Renal cell carcinoma (RCC) is among the top 10 most common cancers in both men and women. The incidence of RCC has gradually risen in recent years, resulting in increased time-, effort-, and cost-related demands on healthcare systems [1]. Adequate RCC diagnosis and treatment planning relies on adequate clinical data, imaging, histology, and molecular profiling ^[2][3][2,3].

Histological analysis, which is supported by genetic and cytogenetic analysis, is crucial for RCC diagnosis, as well as subtyping and defining features with high prognostic and therapeutic impact ^[4][5][4,5]. These features include tumor grade, RCC subtype, lymphovascular invasion, tumor necrosis, sarcomatoid dedifferentiation, etc. ^[6][7][8][6,7,8]. RCC histological diagnosis and classification, in particular, can be a daunting task, as it encompasses a broad spectrum of histopathological entities, which have recently been subject to changes ^[9][10][9,10].

Over the years, the daily clinical practice of treating patients with RCC has changed from using paper charts, analog radiographs, and light microscopes to using more modern counterparts, such as electronic health records and digitalized radiology and virtual pathology. This shift has generated an enormous amount of digital data, which can be utilized in data-characterization algorithms or artificial intelligence (AI) ^[11][12][11,12].

The use of AI in radiology, which is also known as radiomics, has shown excellent diagnostic accuracy for detecting RCC and can even provide information regarding RCC subtyping, nuclear grade prediction, gene mutations, and gene expression-based molecular signatures [13]. In line with AI in radiology, efforts to use AI in RCC histopathology have been undertaken in recent years. This relatively new field, which is called pathomics or computational pathology, can be used to improve efficiency, accessibility, cost-effectiveness, and time consumption, as well as enhance accuracy and reproducibility with lower subjectivity ^{[11][14][15][16][17]}[11,14,15,16,17]. In addition, Whole Slide Imaging (WSI) technology allows machine learning in pathology by providing an enormous amount of high-quality information for training and testing AI models to identify specific features and patterns that can be complex for even the human eye to discern ^[12][18][19][12,18,19]. Ultimately, AI aims to assist pathologists in making more accurate and consistent diagnoses in shorter periods of time and is a valuable implement to undercover the above-cited information ^[20][21][20,21]

Although several advances have been made in RCC diagnostics in the last decade, especially in imaging techniques, histo-pathological diagnosis based on a pathologist’s skill and experience remains the standard clinical practice used to distinguish RCC from normal renal tissue at the microscopic level ^{[13][22][23][24]}[13,29,30,31].

However, RCCs can have complicated characteristics that make the diagnosis difficult, laborious, and time consuming, even for experienced pathologists. These issues are known to lead to a moderate inter-reader agreement for the RCC subtype ^[25][26][27][32,33,34]. In addition, several studies demonstrated that computational pathology could be a solution to more uniform specimen readings and reduce intra- and inter-observer variability ^[28][29][30][35,36,37].

RCC varies in its biological behavior, ranging from indolent to aggressive tumors. Currently, no reliable predictive models that distinguish between different clinical types are available for use in the pre-operative setting, creating concerns about under- and over-treatment, especially in small renal masses (SRMs), which now represent up to 50% of renal lesions ^{[31][32][33][34][35]}[38,39,40,41,42]. Therefore, this issue can lead to overdiagnosis and overtreatment. To date, there are no highly reliable biomarkers or imaging methods that can correctly differentiate between benign and malignant lesions ^[36][37][38][43,44,45] As a result, there has been a growing trend of using renal mass biopsy (RMB) to address this challenge over the past decade ^[39][40][41][46,47,48].

However, RMBs have some limitations as they are non-diagnostic in approximately 10–15% of the cases and remain intrinsically invasive ^[42][49]. The main reason for the high percentage of non-diagnostic results is inadequate sampling of tumors ^[43][50]. Another crucial issue in RMB is a fair degree of interobserver variability ^[44][51], a concern that is also found in breast, prostate, and melanoma biopsies ^[45][46][47][52,53,54].

To tackle these problems, Fenstermaker et al. developed a DL-based algorithm for RCC diagnosis, grading, and subtype assessment ^[48][55]. Their method reached a high accuracy level when using only a 100 square micrometers (µm²) patch, making it a potentially valuable tool in RMB analysis. In addition, although their method was trained on whole-mount surgical specimens, a computational method trained and tested on small tissue samples may reduce the need for repeat biopsies by decreasing insufficient tissue sampling and reducing interobserver variability.

