共查询到20条相似文献，搜索用时 886 毫秒
1.
INTRODUCTIONSegmentation ,acentralissueofcomputervision ,isafundamentalprocessingstepinmostsystemsthatsupportmedicaldiagnosisorplan ningofsurgicaloperationsandradiationtreat ments (Wyattetal.,2 0 0 0 ;Wintereretal.,2 0 0 2 ;Baoetal.,1998) .Contour basedse… 相似文献
2.
A novel technique of three-dimensional reconstruction segmentation and analysis for sliced images of biological tissues 总被引：5，自引：0，他引：5
INTRODUCTION The past decades witnessed unprecedented ad-vances in the imaging science fields(Yelbuz et al.,2002;Campagnola et al.,2002;Sharpe et al.,2002).The technique of3D image reconstruction andanalysis plays a significant role in the basic researchof life science,which developed from2D imageprocessing but provides more information than2Dimage,and has rapidly expanded to molecular andcellular field(Guo et al.,1995;Trehan et al.,2003).Despite the rapid development of the new field,… 相似文献
3.
Take away body parts! An investigation into the use of 3D‐printed anatomical models in undergraduate anatomy education 
下载免费PDF全文
下载免费PDF全文 Claire F. Smith Nicholas Tollemache Derek Covill Malcolm Johnston 《Anatomical sciences education》2018,11(1):44-53
Understanding the three‐dimensional (3D) nature of the human form is imperative for effective medical practice and the emergence of 3D printing creates numerous opportunities to enhance aspects of medical and healthcare training. A recently deceased, un‐embalmed donor was scanned through high‐resolution computed tomography. The scan data underwent segmentation and post‐processing and a range of 3D‐printed anatomical models were produced. A four‐stage mixed‐methods study was conducted to evaluate the educational value of the models in a medical program. (1) A quantitative pre/post‐test to assess change in learner knowledge following 3D‐printed model usage in a small group tutorial; (2) student focus group (3) a qualitative student questionnaire regarding personal student model usage (4) teaching faculty evaluation. The use of 3D‐printed models in small‐group anatomy teaching session resulted in a significant increase in knowledge (P = 0.0001) when compared to didactic 2D‐image based teaching methods. Student focus groups yielded six key themes regarding the use of 3D‐printed anatomical models: model properties, teaching integration, resource integration, assessment, clinical imaging, and pathology and anatomical variation. Questionnaires detailed how students used the models in the home environment and integrated them with anatomical learning resources such as textbooks and anatomy lectures. In conclusion, 3D‐printed anatomical models can be successfully produced from the CT data set of a recently deceased donor. These models can be used in anatomy education as a teaching tool in their own right, as well as a method for augmenting the curriculum and complementing established learning modalities, such as dissection‐based teaching. Anat Sci Educ 11: 44–53. © 2017 American Association of Anatomists. 相似文献
4.
传统的主动轮廓模型只利用图像的边缘或者只利用区域特征实现图像分割。在有些情况下图像分割效果较差．本文给出了一种综合利用图像边缘和区域特征的主动轮廓图像分割方法．实验表明,演变后的曲线与图像的边缘是吻合的,图像分割的结果较好．而对相同的图像应用传统的主动轮廓分割算法得到的图像分割结果则很差．这说明新算法明显提高了传统算法的图像分割性能． 相似文献
5.
周学礼 《常熟理工学院学报》2011,25(4):98-101
周围神经CT图像增强是周围神经三维重建中的基础环节,本文在分析高斯圆模型Hessian矩阵特征值特点的基础上,提出一种基于Hessian矩阵多尺度滤波的周围神经CT图像增强算法.实验证明该方法能够使似圆形周围神经区域得以增强,抑止其他非圆形区域的干扰,得到较好的周围神经增强图像,为后续的分割与三维重建奠定基础. 相似文献
6.
7.
一种基于边缘流的图像分割算法及其应用 总被引：1，自引：0，他引：1
基于边缘流的图像分割算法以方向相反的边缘流相遇的位置确定对象的边缘,解决了传统基于边缘的图像分割算法难以确定合理阙值的问题.论述了基于边缘流图像分割算法的原理,对该算法进行了调整,将其应用于昆虫图像的分割.实验结果表明:基于边缘流的算法不仅能够有效地分割出图像中的昆虫对象,而且对昆虫对象的各个部分还能进行较为有效地分割.与传统的基于闽值分割算法相比是更好的图像分割算法,促进了计算机视觉技术在农林业领域的应用,促进了计算机视觉技术在农林业领域的应用. 相似文献
8.
9.
针对颅骨CT图像中灰度值范围变化较大的特点,阐述了两种图像的分割方法,一种是基于边缘信息的分割,一种是基于区域信息的图像分割,提出了在颅骨CT图像分割中采用基于区域的阈值分割算法,并通过软件编程实验证明了它具有算法简单、识别效果好、效率高的特点． 相似文献
10.
