A Deep learning approach for Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images

Abstract

Histopathological images contain morphological markers of disease progression that have diagnostic and predictive values. However, complex morphological information remains unutilized in unaided approach to histopathology. In this study, we demonstrate how deep learning framework can be used for an automatic classification of Renal Cell Carcinoma (RCC) subtypes, and for identification of features that predict survival outcome from digital histopathological images. Convolutional neural networks (CNN's) trained on whole-slide images distinguish clear cell and chromophobe RCC from normal tissue with a classification accuracy of 93.39 % and 87.34 %, respectively. Further, a CNN trained to distinguish clear cell, chromophobe and papillary RCC achieves a classification accuracy of 92.61 %. Here, we introduced a novel support vector machine based method to deal with data imbalance in multi-class classification to improve the accuracy. Finally, we extracted the morphological features from high probability tumor regions identified by the CNN to predict patient survival outcome of most common clear cell RCC. The generated risk index based on both tumor shape and nuclei features are significantly associated with patient survival outcome. These results highlight that deep learning can play a role in both cancer diagnosis and prognosis.

Predictive performance of radiomic models based on features extracted from pretrained deep networks

“…The benefit of applying DL in radiomics is that it circumvents the suboptimal choice of generic features since a network can learn an optimal feature set specific to the task at hand, which could, in turn, could lead to higher predictive performance [12][13][14][15]. However, in practice, radiomic datasets often have very small sample sizes, which prevent the network from learning highly predictive features [16][17][18].…”

Development and evaluation of deep learning–based segmentation of histologic structures in the kidney cortex with multiple histologic stains

“…In the past few years, several studies have demonstrated the utility of DL networks for low-level image analyses (i.e., detection, segmentation, and classification of histologic primitives) and high-level complex prognosis and prediction tasks. [31][32][33][34][35]…”

OpenHI2 — Open source histopathological image platform

“…Many of them only take selected regions provided by public datasets derived from competitions [20], [21], thus, information at the macro level is being discarded. Meanwhile, [22] is a preliminary evidence proof that visual information at the macro or whole-slide level do reflect the patient's outcome. To promote further development in this area, standardized annotation framework which support largescale collaborative annotation is needed.…”