基于VIP-Man图谱配准的腹部器官分割方法

提出了一种基于图谱配准的腹部器官分割方法.首先将一套预标记图谱向个体图像进行配准,建立二者之间器官的基本对应关系,同时完成对感兴趣器官的识别,其中配准包含全局配准和器官配准.然后,借助已配准的图谱,采用模糊连接方法对感兴趣器官进行分割.腹PCT和MR实验测试结果证明:这种方法实现了模糊连接分割方法中各项参数的自动指定,减轻了人工负担,提高了结果的可靠性.     

基于边缘强化的Unet-TIC模型对前列腺自动勾画研究

目的：通过图像边缘强化以及改进Unet深度学习网络结构提高前列腺自动分割的准确性。方法：随机选取我院50例检查者前列腺核磁扫描图像,以及MICCAI Grand Challenge数据库50例前列腺图像,其中81例作为训练集,10例作为验证集,9例作为测试集。通过旋转不变性相干增强扩散滤波方法（CED-ORI）对图像进行边缘强化,建立双输入收缩路径结构的Unet-Two Input Channel(Unet-TIC)并行提取原始和CED-ORI图像特征,共享一条扩张路径,并通过跳跃连接突出CED-ORI边缘强化的有效特征,获取更多信息增加上采样分辨率。采用Accuracy、Mean DSC、Median DSC、ASD、MSD、RVD 6个指标对Unet、Unet-c和Unet-TIC 3种方法进行评估。结果：Unet-c和Unet-TIC评估指标表现均明显优于Unet,其中表现最好的Unet-TIC相较于Unet,Accuracy提高1.87%,Mean DSC提高1.81%,Median DSC提高1.21%,ASD降低0.32 mm,MSD降低1.63 mm,RVD降低4.64%...     

基于图谱的肝脏CT三维自动分割研究

目的在肝脏外科手术或肝脏病理研究中,计算肝脏体积是重要步骤。由于肝脏外形复杂、临近组织灰度值与之接近等特点,肝脏的自动医学图像分割仍是医学图像处理中的难点之一。方法本文采用图谱结合3D非刚性配准的方法,同时加入肝脏区域搜索算法,实现了鲁棒性较高的肝脏自动分割程序。首先,利用20套训练图像创建图谱,然后程序自动搜索肝脏区域,最后将图谱与待分割CT图像依次进行仿射配准和B样条配准。配准以后的图谱肝脏轮廓即可表示为目标肝脏分割轮廓,进而计算出肝脏体积。结果评估结果显示,上述方法在肝脏体积误差方面表现出色,达到77分,但在局部（主要在肝脏尖端）出现较大的误差。结论该方法分割临床肝脏CT图像具有可行性。     

结合脑图谱和水平集的MR图像分割的研究

本文利用脑图谱的先验知识并结合水平集等算法实现对脑MR图像的初步分割。主要步骤：（1）选取数字脑图谱，对图谱进行预处理；（2）实现图谱与脑MR图像的配准；（3）利用图谱提供的轮廓信息对水平集算法进行初始化，完成颅骨和脑脊液的提取以及脑白质和脑灰质的分割。实验结果表明，利用脑图谱提供的信息可有效解决水平集算法初始化问题，缩小求解空间，减少迭代次数，该方法具有较好的鲁棒性。     

Automatic segmentation of the bone and extraction of the bone-cartilage interface from magnetic resonance images of the knee

The accurate segmentation of the articular cartilages from magnetic resonance (MR) images of the knee is important for clinical studies and drug trials into conditions like osteoarthritis. Currently, segmentations are obtained using time-consuming manual or semi-automatic algorithms which have high inter- and intra-observer variabilities. This paper presents an important step towards obtaining automatic and accurate segmentations of the cartilages, namely an approach to automatically segment the bones and extract the bone-cartilage interfaces (BCI) in the knee. The segmentation is performed using three-dimensional active shape models, which are initialized using an affine registration to an atlas. The BCI are then extracted using image information and prior knowledge about the likelihood of each point belonging to the interface. The accuracy and robustness of the approach was experimentally validated using an MR database of fat suppressed spoiled gradient recall images. The (femur, tibia, patella) bone segmentation had a median Dice similarity coefficient of (0.96, 0.96, 0.89) and an average point-to-surface error of 0.16 mm on the BCI. The extracted BCI had a median surface overlap of 0.94 with the real interface, demonstrating its usefulness for subsequent cartilage segmentation or quantitative analysis.     

