Rapid automated landmarking for morphometric analysis of three‐dimensional facial scans

Automated phenotyping is essential for the creation of large, highly standardized datasets from anatomical imaging data. Such datasets can support large‐scale studies of complex traits or clinical studies related to precision medicine or clinical trials. We have developed a method that generates three‐dimensional landmark data that meet the requirements of standard geometric morphometric analyses. The method is robust and can be implemented without high‐performance computing resources. We validated the method using both direct comparison to manual landmarking on the same individuals and also analyses of the variation patterns and outlier patterns in a large dataset of automated and manual landmark data. Direct comparison of manual and automated landmarks reveals that automated landmark data are less variable, but more highly integrated and reproducible. Automated data produce covariation structure that closely resembles that of manual landmarks. We further find that while our method does produce some landmarking errors, they tend to be readily detectable and can be fixed by adjusting parameters used in the registration and control‐point steps. Data generated using the method described here have been successfully used to study the genomic architecture of facial shape in two different genome‐wide association studies of facial shape.     

Measurement error in μCT‐based three‐dimensional geometric morphometrics introduced by surface generation and landmark data acquisition

Computed‐tomography‐derived (CT‐derived) polymesh surfaces are widely used in geometric morphometric studies. This approach is inevitably associated with decisions on scanning parameters, resolution, and segmentation strategies. Although the underlying processing steps have been shown to potentially contribute artefactual variance to three‐dimensional landmark coordinates, their effects on measurement error have rarely been assessed systematically in CT‐based geometric morphometric studies. The present study systematically assessed artefactual variance in landmark data introduced by the use of different voxel sizes, segmentation strategies, surface simplification degrees, and by inter‐ and intra‐observer differences, and compared their magnitude to true biological variation. Multiple CT‐derived surface variants of the anuran (Amphibia: Anura) pectoral girdle were generated by systematic changes in the factors that potentially influence the surface geometries. Twenty‐four landmarks were repeatedly acquired by different observers. The contribution of all factors to the total variance in the landmark data was assessed using random‐factor nested permanova s. Selected sets of Euclidean distances between landmark sets served further to compare the variance among factor levels. Landmark precision was assessed by landmark standard deviation and compared among observers and days. Results showed that all factors, except for voxel size, significantly contributed to measurement error in at least some of the analyses performed. In total, 6.75% of the variance in landmark data that mimicked a realistic biological study was caused by measurement error. In this landmark dataset, intra‐observer error was the major source of artefactual variance followed by inter‐observer error; the factor segmentation contributed < 1% and slight surface simplification had no significant effect. Inter‐observer error clearly exceeded intra‐observer error in a different landmark dataset acquired by six partly inexperienced observers. The results suggest that intra‐observer error can potentially be reduced by including a training period prior to the actual landmark acquisition task and by acquiring landmarks in as few sessions as possible. Additionally, the application of moderate and careful surface simplification and, potentially, also the use of case‐specific optimal combinations of automatic local thresholding algorithms and parameters for segmentation can help reduce intra‐observer error. If landmark data are to be acquired by several observers, it is important to ensure that all observers are consistent in landmark identification. Despite the significant amount of artefactual variance, we have shown that landmark data acquired from microCT‐derived surfaces are precise enough to study the shape of anuran pectoral girdles. Yet, a systematic assessment of measurement error is advisable for all geometric morphometric studies.     

