A Review of the Impact of Convolutional Neural Networks in the Process of Renal Cancer Diagnosis

Abstract

Accurate diagnosis using histopathology images re-quires experienced pathologists, a large amount of work and time. Recent studies show that AI could be a solution to help pathologist by offering a fast and reliable help for setting a diagnosis. This paper offers a review of the latest advancements in renal cancer diagnosis using advanced AI methods, especially Convolutional Neural Networks. It includes both Computer Aided Diagnosis solutions and algorithms or frameworks that use histopathology images as input. It provides extensive data about the input databases, preprocessing methods, feature extraction, classifier architectures and results quantification. Further, it elaborates on the type of classification each algorithm offers, ranging from segmentation to benign-malignant classification and up to renal cancer subtypes differentiation or Fuhrman grade determination.