Level set-based CT liver image segmentation with watershed and artificial neural networks

The objective of this paper is to evaluate a new combined approach intended for reliable CT liver image segmentation, to separate the liver from other organs, and segment the liver into a set of regions of interest (ROIs). The approach combines the level set with watershed approach used as post segmentation step to produce a reliable segmentation result. Features of first order statistics and grey-level cooccurrence matrix, are calculated and passed to an artificial neural network, to be trained and to classify infected regions. Filtering is used before the segmentation approach to enhance contrast, remove noise and emphasize certain features, as well as connecting ribs around the liver. To evaluate the performance of presented approach, we performed many tests on different CT liver images. The experimental results obtained, show that the overall accuracy offered by the proposed approach is 92.1% in segmenting CT liver images into set of regions even with noise, and 88.9% average accuracy for neural network classification.

[1]  Allen R. Tannenbaum,et al.  Localizing Region-Based Active Contours , 2008, IEEE Transactions on Image Processing.

[2]  Chunming Li,et al.  Minimization of Region-Scalable Fitting Energy for Image Segmentation , 2008, IEEE Transactions on Image Processing.

[3]  Gerald Schaefer,et al.  Rough Sets and near Sets in Medical Imaging: a Review , 2022 .

[4]  A. Salih,et al.  Some numerical studies of interface advection properties of level set method , 2009 .

[5]  Frank Y. Shih,et al.  Image Segmentation , 2007, Encyclopedia of Biometrics.

[6]  Witold Pedrycz,et al.  Unsupervised hierarchical image segmentation with level set and additive operator splitting , 2005, Pattern Recognit. Lett..

[7]  Hichem Sahli,et al.  Multiscale gradient watersheds of color images , 2003, IEEE Trans. Image Process..

[8]  Chien-Cheng Lee,et al.  Classification of Liver Disease from CT Images Using a Support Vector Machine , 2007, J. Adv. Comput. Intell. Intell. Informatics.

[9]  Christopher M. Kuster,et al.  A study of numerical methods for the level set approach , 2007 .

[10]  Alper Yilmaz,et al.  Level Set Methods , 2007, Wiley Encyclopedia of Computer Science and Engineering.

[11]  Erlend Hodneland,et al.  Four-Color Theorem and Level Set Methods for Watershed Segmentation , 2009, International Journal of Computer Vision.

[12]  N. Dalrymple,et al.  Hounsfield unit density in the determination of urinary stone composition. , 2001, Urology.

[13]  Konstantina S. Nikita,et al.  Characterization of CT liver lesions based on texture features and a multiple neural network classification scheme , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[14]  Gerald Schaefer,et al.  Evaluating the effects of image filters in CT Liver CAD system , 2012, Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics.

[15]  Joan Serra,et al.  Image segmentation , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[16]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[17]  S.G. Mougiakakou,et al.  Computer aided diagnosis of CT focal liver lesions by an ensemble of neural network and statistical classifiers , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[18]  Michael Unser,et al.  Variational B-Spline Level-Set: A Linear Filtering Approach for Fast Deformable Model Evolution , 2009, IEEE Transactions on Image Processing.

[19]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.