基于CTVision分析不同配准方式对鼻咽癌摆位误差的影响

目的分析CTVision进行鼻咽癌图像引导时采用不同的配准方式对摆位误差的影响。方法采用两种不同的图像配准方式,对同一个进行调强放射治疗的鼻咽癌患者采集得到的治疗CT图像与计划CT图像进行配准分析。自动配准：系统自动调节窗宽、窗位,进行图像灰度配准。骨性配准：手动调节基于第一颈椎体为骨性标志进行配准。配准得到的摆位误差大小以均数和标准差的形式表示。结果分别计算得到两种方法在X、Y、Z三个方向上的摆位误差数据．自动配准和骨性配准结果分别是X轴为（0．2286±0．1496）cm和（0．0571±0．0976）cm,Y轴为（-0．1000±0．1000）cm和（-0．0714±0．1254）cm．Z轴为（0．1000±0．0816）cm和（0．1000±0．0577）cm。两种配准方法比较,靶区在X轴上的摆位误差差异有统计学意义（P〈0．05）,而在Y轴和Z轴上差异均无统计学意义（P〉0．05）。结论鼻咽癌进行图像引导时．基于骨性标志的手动配准和基于灰度的自动配准．在X轴方向的摆位误差校正差异明显．在Y轴和Z轴方向的无明显差异。采用骨性标志的配准是一种更为准确和有效的配准方式。     

Investigation of filter sets for supervised pixel classification of cephalometric landmarks by spatial spectroscopy

The diagnostic process of orthodontics requires the analysis of a cephalometric radiograph. Image landmarks on this two-dimensional lateral projection image of the patient's head are manually identified and spatial relationships are evaluated. This method is very time consuming. A reliable method for automatic computer landmark identification does not exist. Spatial Spectroscopy is a proposed method of automatic landmark identification on cephalometric radiographs, that decomposes an image by convolving it with a set of filters followed by a statistical decision process. The purpose of this paper is to discuss and test appropriate filter sets for the application of Spatial Spectroscopy for automatic identification of cephalometric radiographic landmarks. This study evaluated two different filter sets with 15 landmarks on fourteen images. Spatial Spectroscopy was able to consistently locate landmarks on all 14 cephalometric radiographs tested. The mean landmark identification error of 0.841±1.253 pixels for a Multiscale Derivative filter set and 0.912±1.364 pixels for an Offset Gaussian filter set was not significantly different. Furthermore, there were no significant differences between identification of individual landmarks for the Multiscale Derivative and the Offset Gaussian filter set (P>0.05). These results suggest that Spatial Spectroscopy may be useful in landmark identification tasks.     

A population level atlas of Mus musculus craniofacial skeleton and automated image‐based shape analysis

Laboratory mice are staples for evo/devo and genetics studies. Inbred strains provide a uniform genetic background to manipulate and understand gene–environment interactions, while their crosses have been instrumental in studies of genetic architecture, integration and modularity, and mapping of complex biological traits. Recently, there have been multiple large‐scale studies of laboratory mice to further our understanding of the developmental basis, evolution, and genetic control of shape variation in the craniofacial skeleton (i.e. skull and mandible). These experiments typically use micro‐computed tomography (micro‐CT) to capture the craniofacial phenotype in 3D and rely on manually annotated anatomical landmarks to conduct statistical shape analysis. Although the common choice for imaging modality and phenotyping provides the potential for collaborative research for even larger studies with more statistical power, the investigator (or lab‐specific) nature of the data collection hampers these efforts. Investigators are rightly concerned that subtle differences in how anatomical landmarks were recorded will create systematic bias between studies that will eventually influence scientific findings. Even if researchers are willing to repeat landmark annotation on a combined dataset, different lab practices and software choices may create obstacles for standardization beyond the underlying imaging data. Here, we propose a freely available analysis system that could assist in the standardization of micro‐CT studies in the mouse. Our proposal uses best practices developed in biomedical imaging and takes advantage of existing open‐source software and imaging formats. Our first contribution is the creation of a synthetic template for the adult mouse craniofacial skeleton from 25 inbred strains and five F1 crosses that are widely used in biological research. The template contains a fully segmented cranium, left and right hemi‐mandibles, endocranial space, and the first few cervical vertebrae. We have been using this template in our lab to segment and isolate cranial structures in an automated fashion from a mixed population of mice, including craniofacial mutants, aged 4–12.5 weeks. As a secondary contribution, we demonstrate an application of nearly automated shape analysis, using symmetric diffeomorphic image registration. This approach, which we call diGPA, closely approximates the popular generalized Procrustes analysis (GPA) but negates the collection of anatomical landmarks. We achieve our goals by using the open‐source advanced normalization tools (ANT) image quantification library, as well as its associated R library (ANTsR) for statistical image analysis. Finally, we make a plea to investigators to commit to using open imaging standards and software in their labs to the extent possible to increase the potential for data exchange and improve the reproducibility of findings. Future work will incorporate more anatomical detail (such as individual cranial bones, turbinals, dentition, middle ear ossicles) and more diversity into the template.     

