MRI segmentation: methods and applications.

L P Clarke; R P Velthuizen; M A Camacho; J J Heine; M Vaidyanathan; L O Hall; R W Thatcher; M L Silbiger

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

Home/Archive/PubMed

PubMed · 7791545

MRI segmentation: methods and applications.

L P Clarke·R P Velthuizen·M A Camacho·J J Heine·M Vaidyanathan·L O Hall·R W Thatcher·M L Silbiger

View original source ↗Export metadata ↓

Abstract

The current literature on MRI segmentation methods is reviewed. Particular emphasis is placed on the relative merits of single image versus multispectral segmentation, and supervised versus unsupervised segmentation methods. Image pre-processing and registration are discussed, as well as methods of validation. The application of MRI segmentation for tumor volume measurements during the course of therapy is presented here as an example, illustrating problems associated with inter- and intra-observer variations inherent to supervised methods.

Explore related subjects

Head Humans Image Processing, Computer-Assisted Magnetic Resonance Imaging Journal Article Research Support, U.S. Gov't, P.H.S.Review

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

L P Clarke, R P Velthuizen, M A Camacho, J J Heine, M Vaidyanathan, L O Hall, R W Thatcher, M L Silbiger. 1995. MRI segmentation: methods and applications.. https://doi.org/10.1016/0730-725x(94)00124-l

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1996

Centennial celebration of otolaryngology-head and neck surgery in the United States: history of the American Academy of Otolaryngology-Head and Neck Surgery.

Explore the source record for details and available documents.

Head↗

PubMed1995

Head and neck surgery for the surgical oncologist.

Explore the source record for details and available documents.

Head↗

PubMed1995

Parametrization of head-scatter factors for rectangular photon fields using an equivalent square formalism.

Head-scatter factors of symmetric square and rectangular fields (field center on the central beam axis) defined by the upper (Y) and lower (X) jaws for 6 and 15 MV photon beams from 2300CD and 600C accelerators (Varian Associates, Inc., Palo Alto, CA) were measured, as well as those for fields shaped by the Y jaws and the multileaf collimator (MLC) of the 2300CD. For rectangular fields, the head-scatter factor for the field (x = a and y = b) was different from that for the field (y = a and x = b). This difference was 2% -3% for fields defined by conventional collimators when [formula, see text] was large, and became 4%-5% when the MLC and YT jaws were used to shape the fields with the X jaws retracted. In order to calculate values for head-scatter factors of rectangular fields accurately using an equivalent square formalism, the side of the equivalent square should be obtained with different weights for lower and upper jaws, as proposed by Vadash and Bjärngard [Med. Phys. 20, 733-734 (1993)]. Our measurements demonstrate that the relative weight (G) of upper and lower jaws is strongly dependent on their distances from the x-ray source, while the beam energy has little effect on the value of G. We further show that G can be calculated simply from these distances. An analytical representation for head-scatter factors of square and rectangular fields is also developed in this paper. The quality of this representation was judged by the root-mean-square (rms) deviation from measured head-scatter factors, which ranged from 0.11%-0.27%.

Head↗