Local adaptive segmentation algorithm for 3-D medical image based on robust feature statistics
Tóm tắt
Medical image segmentation is of pivotal importance in computer-aided clinical diagnosis. Many factors, including noises, bias field effect, local volume effect, as well as tissue movement may affect the medical image, thus causing blurring or uneven characteristics when forming a picture. Such quality defects will inevitably impair the gray-scale difference between adjacent tissues and lead to insufficient segmentation or even leakage during tissue or organ segmentation. In the present investigation, a local adaptive segmentation algorithm for 3-D medical image based on robust feature statistics (LARFS) was proposed. By combining segmentation algorithm principles for traditional region growing (RG) and robust feature statistics (RFS), the location and neighborhood image information of input seed point can be comprehensively analyzed by LARFS. Results show that, for different segmentation objects, under controlling the input parameter of growing factor within certain range, LARFS segmentation algorithm can adapt well to the regional geometric shape. And because the robust feature statistics is applied in the contour evolution process, LARFS algorithm is not sensitive to noises and not easily influenced by image contrast and object topology. Hence, the leakage and excessive segmentation effects are ameliorated with a smooth edge, and the accuracy can be controlled within the effective error range.
Tài liệu tham khảo
citation_title=Medical Image Processing (in Chinese); citation_publication_date=2009; citation_id=CR1; citation_author=X Kang; citation_publisher=People’s Medical Publishing House
citation_title=A review on the current segmentation algorithms for medical images; citation_inbook_title=Proceedings of International Conference on Imaging Theory and Applications, Lisboa; citation_publication_date=2009; citation_id=CR2; citation_author=Z Ma; citation_author=J M Tavares; citation_author=R M Jorge
citation_journal_title=Appl Mech Mater; citation_title=Research and improvement of live-wire interactive algorithm for medical image segmentation; citation_author=J Y Li, J W Dang; citation_volume=182; citation_publication_date=2012; citation_pages=1065-1068; citation_doi=10.4028/www.scientific.net/AMM.182-183.1065; citation_id=CR3
citation_journal_title=Radiology; citation_title=Automatic liver segmentation technique for three-dimensional visualization of CT data; citation_author=L Gao, D G Heath, B Kuszyk; citation_volume=201; citation_publication_date=1996; citation_pages=359-364; citation_doi=10.1148/radiology.201.2.8888223; citation_id=CR4
citation_journal_title=Math Probl Eng; citation_title=Fast image segmentation based on efficient implementation of the Chan-Vese model with discrete gray level sets; citation_author=S S Li, Q P Zhang; citation_volume=2013; citation_publication_date=2013; citation_pages=508543; citation_id=CR5
citation_journal_title=IEEE Trans Image Process; citation_title=A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI; citation_author=C M Li, R Huang, Z H Ding; citation_volume=20; citation_publication_date=2011; citation_pages=2007-2016; citation_doi=10.1109/TIP.2011.2146190; citation_id=CR6
citation_journal_title=Int J Comput Vision; citation_title=Graph cuts and efficient ND image segmentation; citation_author=Y Boykov, G Funka-Lea; citation_volume=70; citation_publication_date=2006; citation_pages=109-131; citation_doi=10.1007/s11263-006-7934-5; citation_id=CR7
citation_journal_title=Comput Med Imag Grap; citation_title=Segmentation of kidneys using a new active shape model generation technique based on non-rigid image registration; citation_author=M Spiegel, D Hahn, V Daum; citation_volume=33; citation_publication_date=2009; citation_pages=29-39; citation_doi=10.1016/j.compmedimag.2008.10.002; citation_id=CR8
citation_journal_title=IEEE Trans Med Imaging; citation_title=Automatic renal cortex segmentation using implicit shape registration and novel multiple surfaces graph search; citation_author=X L Li, X J Chen, J H Yao; citation_volume=31; citation_publication_date=2012; citation_pages=1849-1860; citation_doi=10.1109/TMI.2012.2229852; citation_id=CR9
citation_journal_title=IEEE Trans Vis Comput Graph; citation_title=Optical models for direct volume rendering; citation_author=N Max; citation_volume=1; citation_publication_date=1995; citation_pages=99-108; citation_doi=10.1109/2945.468400; citation_id=CR10
