Prostate cancer detection using deep learning neural network with transfer learning approach

Abstract

Prostate cancer is a ubiquitous form of cancer detected among men all over the world. It is currently the second leading cause of cancer death worldwide among men. Research shows that about 11% of men worldwide are affected by prostate cancer at some point during their lives. In our thesis, we have used a Transfer Learning approach for the Deep Learning model to compare the precision in results using machine learning classifiers. We have also evaluated performance in terms of classification with different evaluation measures using a Deep Learning pre-trained network (VGG16). Parameters such as Precision, Recall, F1 score and Loss vs Accuracy were assessed thoroughly as different performance measures. After applying the Transfer Learning approach, we have recorded the peak performance using the VGG16 architecture. We used the convolutional block and dense layers of VGG16 architecture to extract features from image datasets. We forwarded those features to Machine Learning classifiers for the final classification result. We have procured outstanding accuracy using the Deep Machine Learning method in our research.