Automatic prone to supine haustral fold matching in CT colonography using a Markov random field model
Thomas E. Hampshire,Holger R. Roth,Mingxing Hu,Darren Boone,Greg Slabaugh,Shonit Punwani,Steve Halligan,David J. Hawkes +7 more
- 18 Sep 2011
- Vol. 14, pp 508-515
TL;DR: In this paper, a graph cut method applied to a surface curvature-based metric was used to detect haustral folds in CT images, where image patches were generated using endoluminal CT colonography surface rendering and the intensity difference between image pairs, along with additional neighbourhood information to enforce geometric constraints, were used with a Markov Random Field (MRF) model to estimate the fold labeling assignment.
read more
Abstract: CT colonography is routinely performed with the patient prone and supine to differentiate fixed colonic pathology from mobile faecal residue. We propose a novel method to automatically establish correspondence. Haustral folds are detected using a graph cut method applied to a surface curvature-based metric, where image patches are generated using endoluminal CT colonography surface rendering. The intensity difference between image pairs, along with additional neighbourhood information to enforce geometric constraints, are used with a Markov Random Field (MRF) model to estimate the fold labelling assignment. The method achieved fold matching accuracy of 83.1% and 88.5% with and without local colonic collapse. Moreover, it improves an existing surface-based registration algorithm, decreasing mean registration error from 9.7mm to 7.7mm in cases exhibiting collapse.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Graph matching survey for medical imaging: On the way to deep learning
TL;DR: A survey of graph matching for clinical applications can be found in this paper , where the authors focus on graph matching in medical imaging applications, focusing on the potential of matching to find similarities and differences between data acquired at different points in time.
4
External clinical validation of prone and supine CT colonography registration
Holger R. Roth,Darren Boone,Steve Halligan,Thomas E. Hampshire,Jamie R. McClelland,Mingxing Hu,Shonit Punwani,Stuart A. Taylor,David J. Hawkes +8 more
TL;DR: Full surface-based prone-to-supine registration can successfully map the location of a polyp identified on one acquisition to the corresponding endoluminal surface in the opposing acquisition, greatly facilitating polyp matching and aiding interpretation.
Prone to supine CT colonography registration using a landmark and intensity composite method
Thomas E. Hampshire,Holger R. Roth,Darren Boone,Greg Slabaugh,Steve Halligan,David J. Hawkes +5 more
TL;DR: In this paper, the authors proposed a method to automatically establish correspondence between the two acquisitions by segmenting a set of haustral folds in each view and determining correspondence via a labeling process using a Markov Random Field (MRF) model.
Establishing spatial correspondence for the analysis of images from highly deforming anatomy
David J. Hawkes,Thomy Mertzanidou,John H. Hipwell,David Atkinson,Holger R. Roth,Thomas E. Hampshire,Jamie R. McClelland +6 more
- 12 Nov 2012
TL;DR: This invited presentation summarizes recent advances in the incorporation of knowledge of the geometry, tissue mechanical properties and imaging characteristics in establishing spatial correspondence between multiple images of highly deforming, soft tissue structures.
1
Feasibility of using the marginal blood vessels as reference landmarks for CT colonography.
Zhuoshi Wei,Jianhua Yao,Shijun Wang,Jiamin Liu,Andrew J. Dwyer,Perry J. Pickhardt,Wieslaw L. Nowinski,Ronald M. Summers +7 more
TL;DR: The marginal blood vessels run parallel to the Colon in proximity to the tenia mesocolica and enable accurate supine-prone registration of polyps and localization of the colon path in areas of collapse and may be used as reference landmarks complementary to the colon centerline and teniae coli.
References
An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision
Yuri Boykov,Vladimir Kolmogorov +1 more
TL;DR: This paper compares the running times of several standard algorithms, as well as a new algorithm that is recently developed that works several times faster than any of the other methods, making near real-time performance possible.
A Rapidly Convergent Descent Method for Minimization
Roger Fletcher,M. J. D. Powell +1 more
TL;DR: A number of theorems are proved to show that it always converges and that it converges rapidly, and this method has been used to solve a system of one hundred non-linear simultaneous equations.
On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs
Yair Weiss,William T. Freeman +1 more
TL;DR: It is shown that the assignment based on a fixed point of max-product is a "neighborhood maximum" of the posterior probabilities: the posterior probability of the max- product assignment is guaranteed to be greater than all other assignments in a particular large region around that assignment.
Two moving coordinate frames for sweeping along a 3D trajectory
TL;DR: The central problem is to define a triple of coordinates axes at each point of the trajectory in order to specify the position and orientation of the swept object along the trajectory.
209
Optimizing Colonic Distention for Multi–Detector Row CT Colonography: Effect of Hyoscine Butylbromide and Rectal Balloon Catheter
Stuart A. Taylor,Steve Halligan,Vicky Goh,S Morley,Paul Bassett,Wendy Atkin,Clive I. Bartram +6 more
TL;DR: Hyoscine butylbromide improves colonic distention during CT colonography and should be routinely administered where it is available, and use of a thin rectal tube for insufflation is adequate.
160