乳腺X线成像的计算机辅助诊断技术研究进展

计算机辅助诊断(computer-aided diagnosis,CAD)技术日益成熟,在乳腺癌早期检测诊断中的应用尤其广泛,其标志就是商业化的CAD设备得到了FDA的认证.本文以一个典型的CAD系统的组成为主线,把CAD系统分解成几个重要的功能模块,介绍实现这些功能模块的主要技术,其中重点介绍了医学图像处理技术和模式识别技术,最后讨论了未来CAD技术完善过程中需要解决的几个问题.     

乳腺X线图像的计算机辅助诊断技术研究进展

乳腺癌是妇女中多发的癌症 ,其发病率近年来有增高趋势。早期发现、早期诊断、早期治疗是降低乳腺癌患者死亡的关键。本文就临床上首选的影像学诊断方法——钼靶 X线乳腺摄影的计算机辅助诊断技术进行了较为详细的综述 ,并就该技术的发展趋势进行了展望     

乳腺钼色X线图像的计算机辅助早期诊断技术

乳腺癌是盛行于广大妇女中的癌症，其发病率近年来呈增高趋势，早期发现、早期诊断、早期治疗是降低乳腺癌死亡的关键。本文就临床上首选的影像学诊断方法-钼靶X线摄影的计算机辅助诊断技术进行了较为详细的综述，并就该技术的发展趋势进行了展望。     

基于钼靶X线影像的乳腺微钙化点良恶性识别算法研究

目的:乳腺癌是女性最常见的恶性肿瘤之一,早期发现、早期诊断,对提高乳腺癌治愈率和降低死亡率具有重大意义。早期乳腺癌的计算机辅助诊断方面的研究已经成为乳腺图像处理领域研究的热点和难点问题之一,具有重大的理论价值和社会意义。方法:本论文正是针对上述问题,对早期乳腺癌的计算机辅助诊断算法问题作了探索性研究,进行了微钙化点病变类型识别算法的研究。结果:通过钙化点特征提取和优化及病变类型识别,给出初步诊断结果。结论:用该算法对钙化点进行计数是可行的,具有快速、简单、准确的优点,而且计数结果不受钙化点形态、大小的影响。     

数字人体断层彩色图像数据的真实感体绘制

目的　探索一种用于数字人体断层彩色图像数据的真实感三维重建方法。  方法　改进光线投射体绘制算法,将真实的颜色采样和传递函数颜色映射相结合,使其适应彩色数据;使用分割标记数据,为多重组织彩色数据分类,实现数字人体断层彩色图像的直接体绘制。  结果　此方法实现了数字人体复杂组织和器官的高度真实感三维重建。  结论　断层彩色图像数据的真实感体绘制,能准确反映数字人体结构的细节和颜色信息,得到边界清晰的三维模型。     

基于预分割和贝塞尔函数的口腔全景图重建方法

部分颌骨缺损、囊肿和需要种植牙的患者,在口腔诊断过程中医生为了观察其完整的牙列信息,需要患者拍摄全景X光片,或者需要医生手动绘制牙弓线用以生成全景图。针对患者拍摄全景X光片将增加额外负担以及医生手动分割牙弓线耗时过长的问题,本文基于锥形束计算机断层扫描（CBCT）提出了一种全自动全景图重建方法,使用V型网络（VNet）将牙齿与背景预分割,生成对应的二值图,再利用贝塞尔曲线定义最佳牙弓曲线,生成口腔全景图。此外,本研究还解决了将牙颌骨误识别为牙弓、生成的牙弓线覆盖牙弓区域不全面和鲁棒性低等问题,可为今后牙科诊断智能化以及提高医生工作效率奠定理论基础。     

基于CT断层影像的颅骨解剖结构三维重建

目的:基于CT颅脑断面连续影像,利用Mimics 8.01软件对颅骨进行三维重建,为解剖学教学和研究提供模型.方法:利用Mimics软件对CT颅脑影像中的骨组织进行自动阈值分割后,对重建出的颅骨进行自动分割,分割出舌骨结构.对于其他颅骨结构,在Mimics软件中的三个方位CT图像中,利用定位线结合解剖学中的颅骨毗邻关系,找出区分毗邻颅骨之间的定位点.然后,根据事先规划的不同结构的分割颜色,人工描出相应的颅骨所在区域.随后,对分割出的各个颜色区域进行三维重建,重建出主要的脑颅骨和面颅骨结构,并分别在计算机上对上述结构进行观察.结果:成功对颅骨的结构分别以不同颜色进行分割,并分别重建出额骨、颞骨、枕骨、顶骨、蝶骨、筛骨、鼻骨、泪骨、上颌骨、下颌骨、腭骨、舌骨结构,在计算机中进行任意角度和单独观察.结论:基于CT颅脑断面影像可以对颅骨进行三维重建,为数字化颅骨解剖教学及颅脑手术导航奠定基础.     