Evaluation of morphological changes in the adult skull with age and sex

The morphology of the brain and skull are important in the evaluation of the aging human; however, little is known about how the skull may change with age. The objective of this study was to evaluate the morphological changes of the adult skull using three‐dimensional geometric morphometric analysis of thousands of landmarks with the focus on anatomic regions that may be correlated with brain atrophy and head injury. Computed tomography data were collected between ages 20 and 100. Each scan was segmented using thresholding techniques. An atlas image of a 50th percentile skull was registered to each subject scan by computing a series of rigid, affine, and non‐linear transformations between atlas space and subject space. Landmarks on the atlas skull were transformed to each subject and partitioned into the inner and outer cranial vault and the cranial fossae. A generalized Procrustes analysis was completed for the landmark sets. The coordinate locations describing the shape of each region were regressed with age to generate a model predicting the landmark location with age. Permutation testing was performed to assess significant changes with age. For the males, all anatomic regions reveal significant changes in shape with age except for the posterior cranial fossa. For the females, only the middle cranial fossa and anterior cranial fossa were found to change significantly in shape. Results of this study are important for understanding the adult skull and how shape changes may pertain to brain atrophy, aging, and injury.     

Landmark‐based software for anatomical measurements: A precision study

The aim of this study was to develop a software program, called Landmarker, which would aid studies of complex anatomical morphometry by simplifying the manual identification of landmarks in 3D images. We also tested its precision on routine magnetic resonance imaging (MRI) scans. To understand human biological variation, there is a need to identify morphological characteristics from the exterior and the interior of human anatomy. MRI, as opposed to other radiographic methods (mainly based on X‐ray techniques), supplies good soft tissue contrast, which allows for more complex assessments than what bony landmarks can provide. Because automation of this assessment is highly demanding, one of the primary goals for the new software was to enable more rapid identification of landmark sets in 3D image data. Repeat acquisition of head MRIs having a resolution of 0.94 × 0.94 × 1.20 mm³ were performed on 10 volunteers. Intra‐ and interoperator, as well as interacquisition variations of manual identification of exterior, craniofacial interior, and brain landmarks were studied. The average distances between landmarks were <1.8 mm, <2.3 mm, and <2.0 mm in the intra‐ and interoperator, and interacquisition evaluations, respectively. This study presents new software for time efficient identification of complex craniofacial landmarks in 3D MRI. To the best of our knowledge, no evaluation of software for rapid landmark‐based analysis of complex anatomies from 3D MR data has yet been presented. This software may also be useful for studies in other anatomical regions and for other types of image data. Clin. Anat. 22:456–462, 2009. © 2009 Wiley‐Liss, Inc.     

用无约束优化薄板样条实现平滑的医学图像弹性配准

医学图像弹性配准是医学图像处理的一个重要研究方向。目前采用的方法多是手动选择对应标记点，然后用薄板样条插值方法计算配准变换。由于对应点的选取总是存在误差，所以配准的准确性受到影响，而且手动选点操作繁杂、耗时大。为此，我们根据最优化理论，改进了薄板样条插值方法，并在此基础上采用了一种自动标记点选择方法。将这两者结合，我们得到了一种自动、准确、鲁棒性好的配准方法，运用此方法进行医学图像的弹性配准，得到了更好的结果。     

