In this paper, we propose a new active contour algorithm, i.e. hierarchical contextual active contour (HCAC), and apply it to automatic liver segmentation from three-dimensional CT (3D-CT) images. HCAC is a learning-based method and can be divided into two stages. At the first stage, i.e. the training stage, given a set of abdominal 3D-CT training images and the corresponding manual liver labels, we tried to establish a mapping between automatic segmentations (in each round) and manual reference segmentations via context features, and obtained a series of self-correcting classifiers. At the second stage, i.e. the segmentation stage, we firstly used the basic active contour to segment the image and subsequently used the contextual active contour (CAC) iteratively, which combines the image information and the current shape model, to improve the segmentation result. The current shape model is produced by the corresponding self-correcting classifier (the input is the previous automatic segmentation result). The proposed method was evaluated on the datasets of MICCAI 2007 liver segmentation challenge. The experimental results showed that we would get more and more accurate segmentation results by the iterative steps and the satisfied results would be obtained after about six rounds of iterations.
Lung segmentation is the premise of the computer aided diagnosis of lung cancer. The traditional segmentation method based on local low-level features can not get the correct result when a tumor is connected with pleura due to their similar computed tomography (CT) values. Moreover, because the big size of tumor leads to the loss of a large part of lung area, the traditional segmentation methods of lung with juxta-pleural nodule whose diameter is less than 3 cm are not suitable. Acitve shape model (ASM) combined with prior shape and low level features might be appropriate. But the search steps in conventional ASM is an optimization method based on the least square, which is sensitive to outlier marker points, and it makes profile update to the transition area of normal lung tissue and tumor rather than a true lung contour. To solve the problem, we proposed an improved ASM algorithm. Firstly, we identified these outlier marker points by distance, and then gave the different searching functions to the abnormal and normal marker points. And the search processing should be limited in volume of interesting (VOI). We selected 30 lung images with juxta-pleural tumors, and got the overlap rate with the gold standard as 93.6%. The experimental results showed that the improved ASM could get good segmentation results for the lungs with juxta-pleural tumors, and the running time of the algorithm could be tolerated in clinical.
The geometric bone model of patients is an important basis for individualized biomechanical modeling and analysis, formulation of surgical planning, design of surgical guide plate, and customization of artificial joint. In this study, a rapid three-dimensional (3D) reconstruction method based on statistical shape model was proposed for femur. Combined with the patient plain X-ray film data, rapid 3D modeling of individualized patient femur geometry was realized. The average error of 3D reconstruction was 1.597–1.842 mm, and the root mean square error was 1.453–2.341 mm. The average errors of femoral head diameter, cervical shaft angle, offset distance and anteversion angle of the reconstructed model were 0.597 mm, 1.163°, 1.389 mm and 1.354°, respectively. Compared with traditional modeling methods, the new method could achieve rapid 3D reconstruction of femur more accurately in a shorter time. This paper provides a new technology for rapid 3D modeling of bone geometry, which is helpful to promote rapid biomechanical analysis for patients, and provides a new idea for the selection of orthopedic implants and the rapid research and development of customized implants.
Reconstructing three-dimensional (3D) models from two-dimensional (2D) images is necessary for preoperative planning and the customization of joint prostheses. However, the traditional statistical modeling reconstruction shows a low accuracy due to limited 3D characteristics and information loss. In this study, we proposed a new method to reconstruct the 3D models of femoral images by combining a statistical shape model with Laplacian surface deformation, which greatly improved the accuracy of the reconstruction. In this method, a Laplace operator was introduced to represent the 3D model derived from the statistical shape model. By coordinate transformations in the Laplacian system, novel skeletal features were established and the model was accurately aligned with its 2D image. Finally, 50 femoral models were utilized to verify the effectiveness of this method. The results indicated that the precision of the method was improved by 16.8%–25.9% compared with the traditional statistical shape model reconstruction. Therefore, the method we proposed allows a more accurate 3D bone reconstruction, which facilitates the development of personalized prosthesis design, precise positioning, and quick biomechanical analysis.