Resizing and cleaning of histopathological images using generative adversarial networks

Bilinear and Bicubic interpolation techniques are frequently used to increase image resolution. These techniques with data modeling approach are replaced by intelligent systems that can learn automatically from data. SRGAN is a modern Generative Adversarial Network developed as an alternative to classical interpolation techniques. His ability to produce images in super resolution has attracted the attention of many researchers. In this study, noise elimination performance of super resolution generative adversarial network (SRGAN) with image magnification was investigated. The results of the noise cleaning were compared with the classical approaches (mean, median, adaptive filters). SSIM, PSNR and FFT_MSE metrics were evaluated in experimental studies using images in the data set Camelyon17. When the results were evaluated, it was observed that SRGAN was superior to the classical approaches not only in increasing the resolution but also in the noise cleaning area. •The application of SRGAN algorithm was performed and the performance in medical images was examined.•The SRGAN method was used for the first time in the noise clearing area except for increasing the resolution.•The proposed noise clearance approach compared the performance of classical noise removal algorithms in the image processing area at different noise levels.•When the experimental results were examined, it was seen that SRGAN method could be used as a very ambitious approach in the field of noise cleaning.