Multiscale Deep Neural Networks for Multiclass Tissue Classification of Histological Whole-Slide Images

Abstract

Correct treatment of urothelial carcinoma patients is dependent on accurate grading and staging of the cancer tumour. This is determined manually by a pathologist by examining the histological whole-slide images (WSI). The large size of these images makes this a time-consuming and challenging task. The WSI contain a variety of tissue types, and a method for defining diagnostic relevant regions would have several advantages for visualization as well as further input to automated diagnosis systems. We propose an automatic multiscale method for classification of tiles from WSI of urothelial carcinoma patients into six classes. Three architectures based on convolutional neural network (CNN) were tested: MONO-CNN (400x), DI-CNN (100x/400x) and TRI-CNN (25x/100x/400x). The preliminary results show that the two multiscale models performed significantly better than the mono-scale model, achieving an F1-score of 0.986, substantiating that utilising multiple scales in the model aids the classification accuracy.