# On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## Simple Summary

## Abstract

## 1. Introduction

- Is it possible to utilize GAN fo urinary bladder cancer image data augmentation,
- Are classifier performance higher if an augmented set is used and
- How does the share of data generated in the training set affect the performance of the classifier?

## 2. Problem Description

## 3. Use of DCGAN Networks in Generation of Medical Data

- number of filters—which define the dimensionality of the output,
- the size of kernel (h)—which specify the dimensions of convolution window,
- strides—which specify convolutional strides along the height and width, and
- padding—which defines whether padding will be applied to the output of convolution or should the size remain the same.

- ${L}^{\prime}$ is the output dimension (width or height) of the image,
- L is the dimension (width or height) size of the image,
- F is the dimension of the kernel in the same direction (width or height) as the image dimension being transformed,
- P is the size of padding applied to the image, and
- S is the total number of strides.

## 4. Description of used CNN Models

#### 4.1. AlexNet

#### 4.2. VGG 16

## 5. Dataset Construction Methodology

## 6. Performance Evaluation Measures

#### 6.1. Micro-Average AUC

#### 6.2. Macro-Average AUC

#### 6.3. Model Quality Estimation

## 7. Results and Discussion

## 8. Final Remarks and Conclusions

- It is possible to utilize GAN for augmentation of urinary bladder cancer image dataset,
- It can be noticed that the classifier performances are higher if an augmented set is used,
- By increasing the share of generated images, classifier performances are increasing to a certain level and then decreasing.

