prikaz prve stranice dokumenta On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation
  Preuzmi
PDF 2.3 MB
Znanstveni rad - Izvorni znanstveni rad
On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation
Biology, 10 (2021), 3; 175. https://doi.org/10.3390/biology10030175
Lorencin, Ivan; Baressi Šegota, Sandi; Anđelić, Nikola; Mrzljak, Vedran; Ćabov, Tomislav; Španjol, Josip; Car, Zlatan

Institucijski repozitorij: Repozitorij Fakulteta dentalne medicine

Citirajte ovaj rad

Lorencin, I., Baressi Šegota, S., Anđelić, N., Mrzljak, V., Ćabov, T., Španjol, J. i Car, Z. (2021). On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation. Biology, 10. (3). doi: 10.3390/biology10030175

Lorencin, Ivan, et al. "On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation." Biology, vol. 10, br. 3, 2021. https://doi.org/10.3390/biology10030175

Lorencin, Ivan, Sandi Baressi Šegota, Nikola Anđelić, Vedran Mrzljak, Tomislav Ćabov, Josip Španjol i Zlatan Car. "On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation." Biology 10, br. 3 (2021). https://doi.org/10.3390/biology10030175

Lorencin, I., et al. (2021) 'On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation', Biology, 10(3). doi: 10.3390/biology10030175

Lorencin I, Baressi Šegota S, Anđelić N, Mrzljak V, Ćabov T, Španjol J, i sur.. On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation. Biology [Internet]. 26.02.2021. [pristupljeno 27.12.2024.];10(3). doi: 10.3390/biology10030175

I. Lorencin, et al., "On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation", Biology, vol. 10, br. 3, Veljača 2021. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:271:996581. [Citirano: 27.12.2024.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:271:996581
Podaci o radu
Naslov (engleski)On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation
AutorIvan Lorencin
AutorSandi Baressi Šegota
AutorNikola Anđelić
AutorVedran Mrzljak
AutorTomislav Ćabov
AutorJosip Španjol
AutorZlatan Car
Autorova ustanovaSveučilište u Rijeci
(Fakultet dentalne medicine)
Znanstveno / umjetničko
područje, polje i grana		INTERDISCIPLINARNA PODRUČJA ZNANOSTI
Biotehnologija u biomedicini (prirodno područje, biomedicina i zdravstvo, biotehničko područje)
Sažetak (engleski)
Urinary bladder cancer is one of the most common urinary tract cancers. Standard diagnosis procedure can be invasive and time-consuming. For these reasons, procedure called optical biopsy is introduced. This procedure allows in-vivo evaluation of bladder mucosa without the need for biopsy. Although less invasive and faster, accuracy is often lower. For this reason, machine learning (ML) algorithms are used to increase its accuracy. The issue with ML algorithms is their sensitivity to the amount of input data. In medicine, collection can be time-consuming due to a potentially low number of patients. For these reasons, data augmentation is performed, usually through a series of geometric variations of original images. While such images improve classification performance, the number of new data points and the insight they provide is limited. These issues are a motivation for the application of novel augmentation methods. Authors demonstrate the use of Deep Convolutional Generative Adversarial Networks (DCGAN) for the generation of images. Augmented datasets used for training of commonly used Convolutional Neural Network-based (CNN) architectures (AlexNet and VGG-16) show a significcan performance increase for AlexNet, where AUCmicro reaches values up to 0.99. Average and median results of networks used in grid-search increases. These results point towards the conclusion that GAN-based augmentation has decreased the networks sensitivity to hyperparemeter change.
Ključne riječi (engleski)
Jezikhrvatski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran - međunarodna recenzija
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov časopisaBiology
Brojčani podacivol. 10, br. 3, 175
e-ISSN2079-7737
DOIhttps://doi.org/10.3390/biology10030175
URN:NBNurn:nbn:hr:271:996581
Datum objave publikacije2021-02-26
URL dokumentahttps://www.mdpi.com/2079-7737/10/3/175
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Imenovanje 4.0 međunarodna (CC BY 4.0)
Datum i vrijeme pohrane2023-01-20 10:38:37