基于光子计数探测器的X线CT蒙特卡罗仿真

目的:基于光子计数探测器的X线CT(Photon Counting Computed Tomography,PCCT)较传统CT成像最突出的特点是可实现多参数成像,包括基物质成像和单能量成像等。然而,当前商用光子计数探测器的计数率低、能量分辨率有限,大大限制了PCCT更为广泛的临床应用。为了更好地研究PCCT成像技术,本文系统地研究了基于光子计数探测器的X线CT蒙特卡罗仿真方法,深入探讨了K值效应及能量段宽度对成像质量的影响。方法:首先通过PENELOPE(Penetration and Energy Loss of Positrons and Electrons)仿真软件对PCCT成像系统进行设计,完成光子计数探测器的配置,其后基于仿真系统完成不同体模的能谱CT数据仿真。针对K值效应及能量段宽度对图像质量的影响,对相关数据进行了定量分析。结果:本研究设计的PCCT成像仿真系统能有效地实现能谱CT数据采集与成像性能分析,其中对比剂在K缘处的对比度噪声比较其在非K缘处高,并且对比剂在适当宽度的能量段里获得优质的图像。结论:本研究设计的PCCT成像仿真系统能有效地实现能谱CT数据采集与成像性能分析。     

基于医学图像内容检索的计算机辅助乳腺X线影像诊断技术

乳腺癌是女性中高发的恶性肿瘤疾病.近年来,其发病率呈增高趋势.早期发现、早期诊断和早期治疗是降低乳腺癌患者死亡率的关键.计算机辅助诊断(CAD)技术能够有效提高早期诊断的准确性,而基于内容医学图像检索(CBMIR)技术的引入,为乳腺癌的诊断提供了有效的决策支持.文中就近年来基于医学图像内容检索的计算机辅助乳腺X线影像诊断关键技术进行了较为详尽的综述,包括微钙化和肿块检测、特征提取、相似性测度和相关反馈技术等,同时对该领域的发展趋势进行了展望.     

GPU-accelerated 3D mipmap for real-time visualization of ultrasound volume data

Ultrasound volume rendering is an efficient method for visualizing the shape of fetuses in obstetrics and gynecology. However, in order to obtain high-quality ultrasound volume rendering, noise removal and coordinates conversion are essential prerequisites. Ultrasound data needs to undergo a noise filtering process; otherwise, artifacts and speckle noise cause quality degradation in the final images. Several two-dimensional (2D) noise filtering methods have been used to reduce this noise. However, these 2D filtering methods ignore relevant information in-between adjacent 2D-scanned images. Although three-dimensional (3D) noise filtering methods are used, they require more processing time than 2D-based methods. In addition, the sampling position in the ultrasonic volume rendering process has to be transformed between conical ultrasound coordinates and Cartesian coordinates. We propose a 3D-mipmap-based noise reduction method that uses graphics hardware, as a typical 3D mipmap requires less time to be generated and less storage capacity. In our method, we compare the density values of the corresponding points on consecutive mipmap levels and find the noise area using the difference in the density values. We also provide a noise detector for adaptively selecting the mipmap level using the difference of two mipmap levels. Our method can visualize 3D ultrasound data in real time with 3D noise filtering.     

一种新的CT图像软组织显示方法

本文提出了一种新的软组织显示实现方案，由分割、距离变换、剥皮和体绘制四个步骤组成。在距离变换阶段，该方案采用了一种新的三维欧氏距离变换算法，在保证距离测量精度的同时缩短了运算时间。在体绘制阶段，采用了一种基于体绘制的三维数据场多表面显示方法，为缩短绘制时间它只考虑不同物质的边界体元对显示图象的贡献，并采用投影成像法对边界体元进行快速显示，提高了三维显示的质量。该方案被用于三维医学CT图像中软组织的显示。实验结果表明，该方法能够清晰地再现皮下血管、肌肉与骨骼的空间解剖关系，在临床医学领域具有重要的应用价值。     

CT三维重建技术估算再造手指整形皮瓣形状的研究

目的　应用CT数据三维重建技术及CAD（computeraided design）技术,估算再造手指整形皮瓣的形状。 方法　复制20名健康成人正常右手拇、示、中、环指、右足第2趾的石膏模型,采集其三维CT数据并重建,用计算机软件模拟趾腹减凸术、趾狭窄膨隆术,勾画出所需皮瓣形状。 结果　模拟趾狭窄膨隆术所需皮瓣形态大致分为两型：蟹爪型和十字型。模拟趾腹减凸术所需皮瓣也可分为两型：水滴型和椭圆型。同一患者的拇、示、中、环指的皮瓣基本属于同一型。 结论　本方法可较为直观地估算出第2趾与拇、手指指腹的形态差异,可以获得整形皮瓣的立体形状,皮瓣形状具有较大的个体差异,因此为每一名患者个性化设计才能达到更好的手术效果。     

Error compensation method for improving the accuracy of biomodels obtained from CBCT data