Automatic segmentation of phase-correlated CT scans through nonrigid image registration using geometrically regularized free-form deformation

Conventional radiotherapy is planned using free-breathing computed tomography (CT), ignoring the motion and deformation of the anatomy from respiration. New breath-hold-synchronized, gated, and four-dimensional (4D) CT acquisition strategies are enabling radiotherapy planning utilizing a set of CT scans belonging to different phases of the breathing cycle. Such 4D treatment planning relies on the availability of tumor and organ contours in all phases. The current practice of manual segmentation is impractical for 4D CT, because it is time consuming and tedious. A viable solution is registration-based segmentation, through which contours provided by an expert for a particular phase are propagated to all other phases while accounting for phase-to-phase motion and anatomical deformation. Deformable image registration is central to this task, and a free-form deformation-based nonrigid image registration algorithm will be presented. Compared with the original algorithm, this version uses novel, computationally simpler geometric constraints to preserve the topology of the dense control-point grid used to represent free-form deformation and prevent tissue fold-over. Using mean squared difference as an image similarity criterion, the inhale phase is registered to the exhale phase of lung CT scans of five patients and of characteristically low-contrast abdominal CT scans of four patients. In addition, using expert contours for the inhale phase, the corresponding contours were automatically generated for the exhale phase. The accuracy of the segmentation (and hence deformable image registration) was judged by comparing automatically segmented contours with expert contours traced directly in the exhale phase scan using three metrics: volume overlap index, root mean square distance, and Hausdorff distance. The accuracy of the segmentation (in terms of radial distance mismatch) was approximately 2 mm in the thorax and 3 mm in the abdomen, which compares favorably to the accuracies reported elsewhere. Unlike most prior work, segmentation of the tumor is also presented. The clinical implementation of 4D treatment planning is critically dependent on automatic segmentation, for which is offered one of the most accurate algorithms yet presented.     

基于ITK多图谱配准的脑部皮质下核团的分割研究

大量研究表明,阿尔茨海默症(AD)的病变与大脑皮质下核团的萎缩息息相关,某些核团的萎缩(如海马)可能成为AD疾病早期诊断的标志,而皮质下核团的分割是研究核团萎缩模式的重要前提。基于AD患者和正常人各30例3DT1W-MR图像,先结合直方图分析和三维形态学分析方法对图像进行脑组织提取,后采用ITK配准算法将10个脑图谱图像经两阶段分别配准到提取脑组织后的图像空间。第一阶段实现基于均方差的仿射配准,第二阶段实现基于互信息的B样条形变配准,两阶段的配准均采用线性插值法和梯度下降的优化搜索方法。最后采用STAPLE融合算法,对配准后得到的10个目标图像进行图像融合,得到最终的分割结果。结果表明:除尾状核外,分割得到的其余6对核团的体积与常用的FSL-FIRST算法的分割结果无统计学差别(P>0.05);AD患者的右侧伏核和双侧海马发生萎缩(P<0.05)。因此,基于ITK配准框架的多图谱配准分割方法能有效分割MR图像上边界不明确的皮质下核团。     

