The Role of Artificial Intelligence in the Diagnosis and Prognosis of Renal Cell Tumors

Abstract

The increasing availability of molecular data provided by next-generation sequencing (NGS) techniques is allowing improvement in the possibilities of diagnosis and prognosis in renal cancer. Reliable and accurate predictors based on selected gene panels are urgently needed for better stratification of renal cell carcinoma (RCC) patients in order to define a personalized treatment plan. Artificial intelligence (AI) algorithms are currently in development for this purpose. Here, we reviewed studies that developed predictors based on AI algorithms for diagnosis and prognosis in renal cancer and we compared them with non-AI-based predictors. Comparing study results, it emerges that the AI prediction performance is good and slightly better than non-AI-based ones. However, there have been only minor improvements in AI predictors in terms of accuracy and the area under the receiver operating curve (AUC) over the last decade and the number of genes used had little influence on these indices. Furthermore, we highlight that different studies having the same goal obtain similar performance despite the fact they use different discriminating genes. This is surprising because genes related to the diagnosis or prognosis are expected to be tumor-specific and independent of selection methods and algorithms. The performance of these predictors will be better with the improvement in the learning methods, as the number of cases increases and by using different types of input data (e.g., non-coding RNAs, proteomic and metabolic). This will allow for more precise identification, classification and staging of cancerous lesions which will be less affected by interpathologist variability.

Cultivating Clinical Clarity through Computer Vision: A Current Perspective on Whole Slide Imaging and Artificial Intelligence

“…Fenstermaker et al [ 54 ] developed a CNN model to detect, grade (Fuhrman 1–4), and distinguish RCC subtypes (clear cell, chromophobe, papillary). The model was trained on 3000 normal and 12,168 RCC H&E-stained tissue samples of RCC from 42 patients (acquired from the Cancer Genome Atlas).…”

Proteomics, Personalized Medicine and Cancer

“…Integration of proteomics with artificial intelligence methods like machine and deep learning clearly represents the future trend for proteomics research and personalized/precision medicine and a number of platforms are being developed. Recent examples include applications for HCC [ 228 ], renal cell carcinoma [ 229 ] and lung cancer [ 230 ]. Researchers from the Technical University of Munich successfully used proteomic data to train a neural network, termed Prosit, facilitating the rapid and accurate error free mass analysis of proteins [ 231 ].…”

Multimodal ultrasound fusion network for differentiating between benign and malignant solid renal tumors

“…Deep learning has shown promising results in the classification and diagnosis of renal tumors over the past few years ( Oktay et al, 2018 ; Hussain et al, 2021 ; Wang et al, 2021 ), which does not require subjectively defined features and can capture the entirety of biological information from images compared with traditional machine learning ( Sun et al, 2020 ; Bhandari et al, 2021 ; Giulietti et al, 2021 ; Khodabakhshi et al, 2021 ). The literature indicates that deep learning algorithms are better than human experts in diagnosing many kinds of diseases, such as liver, breast, lung, fundus, skin lesions ( Wu et al, 2017 ; Lin et al, 2020 ; Li et al, 2021 ; Liu et al, 2021 ).…”