Decoding pathology: the role of computational pathology in research and diagnostics

Abstract

Traditional histopathology, characterized by manual quantifications and assessments, faces challenges such as low-throughput and inter-observer variability that hinder the introduction of precision medicine in pathology diagnostics and research. The advent of digital pathology allowed the introduction of computational pathology, a discipline that leverages computational methods, especially based on deep learning (DL) techniques, to analyze histopathology specimens. A growing body of research shows impressive performances of DL-based models in pathology for a multitude of tasks, such as mutation prediction, large-scale pathomics analyses, or prognosis prediction. New approaches integrate multimodal data sources and increasingly rely on multi-purpose foundation models. This review provides an introductory overview of advancements in computational pathology and discusses their implications for the future of histopathology in research and diagnostics.

Keywords: Classification; Deep learning; Digital pathology; Pathomics; Regression; Segmentation.

Fig. 1

Digital pathology ecosystem encompassed in standard tissue analysis workflows. Regular tissue processing is followed by digitalization of tissue slides into whole slide images (WSIs). WSIs are the main data resource for digital pathology ecosystems in which they are stored, associated with other input data in the laboratory information system (LIS), and analyzed by machine or deep learning algorithms. Eventually, clinicians are provided with a bundle of extensive resources including the digitized tissue slide for informed decision making. ML, machine learning; DL, deep learning

Fig. 2

Histomorphometry techniques for different organ systems including analysis applications. Convolutional neural networks (CNNs) are applied to image patches of organ histology for segmentation of regions of interest. These image masks are then used for calculation of morphometric features which can be implemented in downstream analyses. CNN, convolutional neural network

Fig. 3

Deep learning–based classification of histopathology and approaches to interpreting the basis for classification. A Whole slide images (WSIs) are tessellated into image tiles. In a multiple instance setting, typically, a pre-trained deep learning model is used as a feature extractor that transforms each image tile into a high level feature vector which is used by another model to formulate a prediction. B These predictions are usually opaque, but techniques exist to make them interpretable (explainable artificial intelligence (XAI)). Among the most popular XAI techniques in pathology are saliency maps, trust scores, prototype examples, and concept attribution. We thank Yu-Chia Lan, M.Sc., for providing a saliency map visualization for this figure

Fig. 4

Workflow for implementation of computational pathology algorithms into clinical routine practice. Accurately formulating a clinical question, generating meaningful input data, and selecting an appropriate model architecture for the desired task are crucial for then developing a precise and robust algorithm. Computational pathology algorithms should ideally be validated in external independent cohorts and further evaluated in randomized controlled trials to demonstrate their impact on patient outcomes. After successful implementation in clinical workflows, algorithms need to be continuously monitored and adapted to the collected real-world data which provides important long-term longitudinal information to further improve model performance