基于人工智能的多模态影像辅助海马体自动勾画研究

目的:利用基于深度学习的人工智能算法,结合头颅MRI和CT的多模态影像,开发海马结构自动勾画技术,为头颅放疗过程中海马体的保护提供高效、准确的自动勾画方法。方法:收集清华大学第一附属医院放疗科从2020年1月~12月就诊的40例脑转移癌患者的定位头颅CT及MRI影像,分别在CT图像、CT-MRI配准图像的两个数据集上训练3D U-Net、3D U-Net Cascade、3D BUC-Net 3个深度学习模型,计算3个模型自动分割的左右海马体与对应的人工标注之间的Dice相似系数（DSC）和95%豪斯多夫距离（95 HD）,以及两者的体积作为模型的分割准确性的评估,并且以对同一大小patch图像的自动分割耗时作为模型效率的评估。结果:引入MRI图像信息对左右海马的自动分割精度有明显的提升;模型3D BUC-Net在CT-MRI数据集上对左右海马体的自动分割都取得最好分割结果（DSC:0.900±0.017,0.882±0.026;95HD:0.792±0.084,0.823±0.093）,而且该模型的分割效率更高。结论:模型3D BUC-Net能在多模态影像上实现高效、准确的海马区的自动勾画,为头颅放疗过程中海马区的保护提供方便。     

A feasibility study of mutual information based setup error estimation for radiotherapy.

We have investigated a fully automatic setup error estimation method that aligns DRRs (digitally reconstructed radiographs) from a three-dimensional planning computed tomography image onto two-dimensional radiographs that are acquired in a treatment room. We have chosen a MI (mutual information)-based image registration method, hoping for robustness to intensity differences between the DRRs and the radiographs. The MI-based estimator is fully automatic since it is based on the image intensity values without segmentation. Using 10 repeated scans of an anthropomorphic chest phantom in one position and two single scans in two different positions, we evaluated the performance of the proposed method and a correlation-based method against the setup error determined by fiducial marker-based method. The mean differences between the proposed method and the fiducial marker-based method were smaller than 1 mm for translational parameters and 0.8 degree for rotational parameters. The standard deviations of estimates from the proposed method due to detector noise were smaller than 0.3 mm and 0.07 degree for the translational parameters and rotational parameters, respectively.     

利用图谱匹配分割标注VHP数据集

利用TT脑图谱中丰富的结构信息,本文提出了一种自动分割脑图像的方法,并将其用于Visible Human数据集（VHD）的脑图像的分割,这种方法可分为两步,首先,将VHD中的脑图像和TT Atlas配准,通过图像和医学图谱的匹配,可以把图谱中存储的拓朴信息直接映射到ＶＨＤ,然后,利用这个预分割的模板对VHD脑图像进行模糊聚类分割,为自动将模板中的结构信息用于分割,本文利用Chamfer距离变换,提出了一中引入形状因子的FCM聚类算法。     

Extracting Lungs from CT Images via Deep Convolutional Neural Network Based Segmentation and Two-Pass Contour Refinement

Lung segmentation is a key step of thoracic computed tomography (CT) image processing, and it plays an important role in computer-aided pulmonary disease diagnostics. However, the presence of image noises, pathologies, vessels, individual anatomical varieties, and so on makes lung segmentation a complex task. In this paper, we present a fully automatic algorithm for segmenting lungs from thoracic CT images accurately. An input image is first spilt into a set of non-overlapping fixed-sized image patches, and a deep convolutional neural network model is constructed to extract initial lung regions by classifying image patches. Superpixel segmentation is then performed on the preprocessed thoracic CT image, and the lung contours are locally refined according to corresponding superpixel contours with our adjacent point statistics method. Segmented lung contours are further globally refined by an edge direction tracing technique for the inclusion of juxta-pleural lesions. Our algorithm is tested on a group of thoracic CT scans with interstitial lung diseases. Experiments show that our algorithm creates an average Dice similarity coefficient of 97.95% and Jaccard’s similarity index of 94.48%, with 2.8% average over-segmentation rate and 3.3% under-segmentation rate compared with manually segmented results. Meanwhile, it shows better performance compared with several feature-based machine learning methods and current methods on lung segmentation.     

