A Precision Diagnostic Framework of Renal Cell Carcinoma on Whole-Slide Images using Deep Learning
This work addresses diagnostic variability in renal cell carcinoma for pathologists, but it is incremental as it applies an existing method to a specific domain with new data.
The authors tackled the challenge of subjective and variable pathological diagnosis of renal cell carcinoma by developing a deep learning framework using InceptionV3 trained on TCGA data, achieving pathologist-level accuracy in tumor detection, subtype classification, and grade classification.
Diagnostic pathology, which is the basis and gold standard of cancer diagnosis, provides essential information on the prognosis of the disease and vital evidence for clinical treatment. Tumor region detection, subtype and grade classification are the fundamental diagnostic indicators for renal cell carcinoma (RCC) in whole-slide images (WSIs). However, pathological diagnosis is subjective, differences in observation and diagnosis between pathologists is common in hospitals with inadequate diagnostic capacity. The main challenge for developing deep learning based RCC diagnostic system is the lack of large-scale datasets with precise annotations. In this work, we proposed a deep learning-based framework for analyzing histopathological images of patients with renal cell carcinoma, which has the potential to achieve pathologist-level accuracy in diagnosis. A deep convolutional neural network (InceptionV3) was trained on the high-quality annotated dataset of The Cancer Genome Atlas (TCGA) whole-slide histopathological image for accurate tumor area detection, classification of RCC subtypes, and ISUP grades classification of clear cell carcinoma subtypes. These results suggest that our framework can help pathologists in the detection of cancer region and classification of subtypes and grades, which could be applied to any cancer type, providing auxiliary diagnosis and promoting clinical consensus.