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Zlatev, D.V.; Altobelli, E.; Liao, J.C. Advances in imaging technologies in the evaluation of high-grade bladder cancer. Urol. Clin.
**2015**, 42, 147–157. [Google Scholar] [CrossRef] [PubMed][Green Version] - Cancer Genome Atlas Research Network. Comprehensive molecular characterization of urothelial bladder carcinoma. Nature
**2014**, 507, 315–322. [Google Scholar] [CrossRef][Green Version] - Takahashi, K.; Kimura, G.; Endo, Y.; Akatsuka, J.; Hayashi, T.; Toyama, Y.; Hamasaki, T.; Kondo, Y. Urothelial carcinoma of the bladder, lipid cell variant: A case report and literature review. J. Nippon. Med Sch.
**2019**. [Google Scholar] [CrossRef][Green Version] - Dotson, A.; May, A.; Davaro, F.; Raza, S.J.; Siddiqui, S.; Hamilton, Z. Squamous cell carcinoma of the bladder: Poor response to neoadjuvant chemotherapy. Int. J. Clin. Oncol.
**2019**, 24, 706–711. [Google Scholar] [CrossRef] [PubMed] - Celis, J.E.; Wolf, H.; Østergaard, M. Bladder squamous cell carcinoma biomarkers derived from proteomics. Electrophor. Int. J.
**2000**, 21, 2115–2121. [Google Scholar] [CrossRef] - Dadhania, V.; Czerniak, B.; Guo, C.C. Adenocarcinoma of the urinary bladder. Am. J. Clin. Exp. Urol.
**2015**, 3, 51. [Google Scholar] - Sharma, A.; Fröhlich, H.; Zhang, R.; Ebert, A.K.; Rösch, W.; Reis, H.; Kristiansen, G.; Ellinger, J.; Reutter, H. Classic bladder exstrophy and adenocarcinoma of the bladder: Methylome analysis provide no evidence for underlying disease-mechanisms of this association. Cancer Genet.
**2019**, 235, 18–20. [Google Scholar] [CrossRef] [PubMed] - Ismaili, N. A rare bladder cancer-small cell carcinoma: Review and update. Orphanet J. Rare Dis.
**2011**, 6, 75. [Google Scholar] [CrossRef][Green Version] - Gil, R.T.; Esteves, G. Carcinoma de pequenas células da bexiga: Um tumor raro e agressivo. Acta Radiol. Port.
**2019**, 31, 23–26. [Google Scholar] - Mitra, S.; Kaur, G.; Kakkar, N.; Singh, P.; Dey, P. Sarcoma in urine cytology; an extremely rare entity: A report of two cases. J. Cytol.
**2017**, 34, 171. [Google Scholar] [PubMed] - Daga, G.; Kerkar, P. Sarcomatoid carcinoma of urinary bladder: A case report. Indian J. Surg. Oncol.
**2018**, 9, 644–646. [Google Scholar] [CrossRef] - Tanagho, E.A.; McAninch, J.W. Smith s General Urology; Lange Medical Books/McGraw-Hill: New York, NY, USA, 2004. [Google Scholar]
- Duty, B.; Conlin, M. Principles of urologic endoscopy. In Campbell-Walsh Urology, 11th ed.; Elsevier: Philadelphia, PA, USA, 2016; pp. 136–152. [Google Scholar]
- Lerner, S.P.; Liu, H.; Wu, M.F.; Thomas, Y.K.; Witjes, J.A. Fluorescence and white light cystoscopy for detection of carcinoma in situ of the urinary bladder. In Urologic Oncology: Seminars and Original Investigations; Elsevier: Amsterdam, The Netherlands, 2012; Volume 30, pp. 285–289. [Google Scholar]
- Shah, M.; Naik, N.; Somani, B.K.; Hameed, B.Z. Artificial intelligence (AI) in urology-Current use and future directions: An iTRUE study. Turk. J. Urol.
**2020**, 46, S27. [Google Scholar] [CrossRef] [PubMed] - Hashemi, S.M.R.; Hassanpour, H.; Kozegar, E.; Tan, T. Cystoscopic Image Classification Based on Combining MLP and GA. Int. J. Nonlinear Anal. Appl.
**2020**, 11, 93–105. [Google Scholar] - Ikeda, A.; Nosato, H.; Kochi, Y.; Kojima, T.; Kawai, K.; Sakanashi, H.; Murakawa, M.; Nishiyama, H. Support system of cystoscopic diagnosis for bladder cancer based on artificial intelligence. J. Endourol.
**2020**, 34, 352–358. [Google Scholar] [CrossRef][Green Version] - Bogović, K.; Lorencin, I.; Anđelić, N.; Blažević, S.; Smolčić, K.; Španjol, J.; Car, Z. Artificial intelligence-based method for urinary bladder cancer diagnostic. In Proceedings of the International Conference on Innovative Technologies, IN-TECH 2018, Zagreb, Croatia, 1–2 March 2018. [Google Scholar]
- Eminaga, O.; Eminaga, N.; Semjonow, A.; Breil, B. Diagnostic classification of cystoscopic images using deep convolutional neural networks. JCO Clin. Cancer Inform.
**2018**, 2, 1–8. [Google Scholar] [CrossRef] [PubMed][Green Version] - Lorencin, I.; Anđelić, N.; Španjol, J.; Car, Z. Using multi-layer perceptron with Laplacian edge detector for bladder cancer diagnosis. Artif. Intell. Med.
**2020**, 102, 101746. [Google Scholar] [CrossRef] - Lorencin, I.; Anđelić, N.; Šegota, S.B.; Musulin, J.; Štifanić, D.; Mrzljak, V.; Španjol, J.; Car, Z. Edge Detector-Based Hybrid Artificial Neural Network Models for Urinary Bladder Cancer Diagnosis. In Enabling AI Applications in Data Science; Springer: Berlin/Heidelberg, Germany, 2020; pp. 225–245. [Google Scholar]
- Ding, J.; Chen, B.; Liu, H.; Huang, M. Convolutional neural network with data augmentation for SAR target recognition. IEEE Geosci. Remote Sens. Lett.
