Condition relaxation in conditional statistical shape models
作者： Elco Oost , Sho Tomoshige , Akinobu Shimizu
DOI: 10.1007/978-3-642-54851-2_2
关键词: Algorithm 、 Conditional probability distribution 、 Mathematics 、 Artificial intelligence 、 Chain rule (probability) 、 Regular conditional probability 、 Active appearance model 、 Conditional entropy 、 Relaxation (approximation) 、 Subspace topology 、 Machine learning 、 Discriminative model
摘要: A conditional statistical shape model is a valuable subspace method in medical image analysis. During training of the model, relationship between object interest and set features established. Subsequently, while analyzing an unseen image, measured condition matched with this distribution then data marked as relevant used for desired reconstruction shape. This approach can work properly only case when term reliable. Unfortunately, reliability not always sufficiently high such situation, instead being beneficial, hampering model. chapter describes advantages disadvantages models discusses how relaxation help to deal possible unreliability term. The requirements construction functioning relaxed are defined optimal design tested against various alternative (relaxed) models, showing superiority optimally designed
springer.com
sci-hub.st 参考文章(38)
Akinobu Shimizu, Keita Nakagomi, Takuya Narihira, Hidefumi Kobatake, Shigeru Nawano, Kenji Shinozaki, Koich Ishizu, Kaori Togashi, Automated segmentation of 3D CT images based on statistical atlas and graph cuts medical image computing and computer assisted intervention. pp. 214- 223 ,(2010) , 10.1007/978-3-642-18421-5_21
Hans Lamecker, Thomas Lange, Dagmar Kainmüller, Shape Constrained Automatic Segmentation of the Liver based on a Heuristic Intensity Model medical image computing and computer assisted intervention. pp. 109- 116 ,(2007)
Toshiyuki Okada, Ryuji Shimada, Yoshinobu Sato, Masatoshi Hori, Keita Yokota, Masahiko Nakamoto, Yen-Wei Chen, Hironobu Nakamura, Shinichi Tamura, Automated segmentation of the liver from 3D CT images using probabilistic atlas and multi-level statistical shape model medical image computing and computer assisted intervention. ,vol. 10, pp. 86- 93 ,(2007) , 10.1007/978-3-540-75757-3_11
Sho Tomoshige, Elco Oost, Akinobu Shimizu, Hidefumi Watanabe, Hidefumi Kobatake, Shigeru Nawano, Relaxed conditional statistical shape models and their application to non-contrast liver segmentation Abdominal Imaging. pp. 126- 136 ,(2012) , 10.1007/978-3-642-33612-6_14
N. Baka, M. de Bruijne, J.H.C. Reiber, W. Niessen, B.P.F. Lelieveldt, Confidence of model based shape reconstruction from sparse data international symposium on biomedical imaging. pp. 1077- 1080 ,(2010) , 10.1109/ISBI.2010.5490179
Ekaterina Syrkina, Rémi Blanc, Gàbor Székely, Propagating uncertainties in statistical model based shape prediction Proceedings of SPIE. ,vol. 7962, pp. 796240- ,(2011) , 10.1117/12.877960
László Ruskó, György Bekes, Márta Fidrich, Automatic segmentation of the liver from multi- and single-phase contrast-enhanced CT images. Medical Image Analysis. ,vol. 13, pp. 871- 882 ,(2009) , 10.1016/J.MEDIA.2009.07.009
Elco Oost, Pranobe Oemrawsingh, Johan H. Reiber, Boudewijn Lelieveldt, Automated left ventricular delineation in X‐ray angiograms: A validation study Catheterization and Cardiovascular Interventions. ,vol. 73, pp. 231- 240 ,(2009) , 10.1002/CCD.21672
Sho Tomoshige, Elco Oost, Akinobu Shimizu, Hidefumi Watanabe, Shigeru Nawano, A conditional statistical shape model with integrated error estimation of the conditions; Application to liver segmentation in non-contrast CT images Medical Image Analysis. ,vol. 18, pp. 130- 143 ,(2014) , 10.1016/J.MEDIA.2013.10.003
Arthur E. Hoerl, Robert W. Kennard, Ridge Regression: Applications to Nonorthogonal Problems Technometrics. ,vol. 12, pp. 69- 82 ,(1970) , 10.1080/00401706.1970.10488635