共查询到20条相似文献,搜索用时 15 毫秒
1.
?rjan Bergmann Oddvar Christiansen Johan Lie Arvid Lundervold 《Journal of digital imaging》2009,22(3):297-308
During the last ten years or so, diffusion tensor imaging has been used in both research and clinical medical applications.
To construct the diffusion tensor images, a large set of direction sensitive magnetic resonance image (MRI) acquisitions are
required. These acquisitions in general have a lower signal-to-noise ratio than conventional MRI acquisitions. In this paper,
we discuss computationally effective algorithms for noise removal for diffusion tensor magnetic resonance imaging (DTI) using
the framework of 3-dimensional shape-adaptive discrete cosine transform. We use local polynomial approximations for the selection
of homogeneous regions in the DTI data. These regions are transformed to the frequency domain by a modified discrete cosine
transform. In the frequency domain, the noise is removed by thresholding. We perform numerical experiments on 3D synthetical
MRI and DTI data and real 3D DTI brain data from a healthy volunteer. The experiments indicate good performance compared to
current state-of-the-art methods. The proposed method is well suited for parallelization and could thus dramatically improve
the computation speed of denoising schemes for large scale 3D MRI and DTI. 相似文献
2.
Understanding the levator ani complex architecture is of major clinical relevance. The aim of this study was to determine the feasibility of magnetic resonance (MR) fiber tractography with diffusion tensor imaging (DTI) as a tool for the three-dimensional (3D) representation of normal subdivisions of the levator ani. Ten young nulliparous female volunteers underwent DTI at 1.5 T MR imaging. Diffusion-weighted axial sequence of the pelvic floor was performed with additional T2-weighted multiplanar sequences for anatomical reference. Fiber tractography for visualization of each Terminologia Anatomica-listed major levator ani subdivision was performed. Numeric muscular fibers extracted after tractography were judged as accurate when localized within the boundaries of the muscle, and inaccurate when projecting out of the boundaries of the muscle. From the fiber tracking of each subdivision the number of numeric fibers (inaccurate and accurate) and a score (from 3 to 0) of the adequacy of the 3D representation were calculated. All but two volunteers completed the protocol. The mean number of accurate fibers was 17 ± 2 for the pubovisceralis, 14 ± 6 for the puborectalis and 1 ± 1 for the iliococcygeus. The quality of the 3D representation was judged as good (score = 2) for the pubovisceralis and puborectalis, and inaccurate (score = 0) for the iliococcygeus. Our study is the first step to a 3D visualization of the three major levator ani subdivisions, which could help to better understand their in vivo functional anatomy. 相似文献
3.
目的 探讨MR扩散张量成像(DTI)和纤维束示踪技术在经阴道分娩初产妇肛提肌损伤评价中的应用价值,为产后盆底康复治疗及盆腔器官脱垂的预防提供客观依据。方法 纳入2014年6月—2015年1月在天津市第一中心医院经阴道自然分娩后6个月初产妇50名(观察组),无症状未孕未产志愿者33名(对照组)进行前瞻性研究。受试者行盆底横断面、冠状面FSE T2WI MR及DTI检查。对DTI图像进行后处理获得肛提肌各分支(耻骨内脏肌、髂尾肌)的3D肌肉纤维束图像,并评价其纤维示踪的精确性,对能够得到较为精确纤维束示踪图像者测量其各向异性分数(FA)、表观扩散系数(ADC)值。应用FSE T2WI MRI影像评价产妇肛提肌损伤情况,并将其分为耻骨内脏肌无损伤组、耻骨内脏肌损伤组,采用方差分析比较对照组、无损伤组及损伤组间FA、ADC值的差异。结果 2组受试者均获得较为精确的耻骨内脏肌3D肌肉纤维束图像及对应的FA及ADC值,而髂尾肌3D肌肉纤维束图像均不精确。12例(24.0%,12/50)产妇存在耻骨内脏肌损伤,其中9例表现为单侧部分缺损,3例表现为双侧萎缩;4例(8.0%,4/50)产妇存在髂尾肌损伤,均表现为单侧部分缺损。对照组未发现肛提肌损伤。对照组、耻骨内脏肌无损伤组和损伤组耻骨内脏肌的FA值分别为0.49±0.08、0.52±0.11、0.53±0.13,ADC值分别为(1.79±0.29)×10-3 mm2/s、(1.75±0.34)×10-3 mm2/s、(1.93±0.35)×10-3 mm2/s,差异均无统计学意义(F=1.217、1.747, P值均>0.05)。结论 DTI纤维束成像能够3D显示耻骨内脏肌纤维束结构,但髂尾肌的显示较为困难。目前DTI尚不能准确定量诊断肛提肌损伤情况。 相似文献
4.
