prikaz prve stranice dokumenta On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation
  Download
PDF 2.3 MB
Scientific paper - Original scientific paper
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

Cite this document

Lorencin, I., Baressi Šegota, S., Anđelić, N., Mrzljak, V., Ćabov, T., Španjol, J. & 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, no. 3, 2021. https://doi.org/10.3390/biology10030175

Lorencin, Ivan, Sandi Baressi Šegota, Nikola Anđelić, Vedran Mrzljak, Tomislav Ćabov, Josip Španjol and Zlatan Car. "On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation." Biology 10, no. 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, and sur.. On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation. Biology [Internet]. 2021 February 26 [cited 2024 November 28];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, no. 3, February 2021. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:184:668939. [Accessed: 28 November 2024]

Please login to the repository to save this object to your list.
Metadata
Title (english)On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation
AuthorIvan Lorencin
AuthorSandi Baressi Šegota
AuthorNikola Anđelić
AuthorVedran Mrzljak
AuthorTomislav Ćabov
AuthorJosip Španjol
AuthorZlatan Car
Author's institutionUniversity of Rijeka
Faculty of Medicine
(Department of Oral Surgery)
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Clinical Medical Sciences
Urology
Abstract (english)
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.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Journal titleBiology
Numberingvol. 10, no. 3, 175
e-ISSN2079-7737
DOIhttps://doi.org/10.3390/biology10030175
URN:NBNurn:nbn:hr:184:668939
Publication2021-02-26
Document URLhttps://www.mdpi.com/2079-7737/10/3/175
Type of resourceText
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2021-03-03 20:48:49