Adaptation of a 3D prostate cancer atlas for transrectal ultrasound guided target-specific biopsy

Due to lack of imaging modalities to identify prostate cancer in vivo, current TRUS guided prostate biopsies are taken randomly. Consequently, many important cancers are missed during initial biopsies. The purpose of this study was to determine the potential clinical utility of a high-speed registration algorithm for a 3D prostate cancer atlas. This 3D prostate cancer atlas provides voxel-level likelihood of cancer and optimized biopsy locations on a template space (Zhan et al 2007). The atlas was constructed from 158 expert annotated, 3D reconstructed radical prostatectomy specimens outlined for cancers (Shen et al 2004). For successful clinical implementation, the prostate atlas needs to be registered to each patient's TRUS image with high registration accuracy in a time-efficient manner. This is implemented in a two-step procedure, the segmentation of the prostate gland from a patient's TRUS image followed by the registration of the prostate atlas. We have developed a fast registration algorithm suitable for clinical applications of this prostate cancer atlas. The registration algorithm was implemented on a graphical processing unit (GPU) to meet the critical processing speed requirements for atlas guided biopsy. A color overlay of the atlas superposed on the TRUS image was presented to help pick statistically likely regions known to harbor cancer. We validated our fast registration algorithm using computer simulations of two optimized 7- and 12-core biopsy protocols to maximize the overall detection rate. Using a GPU, patient's TRUS image segmentation and atlas registration took less than 12 s. The prostate cancer atlas guided 7- and 12-core biopsy protocols had cancer detection rates of 84.81% and 89.87% respectively when validated on the same set of data. Whereas the sextant biopsy approach without the utility of 3D cancer atlas detected only 70.5% of the cancers using the same histology data. We estimate 10-20% increase in prostate cancer detection rates when TRUS guided biopsies are assisted by the 3D prostate cancer atlas compared to the current standard of care. The fast registration algorithm we have developed can easily be adapted for clinical applications for the improved diagnosis of prostate cancer.     

Automatic bladder segmentation on CBCT for multiple plan ART of bladder cancer using a patient-specific bladder model

In multiple plan adaptive radiotherapy (ART) strategies of bladder cancer, a library of plans corresponding to different bladder volumes is created based on images acquired in early treatment sessions. Subsequently, the plan for the smallest PTV safely covering the bladder on cone-beam CT (CBCT) is selected as the plan of the day. The aim of this study is to develop an automatic bladder segmentation approach suitable for CBCT scans and test its ability to select the appropriate plan from the library of plans for such an ART procedure. Twenty-three bladder cancer patients with a planning CT and on average 11.6 CBCT scans were included in our study. For each patient, all CBCT scans were matched to the planning CT on bony anatomy. Bladder contours were manually delineated for each planning CT (for model building) and CBCT (for model building and validation). The automatic segmentation method consisted of two steps. A patient-specific bladder deformation model was built from the training data set of each patient (the planning CT and the first five CBCT scans). Then, the model was applied to automatically segment bladders in the validation data of the same patient (the remaining CBCT scans). Principal component analysis (PCA) was applied to the training data to model patient-specific bladder deformation patterns. The number of PCA modes for each patient was chosen such that the bladder shapes in the training set could be represented by such number of PCA modes with less than 0.1?cm mean residual error. The automatic segmentation started from the bladder shape of a reference CBCT, which was adjusted by changing the weight of each PCA mode. As a result, the segmentation contour was deformed consistently with the training set to fit the bladder in the validation image. A cost function was defined by the absolute difference between the directional gradient field of reference CBCT sampled on the corresponding bladder contour and the directional gradient field of validation CBCT sampled on the segmentation contour candidate. The cost function measured the goodness of fit of the segmentation on the validation image and was minimized using a simplex optimizer. For each validation CBCT image, the segmentations were done five times using a different reference CBCT. The one with the lowest cost function was selected as the final bladder segmentation. Volume- and distance-based metrics and the accuracy of plan selection were evaluated to quantify the performance. Two to four PCA modes were needed to represent the bladder shape variation with less than 0.1?cm average residual error for the training data of each patient. The automatically segmented bladders had a 78.5% mean conformity index with the manual delineations. The mean SD of the local residual error over all patients was 0.24?cm. The agreement of plan selection between automatic and manual bladder segmentations was 77.5%. PCA is an efficient method to describe patient-specific bladder deformation. The statistical-shape-based segmentation approach is robust to handle the relatively poor CBCT image quality and allows for fast and reliable automatic segmentation of the bladder on CBCT for selecting the appropriate plan from a library of plans.     

