ProGleason-GAN: Conditional progressive growing GAN for prostatic cancer Gleason grade patch synthesis

•Conditional Progressive Growing GAN approach is developed for the first time to synthesise histopathological prostate tissue patches.•This new method allows the grade selection according to the Gleason scale that the generated samples should contain.•Evaluation of the quality of the synthetic samples using Frechet Inception Distance. The results of this metric are provided for each grade on the Gleason scale after a staining normalisation process.•Our approach as data augmentation method boosts classification accuracy by 4%.•External validation by pathology experts confirms the strength of our study in accurately representing cancerous patternsaccording to the Gleason scale. Prostate cancer is one of the most common diseases affecting men. The main diagnostic and prognostic reference tool is the Gleason scoring system. An expert pathologist assigns a Gleason grade to a sample of prostate tissue. As this process is very time-consuming, some artificial intelligence applications were developed to automatize it. The training process is often confronted with insufficient and unbalanced databases which affect the generalisability of the models. Therefore, the aim of this work is to develop a generative deep learning model capable of synthesising patches of any selected Gleason grade to perform data augmentation on unbalanced data and test the improvement of classification models. The methodology proposed in this work consists of a conditional Progressive Growing GAN (ProGleason-GAN) capable of synthesising prostate histopathological tissue patches by selecting the desired Gleason Grade cancer pattern in the synthetic sample. The conditional Gleason Grade information is introduced into the model through the embedding layers, so there is no need to add a term to the Wasserstein loss function. We used minibatch standard deviation and pixel normalisation to improve the performance and stability of the training process. The reality assessment of the synthetic samples was performed with the Frechet Inception Distance (FID). We obtained an FID metric of 88.85 for non-cancerous patterns, 81.86 for GG3, 49.32 for GG4 and 108.69 for GG5 after post-processing stain normalisation. In addition, a group of expert pathologists was selected to perform an external validation of the proposed framework. Finally, the application of our proposed framework improved the classification results in SICAPv2 dataset, proving its effectiveness as a data augmentation method. ProGleason-GAN