An automatic facial landmarking for children with rare diseases

Two to three thousand syndromes modify facial features: their screening requires the eye of an expert in dysmorphology. A widely used tool in shape characterization is geometric morphometrics based on landmarks, which are precise and reproducible anatomical points. Landmark positioning is user dependent and time consuming. Many automatic landmarking tools are currently available but do not work for children, because they have mainly been trained using photographic databases of healthy adults. Here, we developed a method for building an automatic landmarking pipeline for frontal and lateral facial photographs as well as photographs of external ears. We evaluated the algorithm on patients diagnosed with Treacher Collins (TC) syndrome as it is the most frequent mandibulofacial dysostosis in humans and is clinically recognizable although highly variable in severity. We extracted photographs from the photographic database of the maxillofacial surgery and plastic surgery department of Hôpital Necker–Enfants Malades in Paris, France with the diagnosis of TC syndrome. The control group was built from children admitted for craniofacial trauma or skin lesions. After testing two methods of object detection by bounding boxes, a Haar Cascade-based tool and a Faster Region-based Convolutional Neural Network (Faster R-CNN)-based tool, we evaluated three different automatic annotation algorithms: the patch-based active appearance model (AAM), the holistic AAM, and the constrained local model (CLM). The final error corresponding to the distance between the points placed by automatic annotation and those placed by manual annotation was reported. We included, respectively, 1664, 2044, and 1375 manually annotated frontal, profile, and ear photographs. Object recognition was optimized with the Faster R-CNN-based detector. The best annotation model was the patch-based AAM (p < 0.001 for frontal faces, p = 0.082 for profile faces and p < 0.001 for ears). This automatic annotation model resulted in the same classification performance as manually annotated data. Pretraining on public photographs did not improve the performance of the model. We defined a pipeline to create automatic annotation models adapted to faces with congenital anomalies, an essential prerequisite for research in dysmorphology.     

Automatic noise robust registration of radiographs for subtraction using strategic local correlation: an application to radiographs of dental implants

Most of digital subtraction methods in dental radiography are based on registration using manual landmarks. We have developed an automatic registration method without using the manual selection of landmarks. By restricting a geometrical matching of images to a region of interest (ROI), we compare the cross-correlation coefficient only between the ROIs. The affine or perspective transform parameters satisfying maximum of cross-correlation between the local regions are searched iteratively by a fast searching strategy. The parameters are searched on the 14 scale image coarsely and then, the fine registration is performed on the original scale image. The developed method can match the images corrupted by Gaussian noise with the same accuracy for the images without any transform simulation. The registration accuracy of the perspective method shows a 17% improvement over the manual method. The application of the developed method to radiographs of dental implants provides an automatic noise robust registration with high accuracy in almost real time.     

Cephalometric image analysis and measurement for orthognathic surgery

Automatic identification of landmarks in cephalometry is very important and useful for orthognathic surgery. A computerised automatic cephalometric analysis system (CACAS), based on image processing, is presented. For an original X-ray image, median filtering and histogram equalisation are used to improve image quality. The edge of an X-ray image is detected by a wavelet transform and Canny filter. Seventeen landmarks in cephalometry are successfully identified by knowledge-based edge tracing and changeable templates. Seventy-three measurements based on distances, angles and ratios between landmarks are computed automatically. The reliability of the landmarks and the validity of the measurements are compared for automatic and manual operation. The values of measurements obtained by CACAS are more precise and reliable: the mean error for linear measurements is less than 0.9 mm; the mean error for angular measurements is less than 1.2°. The rate of validity is over 80%, even if the image quality is poor. For an image with a high signal-to-noise ratio, the rate of validity of landmarking and measurements using the CACAS system is over 90%.     