citation_journal_title=Annu Rev Biomed Eng; citation_title=The process and development of image-guided procedures; citation_author=R L Galloway; citation_volume=3; citation_publication_date=2001; citation_pages=83-108; citation_doi=10.1146/annurev.bioeng.3.1.83; citation_id=CR11
citation_journal_title=J Comput Res Dev; citation_title=Image guided computer assisted microwave ablation for liver cancer (in Chinese); citation_author=W Zhai, L Sheng, Y Song; citation_volume=48; citation_publication_date=2011; citation_pages=281-288; citation_id=CR12
citation_title=Digital Image Processing; citation_publication_date=2002; citation_id=CR13; citation_author=R C Gonzales; citation_author=R E Woods; citation_publisher=Prentice Hall
citation_title=Segmentation using a region-growing thresholding; citation_inbook_title=Proceedings of SPIE 5672, Image Processing: Algorithms and Systems IV. San Jose: SPIE; citation_publication_date=2005; citation_pages=388-398; citation_id=CR14; citation_author=M Mancas; citation_author=B Gosselin; citation_author=B Macq
citation_title=Robust Statistics: A Brief Introduction and Overview; citation_publication_date=2001; citation_id=CR15; citation_author=F A Hampel; citation_author=F R Hampel; citation_publisher=Seminar für Statistik, Eidgenössische Technische Hochschule
citation_title=Research and implementation of robust multivariate statistical analysis method (in Chinese); citation_publication_date=2005; citation_id=CR16; citation_author=Y Chen; citation_publisher=Jinan University
citation_title=Robust statistical estimation and segmentation of multiple subspaces; citation_inbook_title=Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshop; citation_publication_date=2006; citation_pages=99-99; citation_id=CR17; citation_author=A Y Yang; citation_author=S R Rao; citation_author=Y Ma; citation_publisher=IEEE
citation_journal_title=Med Image Anal; citation_title=Robust statistical shape models for MRI bone segmentation in presence of small field of view; citation_author=J Schmid, J Kim, N Magnenat-Thalmann; citation_volume=15; citation_publication_date=2011; citation_pages=155-168; citation_doi=10.1016/j.media.2010.09.001; citation_id=CR18
citation_title=Simultaneous multi-object segmentation using local robust statistics and contour interaction; citation_inbook_title=Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging; citation_publication_date=2011; citation_pages=195-203; citation_id=CR19; citation_author=Y Gao; citation_author=A Tannenbaum; citation_author=R Kikinis; citation_publisher=Springer
citation_title=Theory of variational level set method and its application to medical image segmentation (in Chinese); citation_publication_date=2009; citation_id=CR20; citation_author=Q Xie; citation_publisher=Zhejiang University
citation_journal_title=J Comput Phys; citation_title=Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations; citation_author=S Osher, J A Sethian; citation_volume=79; citation_publication_date=1988; citation_pages=12-49; citation_doi=10.1016/0021-9991(88)90002-2; citation_id=CR21
citation_journal_title=IEEE Trans Image Process; citation_title=Active contours without edges; citation_author=T F Chan, L A Vese; citation_volume=10; citation_publication_date=2001; citation_pages=266-277; citation_doi=10.1109/83.902291; citation_id=CR22
citation_journal_title=Comput Graph; citation_title=Interactive 3D medical image segmentation with energy-minimizing implicit functions; citation_author=F Heckel, O Konrad, H Karl Hahn; citation_volume=35; citation_publication_date=2011; citation_pages=275-287; citation_doi=10.1016/j.cag.2010.12.006; citation_id=CR23
citation_title=Automatic lung lobe segmentation using particles, thin plate splines, and maximum a posteriori estimation; citation_inbook_title=Proceedings of 13th International Conference on Medical Image Computing and Computer-Assisted Intervention, Beijing; citation_publication_date=2010; citation_pages=163-171; citation_id=CR24; citation_author=J C Ross; citation_author=R S J Estépar; citation_author=G Kindlmann
citation_title=Pulmonary lobe segmentation using the thin plate spline (TPS) with the help of the fissure localization areas; citation_inbook_title=Proceedings of SPIE 8669, Medical Imaging 2013: Image Processing, Florida: SPIE; citation_publication_date=2013; citation_pages=86690X; citation_id=CR25; citation_author=B Odry; citation_author=P Steininger; citation_author=L Zhang
citation_journal_title=J Image Graph; citation_title=A dynamic adaptive 3D voxel-growing segmentation algorithm for pulmonary CT images (in Chinese); citation_author=W Zhai, C Hu, H Zhang; citation_volume=10; citation_publication_date=2005; citation_pages=1269-1274; citation_id=CR26