Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review

Abstract

Bladder cancer (BC) diagnosis and prediction of prognosis are hindered by subjective pathological evaluation, which may cause misdiagnosis and under-/over-treatment. Computational pathology (CPATH) can identify clinical outcome predictors, offering an objective approach to improve prognosis. However, a systematic review of CPATH in BC literature is lacking. Therefore, we present a comprehensive overview of studies that used CPATH in BC, analyzing 33 out of 2285 identified studies. Most studies analyzed regions of interest to distinguish normal versus tumor tissue and identify tumor grade/stage and tissue types (e.g., urothelium, stroma, and muscle). The cell's nuclear area, shape irregularity, and roundness were the most promising markers to predict recurrence and survival based on selected regions of interest, with >80% accuracy. CPATH identified molecular subtypes by detecting features, e.g., papillary structures, hyperchromatic, and pleomorphic nuclei. Combining clinicopathological and image-derived features improved recurrence and survival prediction. However, due to the lack of outcome interpretability and independent test datasets, robustness and clinical applicability could not be ensured. The current literature demonstrates that CPATH holds the potential to improve BC diagnosis and prediction of prognosis. However, more robust, interpretable, accurate models and larger datasets-representative of clinical scenarios-are needed to address artificial intelligence's reliability, robustness, and black box challenge.

Keywords: artificial intelligence; bladder cancer; computational pathology; computer-aided diagnosis; digital pathology; histopathology; image analysis.

Figure 1

A general overview of types of input, processing methods, output, and applications of AI systems in analyzing H&E WSIs. (A) Input for the algorithm are the image tiles that are extracted from WSIs and can be labeled for processing and output evaluation. Labeled data can include clinical records, molecular data, and annotations like stage, grade, and tissue types. (B) AI, ML, and DL can be used to process input data. ML is a subfield of AI, and DL is a subfield of ML. ML algorithms learn from hand-crafted features and require feature engineering in the design phase to extract a set of features and train the algorithm. DL algorithms automatically extract relevant features from raw data (without human intervention) to train the algorithm and stratify features into similar groups via classification networks. (C) Output and applications of CPATH in BC image analysis can assist pathologists in improving the diagnostic process, predicting clinical outcomes, or discovering novel features. Diagnostic applications mainly focus on tissue and cell segmentation, tumor vs. normal tissue detection, grading and staging, and generation of a diagnostic report for clinical implementation. Current prognostic applications focus on predicting clinical outcomes or molecular alterations. The output can be evaluated using labels on the dataset. Abbreviations: WSI—Whole-slide image, AI—artificial intelligence, ML—machine learning, DL—deep learning, BC—bladder cancer, CPATH—computational pathology, H&E—Hematoxylin and eosin.

Figure 2

Flowchart of the study according to the PRISMA statement. PRISMA—Preferred Reporting Items for Systematic Reviews and meta-analysis.