A fully automated framework for renal cortex segmentation

Authors:
Xinjian Chen;Hemin Zhao;Jianhua Yao
Affiliations:
School of Electronics and Information Engineering, Soochow University, Suzhou, Jiangsu, China;School of Electronics and Information Engineering, Soochow University, Suzhou, Jiangsu, China;Department of Radiology and Imaging Sciences, National Institute of Health Clinical Center, Bethesda, Maryland
Venue:
MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications
Year:
2012

Citing 7
Cited 0

User-steered image segmentation paradigms: live wire and live lane

Graphical Models and Image Processing
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Segmentation of Dynamic N-D Data Sets via Graph Cuts Using Markov Models

MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
Graph cuts framework for kidney segmentation with prior shape constraints

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Non-parametric iterative model constraint graph min-cut for automatic kidney segmentation

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III
Linear Time Algorithms for Exact Distance Transform

Journal of Mathematical Imaging and Vision
Computer-aided kidney segmentation on abdominal CT images

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

The current procedure of renal cortex segmentation is subjective and tedious. This investigation is to develop and validate an automated method to segment renal cortex on contrast-enhanced abdominal CT images. The proposed framework consists of four parts: first, an active appearance model (AAM) is built using a set of training images; second, the AAM is refined by live wire (LW) method to initialize the shape and location of the kidney; third, an iterative graph cut-oriented active appearance model (IGC-OAAM) method is applied to segment the kidney; Finally, the identified kidney contour is used as shape constraints for renal cortex segmentation which is also based on IGC-OAAM. The proposed method was validated on a clinical data set of 27 CT angiography images. The experimental results show that: (1) an overall cortex segmentation accuracy with overlap error ≤12.7%, volume difference ≤ 3.9%, average distance ≤ 1.5 mm, root mean square (RMS) distance ≤ 2.8 mm and maximal distance ≤ 19.5 mm could be achieved. (2) The proposed method is highly efficient such that the overall segmentation can be finalized within 2 minutes.