Symptoms recognition of portal hypertensive gastropathy (PHG) can be done by analysing endoscopic recordings, but manual analysis done by physician may take a long time. This increases probability of missing some symptoms and automated methods may be applied to prevent that. In this paper a novel hybrid algorithm for recognition of early stage of portal hypertensive gastropathy is proposed. First image preprocessing is described. Then disease symptoms characteristics are presented and hybrid algorithm scheme combining edge detection, Local Binary Patterns and local maxima clustering is shown. Finally the detailed description of these methods are provided. The pa- rameters of the algorithm are also described with ranges used in tests and their best values (obtained empirically) are presented. The proposed algorithm is tested and compared to a few other algorithms showing it’s comparable in terms of effectiveness in general case and a bit better than other ones in recognition of early stage of PHG.
Authors
Additional information
- Category
- Publikacja monograficzna
- Type
- rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
- Language
- angielski
- Publication year
- 2014
