Automated Method for Optimum Scale Search when Using Trained Models for Histological Image Analysis

Maksim A. Penkin, Alexander V. Khvostikov, Andrey S. Krylov

Abstract: Preparation of input data for an artificial neural network is a key step to achieve a high accuracy of its predictions. It is well known that convolutional neural models have low invariance to changes in the scale of input data. For instance, processing multiscale whole-slide histological images by convolutional neural networks naturally poses a problem of choosing an optimal processing scale. In this paper, this problem is solved by iterative analysis of distances to a separating hyperplane that are generated by a convolutional classifier at different input scales. The proposed method is tested on the DenseNet121 deep architecture pre-trained on PATH-DT-MSU data, which implements patch classification of whole-slide histological images.