A deep learning based multiscale approach to segment the areas of interest in whole slide images.

• We propose a multi-scale image processing method to facilitate and assist the reliable segmentation of liver cancer area in Whole Slide Image (WSI). • We use a method of partial color normalization for equalizing the color representation of different tissue areas. • We adapt a weighted overlapping method to overcome the loss of border information resulted by cropping operation. • We propose a voting mechanism to integrate multi-scale information by multiple validation to get the optimal final result. This paper addresses the problem of liver cancer segmentation in Whole Slide Images (WSIs). We propose a multi-scale image processing method based on an automatic end-to-end deep neural network algorithm for the segmentation of cancerous areas. A seven-level gaussian pyramid representation of the histopathological image was built to provide the texture information at different scales. In this work, several neural architectures were compared using the original image level for the training procedure. The proposed method is based on U-Net applied to seven levels of various resolutions (pyramidal subsampling). The predictions in different levels are combined through a voting mechanism. The final segmentation result is generated at the original image level. Partial color normalization and the weighted overlapping method were applied in preprocessing and prediction separately. The results show the effectiveness of the proposed multi-scale approach which achieved better scores than state-of-the-art methods. [ABSTRACT FROM AUTHOR]