Multi-object Segmentation Using Shape Particles

Bruijne, Marleen de; Nielsen, Mads

doi:10.1007/11505730_63

Cited by 9 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4,5 Bruijne and Nielsen designed a shape particle model based on ASM (Active Shape Model) for ribs. 6 While ASM/AAM proved to be suitable for either multi-object or multi-surface segmentation, it is difficult to design a general multi-object multi-surface segmentation system based on AAM due to the training set size requirements in higher-dimensional spaces. Other examples may include atlas-based methods, 7 multi-agent based methods, 8,9 or pixel classification based methods.…”

Section: Previous Workmentioning

confidence: 99%

Simultaneous segmentation of the bone and cartilage surfaces of a knee joint in 3D

et al. 2009

View full text Add to dashboard Cite

We present a novel framework for the simultaneous segmentation of multiple interacting surfaces belonging to multiple mutually interacting objects. The method is a non-trivial extension of our previously reported optimal multi-surface segmentation. Considering an example application of knee-cartilage segmentation, the framework consists of the following main steps: 1) Shape model construction: Building a mean shape for each bone of the joint (femur, tibia, patella) from interactively segmented volumetric datasets. Using the resulting mean-shape model -identification of cartilage, non-cartilage, and transition areas on the mean-shape bone model surfaces. 2) Presegmentation: Employment of iterative optimal surface detection method to achieve approximate segmentation of individual bone surfaces. 3) Cross-object surface mapping: Detection of inter-bone equidistant separating sheets to help identify corresponding vertex pairs for all interacting surfaces. 4) Multi-object, multi-surface graph construction and final segmentation: Construction of a single multi-bone, multi-surface graph so that two surfaces (bone and cartilage) with zero and non-zero intervening distances can be detected for each bone of the joint, according to whether or not cartilage can be locally absent or present on the bone. To define inter-object relationships, corresponding vertex pairs identified using the separating sheets were interlinked in the graph. The graph optimization algorithm acted on the entire multiobject, multi-surface graph to yield a globally optimal solution.The segmentation framework was tested on 16 MR-DESS knee-joint datasets from the Osteoarthritis Initiative database. The average signed surface positioning error for the 6 detected surfaces ranged from 0.00 to 0.12 mm. When independently initialized, the signed reproducibility error of bone and cartilage segmentation ranged from 0.00 to 0.26 mm. The results showed that this framework provides robust, accurate, and reproducible segmentation of the knee joint bone and cartilage surfaces of the femur, tibia, and patella. As a general segmentation tool, the developed framework can be applied to a broad range of multi-object segmentation problems.Medical image segmentation is a continuously evolving field. Due to the anatomical complexity and possible presence of pathologies, segmentation tools for general purpose tasks are difficult to derive. The medical image analysis objects of interest are typically three-dimensional, and they frequently consist of 3D regions separated by interacting surfaces, e.g., inner and outer vascular walls, endo-and epicardial heart surfaces, multi-layer structure of human retina, etc. These are intra-object interactions. Similarly, organs typically occur in prespecified anatomical relationships and it seems advantageous to consider such relationships when segmenting the medical images, e.g., the mutual positions of cardiac ventricles and atria, of the prostate and bladder, etc. These are inter-object relationships. Yet, most of the contemporary metho...

show abstract

Section: Previous Workmentioning

confidence: 99%

Simultaneous segmentation of the bone and cartilage surfaces of a knee joint in 3D

et al. 2009

View full text Add to dashboard Cite

show abstract

“…[34]. Furthermore, in the field of medical image processing, particle filters were used in segmentation of good quality still medical images such as X-ray radiography and CT [36,37].…”

Section: Related Workmentioning

confidence: 99%

Automated tracking in digitized videofluoroscopy sequences for spine kinematic analysis

Lam¹,

McCane²,

Allen³

2009

Image and Vision Computing

View full text Add to dashboard Cite

“…They also proposed to model objects appearance by learning long-distances dependences between pixel values using Bayesian networks. De Bruijne et al (2005) used the normal probability distribution to model spatial relationships between shape particle set and its expected neighbour. Additionally, multi-scale probabilistic Markov models have also been employed to characterize inter-object relationships (Lu et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Anatomical Structures by Connected Statistical Models

Bukovec¹,

Likar²,

Pernuš³

2011

Image Anal Stereol

View full text Add to dashboard Cite

This paper presents a framework for the segmentation of anatomical structures in medical imagery by connected statistical models. The framework is based on three types of models: first, generic models which operate directly on image intensities, second, connecting models that impose restrictions on the spatial relationship of generic models, and third, a supervising model that represents an arbitrary number of generic and connecting models. In this paper, the statistical model of appearance is used as the generic model, whiles the statistical model of topology, obtained by applying principal component analysis (PCA) on aligned pose and shape parameters of the generic model, is used as the connecting model. The performance of such connected statistical model is demonstrated on anterior-posterior (AP) X-ray images of the hips and pelvis and compared to the modelling by one and six unconnected generic models. The most accurate and robust results were obtained by two-level hierarchical modelling, wherein connected statistical models were used first, followed by unconnected statistical models.

show abstract

Multi-object Segmentation Using Shape Particles

Cited by 9 publications

References 9 publications

Simultaneous segmentation of the bone and cartilage surfaces of a knee joint in 3D

Simultaneous segmentation of the bone and cartilage surfaces of a knee joint in 3D

Automated tracking in digitized videofluoroscopy sequences for spine kinematic analysis

Segmentation of Anatomical Structures by Connected Statistical Models

Contact Info

Product

Resources

About