Utilization of Convolutional Neural Networks for Urinary Bladder Cancer Diagnosis Recognition From CT Imagery (CROSBI ID 709582)
Prilog sa skupa u zborniku | ostalo | međunarodna recenzija
Podaci o odgovornosti
Lorencin, Ivan ; Smolić, Klara ; Baressi Šegota, Sandi ; Anđelić, Nikola ; Štifanić, Daniel ; Musulin, Jelena ; Markić, Dean ; Španjol, Josip ; Car, Zlatan
engleski
Utilization of Convolutional Neural Networks for Urinary Bladder Cancer Diagnosis Recognition From CT Imagery
In this paper, an approach for urinary bladder cancer diagnosis from computer tomography (CT) images based on the application of convolutional neural networks (CNN) is presented. The image data set that consists of three main parts (frontal, horizontal, and sagittal plane) is used. In order to classify images, pre-defined CNN architectures are used. CNN performances are evaluated by using 5-fold cross-validation procedure that gives information about classification and generalization performances. From the presented results, it can be noticed that higher performances are achieved if more complex CNN architectures are used. Higher performances can be noticed regardless of a plane in which images are captured. An increase in performances can be noticed in both classification and generalization context.
Artificial intelligence, Convolutional neural network, Machine learning, Urinary bladder cancer
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1-6.
2021.
objavljeno
Podaci o matičnoj publikaciji
2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)
Kragujevac: Institute of Electrical and Electronics Engineers (IEEE)
Podaci o skupu
21st IEEE International Conference on BioInformatics and BioEngineering (BIBE 2021)
predavanje
25.10.2021-27.10.2021
Kragujevac, Srbija