Level set based segmentation with intensity and curvature priors

Leventon, Michael E.; Faugeras, Olivier; Grimson, W. Eric L.; Wells, William M.

doi:10.1109/mmbia.2000.852354

Cited by 99 publications

(63 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…21,22 Tumor volume measurements were conducted using three-dimensional (3D) Slicer software tools that were developed by our surgical planning laboratory in the Department of Radiology at BWH. [21][22][23][24][25] These software tools comprise a wide range of operations, including capabilities for coregistration of different imaging data sets, manual or semiautomated segmentation, and generation of various 3D models and reformats. All of the imaging data sets (fast spoiled-gradient [FSPGR], T1, T2, gradient sequences) from each patient are transferred from the 0.5-T MR console to a UNIX network, where the images can be viewed and brought up for interactive segmentation (MRX; GE Medical Systems) on an Ultra 10 Workstation (Sun Microsystems, Mountain View, CA).…”

Section: Methodsmentioning

confidence: 99%

Survival rates in patients with low‐grade glioma after intraoperative magnetic resonance image guidance

Claus

Horlacher

Hsu

et al. 2005

Cancer

430

191

View full text Add to dashboard Cite

Background We sought to examine hearing loss in a group from the Royal Australian Air Force who undertook fuel tank maintenance on F‐111 aircraft, with exposure to formulations containing ototoxins, relative to two different comparison groups. Methods Using pure‐tone audiometry, hearing thresholds were assessed in 614 exposed personnel, 513 technical‐trade comparisons (different base, same job), and 403 non‐technical comparisons (same base, different job). We calculated percentage loss of hearing (PLH) and used regression models to examine whether there was an association between PLH and F‐111 fuel tank maintenance, adjusting for possible confounders. In addition, the difference between the observed hearing thresholds and the expected thresholds based on an otologically normal population (ISO‐7029‐2003) was determined. Results The PLH ranged from nil to 96 (median 1.5, quartiles 0.3, 5.5). A logistic regression model showed no statistically significant difference in PLH among the three exposure groups (exposed vs. non‐technical controls 1.1: 95% CI 0.7, 2.0 and exposed vs. technical OR 0.9: 95% CI 0.6, 1.3). The model also highlighted a number of other risk factors for PLH including age, tinnitus, smoking, depression, and use of depression medications. However, at all eight frequencies measured, all populations had lower than expected hearing thresholds based on published ISO‐7029 medians. Conclusions Although there was no difference in PLH between the three exposure groups, the study did reveal a high degree of hearing loss between the 3 groups and a normal population. Am. J. Ind. Med. 53:1159–1169, 2010. © 2010 Wiley‐Liss, Inc.

show abstract

Section: Methodsmentioning

confidence: 99%

Survival rates in patients with low‐grade glioma after intraoperative magnetic resonance image guidance

Claus

Horlacher

Hsu

et al. 2005

Cancer

430

191

View full text Add to dashboard Cite

show abstract

“…Therefore, an important future work on this research is to investigate the image intensity distributions. Besides, we also plan to introduce some a priori knowledge of the prostate shape to constrain the surface deformation to improve the algorithm accuracy [17]. Assessment method should be included too to evaluate the experimental results quantitatively.…”

Section: Discussionmentioning

confidence: 99%

3D Prostate Surface Detection from Ultrasound Images Based on Level Set Method

Fan

Voon

2002

Medical Image Computing and Computer-Assisted Intervention — MICCAI 2002

View full text Add to dashboard Cite

Abstract. Accurate detection of prostate boundaries is required in many diagnostic and treatment procedures for prostate diseases. In this paper, a new approach based on level set method to perform 3D prostate surface detection from transrectal ultrasound (TRUS) images is presented. Contrary to many other deformable models, level set method offers several advantages such as minimal need for user input, flexible topology, and straightforward extension to 3D. However, it is subject to "boundary leaking" problem for ultrasound image segmentation due to the poor image quality. In this work, we first develop a fast discrimination method to extract the prostate region, then this region information, instead of the spatial image gradient, is incorporated into the level set method to remedy the "boundary leaking" problem. Various experimental results show the effectiveness of the proposed method.

show abstract

“…Bayesian models were proposed in the literature to incorporate prior knowledge about the target structure to constrain the evolution of the level set [40]. Recent improvements of this approach were proposed for example in [41].…”

Section: Chan-vese Energy With Priormentioning

confidence: 99%

Geodesic voting for the automatic extraction of tree structures. Methods and applications

Rouchdy

Cohen

2013

Computer Vision and Image Understanding

View full text Add to dashboard Cite

This paper presents new methods to segment thin tree structures, which are, for example present in microglia extensions and cardiac or neuronal blood vessels. Many authors have used minimal cost paths, or geodesics relative to a local weighting potential P, to find a vessel pathway between two end points.We utilize a set of such geodesic paths to find a tubular tree structure by seeking minimal interaction. We introduce a new idea that we call Geodesic Voting or Geodesic Density. The approach consists of computing geodesics from a set of end points scattered in the image which flow toward a given source point. The target structure corresponds to image points with a high geodesic density. The "Geodesic density" is defined at each pixel of the image as the number of geodesics that pass over this pixel. The potential P is defined in such way that it takes low values along the tree structure, therefore geodesics will migrate toward this structure thereby yielding a high geodesic density. We further adapt these methods to segment complex tree structures in a noisy medium and apply them to segment microglia extensions from confocal microscope images as well as vessels.

show abstract

Level set based segmentation with intensity and curvature priors

Cited by 99 publications

References 17 publications

Survival rates in patients with low‐grade glioma after intraoperative magnetic resonance image guidance

Survival rates in patients with low‐grade glioma after intraoperative magnetic resonance image guidance

3D Prostate Surface Detection from Ultrasound Images Based on Level Set Method

Geodesic voting for the automatic extraction of tree structures. Methods and applications

Contact Info

Product

Resources

About