ARTIFICIAL INTELLIGENCE-BASED METHOD FOR URINARY BLADDER CANCER DIAGNOSTIC

Autor: Bogović, Korino, Lorencin, Ivan, Anđelić, Nikola, Blažević, Sebastijan, Smolčić, Klara, Španjol, Josip, Car, Zlatan
Přispěvatelé: Car, Zlatan, Kudláček, Jan
Jazyk: angličtina
Rok vydání: 2018
Předmět:
Popis: Bladder cancer is a disease that involves abnormal urinary bladder cell growth. The aim of this paper is to describe a diagnostic method of detecting bladder cancer using artificial intelligence. The first step was to obtain a sufficient image data set, which is achieved by using appropriate image pre- processing algorithms. These algorithms were created using digital filters and various statistical methods. The convolutional neural network model, is being used for feature extraction and bladder cancer detection. Aforementioned image data set is divided into two parts which are used for training and testing convolutional neural network. Based on training and testing data the accuracy of neural network was investigated.
Databáze: OpenAIRE