3D Statistical Models of the Aorta and the Supra-Aortic Branches

Wörz, Stefan ;   von Tengg-Kobligk, Hendrik ;   Rohr, Karl

Tags Probabilistic and statistical models & methodsVesselsMagnetic resonance imaging (MRI)

We introduce a new approach for creating 3D statistical models of the aorta and supra-aortic branches to investigate the variability of the...

Read More Download this Paper

Joint Labeling of Multiple Regions of Interest (ROIs) by Enhanced Auto Context Models

Kim, Minjeong ;   Wu, Guorong ;   Guo, Yanrong ;   Shen, Dinggang

Tags Image segmentationMachine learningMagnetic resonance imaging (MRI)

Accurate segmentation of a set of regions of interest (ROIs) in the brain images is a key step in many neuroscience studies. Due to the...

Read More Download this Paper

Level Set Segmentation with Shape Prior Knowledge using Intrinsic Rotation, Translation and Scaling Alignment

Arrieta, Cristobal ;   Sing-Long, Carlos ;   Uribe, Sergio ;   Andia, Marcelo Edgardo ;   Irarrazaval, Pablo ;   Tejos, Cristian

Tags Image segmentationShape analysisModeling - Knowledge

Level set-based algorithms have been extensively used for medical image segmentation. Despite their relative success, standard level set...

Read More Download this Paper

Segmentation of Pelvic Organs at Risk using Superpixels and Graph Diffusion in Prostate Radiotherapy

Guinin, Maxime ;   Ruan, Su ;   Nkhali, Lamyaa ;   Dubray, Bernard ;   Massoptier, Laurent ;   Gardin, Isabelle

Tags Image segmentationRadiation therapy, planing and treatment

Segmentation of organs at risk (OAR) in male pelvis is critical for planning prostate cancer radiotherapy. We are interested in femoral heads,...

Read More Download this Paper

Unbalanced Graph-Based Transduction on Superpixels for Automatic Cervigram Image Segmentation

Huang, Sheng ;   Gao, Mingchen ;   Yang, Dan ;   Huang, Xiaolei ;   Elgammal, Ahmed ;   Zhang, Xiaohong

Tags Image segmentationMachine learningCervix

We propose a novel medical image segmentation algorithm by transductively inferring the labels. In this approach, superpixels are first...

Read More Download this Paper