CorteXpert: a model-based method for automatic renal cortex segmentation
Medical Image Analysis, volume 42, pages 257–273
Abstract
This paper introduces a model-based approach for a fully automatic delineation of kidney and cortex tissue from contrast-enhanced abdominal CT scans. The proposed framework, named CorteXpert, consists of two new strategies for kidney tissue delineation: cortex model adaptation and non-uniform graph search. CorteXpert was validated on a clinical data set of 58 CT scans using the cross-validation evaluation strategy. The experimental results indicated the state-of-the-art segmentation accuracies (as dice coefficient): 97.86% ± 2.41% and 97.48% ± 3.18% for kidney and renal cortex delineations, respectively.
Abstract sourceThis 2017 study introduced CorteXpert, a model-based method for delineating kidney and renal cortex tissue in contrast-enhanced abdominal CT scans. The authors evaluated it on 58 scans using cross-validation.
Summary
The paper presents CorteXpert, a coarse-to-fine method for automatic kidney and renal cortex segmentation in contrast-enhanced abdominal CT. Its approach combines statistical shape models with a non-uniform graph search, which uses image intensity information to locate tissue boundaries. The authors report validation on 58 CT scans using cross-validation; this evaluation does not by itself establish performance in prospective clinical use.
Cite this work
Dehui Xiang, Ulas Bagci, Chao Jin, Fei Shi, Weifang Zhu, Jianhua Yao, Milan Sonka, Xinjian Chen (2017). CorteXpert: a model-based method for automatic renal cortex segmentation. Medical Image Analysis, volume 42, pages 257–273 https://doi.org/10.1016/j.media.2017.06.010
BibTeX