Daniel Schwarz Petr ?toura? Martin Komenda Hana Harazim Martina Kosinová Jakub Gregor Richard H?lek Olga Smékalová Ivo K?ikava Roman ?toudek Ladislav Du?ek 《Journal of medical Internet research》2013,15(7)
Background
Medical Faculties Network (MEFANET) has established itself as the authority for setting standards for medical educators in the Czech Republic and Slovakia, 2 independent countries with similar languages that once comprised a federation and that still retain the same curricular structure for medical education. One of the basic goals of the network is to advance medical teaching and learning with the use of modern information and communication technologies.Objective
We present the education portal AKUTNE.CZ as an important part of the MEFANET’s content. Our focus is primarily on simulation-based tools for teaching and learning acute medicine issues.Methods
Three fundamental elements of the MEFANET e-publishing system are described: (1) medical disciplines linker, (2) authentication/authorization framework, and (3) multidimensional quality assessment. A new set of tools for technology-enhanced learning have been introduced recently: Sandbox (works in progress), WikiLectures (collaborative content authoring), Moodle-MEFANET (central learning management system), and Serious Games (virtual casuistics and interactive algorithms). The latest development in MEFANET is designed for indexing metadata about simulation-based learning objects, also known as electronic virtual patients or virtual clinical cases. The simulations assume the form of interactive algorithms for teaching and learning acute medicine. An anonymous questionnaire of 10 items was used to explore students’ attitudes and interests in using the interactive algorithms as part of their medical or health care studies. Data collection was conducted over 10 days in February 2013.Results
In total, 25 interactive algorithms in the Czech and English languages have been developed and published on the AKUTNE.CZ education portal to allow the users to test and improve their knowledge and skills in the field of acute medicine. In the feedback survey, 62 participants completed the online questionnaire (13.5%) from the total 460 addressed. Positive attitudes toward the interactive algorithms outnumbered negative trends.Conclusions
The peer-reviewed algorithms were used for conducting problem-based learning sessions in general medicine (first aid, anesthesiology and pain management, emergency medicine) and in nursing (emergency medicine for midwives, obstetric analgesia, and anesthesia for midwifes). The feedback from the survey suggests that the students found the interactive algorithms as effective learning tools, facilitating enhanced knowledge in the field of acute medicine. The interactive algorithms, as a software platform, are open to academic use worldwide. The existing algorithms, in the form of simulation-based learning objects, can be incorporated into any educational website (subject to the approval of the authors). 相似文献5.