Sequential Registration-Based Segmentation of the Prostate Gland in MR Image Volumes

Accurate and fast segmentation and volume estimation of the prostate gland in magnetic resonance (MR) images are necessary steps in the diagnosis, treatment, and monitoring of prostate cancer. This paper presents an algorithm for the prostate gland volume estimation based on the semi-automated segmentation of individual slices in T2-weighted MR image sequences. The proposed sequential registration-based segmentation (SRS) algorithm, which was inspired by the clinical workflow during medical image contouring, relies on inter-slice image registration and user interaction/correction to segment the prostate gland without the use of an anatomical atlas. It automatically generates contours for each slice using a registration algorithm, provided that the user edits and approves the marking in some previous slices. We conducted comprehensive experiments to measure the performance of the proposed algorithm using three registration methods (i.e., rigid, affine, and nonrigid). Five radiation oncologists participated in the study where they contoured the prostate MR (T2-weighted) images of 15 patients both manually and using the SRS algorithm. Compared to the manual segmentation, on average, the SRS algorithm reduced the contouring time by 62 % (a speedup factor of 2.64×) while maintaining the segmentation accuracy at the same level as the intra-user agreement level (i.e., Dice similarity coefficient of 91 versus 90 %). The proposed algorithm exploits the inter-slice similarity of volumetric MR image series to achieve highly accurate results while significantly reducing the contouring time.     

Registration-based Automatic 3D Segmentation of Cardiac CT Images

Segmenting whole heart from cardiac computed tomography(CT images can provide an important basis for the evaluation of cardiac function and help improve the accuracy of clinical diagnosis. Manual segmentation is the most accurate method for cardiac segmentation. But it is time consuming and not sufficiently reproducible. However, clinicians still rely on this method in practical applications. So a fully automatic method is needed to improve the segmentation efficiency. This pape proposes a registration-based automatic approach for three-dimensional(3D segmentation of cardiac CT images. The proposed method utilizes the similarity o cardiac CT images between different individuals, and uses registration to achieve the segmentation. Affine transformation is firstly implemented to achieve global coarse registration. Then, cubic B-splines are used to refine the local details in locally accurate registration. Mutual information(Ml) is used as the similarity measure, and adaptive stochastic gradient descent(ASGD) as the optimization algorithm. Ou method is applied to the dual-source cardiac CT images to segment whole heart Experimental results show that the proposed method can automatically segment whole heart from cardiac CT images.     

基于联合深度网络和形态结构约束的三维医学图像分割方法

医学图像自动分割具有广泛和重要临床应用价值,特别是病灶、脏器的自动分割。基于传统图像处理方法的医学图像分割仅能利用浅层结构模型的浅层特征来识别感兴趣区域,并且需要大量人工干预。而基于机器学习的分割方法在模型建模时存在局限性且缺乏可解释性。本研究提出一种基于Transformer和卷积神经网络结合形态结构约束的三维医学图像分割方法。编码器中利用卷积神经网络和Transformer构建U型网络结构提取多重特征;解码器中采用上采样并通过跳跃连接将不同层次的特征拼接在一起;加入形态结构约束模块,通过提取病灶和脏器等分割目标的形状信息,以增强模型可解释性,并采用最大池化和平均池化操作,对经过卷积神经网络得到的结果进一步提取有代表性的特征,作为形态结构模块的输入,最终提高分割结果的准确性。在公开数据集Synapse和ACDC上利用评价指标Dice相似系数(DSC)和Hausdorff距离(HD)验证所提出算法的有效性。其中,在Synapse数据集上,18例数据作为训练集,12例数据作为测试集;在ACDC数据集上,70例数据作为训练集,10例数据作为验证集,20例数据作为测试集。实验结果表明,在Sy...     

