MRI segmentation: Methods and applications

Clarke, Laurence P.; Velthuizen, R.P.; Camacho, Marc A.; Heine, John J.; Vaidyanathan, M.; Hall, Lawrence O.; Thatcher, Robert W.; Silbiger, Martin L.

doi:10.1016/0730-725x(94)00124-l

Cited by 603 publications

(338 citation statements)

References 124 publications

Supporting

Mentioning

327

Contrasting

Unclassified

Order By: Relevance

“…This 'segmentation' of an image into anatomic structures can be performed to identify the border of the structure, or identification of all voxels contained within the structure. Segmentation has a long and rich literature, the reader is directed to comprehensive reviews such as [Clarke et al, 1995;Viergever et al, 2001] for a more detailed presentation on this topic. Another approach receiving substantial use is 'voxel-based morphometry' (VBM) [Ashburner and Friston, 2000].…”

Section: Methodsmentioning

confidence: 99%

MRI‐based morphometric analysis of typical and atypical brain development

Kennedy

Haselgrove

McInerney

2003

Ment. Retard. Dev. Disabil. Res. Rev.

View full text Add to dashboard Cite

The neuroinformatics landscape in which human brain morphometry occurs has advanced dramatically over the past few years. Rapid advancement in image acquisition methods, image analysis tools and interpretation of morphometric results make the study of in vivo anatomic analysis both challenging and rewarding. This has revolutionized our expectations for current and future diagnostic and investigative work with the developing brain. This paper will briefly cover the methods of morphometric analysis that available for neuroanatomic analysis, and tour some sample results from a prototype retrospective database of neuroanatomic volumetric information. From these observations, issues regarding the anatomic variability of developmental maturation of neuroanatomic structures in both typically and atypically developing populations can be discussed.

show abstract

Section: Methodsmentioning

confidence: 99%

MRI‐based morphometric analysis of typical and atypical brain development

Kennedy

Haselgrove

McInerney

2003

Ment. Retard. Dev. Disabil. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…The main difficulty is the non-uniform nature of the MR signal intensity introduced by noise, physiological factors, partial volume effects and non-uniform radio frequency (RF) fields. The latter probably has the greatest influence on the intensity variations, and depends on a number of factors including the subject, slice orientation, RF coil design and pulse sequence [18]. Furthermore, there are particular difficulties involved in MR imaging of the lungs.…”

Section: Image Data and Labellingmentioning

confidence: 99%

“…For example, it is well documented that (unlike CT images) MR images cannot be segmented using histogram-based thresholding because of the non-uniform nature of the data [18,25]. To justify the approach taken here, various other standard imageprocessing techniques have been investigated for MR image segmentation.…”

Section: Alternative Segmentation Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of magnetic resonance images using a combination of neural networks and active contour models

Middleton

Damper

2004

Medical Engineering & Physics

View full text Add to dashboard Cite

Segmentation of medical images is very important for clinical research and diagnosis, leading to a requirement for robust automatic methods. This paper reports on the combined use of a neural network (a multilayer perceptron, MLP) and active contour model ('snake') to segment structures in magnetic resonance (MR) images. The perceptron is trained to produce a binary classification of each pixel as either a boundary or a non-boundary point. Subsequently, the resulting binary (edge-point) image forms the external energy function for a snake, used to link the candidate boundary points into a continuous, closed contour. We report here on the segmentation of the lungs from multiple MR slices of the torso; lung-specific constraints have been avoided to keep the technique as general as possible. In initial investigations, the inputs to the MLP were limited to normalised intensity values of the pixels from an (7 × 7) window scanned across the image. The use of spatial coordinates as additional inputs to the MLP is then shown to provide an improvement in segmentation performance as quantified using the effectiveness measure (a weighted product of precision and recall). Training sets were first developed using a lengthy iterative process. Thereafter, a novel cost function based on effectiveness is proposed for training that allows us to achieve dramatic improvements in segmentation performance, as well as faster, non-iterative selection of training examples. The classifications produced using this cost function were sufficiently good that the binary image produced by the MLP could be post-processed using an active contour model to provide an accurate segmentation of the lungs from the multiple slices in almost all cases, including unseen slices and subjects.

show abstract

“…The applications of robust techniques for object classification in images are extensive, none more so than in the rapidly advancing field of medical imaging [1,2]. With the introduction of faster and more powerful imaging devices the amount of data produced makes it impractical for experts to manually segment objects of interest.…”

Section: Introductionmentioning

confidence: 99%

Automatic seed initialization for the expectation-maximization algorithm and its application in 3D medical imaging

Lynch

Ilea

Robinson

et al. 2007

Journal of Medical Engineering & Technology

View full text Add to dashboard Cite

Statistical partitioning of images into meaningful areas is the goal of all region-based segmentation algorithms. The clustering or creation of these meaningful partitions can be achieved in number of ways but in most cases it is achieved through the minimization or maximization of some function of the image intensity properties. Commonly these optimization schemes are locally convergent, therefore initialization of the parameters of the function plays a very important role in the final solution. In this paper we perform an automatically initialized expectation-maximization algorithm to partition the data in medical MRI images. We present analysis and illustrate results against manual initialization and apply the algorithm to some common medical image processing tasks.

show abstract

MRI segmentation: Methods and applications

Cited by 603 publications

References 124 publications

MRI‐based morphometric analysis of typical and atypical brain development

MRI‐based morphometric analysis of typical and atypical brain development

Segmentation of magnetic resonance images using a combination of neural networks and active contour models

Automatic seed initialization for the expectation-maximization algorithm and its application in 3D medical imaging

Contact Info

Product

Resources

About