David A. Gutman Matthew Magnuson Waqas Majeed Orion P. Keifer Jr Michael Davis Kerry J. Ressler Shella Keilholz 《Brain structure & function》2013,218(2):527-537
As the power of studying mouse genetics and behavior advances, research tools to examine systems level connectivity in the mouse are critically needed. In this study, we compared statistical mapping of the olfactory system in adult mice using manganese-enhanced MRI (MEMRI) and diffusion tensor imaging (DTI) with probabilistic tractography. The primary goal was to determine whether these complementary techniques can determine mouse olfactory bulb (OB) connectivity consistent with known anatomical connections. For MEMRI, 3D T1-weighted images were acquired before and after bilateral nasal administration of MnCl2 solution. Concomitantly, high-resolution diffusion-tensor images were obtained ex vivo from a second group of mice and processed with a probabilistic tractography algorithm originating in the OB. Incidence maps were created by co-registering and overlaying data from the two scan modalities. The resulting maps clearly show pathways between the OB and amygdala, piriform cortex, caudate putamen, and olfactory cortex in both the DTI and MEMRI techniques that are consistent with the known anatomical connections. These data demonstrate that MEMRI and DTI are complementary, high-resolution neuroimaging tools that can be applied to mouse genetic models of olfactory and limbic system connectivity. 相似文献
6.
Estimation of white matter connectivity based on a three-dimensional directional diffusion function in diffusion tensor MRI 总被引:1,自引:0,他引:1
Kumazawa S Yoshiura T Arimura H Mihara F Honda H Higashida Y Toyofuku F 《Medical physics》2006,33(12):4643-4652
Diffusion tensor (DT) magnetic resonance imaging (MRI) provides the directional information of local neuronal fibers, and has been used to estimate the neuroanatomical connectivity in the cerebral white matter. Several methods for white matter tractography have been developed based on DT-MRI. However, it has been difficult to estimate the white matter tract pathways in the fiber crossing and branching region because of the ambiguity of the principal eigenvector and/or low anisotropy due to the partial volume effect. In this paper, we proposed a new method for white matter tractography, which permits fiber tract branching and passing through crossing regions. Our tractography method is based on a three-dimensional (3D) directional diffusion function (DDF), which was given by a 3D anisotropic Gaussian function defined by normalized three eigenvalues and their corresponding eigenvectors of DT. The DDF was used for generation of a 3D directional diffusion field and for determination of the connectivity between the voxels in fiber tracking. To extract the white matter tract region, DDF-based tractography (DDFT) method used the directional diffusion field instead of a threshold fractional anisotropy map, which has been used in the conventional methods, so that low anisotropy voxels in the branching and crossing regions may be included. We applied the DDFT method and two conventional tractography methods (a streamline technique and a tensorline algorithm) to DT-MRI data of five normal subjects for visualizing the pyramidal tract. Our method visualized the pathways connected to a large portion of the primary motor cortex, including foot, hand and face motor areas, passing through the crossing regions with other white matter tracts in all subjects, whereas the conventional methods showed only a small portion of the pyramidal tract. The pyramidal tract pathways estimated by our method were consistent with the neuroanatomical knowledge. In conclusion, the DDFT method may be useful in assisting neuroradiologists in estimating the white matter tracts. 相似文献
7.
依托国家精品资源共享课程《生物医学信号处理》,利用三维虚拟现实开发技术(Unity3D),以C#为脚本语言,开发了脑电图检测与分析虚拟仿真实验平台。该平台通过交互式的实验流程、可视化的数据分析、生动形象的结果展示,可以让学生在有限的课程时间里真实体验脑电图检测和分析这一复杂的实验操作过程,对脑电图检测与分析进行更全面深入的学习,从而提高学生基本的实验操作与数据分析能力。最后,本文详细地介绍了实验流程的总体框架和软件系统模块设计,为虚拟仿真技术在教学上的应用和推广提供了重要参考。 相似文献
8.
An analytical representation of the leading non‐Gaussian corrections for a class of diffusion orientation distribution functions (dODFs) is presented. This formula is constructed from the diffusion and diffusional kurtosis tensors, both of which may be estimated with diffusional kurtosis imaging (DKI). By incorporating model‐independent non‐Gaussian diffusion effects, it improves on the Gaussian approximation used in diffusion tensor imaging (DTI). This analytical representation therefore provides a natural foundation for DKI‐based white matter fiber tractography, which has potential advantages over conventional DTI‐based fiber tractography in generating more accurate predictions for the orientations of fiber bundles and in being able to directly resolve intra‐voxel fiber crossings. The formula is illustrated with numerical simulations for a two‐compartment model of fiber crossings and for human brain data. These results indicate that the inclusion of the leading non‐Gaussian corrections can significantly affect fiber tractography in white matter regions, such as the centrum semiovale, where fiber crossings are common. Copyright © 2013 John Wiley & Sons, Ltd. 相似文献
9.