Assessment of rigid multi-modality image registration consistency using the multiple sub-volume registration (MSR) method

Registration of different imaging modalities such as CT, MRI, functional MRI (fMRI), positron (PET) and single photon (SPECT) emission tomography is used in many clinical applications. Determining the quality of any automatic registration procedure has been a challenging part because no gold standard is available to evaluate the registration. In this note we present a method, called the 'multiple sub-volume registration' (MSR) method, for assessing the consistency of a rigid registration. This is done by registering sub-images of one data set on the other data set, performing a crude non-rigid registration. By analysing the deviations (local deformations) of the sub-volume registrations from the full registration we get a measure of the consistency of the rigid registration. Registration of 15 data sets which include CT, MR and PET images for brain, head and neck, cervix, prostate and lung was performed utilizing a rigid body registration with normalized mutual information as the similarity measure. The resulting registrations were classified as good or bad by visual inspection. The resulting registrations were also classified using our MSR method. The results of our MSR method agree with the classification obtained from visual inspection for all cases (p < 0.02 based on ANOVA of the good and bad groups). The proposed method is independent of the registration algorithm and similarity measure. It can be used for multi-modality image data sets and different anatomic sites of the patient.     

Quantitative characterization of metastatic disease in the spine. Part I. Semiautomated segmentation using atlas-based deformable registration and the level set method

Quantitative assessment of metastatic disease in bone is often considered immeasurable and, as such, patients with skeletal metastases are often excluded from clinical trials. In order to effectively quantify the impact of metastatic tumor involvement in the spine, accurate segmentation of the vertebra is required. Manual segmentation can be accurate but involves extensive and time-consuming user interaction. Potential solutions to automating segmentation of metastatically involved vertebrae are demons deformable image registration and level set methods. The purpose of this study was to develop a semiautomated method to accurately segment tumor-bearing vertebrae using the aforementioned techniques. By maintaining morphology of an atlas, the demons-level set composite algorithm was able to accurately differentiate between trans-cortical tumors and surrounding soft tissue of identical intensity. The algorithm successfully segmented both the vertebral body and trabecular centrum of tumor-involved and healthy vertebrae. This work validates our approach as equivalent in accuracy to an experienced user.     

Large deformation three-dimensional image registration in image-guided radiation therapy

In this paper, we present and validate a framework, based on deformable image registration, for automatic processing of serial three-dimensional CT images used in image-guided radiation therapy. A major assumption in deformable image registration has been that, if two images are being registered, every point of one image corresponds appropriately to some point in the other. For intra-treatment images of the prostate, however, this assumption is violated by the variable presence of bowel gas. The framework presented here explicitly extends previous deformable image registration algorithms to accommodate such regions in the image for which no correspondence exists. We show how to use our registration technique as a tool for organ segmentation, and present a statistical analysis of this segmentation method, validating it by comparison with multiple human raters. We also show how the deformable registration technique can be used to determine the dosimetric effect of a given plan in the presence of non-rigid tissue motion. In addition to dose accumulation, we describe a method for estimating the biological effects of tissue motion using a linear-quadratic model. This work is described in the context of a prostate treatment protocol, but it is of general applicability.     

Gland and Zonal Segmentation of Prostate on T2W MR Images

For many years, prostate segmentation on MR images concerned only the extraction of the entire gland. Currently, in the focal treatment era, there is a continuously increasing need for the separation of the different parts of the organ. In this paper, we propose an automatic segmentation method based on the use of T2W images and atlas images to segment the prostate and to isolate the peripheral and transition zones. The algorithm consists of two stages. First, the target image is registered with each zonal atlas image then the segmentation is obtained by the application of an evidential C-Means clustering. The method was evaluated on a representative and multi-centric image base and yielded mean Dice accuracy values of 0.81, 0.70, and 0.62 for the prostate, the transition zone, and peripheral zone, respectively.