However, this research focused on identifying the three main subtypes of RCC without considering benign tumors or oncocytomas. A significant proportion of small renal masses (SRMs) are benign, with oncocytoma being the most frequent benign contrast-enhancing renal mass found. A well-known problem faced by pathologists is differentiating oncocytomas from chromophobe RCC ^[49][50][51][56,57,58]. Zhu et al. reported favorable results in RCC subtyping in surgical resection and RMB specimens, as well as promising results in oncocytoma diagnosis in RMB ^[52][59]. The group trained and tested a model on an internal dataset of renal resections. In addition, they tested this model on 79 RCC biopsy slides, 24 of which were diagnosed as renal oncocytoma, and an external dataset, achieving good performance, as shown in Table 1.

Despite the recent increased use of RMB and enormous advances in diagnostic accuracy ^[53][54][60,61], approximately 73% of surveyed urologists would not perform a RMB for various reasons ^[55][62]. Currently, the standard of treatment for non-metastatic RCC is surgical resection, carried out via either a radical or partial nephrectomy; this technique was also used in some selected cases of metastatic RCC ^[56][57][63,64]. However, examining and analyzing the complex histological patterns of RCC surgical resection specimens under a microscope can be challenging and time consuming for pathologists for many reasons. For instance, nephrectomy specimens exhibit substantial heterogeneity, exemplifying the wide variation observed within RCC surgical resection samples ^[58][65]. Moreover, variability among different observers, and even within the same observer, has been reported ^[26][33].

Good results were obtained by Tabibu et al. in terms of distinguishing between ccRCC and chRCC and normal tissue using two pre-trained convolutional neural networks (CNN) and replacing the final layers with two output layers, which were fine-tuned using RCC data ^[59][66]. Moreover, for subtype classification, the group introduced a so-called directed acyclic graph support vector machine (DAG-SVM) on top of the deep network, obtaining good accuracy in this task. Unlike Tabibu et al.’s model, Chen et al. developed a DL algorithm to detect RCC that was externally validated on an independent dataset ^[60][67]. To accomplish this task, they used LASSO (least absolute shrinkage and selection operator), which is a method used in ML to select from a more extensive set of features, i.e., the most important in predicting outcomes. Through LASSO analysis, they identified various image features based on the “The Cancer Genome Atlas” (TCGA) cohort to distinguish between ccRCC and normal renal parenchyma, as well as ccRCC and pRCC and chRCC, obtaining high accuracy in test and external validation cohorts.

Also, Marostica et al. created a pipeline using transfer learning to identify cancerous regions from slide images and classify the three major subtypes, obtaining good performance in both the test set and two external independent datasets (Table 3) ^[61][68].

RCC classification is a challenging task not only due to the complexity of the procedure itself, but also because the classification system is subject to periodic updates ^[62][63][69,70]. For example, only in recent years has clear cell papillary renal cell carcinoma (ccpRCC) been recognized as a specific entity [4]. This subtype of RCC histologically resembles both ccRCC and pRCC, and it has clear cell changes. However, ccpRCC has distinct immuno-histochemical and genetic profiles compared to ccRCC and pRCC ^[64][71]. It also carries a favorable prognosis relative to the latter carcinoma; therefore, the World Health Organization recently changed its denomination to a clear cell papillary renal cell tumor ^[65][72]. Abdeltawab et al. developed a computational model that could distinguish between ccRCC and ccpRCC, obtaining an accuracy of 91% in identifying ccpRCC using the institution files and 90% in diagnosing ccRCC using an external dataset ^[66][73].

The abovementioned studies were mainly supervised and highly defined for RCC approaches, making them time consuming to conduct. However, the capability to apply knowledge gained from previous experiences to novel situations is a vital skill among human beings. For example, pathologists can use lessons learned outside of their specific subspecialty because several cancer types exhibit common hallmarks of malignancy, as demonstrated by Faust et al., who tested whether a previously trained AI system developed to recognize brain tumor features could be applied to clusters and analyze RCC specimens in an unsupervised fashion ^[67][74]. The results showed that grouping cancer regions from non-neoplastic tissue elements matched expert annotations in multiple randomly selected cases. This result, hypothetically, represents a way to demonstrate that unsupervised ML-based methods, which were built for the diagnosis of other cancers, can also be used to diagnose RCC, reducing development and work time.