Anna Gambin Author Vitae Ewa Szczurek Author Vitae Janusz Dutkowski Author Vitae Author Vitae Micha? Dadlez Author Vitae 《Computers in biology and medicine》2009,39(5):460-473
We have developed an integrated tool for statistical analysis of large-scale LC-MS profiles of complex protein mixtures comprising a set of procedures for data processing, selection of biomarkers used in early diagnostic and classification of patients based on their peptide mass fingerprints.Here, a novel boosting technique is proposed, which is embedded in our framework for MS data analysis. Our boosting scheme is based on Hannan-consistent game playing strategies. We analyze boosting from a game-theoretic perspective and define a new class of boosting algorithms called H-boosting methods.In the experimental part of this work we apply the new classifier together with classical and state-of-the-art algorithms to classify ovarian cancer and cystic fibrosis patients based on peptide mass spectra.The methods developed here provide automatic, general, and efficient means for processing of large scale LC-MS datasets. Good classification results suggest that our approach is able to uncover valuable information to support medical diagnosis. 相似文献
10.
Mercedes Huertas-Migueláñez Daniel Mora Isaac Cano Dieter Maier David Gomez-Cabrero Magí Lluch-Ariet Felip Miralles 《Journal of translational medicine》2014,12(Z2):S7
Background
Today, many different tools are developed to execute and visualize physiological models that represent the human physiology. Most of these tools run models written in very specific programming languages which in turn simplify the communication among models. Nevertheless, not all of these tools are able to run models written in different programming languages. In addition, interoperability between such models remains an unresolved issue.Results
In this paper we present a simulation environment that allows, first, the execution of models developed in different programming languages and second the communication of parameters to interconnect these models. This simulation environment, developed within the Synergy-COPD project, aims at helping and supporting bio-researchers and medical students understand the internal mechanisms of the human body through the use of physiological models. This tool is composed of a graphical visualization environment, which is a web interface through which the user can interact with the models, and a simulation workflow management system composed of a control module and a data warehouse manager. The control module monitors the correct functioning of the whole system. The data warehouse manager is responsible for managing the stored information and supporting its flow among the different modules.This simulation environment has been validated with the integration of three models: two deterministic, i.e. based on linear and differential equations, and one probabilistic, i.e., based on probability theory. These models have been selected based on the disease under study in this project, i.e., chronic obstructive pulmonary disease.Conclusion
It has been proved that the simulation environment presented here allows the user to research and study the internal mechanisms of the human physiology by the use of models via a graphical visualization environment. A new tool for bio-researchers is ready for deployment in various use cases scenarios.11.
Erika Gyengesi Evan Calabrese Matthew C. Sherrier G. Allan Johnson George Paxinos Charles Watson 《Brain structure & function》2014,219(2):539-550
Researchers working with rodent models of neurological disease often require an accurate map of the anatomical organization of the white matter of the rodent brain. With the increasing popularity of small animal MRI techniques, including diffusion tensor imaging (DTI), there is considerable interest in rapid segmentation methods of neurological structures for quantitative comparisons. DTI-derived tractography allows simple and rapid segmentation of major white matter tracts, but the anatomic accuracy of these computer-generated fibers is open to question and has not been rigorously evaluated in the rat brain. In this study, we examine the anatomic accuracy of tractography-based segmentation in the adult rat brain. We analysed 12 major white matter pathways using semi-automated tractography-based segmentation alongside manual segmentation of Gallyas silver-stained histology sections. We applied four fiber-tracking algorithms to the DTI data—two integration methods and two deflection methods. In many cases, tractography-based segmentation closely matched histology-based segmentation; however different tractography algorithms produced dramatically different results. Results suggest that certain white matter pathways are more amenable to tractography-based segmentation than others. We believe that these data will help researchers decide whether it is appropriate to use tractography-based segmentation of white matter structures for quantitative DTI-based analysis of neurologic disease models. 相似文献
12.