Computational mouse atlases and their application to automatic assessment of craniofacial dysmorphology caused by the Crouzon mutation Fgfr2(C342Y)

Crouzon syndrome is characterized by premature fusion of sutures and synchondroses. Recently, the first mouse model of the syndrome was generated, having the mutation Cys342Tyr in Fgfr2c, equivalent to the most common human Crouzon/Pfeiffer syndrome mutation. In this study, a set of micro-computed tomography (CT) scannings of the skulls of wild-type mice and Crouzon mice were analysed with respect to the dysmorphology caused by Crouzon syndrome. A computational craniofacial atlas was built automatically from the set of wild-type mouse micro-CT volumes using (1) affine and (2) non-rigid image registration. Subsequently, the atlas was deformed to match each subject from the two groups of mice. The accuracy of these registrations was measured by a comparison of manually placed landmarks from two different observers and automatically assessed landmarks. Both of the automatic approaches were within the interobserver accuracy for normal specimens, and the non-rigid approach was within the interobserver accuracy for the Crouzon specimens. Four linear measurements, skull length, height and width and interorbital distance, were carried out automatically using the two different approaches. Both automatic approaches assessed the skull length, width and height accurately for both groups of mice. The non-rigid approach measured the interorbital distance accurately for both groups while the affine approach failed to assess this parameter for both groups. Using the full capability of the non-rigid approach, local displacements obtained when registering the non-rigid wild-type atlas to a non-rigid Crouzon mouse atlas were determined on the surface of the wild-type atlas. This revealed a 0.6-mm bending in the nasal region and a 0.8-mm shortening of the zygoma, which are similar to characteristics previously reported in humans. The most striking finding of this analysis was an angulation of approximately 0.6 mm of the cranial base, which has not been reported in humans. Comparing the two different methodologies, it is concluded that the non-rigid approach is the best way to assess linear skull parameters automatically. Furthermore, the non-rigid approach is essential when it comes to analysing local, non-linear shape differences.     

Three-dimensional morphometric analysis of brain shape in nonsyndromic orofacial clefting

Previous studies report structural brain differences in individuals with nonsyndromic orofacial clefts (NSOFC) compared with healthy controls. These changes involve non‐uniform shifts in tissue volume within the cerebral cortex and cerebellum, suggesting that the shape of the brain may be altered in cleft‐affected individuals. To test this hypothesis, a landmark‐based morphometric approach was utilized to quantify and compare brain shape in a sample of 31 adult males with cleft lip with or without cleft palate (CL/P), 14 adult males with cleft palate only (CPO) and 41 matched healthy controls. Fifteen midline and surface landmarks were collected from MRI brain scans and the resulting 3D coordinates were subjected to statistical shape analysis. First, a geometric morphometric analysis was performed in three steps: Procrustes superimposition of raw landmark coordinates, omnibus testing for group difference in shape, followed by canonical variates analysis (CVA) of shape coordinates. Secondly, Euclidean distance matrix analysis (EDMA) was carried out on scaled inter‐landmark distances to identify localized shape differences throughout the brain. The geometric morphometric analysis revealed significant differences in brain shape among all three groups (P < 0.001). From CVA, the major brain shape changes associated with clefting included selective enlargement of the anterior cerebrum coupled with a relative reduction in posterior and/or inferior cerebral portions, changes in the medio‐lateral position of the cerebral poles, posterior displacement of the corpus callosum, and reorientation of the cerebellum. EDMA revealed largely similar brain shape changes. Thus, compared with controls, major brain shape differences were present in adult males with CL/P and CPO. These results both confirm and expand previous findings from traditional volumetric studies of the brain in clefting and provide further evidence that the neuroanatomical phenotype in individuals with NSOFC is a primary manifestation of the defect and not a secondarily acquired characteristic.     

