An approach to three-dimensional image segmentation

Liou, Shih-Ping; Jain, Ramesh

doi:10.1016/1049-9660(91)90014-g

Cited by 19 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The extensions include: 1) the use of an inhomogeneity-tolerant, preliminary segmentation technique, and 2) increased region of support for calculation of the inhomogeneity function through the simultaneous use of many different tissue segments and three dimensional (3-D) modeling functions. The use of a relatively new segmentation algorithm, referred to in the remainder of this paper as LCJ-segmentation [14], [15], and a novel method of modeling the segmented data set, allows computation of stable estimates of the corrupting process using only the patient's data set. The estimate is then used to correct the global effect.…”

Section: Introductionmentioning

confidence: 99%

Retrospective correction of intensity inhomogeneities in MRI

Meyer

Bland

Pipe

1995

IEEE Trans. Med. Imaging

164

View full text Add to dashboard Cite

Medical imaging data sets are often corrupted by multiplicative inhomogeneities, often referred to as nonuniformities or intensity variations, that hamper the use of quantitative analyses. The authors describe an automatic technique that not only improves the worst situations, such as those encountered with magnetic resonance imaging (MRI) surface coils, but also corrects typical inhomogeneities encountered in routine volume data sets, such as MRI head scans, without generating additional artifact. Because the technique uses only the patient data set, the technique can be applied retrospectively to all data sets, and corrects both patient independent effects, such as rf coil design, and patient dependent effects, such as attenuation of overlying tissue experienced both in high field MRI and X-ray computed tomography (CT). The authors show results for several MRI imaging situations including thorax, head, and breast. Following such corrections, region of interest analyses, volume histograms, and thresholding techniques are more meaningful. The value of such correction algorithms may increase dramatically with increased use of high field strength magnets and associated patient-dependent rf attenuation in overlying tissues.

show abstract

Section: Introductionmentioning

confidence: 99%

Retrospective correction of intensity inhomogeneities in MRI

Meyer

Bland

Pipe

1995

IEEE Trans. Med. Imaging

164

View full text Add to dashboard Cite

show abstract

“…Besl and Jain [5] also addressed image segmentation using polynomial surface fitting, but the criterion function uws a user-specified threshold for acceptable noise variance nd does not account for the model complexity as t t e MDL principle does. Another approach that uses a similar image model (polynomial surfaces plus Gaussian noise) is applied to 2D images in [14] and 3D surfaces in (151. This work is also not based on MDL however, and uses a different optimization algorithm.…”

Section: Related Workmentioning

confidence: 99%

A fast algorithm for MDL-based multi-band image segmentation

Kanungo

Niblack

Steele

1994

Proceedings of IEEE Conference on Computer Vision and Pattern Recognition CVPR-94

View full text Add to dashboard Cite

We consider the problem of image segmentation and describe an algorithm that is based on the Minimum Description Length (MDL) principle, is fast, is applicable to multi-band images, and guarantees closed regions. We construct an objective €unction that, when minimized, yields a partitioning of the image into regions where the pixel values in each band of each region are described by a polynomial surface plus noise. The polynomial orders and their coefficients are determined by the algorithm. The minimization is difficult because (1) it involves a search over a very large space and (2) there is extensive computation required at each stage of the search. To address the first of these problems we use a region-merging minimization algorithm. To address the second we use an incremental polynomial regression that uses computations from the previous stage to compute results in the current stage, resulting in a significant speed up over the non-incremental technique. The segmentation result obtained is suboptimal in general but of high quality. Results on real images are shown.

show abstract

“…More recently, an automatic, retrospective image intensity correction technique was reported 12, 13 using the LCJ-segmentation algorithm. 14,15 This novel method allows computation of stable estimates of the corrupting processes using only a limited subset of data sampled from the image which is then used to correct the global effect of inhomogeneities.…”

Section: Introductionmentioning

confidence: 99%