P. Schenk T. Siebert P. Hiepe D. Güllmar J. R. Reichenbach C. Wick R. Blickhan M. Böl 《Journal of anatomy》2013,223(1):61-68
In the last decade, diffusion tensor imaging (DTI) has been used increasingly to investigate three-dimensional (3D) muscle architectures. So far there is no study that has proved the validity of this method to determine fascicle lengths and pennation angles within a whole muscle. To verify the DTI method, fascicle lengths of m. soleus as well as their pennation angles have been measured using two different methods. First, the 3D muscle architecture was analyzed in vivo applying the DTI method with subsequent deterministic fiber tractography. In a second step, the muscle architecture of the same muscle was analyzed using a standard manual digitization system (MicroScribe MLX). Comparing both methods, we found differences for the median pennation angles (P < 0.001) but not for the median fascicle lengths (P = 0.216). Despite the statistical results, we conclude that the DTI method is appropriate to determine the global fiber orientation. The difference in median pennation angles determined with both methods is only about 1.2° (median pennation angle of MicroScribe: 9.7°; DTI: 8.5°) and probably has no practical relevance for muscle simulation studies. Determining fascicle lengths requires additional restriction and further development of the DTI method. 相似文献
13.
Elisa Scaccianoce Maria Marcella Laganà Francesca Baglio Maria Giulia Preti Niels Bergsland Pietro Cecconi Mario Clerici Giuseppe Baselli George Papadimitriou Nikos Makris 《Brain topography》2016,29(6):814-823
Diffusion tensor imaging (DTI) tractography and functional magnetic resonance imaging (fMRI) are powerful techniques to elucidate the anatomical and functional aspects of brain connectivity. However, integrating these approaches to describe the precise link between structure and function within specific brain circuits remains challenging. In this study, a novel DTI–fMRI integration method is proposed, to provide the topographical characterization and the volumetric assessment of the functional and anatomical connections within the language circuit. In a group of 21 healthy elderly subjects (mean age 68.5 ± 5.8 years), the volume of connection between the cortical activity elicited by a verbal fluency task and the cortico-cortical fiber tracts associated with this function are mapped and quantified. An application of the method to a case study in neuro-rehabilitation context is also presented. Integrating structural and functional data within the same framework, this approach provides an overall view of white and gray matter when studying specific brain circuits. 相似文献
14.
Juan Martino Philip C. De Witt Hamer Mitchel S. Berger Michael T. Lawton Christine M. Arnold Enrique Marco de Lucas Hugues Duffau 《Brain structure & function》2013,218(1):105-121
The anatomy of the perisylvian component of the superior longitudinal fasciculus (SLF) has recently been reviewed by numerous diffusion tensor imaging tractography (DTI) studies. However, little is known about the exact cortical terminations of this tract. The aim of the present work is to isolate the different subcomponents of this tract with fiber dissection and DTI tractography, and to identify the exact cortical connections. Twelve postmortem human hemispheres (6 right and 6 left) were dissected using the cortex-sparing fiber dissection. In addition, three healthy brains were analyzed using DTI-based tractography software. The different components of the perisylvian SLF were isolated and the fibers were followed until the cortical terminations. Three segments of the perisylvian SLF were identified: (1) anterior segment, connecting the supramarginal gyrus and superior temporal gyrus with the precentral gyrus, (2) posterior segment, connecting the posterior portion of the middle temporal gyrus with the angular gyrus, and (3) long segment of the arcuate fasciculus that connects the middle and inferior temporal gyri with the precentral gyrus and posterior portion of the inferior and middle frontal gyri. In the present study, three different components of the perisylvian SLF were identified. For the first time, our dissections revealed that each component was connected to a specific cortical area within the frontal, parietal and temporal lobes. By accurately depicting not only the trajectory but also cortical connections of this bundle, it is possible to develop new insights into the putative functional role of this tract. 相似文献
15.