Registration of electronic portal images for patient set-up verification

Images acquired from an electronic portal imaging device are aligned with digitally reconstructed radiographs (DRRs) or other portal images to verify patient positioning during radiation therapy. Most of the currently available computer aided registration methods are based on the manual placement of corresponding landmarks. The purpose of the paper is twofold: (a) the establishment of a methodology for patient set-up verification during radiotherapy based on the registration of electronic portal images, and (b) the evaluation of the proposed methodology in a clinical environment. The estimation of set-up errors, using the proposed methodology, can be accomplished by matching the portal image of the current fraction of the treatment with the portal image of the baseline treatment (reference portal image) using a nearly automated technique. The proposed registration method is tested on a number of phantom data as well as on data from four patients. The phantom data included portal images that corresponded to various positions of the phantom on the treatment couch. For each patient, a set of 30 portal images was used. For the phantom data (for both transverse and lateral portal images), the maximum absolute deviations of the translational shifts were within 1.5 mm, whereas the in-plane rotation angle error was less than 0.5 degrees. The two-way Anova revealed no statistical significant variability both within observer and between-observer measurements (P > 0.05). For the patient data, the mean values obtained with manual and the proposed registration methods were within 0.5 mm. In conclusion, the proposed registration method has been incorporated within a system, called ESTERR-PRO. Its image registration capability achieves high accuracy and both intra- and inter-user reproducibility. The system is fully operational within the Radiotherapy Department of 'HYGEIA' Hospital in Athens and it could be easily installed in any other clinical environment since it requires standardized hardware specifications and minimal human intervention.     

How Effective Are Geometric Morphometric Techniques for Assessing Functional Shape Variation? An Example From the Great Ape Temporomandibular Joint

Functional shape analyses have long relied on the use of shape ratios to test biomechanical hypotheses. This method is powerful because of the ease with which results are interpreted, but these techniques fall short in quantifying complex morphologies that may not have a strong biomechanical foundation but may still be functionally informative. In contrast, geometric morphometric methods are continually being adopted for quantifying complex shapes, but they tend to prove inadequate in functional analyses because they have little foundation in an explicit biomechanical framework. The goal of this study was to evaluate the intersection of these two methods using the great ape temporomandibular joint as a case study. Three‐dimensional coordinates of glenoid fossa and mandibular condyle shape were collected using a Microscribe digitizer. Linear distances extracted from these landmarks were analyzed using a series of one‐way ANOVAs; further, the landmark configurations were analyzed using geometric morphometric techniques. Results suggest that the two methods are broadly similar, although the geometric morphometric data allow for the identification of shape differences among taxa that were not immediately apparent in the univariate analyses. Furthermore, this study suggests several new approaches for translating these shape data into a biomechanical context by adjusting the data using a biomechanically relevant variable. © 2013 Wiley Periodicals, Inc.     

An enhanced block matching algorithm for fast elastic registration in adaptive radiotherapy

Image registration has many medical applications in diagnosis, therapy planning and therapy. Especially for time-adaptive radiotherapy, an efficient and accurate elastic registration of images acquired for treatment planning, and at the time of the actual treatment, is highly desirable. Therefore, we developed a fully automatic and fast block matching algorithm which identifies a set of anatomical landmarks in a 3D CT dataset and relocates them in another CT dataset by maximization of local correlation coefficients in the frequency domain. To transform the complete dataset, a smooth interpolation between the landmarks is calculated by modified thin-plate splines with local impact. The concept of the algorithm allows separate processing of image discontinuities like temporally changing air cavities in the intestinal track or rectum. The result is a fully transformed 3D planning dataset (planning CT as well as delineations of tumour and organs at risk) to a verification CT, allowing evaluation and, if necessary, changes of the treatment plan based on the current patient anatomy without time-consuming manual re-contouring. Typically the total calculation time is less than 5 min, which allows the use of the registration tool between acquiring the verification images and delivering the dose fraction for online corrections. We present verifications of the algorithm for five different patient datasets with different tumour locations (prostate, paraspinal and head-and-neck) by comparing the results with manually selected landmarks, visual assessment and consistency testing. It turns out that the mean error of the registration is better than the voxel resolution (2 x 2 x 3 mm(3)). In conclusion, we present an algorithm for fully automatic elastic image registration that is precise and fast enough for online corrections in an adaptive fractionated radiation treatment course.     