最大类间距离法已经被证明是一种较好的阈值化方法[1],但在用于双阈值或多阈值分割时存在实现效率较低等问题,而遗传算法高效的随机搜索能力正好能弥补其不足.根据脑部图像分为灰质、白质等三类的特点,通过把遗传算法引入最大类间距离法来实行对脑部图像的分割,实验验证取得了较好的分割效果. 相似文献
11.
The inherent spatial complexity of the human cerebral ventricular system, coupled with its deep position within the brain, poses a problem for conceptualizing its anatomy. Cadaveric dissection, while considered the gold standard of anatomical learning, may be inadequate for learning the anatomy of the cerebral ventricular system; even with intricate dissection, ventricular structures remain difficult to observe. Three-dimensional (3D) computer reconstruction of the ventricular system offers a solution to this problem. This study aims to create an accurate 3D computer reconstruction of the ventricular system with surrounding structures, including the brain and cerebellum, using commercially available 3D rendering software. Magnetic resonance imaging (MRI) scans of a male cadaver were segmented using both semiautomatic and manual tools. Segmentation involves separating voxels of different grayscale values to highlight specific neural structures. User controls enable adding or removing of structures, altering their opacity, and making cross-sectional slices through the model to highlight inner structures. Complex physiologic concepts, such as the flow of cerebrospinal fluid, are also shown using the 3D model of the ventricular system through a video animation. The model can be projected stereoscopically, to increase depth perception and to emphasize spatial relationships between anatomical structures. This model is suited for both self-directed learning and classroom teaching of the 3D anatomical structure and spatial orientation of the ventricles, their connections, and their relation to adjacent neural and skeletal structures. 相似文献
12.
13.
为解决传统谱聚类算法在图像分割时计算量大、使用单一特征分割的局限性问题,设计一种融合谱聚类和多特征的图像分割算法。首先进行超像素分割以减少计算量,分别提取每个超像素的颜色特征和纹理特征,构建超像素相似度矩阵|然后采用特征加权方法线性融合颜色和纹理特征的超像素相似度矩阵|最后采用谱聚类算法进行聚类分割。在UCMerced_LandUse和Berkeley数据集上进行实验测试,并与现有方法进行比较。实验结果表明,大多数实验图像IOU指标均在90%以上,相比于传统方法有了显著提高。 相似文献
14.
Volume rendering of 3D data sets composed of sequential 2D medical images has become an important branch in image processing and computer graphics.To help physicians fully understand deep-seated human organs and focuses(e.g.a tumour)as 3D structures.in this paper,we present a modified volume rendering algorithm to render volumetric data,Using this method.the projection images of structures of interest from different viewing directions can be obtained satisfactorily.By rotating the light source and the observer eyepoint,this method avoids rotates the whole volumetric data in main memory and thus reduces computational complexity and rendering time.Experiments on CT images suggest that the proposed method is useful and efficient for rendering 3D data sets. 相似文献
15.
传统边缘检测算子如Canny、Sobel等是通过计算图像中局部小区域的差分来工作的,对噪声比较敏感,在检测边缘的同时常会加强噪声,形态边缘检测器在检测边缘的时候不会加强或放大噪声,单尺度形态学梯度算子结构元素过大或过小都不能检测到满意的结果.将多尺度形态学边缘检测和形态学滤波结合起来,提出一种边缘检测方法.首先利用形态学对多尺度的形态学梯度算子进行边缘检测,再进行填充内部缝隙,接着进行形态学边界平滑,最后通过分割掩模到原图像的结果.仿真结果表明,所提算法能够非常清晰地检测到目标图像的边缘,提取的图像边缘定位准确且平滑,同时具有较强的抗噪能力. 相似文献
16.
杨新 《上海大学学报(英文版)》2008,12(3):240-248
Medical diagnosis software and computer-assisted surgical systems often use segmented image data to help clinicians make decisions. The segmentation extracts the region of interest from the background, which makes the visualization clearer. However, no segmentation method can guarantee accurate results under all circumstances. As a result, the clinicians need a solution that enables them to check and validate the segmentation accuracy as well as displaying the segmented area without ambiguities.With the method presented in this paper, the real CT or MR image is displayed within the segmented region and the segmented boundaries can be expanded or contracted interactively. By this way, the clinicians are able to check and validate the segmentation visually and make more reliable decisions. After experiments with real data from a hospital, the presented method is proved to be suitable for efficiently detecting segmentation errors. The new algorithm uses new graphic processing uint (GPU) shading functions recently introduced in graphic cards and is fast enough to interact on the segmented area, which was not possible with previous methods. 相似文献
17.