This paper presents a method of improving the accuracy of the tridimensional reconstruction of human bone biomodels by means of tomography, with a view to finite element modelling or surgical planning, and the subsequent manufacturing using rapid prototyping technologies. It is focused on the analysis and correction of the results obtained by means of cone beam computed tomography (CBCT), which is used to digitalize non-superficial biological parts along with a gauge part with calibrated dimensions. A correction of both the threshold and the voxel size in the tomographic images and the final reconstruction is proposed. Finally, a comparison between a reconstruction of a gauge part using the proposed method and the reconstruction of that same gauge part using a standard method is shown. The increase in accuracy in the biomodel allows an improvement in medical applications based on image diagnosis, more accurate results in computational modelling, and improvements in surgical planning in situations in which the required accuracy directly affects the procedure's results. Thus, the subsequent constructed biomodel will be affected mainly by dimensional errors due to the additive manufacturing technology utilized, not because of the 3D reconstruction or the image acquisition technology.     

Fast perspective volume ray casting method using GPU-based acceleration techniques for translucency rendering in 3D endoluminal CT colonography

Recent advances in graphics processing unit (GPU) have enabled direct volume rendering at interactive rates. However, although perspective volume rendering for opaque isosurface is rapidly performed using conventional GPU-based method, perspective volume rendering for non-opaque volume such as translucency rendering is still slow. In this paper, we propose an efficient GPU-based acceleration technique of fast perspective volume ray casting for translucency rendering in computed tomography (CT) colonography. The empty space searching step is separated from the shading and compositing steps, and they are divided into separate processing passes in the GPU. Using this multi-pass acceleration, empty space leaping is performed exactly at the voxel level rather than at the block level, so that the efficiency of empty space leaping is maximized for colon data set, which has many curved or narrow regions. In addition, the numbers of shading and compositing steps are fixed, and additional empty space leapings between colon walls are performed to increase computational efficiency further near the haustral folds. Experiments were performed to illustrate the efficiency of the proposed scheme compared with the conventional GPU-based method, which has been known to be the fastest algorithm. The experimental results showed that the rendering speed of our method was 7.72 fps for translucency rendering of 1024×1024 colonoscopy image, which was about 3.54 times faster than that of the conventional method. Since our method performed the fully optimized empty space leaping for any kind of colon inner shapes, the frame-rate variations of our method were about two times smaller than that of the conventional method to guarantee smooth navigation. The proposed method could be successfully applied to help diagnose colon cancer using translucency rendering in virtual colonoscopy.     

3D reconstruction of peripheral nerves from optical projection tomography images: A method for studying fascicular interconnections and intraneural plexuses

The general microscopic characteristics of nerves are described in several textbooks of histology, but the specific microanatomies of most nerves that can be blocked by anesthesiologists are usually less well known. Our objective was to evaluate the 3D reconstruction of nerve fascicles from optical projection tomography images (OPT) and the ability to undertake an internal navigation exploring the morphology in detail, more specifically the fascicular interconnections. Median and lingual nerve samples were obtained from five euthanized piglets. OPT images of the samples were acquired and 3D reconstruction was performed. The OPT technique revealed the inner structure of the nerves at high resolution, including large and small fascicles, perineurium, interfascicular tissue, and epineurium. The fascicles were loosely packed inside the median nerve and more densely so in the lingual nerve. Analysis of the 3D models demonstrated that the nerve fascicles can show six general spatial patterns. Fascicular interconnections were clearly identified. The 3D reconstruction of nerve fascicles from OPT images opens a new path for research into the microstructure of the inner contents of fascicular nerve groups and their spatial disposition within the nerve including their interconnections. These techniques enable 3D images of partial areas of nerves to be produced and could became an excellent tool for obtaining data concerning the 3D microanatomy of nerves, essential for better interpretation of ultrasound images in clinical practice and thus avoiding possible neurological complications. Clin. Anat. 31:424–431, 2018. © 2017 Wiley Periodicals, Inc.     

A semi-automated method using interpolation and optimisation for the 3D reconstruction of the spine from bi-planar radiography: a precision and accuracy study

The 3D reconstruction of the spine in upright posture can be obtained by bi-planar radiographic methods, developed since the 1970s. The principle is to identify 4–25 anatomical landmarks per vertebrae and per images. This identification time is hardly manageable in clinical practice. A semi-automated method is used: 3D standard vertebral models are positioned along with a 3D curve (identified all the way through the vertebral bodies). The silhouettes of the models of C7 and L5 vertebrae are first adjusted and the positions of the other vertebrae are interpolated and optimised. The inter- and intra-operator variabilities and the errors between the semi-automated method and the manual identification of six anatomical landmarks per vertebra are evaluated on 20 pairs of X-ray images of subjects with different spinal deformities. The identification time for the semi-automated method is 5 min. For scolitic subjects, the precision is under 2.2° and the accuracy is under 3.2° for all lateral, sagittal and axial rotations.