Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Statistical Shape Model for the Liver
MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part II
Liver Segmentation from CT Scans: A Survey
WILF '07 Proceedings of the 7th international workshop on Fuzzy Logic and Applications: Applications of Fuzzy Sets Theory
3D Modeling for Deformable Objects
AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
Liver segmentation using sparse 3D prior models with optimal data support
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Simultaneous segmentation of multiple closed surfaces using optimal graph searching
IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Organ pose distribution model and an MAP framework for automated abdominal multi-organ localization
MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality
| Hi-index | 0.01 |
This paper presents a novel liver segmentation algorithm. This is a model-driven approach; however, unlike previous techniques which use a statistical model obtained from a training set, we initialize patient-specific models directly from their own pre-segmentation. As a result, the non-trivial problems such as landmark correspondences, model registration etc. can be avoided. Moreover, by dividing the liver region into three sub-regions, we convert the problem of building one complex shape model into constructing three much simpler models, which can be fitted independently, greatly improving the computation efficiency. A robust graph-based narrow band optimal surface fitting scheme is also presented. The proposed approach is evaluated on 35 CT images. Compared to contemporary approaches, our approach has no training requirement and requires significantly less processing time, with an RMS error of 2.44±0.53mm against manual segmentation.