing and Gene Therapy Production (Video) | JoVE

在自动化细胞处理器上制造嵌合抗原受体T细胞

Chimeric antigen receptor (CAR)-T cells represent a promising immunotherapeutic approach for the treatment of various malignant and non-malignant ...