Identifying regions of interest in whole slide images of renal cell carcinoma

Abstract

PurposeThe histopathological images contain a huge amount of information, which can make diagnosis an extremely time-consuming and tedious task. In this study, we developed a completely automated system to detect regions of interest (ROIs) in whole slide images (WSI) of renal cell carcinoma (RCC), to reduce time analysis and assist pathologists in making more accurate decisions.MethodsFor this purpose, the WSIs are divided into patches at high resolution and a method is proposed to classify the patches into a tumor and healthy tissue. The proposed approach is based on an efficient texture descriptor named dominant rotated local binary pattern (DRLBP) and color transformation (hematoxylin and violet channels) to reveal and exploit the immense texture variability at the microscopic high magnifications level. Thereby, the DRLBPs retain the structural information and utilize the magnitude values in a local neighborhood for more discriminative power. For the classification of the relevant ROIs, feature extraction of WSIs patches was performed on the color channels separately to form the histograms. Next, we used the most frequently occurring patterns as a feature selection step to discard non-informative features. The performances of different classifiers (k-NN, SVM and RF) on a set of 1800 kidney cancer patches originating from 12 whole slide images were compared and evaluated. Furthermore, the small size of the image dataset allows to investigate deep learning approach based on transfer learning for image patches classification by using deep features (VGG-16) and fine-tuning (ResNet-50) methods.ResultsHigh recognition accuracy was obtained and the classifiers are efficient, the best precision result was 99.17% achieved with SVM. Moreover, transfer learning models perform well with comparable performance, and the highest precision using ResNet-50 reached 98.50%. The proposed approach results revealed a very efficient image classification and demonstrated efficacy in identifying ROIs.ConclusionThis study presents an automatic system to detect regions of interest relevant to the diagnosis of kidney cancer in whole slide histopathology images.