Helge Petersson David Sinkvist Chunliang Wang Örjan Smedby 《Anatomical sciences education》2009,2(2):61-68
Despite a long tradition, conventional anatomy education based on dissection is declining. This study tested a new virtual reality (VR) technique for anatomy learning based on virtual contrast injection. The aim was to assess whether students value this new three‐dimensional (3D) visualization method as a learning tool and what value they gain from its use in reaching their anatomical learning objectives. Several 3D vascular VR models were created using an interactive segmentation tool based on the “virtual contrast injection” method. This method allows users, with relative ease, to convert computer tomography or magnetic resonance images into vivid 3D VR movies using the OsiriX software equipped with the CMIV CTA plug‐in. Once created using the segmentation tool, the image series were exported in Quick Time Virtual Reality (QTVR) format and integrated within a web framework of the Educational Virtual Anatomy (EVA) program. A total of nine QTVR movies were produced encompassing most of the major arteries of the body. These movies were supplemented with associated information, color keys, and notes. The results indicate that, in general, students' attitudes towards the EVA‐program were positive when compared with anatomy textbooks, but results were not the same with dissections. Additionally, knowledge tests suggest a potentially beneficial effect on learning. Anat Sci Ed 2:61–68, 2009. © 2009 American Association of Anatomists. 相似文献
18.
Kenneth C. Hisley Larry D. Anderson Stacy E. Smith Stephen M. Kavic J. Kathleen Tracy 《Anatomical sciences education》2008,1(1):27-40
This research effort compared and contrasted two conceptually different methods for the exploration of human anatomy in the first‐year dissection laboratory by accomplished students: “physical” dissection using an embalmed cadaver and “digital” dissection using three‐dimensional volume modeling of whole‐body CT and MRI image sets acquired using the same cadaver. The goal was to understand the relative contributions each method makes toward student acquisition of intuitive sense of practical anatomical knowledge gained during “hands‐on” structural exploration tasks. The main instruments for measuring anatomical knowledge under this conceptual model were questions generated using a classification system designed to assess both visual presentation manner and the corresponding response information required. Students were randomly divided into groups based on exploration method (physical or digital dissection) and then anatomical region. The physical dissectors proceeded with their direct methods, whereas the digital dissectors generated and manipulated indirect 3D digital models. After 6 weeks, corresponding student anatomical assignment teams compared their results using photography and animated digital visualizations. Finally, to see whether each method provided unique advantages, a visual test protocol of new visualizations based on the classification schema was administered. Results indicated that all students, regardless of gender, dissection method, and anatomical region dissected performed significantly better on questions presented as rotating models requiring spatial ordering or viewpoint determination responses in contrast to requests for specific lexical feature identifications. Additional results provided evidence of trends showing significant differences in gender and dissection method scores. These trends will be explored with further trials with larger populations. Anat Sci Ed 1:27–40, 2008. © 2007 American Association of Anatomists. 相似文献
19.
Experimental evidence for improved neuroimaging interpretation using three-dimensional graphic models 总被引：1，自引：0，他引：1
Ruisoto P Juanes JA Contador I Mayoral P Prats-Galino A 《Anatomical sciences education》2012,5(3):132-137
Three-dimensional (3D) or volumetric visualization is a useful resource for learning about the anatomy of the human brain. However, the effectiveness of 3D spatial visualization has not yet been assessed systematically. This report analyzes whether 3D volumetric visualization helps learners to identify and locate subcortical structures more precisely than classical cross-sectional images based on a two dimensional (2D) approach. Eighty participants were assigned to each experimental condition: 2D cross-sectional visualization vs. 3D volumetric visualization. Both groups were matched for age, gender, visual-spatial ability, and previous knowledge of neuroanatomy. Accuracy in identifying brain structures, execution time, and level of confidence in the response were taken as outcome measures. Moreover, interactive effects between the experimental conditions (2D vs. 3D) and factors such as level of competence (novice vs. expert), image modality (morphological and functional), and difficulty of the structures were analyzed. The percentage of correct answers (hit rate) and level of confidence in responses were significantly higher in the 3D visualization condition than in the 2D. In addition, the response time was significantly lower for the 3D visualization condition in comparison with the 2D. The interaction between the experimental condition (2D vs. 3D) and difficulty was significant, and the 3D condition facilitated the location of difficult images more than the 2D condition. 3D volumetric visualization helps to identify brain structures such as the hippocampus and amygdala, more accurately and rapidly than conventional 2D visualization. This paper discusses the implications of these results with regards to the learning process involved in neuroimaging interpretation. 相似文献
20.
阈值分割是图像分割中的一种常用且有效的方法,其关键问题是搜索到最佳分割阈值.文中基于混沌优化理论,利用Lorenz混沌系统对图像进行了阈值分割,同时提出了一种基于耦合映象格子的时空混沌优化算法,并且将其应用于图像分割实验.实验表明,与Lorenz混沌优化算法相比,时空混沌优化算法用于阈值寻优能够给出更加理想的分割结果. 相似文献