Detection of Lumbar Vertebrae in CT Spine Images
computed tomography (CT) images of the lumbar spine. The resulting mean symmetric absolute surface distance of mm and Dice coefficient of %, computed from the final vertebra detection results against…
Segmentation of the Thoracic and Lumbar Vertebrae
was achieved on the training data set. 1 Introduction The spinal column forms an important support structure in the human body and mainly consists of the vertebral bones. As such,…
Segmentation of the Spinal Cord Using Continuous Max Flow with Cross-sectional Similarity Prior and Tubularity Features
denote the intensity non uniformity corrected image [8] with intensities in the normalized intensity space , where are the coordinates in the continuous image domain Throughout the whole section, we furthermore…
and Angle-Preserving Parameterization for Vertebra Surface Mesh
of a vertebra with one genus is represented by triangular patches. For each vertex in , its 1-ring region consists of patches containing the vertex . 2.1 Modified Self-organizing Deformable…
Improved Shape-Constrained Deformable Model for Segmentation of Vertebrae from CT Lumbar Spine Images
computed tomography (CT) images of the lumbar spine. The overall segmentation performance of mm in terms of mean symmetric absolute surface distance and in terms of Dice coefficient, computed against…
Shape-Constrained Deformable Model Approach for Segmentation of Vertebrae from CT Spine Images
contain three-dimensional (3D) images of the thoracolumbar spine, where each image is assigned a series of binary masks representing reference segmentations of each individual thoracolumbar vertebra from level T1 to…
Profiles: Simple, Fast, and Reliable Spine Localization in CT Scans
coordinate and pixel spacing, both given in millimeters. We denote the pixel positions in the patient coordinates as . For sake of simplicity we also assume the feet-to-head, face-up (supine)…
Auto-encoders for Classification of 3D Spine Models in Adolescent Idiopathic Scoliosis
of dimension , representing the 3D coordinates of a spine model, is mapped by an encoder function into the hidden layer , often called a code layer in the case…
of Vertebrae on DXA Images Using Constrained Local Models with Random Forest Regression Voting
of a set of landmarks on each, a statistical shape model is trained by applying principal component analysis (PCA) to the aligned shapes [2]. This yields a linear model of…
Vertebral Segmentation Using Part-Based Decomposition and Conditional Shape Models
Fig. 1 Examples of segmentations (in blue) obtained with local PDMs, showing suboptimal fitting in areas of complex geometry and high curvature on the spine (Color figure online) Amongst existing…
