Abstract | ||
---|---|---|
Adrenal glands are the organs at which vitally important hormones are released. In adrenal glands, different kind of benign and malign lesions can arise. Herein, Dynamic Computed Tomography (dynamic CT) is the most used scan type for definition of lesion types. On the events that dynamic CT underwhelms, biopsy process is performed which is difficultly implemented because of the location of adrenal glands. During biopsy process, different complications can happen since adrenals glands are surrounded by spleen, lung, etc. At this point, a decision support system is needed for helping to medical experts. In this study, a Region of Interest (ROI) is defined that includes adrenal lesions. After that, feature extraction is realized by using Gray-Level Co-Occurance Matrix (GLCM) and the second-order statistics. At classification part, Neural Network (NN) and a novel approach including NN (Bounded PSO-NN) are evaluated by utilizing from three performance metrics. As a result, it's confirmed that Bounded PSO-NN classifies the malign and benign patterns more accurately which obtained by analysis taken from ROI. |
Year | Venue | Keywords |
---|---|---|
2017 | Signal Processing and Communications Applications Conference | Adrenal Lesion,Dynamic CT,Hybrid Classifier,Lesion Classification,Image Analysis |
Field | DocType | ISSN |
Lesion types,Pattern recognition,Computer science,Biopsy,Feature extraction,Computed tomography,Artificial intelligence,Region of interest,Artificial neural network,Bounded function | Conference | 2165-0608 |
Citations | PageRank | References |
2 | 0.43 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hasen Koyuncu | 1 | 14 | 4.84 |
Rahime Ceylan | 2 | 259 | 17.10 |