**2016**, 13, 364–368. [Google Scholar] [CrossRef] - Salamon, J.; Bello, J.P. Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett.
**2017**, 24, 279–283. [Google Scholar] [CrossRef] - Okafor, E.; Smit, R.; Schomaker, L.; Wiering, M. Operational data augmentation in classifying single aerial images of animals. In Proceedings of the 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Gdynia, Poland, 3–5 July 2017; pp. 354–360. [Google Scholar]
- Frid-Adar, M.; Diamant, I.; Klang, E.; Amitai, M.; Goldberger, J.; Greenspan, H. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing
**2018**, 321, 321–331. [Google Scholar] [CrossRef][Green Version] - Zhao, A.; Balakrishnan, G.; Durand, F.; Guttag, J.V.; Dalca, A.V. Data augmentation using learned transformations for one-shot medical image segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 16–20 June 2019; pp. 8543–8553. [Google Scholar]
- Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2009. [Google Scholar]
- Bishop, C.M. Pattern Recognition and Machine Learning; Springer: Berlin/Heidelberg, Germany, 2006. [Google Scholar]
- Liang, X.; Hu, Z.; Zhang, H.; Gan, C.; Xing, E.P. Recurrent topic-transition gan for visual paragraph generation. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 3362–3371. [Google Scholar]
- Suárez, P.L.; Sappa, A.D.; Vintimilla, B.X. Infrared image colorization based on a triplet dcgan architecture. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 21–26 July 2017; pp. 18–23. [Google Scholar]
- Boashash, B. Time-Frequency Signal Analysis and Processing: A Comprehensive Reference; Academic Press: Cambridge, MA, USA, 2015. [Google Scholar]
- Gonzalez, R.C.; Woods, R.E.; Eddins, S.L. Digital Image Processing Using MATLAB; Pearson Education India: Chennai, India, 2004. [Google Scholar]
- Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016. [Google Scholar]
- Li, G.; Tang, H.; Sun, Y.; Kong, J.; Jiang, G.; Jiang, D.; Tao, B.; Xu, S.; Liu, H. Hand gesture recognition based on convolution neural network. Clust. Comput.
**2019**, 22, 2719–2729. [Google Scholar] [CrossRef] - Abadi, M.; Barham, P.; Chen, J.; Chen, Z.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Irving, G.; Isard, M.; et al. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), Savannah, GA, USA, 2–4 November 2016; pp. 265–283.
- Haykin, S.; Van Veen, B. Signals and Systems; John Wiley & Sons: Hoboken, NJ, USA, 2007. [Google Scholar]
- Fang, W.; Zhang, F.; Sheng, V.S.; Ding, Y. A method for improving CNN-based image recognition using DCGAN. CMC Comput. Mater. Contin.
**2018**, 57, 167–178. [Google Scholar] [CrossRef] - Creswell, A.; White, T.; Dumoulin, V.; Arulkumaran, K.; Sengupta, B.; Bharath, A.A. Generative adversarial networks: An overview. IEEE Signal Process. Mag.
**2018**, 35, 53–65. [Google Scholar] [CrossRef][Green Version] - Hong, Y.; Hwang, U.; Yoo, J.; Yoon, S. How generative adversarial networks and their variants work: An overview. ACM Comput. Surv. (CSUR)
**2019**, 52, 1–43. [Google Scholar] [CrossRef][Green Version] - Patel, R. A Brief Overview on Generative Adversarial Networks. In Data and Communication Networks; Springer: Berlin/Heidelberg, Germany, 2019; pp. 267–277. [Google Scholar]
- Santurkar, S.; Tsipras, D.; Ilyas, A.; Madry, A. How does batch normalization help optimization? In Advances in Neural Information Processing Systems; Mit Press: Cambridge, MA, USA, 2018; pp. 2483–2493. [Google Scholar]
- Zhang, X.; Zou, Y.; Shi, W. Dilated convolution neural network with LeakyReLU for environmental sound classification. In Proceedings of the 2017 22nd International Conference on Digital Signal Processing (DSP), London, UK, 23–25 August 2017; pp. 1–5. [Google Scholar]
- Liu, Y.; Wang, X.; Wang, L.; Liu, D. A modified leaky ReLU scheme (MLRS) for topology optimization with multiple materials. Appl. Math. Comput.
**2019**, 352, 188–204. [Google Scholar] [CrossRef] - De Boer, P.T.; Kroese, D.P.; Mannor, S.; Rubinstein, R.Y. A tutorial on the cross-entropy method. Ann. Oper. Res.
**2005**, 134, 19–67. [Google Scholar] [CrossRef] - Gray, R.M. Entropy and Information Theory; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2011. [Google Scholar]
- Sinha, S.; Singh, T.; Singh, V.; Verma, A. Epoch determination for neural network by self-organized map (SOM). Comput. Geosci.
**2010**, 14, 199–206. [Google Scholar] [CrossRef] - Odena, A.; Dumoulin, V.; Olah, C. Deconvolution and checkerboard artifacts. Distill
**2016**, 1, e3. [Google Scholar] [CrossRef] - Krizhevsky, A.; Sutskever, I.; Hinton, G.E. Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst.
**2012**, 25, 1097–1105. [Google Scholar] [CrossRef] - Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv
**2014**, arXiv:1409.1556. [Google Scholar] - Fawcett, T. An introduction to ROC analysis. Pattern Recognit. Lett.
**2006**, 27, 861–874. [Google Scholar] [CrossRef]

