The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Um bom atlas probabilístico abdominal pode fornecer informações importantes para orientar aplicações de segmentação e registro no abdômen. Aqui construímos e testamos atlas probabilísticos usando 24 tomografias computadorizadas abdominais com segmentações manuais especializadas disponíveis. Os atlas são construídos escolhendo um alvo e mapeando outras varreduras de treinamento nesse alvo e depois somando os resultados em um atlas probabilístico. Melhoramos nosso atlas abdominal anterior 1) escolhendo um alvo menos tendencioso conforme determinado por uma ferramenta estatística, ou seja, escala multidimensional operando na energia de flexão, 2) usando um melhor conjunto de pontos de controle para modelar a deformação, e 3) usando maior conteúdo de informação Tomografias computadorizadas com estruturas hepáticas internas visíveis. Um atlas é construído no espaço alvo menos tendencioso e dois atlas são construídos em outros espaços alvo para comparações de desempenho. O valor de um atlas é avaliado com base nas segmentações resultantes; qualquer atlas que produza o melhor desempenho de segmentação é considerado o melhor atlas. Consideramos dois métodos de segmentação de volumes abdominais após registro no atlas probabilístico: 1) segmentação simples por limiarização do atlas e 2) aplicação de um método bayesiano máximo a posteriori. Usando jackknifing, medimos o desempenho da segmentação aumentada pelo atlas em relação à segmentação manual de especialistas e mostramos que o atlas construído no espaço alvo menos tendencioso produz melhor desempenho de segmentação do que atlas construídos em outros espaços alvo.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Hyunjin PARK, Alfred HERO, Peyton BLAND, Marc KESSLER, Jongbum SEO, Charles MEYER, "Construction of Abdominal Probabilistic Atlases and Their Value in Segmentation of Normal Organs in Abdominal CT Scans" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 8, pp. 2291-2301, August 2010, doi: 10.1587/transinf.E93.D.2291.
Abstract: A good abdominal probabilistic atlas can provide important information to guide segmentation and registration applications in the abdomen. Here we build and test probabilistic atlases using 24 abdominal CT scans with available expert manual segmentations. Atlases are built by picking a target and mapping other training scans onto that target and then summing the results into one probabilistic atlas. We improve our previous abdominal atlas by 1) choosing a least biased target as determined by a statistical tool, i.e. multidimensional scaling operating on bending energy, 2) using a better set of control points to model the deformation, and 3) using higher information content CT scans with visible internal liver structures. One atlas is built in the least biased target space and two atlases are built in other target spaces for performance comparisons. The value of an atlas is assessed based on the resulting segmentations; whichever atlas yields the best segmentation performance is considered the better atlas. We consider two segmentation methods of abdominal volumes after registration with the probabilistic atlas: 1) simple segmentation by atlas thresholding and 2) application of a Bayesian maximum a posteriori method. Using jackknifing we measure the atlas-augmented segmentation performance with respect to manual expert segmentation and show that the atlas built in the least biased target space yields better segmentation performance than atlases built in other target spaces.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2291/_p
Copiar
@ARTICLE{e93-d_8_2291,
author={Hyunjin PARK, Alfred HERO, Peyton BLAND, Marc KESSLER, Jongbum SEO, Charles MEYER, },
journal={IEICE TRANSACTIONS on Information},
title={Construction of Abdominal Probabilistic Atlases and Their Value in Segmentation of Normal Organs in Abdominal CT Scans},
year={2010},
volume={E93-D},
number={8},
pages={2291-2301},
abstract={A good abdominal probabilistic atlas can provide important information to guide segmentation and registration applications in the abdomen. Here we build and test probabilistic atlases using 24 abdominal CT scans with available expert manual segmentations. Atlases are built by picking a target and mapping other training scans onto that target and then summing the results into one probabilistic atlas. We improve our previous abdominal atlas by 1) choosing a least biased target as determined by a statistical tool, i.e. multidimensional scaling operating on bending energy, 2) using a better set of control points to model the deformation, and 3) using higher information content CT scans with visible internal liver structures. One atlas is built in the least biased target space and two atlases are built in other target spaces for performance comparisons. The value of an atlas is assessed based on the resulting segmentations; whichever atlas yields the best segmentation performance is considered the better atlas. We consider two segmentation methods of abdominal volumes after registration with the probabilistic atlas: 1) simple segmentation by atlas thresholding and 2) application of a Bayesian maximum a posteriori method. Using jackknifing we measure the atlas-augmented segmentation performance with respect to manual expert segmentation and show that the atlas built in the least biased target space yields better segmentation performance than atlases built in other target spaces.},
keywords={},
doi={10.1587/transinf.E93.D.2291},
ISSN={1745-1361},
month={August},}
Copiar
TY - JOUR
TI - Construction of Abdominal Probabilistic Atlases and Their Value in Segmentation of Normal Organs in Abdominal CT Scans
T2 - IEICE TRANSACTIONS on Information
SP - 2291
EP - 2301
AU - Hyunjin PARK
AU - Alfred HERO
AU - Peyton BLAND
AU - Marc KESSLER
AU - Jongbum SEO
AU - Charles MEYER
PY - 2010
DO - 10.1587/transinf.E93.D.2291
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2010
AB - A good abdominal probabilistic atlas can provide important information to guide segmentation and registration applications in the abdomen. Here we build and test probabilistic atlases using 24 abdominal CT scans with available expert manual segmentations. Atlases are built by picking a target and mapping other training scans onto that target and then summing the results into one probabilistic atlas. We improve our previous abdominal atlas by 1) choosing a least biased target as determined by a statistical tool, i.e. multidimensional scaling operating on bending energy, 2) using a better set of control points to model the deformation, and 3) using higher information content CT scans with visible internal liver structures. One atlas is built in the least biased target space and two atlases are built in other target spaces for performance comparisons. The value of an atlas is assessed based on the resulting segmentations; whichever atlas yields the best segmentation performance is considered the better atlas. We consider two segmentation methods of abdominal volumes after registration with the probabilistic atlas: 1) simple segmentation by atlas thresholding and 2) application of a Bayesian maximum a posteriori method. Using jackknifing we measure the atlas-augmented segmentation performance with respect to manual expert segmentation and show that the atlas built in the least biased target space yields better segmentation performance than atlases built in other target spaces.
ER -