Rochelle Smits Jamie Bryant Rob Sanson-Fisher Flora Tzelepis Frans Henskens Christine Paul William Stevenson 《Journal of medical Internet research》2014,16(3)
Background
Effective communication with cancer patients and their families about their disease, treatment options, and possible outcomes may improve psychosocial outcomes. However, traditional approaches to providing information to patients, including verbal information and written booklets, have a number of shortcomings centered on their limited ability to meet patient preferences and literacy levels. New-generation Web-based technologies offer an innovative and pragmatic solution for overcoming these limitations by providing a platform for interactive information seeking, information sharing, and user-centered tailoring.Objective
The primary goal of this paper is to discuss the advantages of comprehensive and iterative Web-based technologies for health information provision and propose a four-phase framework for the development of Web-based information tools.Methods
The proposed framework draws on our experience of constructing a Web-based information tool for hematological cancer patients and their families. The framework is based on principles for the development and evaluation of complex interventions and draws on the Agile methodology of software programming that emphasizes collaboration and iteration throughout the development process.Results
The DoTTI framework provides a model for a comprehensive and iterative approach to the development of Web-based informational tools for patients. The process involves 4 phases of development: (1) Design and development, (2) Testing early iterations, (3) Testing for effectiveness, and (4) Integration and implementation. At each step, stakeholders (including researchers, clinicians, consumers, and programmers) are engaged in consultations to review progress, provide feedback on versions of the Web-based tool, and based on feedback, determine the appropriate next steps in development.Conclusions
This 4-phase framework is evidence-informed and consumer-centered and could be applied widely to develop Web-based programs for a diverse range of diseases. 相似文献16.
基于弥散磁共振成像(dMRI)的纤维束重建,是分析大脑白质结构的主要工具.现有的纤维追踪成像算法受dMRI分辨率及成像机理约束,在构建大脑白质灰质边界区域的纤维时成像性能和准确性大大下降.为克服该缺陷,提出一种结合功能磁共振成像(fMRI)的新型dMRI纤维追踪成像算法.该算法引入表征白质中fMRI信号各向异性的空间相... 相似文献
17.
目的建立扩散张量纤维束成像对人脑白质纤维的显示方法,并应用中国数字化可视人体数据进行对照观察,验证扩散张量成像(DTI)方法的可靠性。方法选择5名健康志愿者进行DTI成像,采用DtiStudio软件进行分析处理,重建出部分各向异性(FA)图、容积比(VR)图、相对各向异性(RA)图、表面扩散系数(ADC)图以及二维彩色张量图。应用中国数字化可视人体数据集断面图像、FA图及彩色FA图进行对照观察,利用fibertracking纤维跟踪软件及3DMRI软件进行三维重建显示脑内主要白质纤维束,辨认脑内白质纤维束的位置、形态。结果应用DTI纤维束成像可以清晰准确地描绘脑白质内主要神经纤维束的解剖图谱,包括联络纤维如弓形纤维、钩束、扣带束、上纵束和下纵束,连合纤维如胼胝体、前连合和穹隆,投射纤维如锥体束、视放射、内侧丘系等。DTI纤维束成像结果与已知解剖知识、中国可视化人体断面图像具有很好的一致性。结论应用DTI纤维束成像可以清晰准确地描绘脑白质内主要神经纤维束的解剖图谱,其结果与中国可视化人体断面图像、已知解剖知识是一致的,应用DTI纤维束成像研究脑内纤维连通性是可靠的。 相似文献
18.