**Figure 1.**Dataflow diagram of Convolutional Neural Network-based (CNN) utilization in urinary bladder cancer diagnosis.

**Figure 3.**The process of Generative Adversarial Networks (GAN) use for a single image type is shown. Data is split into training and testing sets, and training set is used to generate additional images. Generated images are mixed with existing dataset and used for training, generating models which are finally evaluated on the testing set.

**Figure 5.**Comparison of images representing healthy mucosa generated by GAN executed for: 100 (

**a**), 250 (

**b**) 500 (

**c**) and 1000 (

**d**) epochs respectively.

**Figure 7.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of AlexNet trained with images generated by GAN in 100 epochs.

**Figure 8.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of AlexNet trained with images generated by GAN in 250 epochs.

**Figure 9.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of AlexNet trained with images generated by GAN in 500 epochs.

**Figure 10.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of AlexNet trained with images generated by GAN in 1000 epochs.

**Figure 11.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of VGG-16 trained with images generated by GAN in 100 epochs.

**Figure 12.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of VGG-16 trained with images generated by GAN in 250 epochs.

**Figure 13.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of VGG-16 trained with images generated by GAN in 500 epochs.

**Figure 14.**Median, average $\overline{AU{C}_{micro}}$ and standard deviation of $\overline{AU{C}_{micro}}$ and $\sigma \left(AU{C}_{micro}\right)$ for the case of VGG-16 trained with images generated by GAN in 1000 epochs.

**Table 1.**Description of AlexNet architecture (C—convolutional layer, P—Max pooling, FC—fully connected).

Layer | Type | Feature Map | Size | Kernel Size | Stride | Activation Function |
---|---|---|---|---|---|---|

Input | Image | 1 | $227\times 227\times 1$ | - | - | - |

1 | C | 96 | $55\times 55\times 96$ | $11\times 11$ | 4 | ReLU |

P | 96 | $27\times 27\times 96$ | $3\times 3$ | 2 | - | |

2 | C | 256 | $27\times 27\times 256$ | $5\times 5$ | 1 | ReLU |

P | 256 | $13\times 13\times 256$ | $3\times 3$ | 2 | - | |

3 | C | 384 | $13\times 13\times 384$ | $3\times 3$ | 1 | ReLU |

4 | C | 384 | $13\times 13\times 384$ | $3\times 3$ | 1 | ReLU |

5 | C | 256 | $13\times 13\times 256$ | $3\times 3$ | 1 | ReLU |

P | 256 | $6\times 6\times 256$ | $3\times 3$ | 2 | - | |

6 | FC | - | 9216 | - | - | ReLU |

7 | FC | - | 4096 | - | - | ReLU |

8 | FC | - | 4096 | - | - | ReLU |

Output | FC | - | 4 | - | - | Softmax |

**Table 2.**Description of VGG 16 architecture (C—convolutional layer; P—Max pooling; FC—fully connected).

Layer | Type | Feature Map | Size | Kernel Size | Stride | Activation Function |
---|---|---|---|---|---|---|

Input | Image | 1 | $224\times 224\times 1$ | - | - | - |

1 | $2\times C$ | 96 | $224\times 224\times 64$ | $3\times 3$ | 1 | ReLU |

P | 64 | $112\times 112\times 64$ | $3\times 3$ | 2 | - | |

3 | $2\times C$ | 128 | $112\times 112\times 128$ | $3\times 3$ | 1 | ReLU |

P | 256 | $56\times 56\times 128$ | $3\times 3$ | 2 | - | |

5 | $2\times C$ | 256 | $56\times 56\times 256$ | $3\times 3$ | 1 | ReLU |

P | 384 | $28\times 28\times 256$ | $3\times 3$ | 2 | ReLU | |

7 | $3\times C$ | 512 | $28\times 28\times 512$ | $3\times 3$ | 1 | ReLU |

P | 256 | $14\times 14\times 512$ | $3\times 3$ | 2 | - | |

10 | $3\times C$ | 512 | $14\times 14\times 512$ | $3\times 3$ | 1 | ReLU |

P | 512 | $7\times 7\times 512$ | $3\times 3$ | 2 | - | |

13 | FC | - | 25,088 | - | - | ReLU |

14 | FC | - | 4096 | - | - | ReLU |

15 | FC | - | 4096 | - | - | ReLU |

Output | FC | - | 4 | - | - | Softmax |

Number of Images | ||||
---|---|---|---|---|

Non-cancer tissue | High grade cancer | Low grade cancer | CIS | |

900 | 600 | 680 | 345 |

Case | Number of Original Images | Number of Generated Images | Total Number of Images |
---|---|---|---|

1 | 2020 | 0 | 2020 |

2 | 2020 | 2020 | 4040 |

3 | 2020 | 10,100 | 12,120 |

4 | 2020 | 18,180 | 20,200 |

Architecture | Solver | Batch Size | Number of Epochs | $\overline{{\mathit{AUC}}_{\mathit{micro}}}$ | ${\mathit{\sigma}}_{{\mathit{AUC}}_{\mathit{macro}}}$ | $\overline{{\mathit{AUC}}_{\mathit{macro}}}$ | ${\mathit{\sigma}}_{{\mathit{AUC}}_{\mathit{macro}}}$ |
---|---|---|---|---|---|---|---|

