Automatic anatomy recognition via multiobject oriented active shape models.

Purpose: This paper studies the feasibility of developing an automatic anatomy recognition (AAR) system in clinical radiology and demonstrates its operation on clinical 2D images. Methods: The anatomy recognition method described here consists of two main components: (a) multiobject generalization of OASM and (b) object recognition strategies. The OASM algorithm is generalized to multiple objects by including a model for each object and assigning a cost structure specific to each object in the spirit of live wire. The delineation of multiobject boundaries is done in MOASM via a three level dynamic programming algorithm, wherein the first level is at pixel level which aims to find optimal oriented boundary segments between successive landmarks, the second level is at landmark level which aims to find optimal location for the landmarks, and the third level is at the object level which aims to find optimal arrangement of object boundaries over all objects. The object recognition strategy attempts to find that pose vector (consisting of translation, rotation, and scale component) for the multiobject model that yields the smallest total boundary cost for all objects. The delineation and recognition accuracies were evaluated separately utilizing routine clinical chest CT, abdominal CT, and foot MRI data sets. The delineation accuracy was evaluated in terms of true and false positive volume fractions (TPVF and FPVF). The recognition accuracy was assessed (1) in terms of the size of the space of the pose vectors for the model assembly that yielded high delineation accuracy, (2) as a function of the number of objects and objects’ distribution and size in the model, (3) in terms of the interdependence between delineation and recognition, and (4) in terms of the closeness of the optimum recognition result to the global optimum. Results: When multiple objects are included in the model, the delineation accuracy in terms of TPVF can be improved to 97%–98% with a low FPVF of 0.1%–0.2%. Typically, a recognition accuracy of ≥90% yielded a TPVF ≥95% and FPVF ≤0.5%. Over the three data sets and over all tested objects, in 97% of the cases, the optimal solutions found by the proposed method constituted the true global optimum. Conclusions: The experimental results showed the feasibility and efficacy of the proposed automatic anatomy recognition system. Increasing the number of objects in the model can significantly improve both recognition and delineation accuracy. More spread out arrangement of objects in the model can lead to improved recognition and delineation accuracy. Including larger objects in the model also improved recognition and delineation. The proposed method almost always finds globally optimum solutions.

[1]  Jøger Hansegård,et al.  Constrained Active Appearance Models for Segmentation of Triplane Echocardiograms , 2007, IEEE Transactions on Medical Imaging.

[2]  Benoit M. Dawant,et al.  Automatic segmentation of the optic nerves and chiasm in CT and MR using the atlas-navigated optimal medial axis and deformable-model algorithm , 2009, Medical Imaging.

[3]  Xinjian Chen,et al.  3D automatic anatomy segmentation based on graph cut-oriented active appearance models , 2010, 2010 IEEE International Conference on Image Processing.

[4]  Jing Bai,et al.  Atlas-Based Fuzzy Connectedness Segmentation and Intensity Nonuniformity Correction Applied to Brain MRI , 2007, IEEE Transactions on Biomedical Engineering.

[5]  Cristian Lorenz,et al.  Automated vertebra identification in CT images , 2009, Medical Imaging.

[6]  Jayaram K. Udupa,et al.  Oriented Active Shape Models , 2009, IEEE Transactions on Medical Imaging.

[7]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[8]  Jayaram K. Udupa,et al.  An ultra-fast user-steered image segmentation paradigm: live wire on the fly , 2000, IEEE Transactions on Medical Imaging.

[9]  Pushmeet Kohli,et al.  Simultaneous Segmentation and Pose Estimation of Humans Using Dynamic Graph Cuts , 2008, International Journal of Computer Vision.

[10]  Nikos Paragios,et al.  Prior Knowledge, Level Set Representations & Visual Grouping , 2008, International Journal of Computer Vision.

[11]  Marco Rovaris,et al.  Incorporating Domain Knowledge Into the Fuzzy Connectedness Framework: Application to Brain Lesion Volume Estimation in Multiple Sclerosis , 2007, IEEE Transactions on Medical Imaging.

[12]  Claudio Pollo,et al.  Atlas-based segmentation of pathological MR brain images using a model of lesion growth , 2004, IEEE Transactions on Medical Imaging.

[13]  Hyunjin Park,et al.  Construction of an abdominal probabilistic atlas and its application in segmentation , 2003, IEEE Transactions on Medical Imaging.

[14]  Binsheng Zhao,et al.  Liver segmentation for CT images using GVF snake. , 2005, Medical physics.

[15]  Jayaram K. Udupa,et al.  A framework for evaluating image segmentation algorithms , 2006, Comput. Medical Imaging Graph..

[16]  Dorin Comaniciu,et al.  Hierarchical parsing and semantic navigation of full body CT data , 2009, Medical Imaging.

[17]  Pau-Choo Chung,et al.  Identifying multiple abdominal organs from CT image series using a multimodule contextual neural network and spatial fuzzy rules , 2003, IEEE Transactions on Information Technology in Biomedicine.

[18]  Lixu Gu,et al.  Recognition of abdominal organs using 3D mathematical morphology , 2002, Systems and Computers in Japan.

[19]  Jianhua Yao,et al.  Live level set: a hybrid method of livewire and level set for medical image segmentation. , 2008, Medical physics.

[20]  Pierre-Louis Bazin,et al.  Homeomorphic brain image segmentation with topological and statistical atlases , 2008, Medical Image Anal..

[21]  Xinjian Chen,et al.  Automatic anatomy recognition via multi-object-oriented active shape models , 2009, Medical Imaging.

[22]  Alejandro F. Frangi,et al.  Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling , 2002, IEEE Transactions on Medical Imaging.

[23]  Milan Sonka,et al.  Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images , 2001, IEEE Transactions on Medical Imaging.

[24]  Gabriele Lombardi,et al.  Automatic Abdominal Organ Segmentation from CT images , 2009 .

[25]  Dorin Comaniciu,et al.  Hierarchical, learning-based automatic liver segmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Xiangrong Zhou,et al.  Automated segmentation and recognition of the bone structure in non-contrast torso CT images using implicit anatomical knowledge , 2009, Medical Imaging.

[27]  B Haas,et al.  Automatic segmentation of thoracic and pelvic CT images for radiotherapy planning using implicit anatomic knowledge and organ-specific segmentation strategies , 2008, Physics in medicine and biology.

[28]  R. Rabbitt,et al.  3D brain mapping using a deformable neuroanatomy. , 1994, Physics in medicine and biology.