Seizeur R Wiest-Daessle N Prima S Maumet C Ferre JC Morandi X 《Surgical and radiologic anatomy : SRA》2012,34(8):709-719
Purpose
Diffusion tensor imaging permits study of white matter fibre bundles; however, its main limitation is lack of validation on anatomical data, especially in crossing fibre regions. Our study aimed to compare four deterministic tractography algorithms used in clinical routine. We studied the corticospinal tract, the bundle mediating voluntary movement. Our study seeks to evaluate tractography provided by algorithms through comparative analysis by expert neuroradiologists.Methods
MRI data from 15 right-handed volunteers (30.8?years) were studied. Regions of interest (ROIs) were segmented on morphological and functional MRI. Diffusion weighted images (15 directions) were performed, then for each voxel the tensor was estimated. Tractography of the corticospinal tract was performed using four fibre-tracking algorithms. Three numerical integration methods Euler, Runge–Kutta second (RK2) and fourth order (RK4), and a tensor deflection method (TEND). Quantitative measurement was performed. Qualitative evaluation was carried out by two expert neuroradiologists using Kappa test concordance.Results
For the quantitative aspect, only RK2 and TEND presented no significant difference concerning the number of fibres (p?=?0.58). There was no difference between right and left side for each algorithm. Regarding the qualitative aspects, there was a lack of fibres from the ventrolateral part of the functional ROIs. Comparison by expert neuroradiologists revealed low rather than high concordance. The algorithm ranked first was RK2 according to expert preferences.Conclusions
Different algorithms used in clinical routine failed to show realistic anatomical bundles. The most mathematically robust algorithm was not selected, nor was the algorithm defining more fibres. Validation of anatomical data provided by tractography remains a challenge. 相似文献19.
The majority of modern electroencephalogram (EEG) processing systems are not directly used for neurocomputer interfaces (NCI)
because these systems do not provide flexibility in real-time processing and do not allow modifications and additions of custom
processing algorithms. These disadvantages encourage the creation of new programming frameworks comprising a set of EEG processing
and visualization units. The order of data flow between the units is determined by their interconnections on a graph. One
example of possible NCI realizations is provided here. It is the 2D control of a device based on μ-rhythm desynchronization
analysis.
Translated from Meditsinskaya Tekhnika, Vol. 43, No. 3, 2009, pp. 16–19. 相似文献
20.
Mingrui Zhuang Zhonghua Chen Hongkai Wang Hong Tang Jiang He Bobo Qin Yuxin Yang Xiaoxian Jin Mengzhu Yu Baitao Jin Taijing Li Lauri Kettunen 《Journal of digital imaging》2022,35(6):1623
The development of medical image analysis algorithm is a complex process including the multiple sub-steps of model training, data visualization, human–computer interaction and graphical user interface (GUI) construction. To accelerate the development process, algorithm developers need a software tool to assist with all the sub-steps so that they can focus on the core function implementation. Especially, for the development of deep learning (DL) algorithms, a software tool supporting training data annotation and GUI construction is highly desired. In this work, we constructed AnatomySketch, an extensible open-source software platform with a friendly GUI and a flexible plugin interface for integrating user-developed algorithm modules. Through the plugin interface, algorithm developers can quickly create a GUI-based software prototype for clinical validation. AnatomySketch supports image annotation using the stylus and multi-touch screen. It also provides efficient tools to facilitate the collaboration between human experts and artificial intelligent (AI) algorithms. We demonstrate four exemplar applications including customized MRI image diagnosis, interactive lung lobe segmentation, human-AI collaborated spine disc segmentation and Annotation-by-iterative-Deep-Learning (AID) for DL model training. Using AnatomySketch, the gap between laboratory prototyping and clinical testing is bridged and the development of MIA algorithms is accelerated. The software is opened at https://github.com/DlutMedimgGroup/AnatomySketch-Software.Supplementary InformationThe online version contains supplementary material available at 10.1007/s10278-022-00660-5. 相似文献