AlexNet | RMSprop | 16 | 10 | 0.96 | 0.04 | 0.96 | 0.05 |

VGG16 | Adam | 16 | 7 | 0.97 | 0.01 | 0.97 | 0.01 |

Case | GAN Epochs | Solver | Batch Size | Number of Epochs | $\overline{{\mathit{AUC}}_{\mathit{micro}}}$ | ${\mathit{\sigma}}_{{\mathit{AUC}}_{\mathit{micro}}}$ | $\overline{{\mathit{AUC}}_{\mathit{macro}}}$ | ${\mathit{\sigma}}_{{\mathit{AUC}}_{\mathit{macro}}}$ |
---|---|---|---|---|---|---|---|---|

100 | AdaDelta | 32 | 9 | 0.98 | 0.01 | 0.98 | 0.013 | |

2 | 250 | AdaMax | 32 | 9 | 0.99 | 0.003 | 0.99 | 0.003 |

500 | AdaMax | 32 | 8 | 0.99 | 0.003 | 0.99 | 0.003 | |

1000 | AdaMax | 32 | 10 | 0.99 | 0.003 | 0.99 | 0.002 | |

100 | AdaMax | 4 | 9 | 0.98 | 0.02 | 0.98 | 0.011 | |

3 | 250 | AdaMax | 32 | 8 | 0.99 | 0.002 | 0.99 | 0.002 |

500 | AdaMax | 32 | 5 | 0.99 | 0.001 | 0.99 | 0.001 | |

1000 | AdaMax | 32 | 9 | 0.99 | 0.003 | 0.99 | 0.003 | |

100 | AdaDelta | 8 | 8 | 0.98 | 0.005 | 0.98 | 0.005 | |

4 | 250 | AdaGrad | 16 | 10 | 0.99 | 0.004 | 0.99 | 0.004 |

500 | AdaMax | 32 | 10 | 0.99 | 0.003 | 0.99 | 0.003 | |

1000 | AdaMax | 32 | 10 | 0.99 | 0.002 | 0.99 | 0.002 |

Case | GAN Epochs | Solver | Batch Size | Number of Epochs | $\overline{{\mathit{AUC}}_{\mathit{micro}}}$ | ${\mathit{\sigma}}_{{\mathit{AUC}}_{\mathit{macro}}}$ | $\overline{{\mathit{AUC}}_{\mathit{macro}}}$ | ${\mathit{\sigma}}_{{\mathit{AUC}}_{\mathit{macro}}}$ |
---|---|---|---|---|---|---|---|---|

100 | AdaGrad | 8 | 9 | 0.99 | 0.004 | 0.99 | 0.004 | |

2 | 250 | AdaGrad | 8 | 8 | 0.99 | 0.002 | 0.99 | 0.002 |

500 | AdaGrad | 4 | 6 | 0.99 | 0.0007 | 0.99 | 0.0007 | |

1000 | AdaGrad | 16 | 10 | 0.99 | 0.0004 | 0.99 | 0.0004 | |

100 | AdaGrad | 8 | 4 | 0.99 | 0.004 | 0.99 | 0.003 | |

3 | 250 | AdaDelta | 4 | 8 | 0.99 | 0.002 | 0.99 | 0.002 |

500 | AdaGrad | 16 | 6 | 0.99 | 0.0005 | 0.99 | 0.0005 | |

1000 | AdaGrad | 8 | 9 | 0.99 | 0.001 | 0.99 | 0.001 | |

100 | AdaDelta | 8 | 10 | 0.99 | 0.005 | 0.99 | 0.004 | |

4 | 250 | AdaGrad | 16 | 10 | 0.99 | 0.002 | 0.99 | 0.002 |

500 | AdaDelta | 8 | 10 | 0.99 | 0.002 | 0.99 | 0.002 | |

1000 | AdaGrad | 16 | 10 | 0.99 | 0.001 | 0.99 | 0.001 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Lorencin, I.; Baressi Šegota, S.; Anđelić, N.; Mrzljak, V.; Ćabov, T.; Španjol, J.; Car, Z. On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation. *Biology* **2021**, *10*, 175.
https://doi.org/10.3390/biology10030175

**AMA Style**

Lorencin I, Baressi Šegota S, Anđelić N, Mrzljak V, Ćabov T, Španjol J, Car Z. On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation. *Biology*. 2021; 10(3):175.
https://doi.org/10.3390/biology10030175

**Chicago/Turabian Style**

Lorencin, Ivan, Sandi Baressi Šegota, Nikola Anđelić, Vedran Mrzljak, Tomislav Ćabov, Josip Španjol, and Zlatan Car. 2021. "On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation" *Biology* 10, no. 3: 175.
https://doi.org/10.3390/biology10030175