An improved 2d colonic polyp segmentation framework based on gradient vector flow deformable model

Authors:
Dongqing Chen;M. Sabry Hassouna;Aly A. Farag;Robert Falk
Affiliations:
Computer Vision and Image Processing (CVIP) Lab, Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY.;Computer Vision and Image Processing (CVIP) Lab, Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY.;Computer Vision and Image Processing (CVIP) Lab, Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY.;Department of Medial Imaging, Jewish Hospital, Louisville, KY.
Venue:
Miar'06 Proceedings of the Third international conference on Medical Imaging and Augmented Reality
Year:
2006

Citing 5
Cited 1

On active contour models and balloons

CVGIP: Image Understanding
Finding the Brain Cortex Using Fuzzy Segmentation, Isosurfaces, and Deformable Surface Models

IPMI '97 Proceedings of the 15th International Conference on Information Processing in Medical Imaging
Estimating the tensor of curvature of a surface from a polyhedral approximation

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Differential fly-throughs (DFT): a general framework for computing flight paths

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Snakes, shapes, and gradient vector flow

IEEE Transactions on Image Processing

Image processing framework for virtual colonoscopy

ICIC'09 Proceedings of the 5th international conference on Emerging intelligent computing technology and applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Computed Tomography Colonography has been proved to be a valid technique for detecting and screening colorectal cancers. In this paper, we present a framework for colonic polyp detection and segmentation. Firstly, we propose to use four different geometric features for colonic polyp detection, which include shape index, curvedness, sphericity ratio and the absolute value of inner product of maximum principal curvature and gradient vector flow. Then, we use the bias-corrected fuzzy c-mean algorithm and gradient vector flow based deformable model for colonic polyp segmentation. Finally, we measure the overlap between the manual segmentation and the algorithm segmentation to test the accuracy of our frame work. The quantitative experiment results have shown that the average overlap is 85.17%±3.67%.