Recent trends and analysis of Generative Adversarial Networks in Cervical Cancer Imaging
This is an incremental review paper that synthesizes existing research on GAN applications in cervical cancer imaging, aimed at researchers and practitioners in medical imaging and oncology.
The paper analyzes recent trends in using Generative Adversarial Networks (GANs) for screening, detection, and classification of cervical cancer in imaging, providing a detailed review of models, applications, and evaluation metrics.
Cervical cancer is one of the most common types of cancer found in females. It contributes to 6-29% of all cancers in women. It is caused by the Human Papilloma Virus (HPV). The 5-year survival chances of cervical cancer range from 17%-92% depending upon the stage at which it is detected. Early detection of this disease helps in better treatment and survival rate of the patient. Many deep learning algorithms are being used for the detection of cervical cancer these days. A special category of deep learning techniques known as Generative Adversarial Networks (GANs) are catching up with speed in the screening, detection, and classification of cervical cancer. In this work, we present a detailed analysis of the recent trends relating to the use of various GAN models, their applications, and the evaluation metrics used for their performance evaluation in the field of cervical cancer imaging.