|
|||||
|
|
Recognition of diffuse liver cirrhosis based on image analysis |
|
| Authors: | A Gaber G Attiya A Hamdy T Elsayed |
| Affiliation: | 1. Department of Computer Science, Higher Institute of Computer Science and Information System, Cairo, Egypt;2. Department of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia University, Cairo, Egypt;3. Department of Communications, Electronics and Computer, Faculty of Engineering, Helwan University, Cairo, Egypt;4. Department of Electronics and Communication Engineering, Faculty of Electronic Engineering, Menoufia University, Cairo, Egypt |
| Abstract: | This paper presents non-invasive method for diagnosis of diffuse liver cirrhosis using ultrasound images. There are three main contributions of our detection method. The first contribution of this method is based on selection of multiple regions of interest (ROIs) with dynamic sizes in liver tissue. The use of multiple ROIs significantly achieves low computations that are required to classify the liver. The number of ROIs is variable and is optimised to achieve the best results. Then, simple but efficient features are extracted from each ROI. The second one is to apply a voting classification with use of multiple ROIs. The third one is to optimise the automatic selection of the parameters using the genetic algorithm. The proposed method has a higher performance compared to other research work and the obtained results show that the recognition accuracy is of 80.77%. |
| Keywords: | Cirrhosis liver Genetic algorithm HCV Multiple ROI Ultrasound image Voting |