Genetics of murine craniofacial morphology: diallel analysis of the eight founders of the Collaborative Cross

Using eight inbred founder strains of the mouse Collaborative Cross (CC) project and their reciprocal F1 hybrids, we quantified variation in craniofacial morphology across mouse strains, explored genetic contributions to craniofacial variation that distinguish the founder strains, and tested whether specific or summary measures of craniofacial shape display stronger additive genetic contributions. This study thus provides critical information about phenotypic diversity among CC founder strains and about the genetic contributions to this phenotypic diversity, which is relevant to understanding the basis of variation in standard laboratory strains and natural populations. Craniofacial shape was quantified as a series of size‐adjusted linear dimensions (RDs) and by principal components (PC) analysis of morphological landmarks captured from computed tomography images from 62 of the 64 reciprocal crosses of the CC founder strains. We first identified aspects of skull morphology that vary between these phenotypically ‘normal’ founder strains and that are defining characteristics of these strains. We estimated the contributions of additive and various non‐additive genetic factors to phenotypic variation using diallel analyses of a subset of these strongly differing RDs and the first eight PCs of skull shape variation. We find little difference in the genetic contributions to RD measures and PC scores, suggesting fundamental similarities in the magnitude of genetic contributions to both specific and summary measures of craniofacial phenotypes. Our results indicate that there are stronger additive genetic effects associated with defining phenotypic characteristics of specific founder strains, suggesting these distinguishing measures are good candidates for use in genotype–phenotype association studies of CC mice. Our results add significantly to understanding of genotype–phenotype associations in the skull, which serve as a foundation for modeling the origins of medically and evolutionarily relevant variation.     

Using three-dimensional multigrid-based snake and multiresolution image registration for reconstruction of cranial defect

In cranioplasty, neurosurgeons use bone grafts to repair skull defects. To ensure the protection of intracranial tissues and recover the original head shape for aesthetic purposes, a custom-made pre-fabricated prosthesis must match the cranial incision as closely as possible. In our previous study (Liao et al. in Med Biol Eng Comput 49:203–211, 2011), we proposed an algorithm consisting of the 2D snake and image registration using the patient’s own diagnostic low-resolution and defective high-resolution computed tomography (CT) images to repair the impaired skull. In this study, we developed a 3D multigrid snake and employed multiresolution image registration to improve the computational efficiency. After extracting the defect portion images, we designed an image-trimming process to remove the bumped inner margin that can facilitate the placement of skull implants without manual trimming during surgery. To evaluate the performance of the proposed algorithm, a set of skull phantoms were manufactured to simulate six different conditions of cranial defects, namely, unilateral, bilateral, and cross-midline defects with 20 or 40 % skull defects. The overall image processing time in reconstructing the defect portion images can be reduced from 3 h to 20 min, as compared with our previous method. Furthermore, the reconstruction accuracies using the 3D multigrid snake were superior to those using the 2D snake.     

基于随机森林算法的小鼠micro-CT影像中骨骼关节特征点定位

随着小动物成像技术的发展,技术人员每天需要处理的小动物影像数量急剧增长,这使得自动化的小动物图像分析方法成为迫切的需求。在小鼠图像分析方面,小鼠灵活多变的身体姿态给自动化的图像分析带来困难。基于随机森林算法实现小鼠micro-CT图像中骨骼关节点的自动定位,为解决小鼠影像中身体姿态的自动识别打下基础。该算法主要分3步:先通过分类随机森林算法得到小鼠骨骼关节点的粗定位,再通过回归随机森林算法进一步减小定位误差,最后通过图匹配的方法在备选点中挑选正确位置上的关节点。对49例不同身体姿态的小鼠全身三维micro-CT图像进行测试,全身关节点定位的成功率为98.27%,定位误差的中值为0.68 mm。同时验证联合使用分类与回归随机森林的必要性,并探究训练数据的数量对不同骨关节的识别效果的影响。研究为小鼠micro-CT影像中身体姿态的识别提供一种新方法,为后续的自动化图像配准、图像分割以及自动化图像测量提供重要的定位信息。