Digital pathology is on the verge of becoming a mainstream option for routine diagnostics. Faster whole slide image scanning has paved the way for this development, but implementation on a large scale is challenging on technical, logistical, and financial levels. Comparative studies have published reassuring data on safety and feasibility, but implementation experiences highlight the need for training and the knowledge of pitfalls. Up to half of the pathologists are reluctant to sign out reports on only digital slides and are concerned about reporting without the tool that has represented their profession since its beginning. Guidelines by international pathology organizations aim to safeguard histology in the digital realm, from image acquisition over the setup of work-stations to long-term image archiving, but must be considered a starting point only. Cost-efficiency analyses and occupational health issues need to be addressed comprehensively. Image analysis is blended into the traditional work-flow, and the approval of artificial intelligence for routine diagnostics starts to challenge human evaluation as the gold standard. Here we discuss experiences from past digital pathology implementations, future possibilities through the addition of artificial intelligence, technical and occupational health challenges, and possible changes to the pathologist’s profession.

Deriving interpretable prognostic features from deep-learning-based prognostic histopathology models remains a challenge. In this study, we developed a deep learning system (DLS) for predicting disease-specific survival for stage II and III colorectal cancer using 3652 cases (27,300 slides). When evaluated on two validation datasets containing 1239 cases (9340 slides) and 738 cases (7140 slides), respectively, the DLS achieved a 5-year disease-specific survival AUC of 0.70 (95% CI: 0.66–0.73) and 0.69 (95% CI: 0.64–0.72), and added significant predictive value to a set of nine clinicopathologic features. To interpret the DLS, we explored the ability of different human-interpretable features to explain the variance in DLS scores. We observed that clinicopathologic features such as T-category, N-category, and grade explained a small fraction of the variance in DLS scores (R² = 18% in both validation sets). Next, we generated human-interpretable histologic features by clustering embeddings from a deep-learning-based image-similarity model and showed that they explained the majority of the variance (R²of 73–80%). Furthermore, the clustering-derived feature most strongly associated with high DLS scores was also highly prognostic in isolation. With a distinct visual appearance (poorly differentiated tumor cell clusters adjacent to adipose tissue), this feature was identified by annotators with 87.0–95.5% accuracy. Our approach can be used to explain predictions from a prognostic deep learning model and uncover potentially-novel prognostic features that can be reliably identified by people for future validation studies.

Personas have successfully supported the development of classical user interfaces for more than two decades by mapping users’ mental models to specific contexts. The rapid proliferation of Artificial Intelligence (AI) applications makes it necessary to create new approaches for future human-AI interfaces. Human-AI interfaces differ from classical human-computer interfaces in many ways, such as gaining some degree of human-like cognitive, self-executing, and self-adaptive capabilities and autonomy, and generating unexpected outputs that require non-deterministic interactions. Moreover, the most successful AI approaches are so-called “black box” systems, where the technology and the machine learning process are opaque to the user and the AI output is far not intuitive. This work shows how the personas method can be adapted to support the development of human-centered AI applications, and we demonstrate this on the example of a medical context. This work is - to our knowledge - the first to provide personas for AI using an openly available Personas for AI toolbox . The toolbox contains guidelines and material supporting persona development for AI as well as templates and pictures for persona visualisation. It is ready to use and freely available to the international research and development community. Additionally, an example from medical AI is provided as a best practice use case. This work is intended to help foster the development of novel human-AI interfaces that will be urgently needed in the near future.

The current move towards digital pathology enables pathologists to use artificial intelligence (AI)‐based computer programmes for the advanced analysis of whole slide images. However, currently, the best‐performing AI algorithms for image analysis are deemed black boxes since it remains – even to their developers – often unclear why the algorithm delivered a particular result. Especially in medicine, a better understanding of algorithmic decisions is essential to avoid mistakes and adverse effects on patients. This review article aims to provide medical experts with insights on the issue of explainability in digital pathology. A short introduction to the relevant underlying core concepts of machine learning shall nurture the reader's understanding of why explainability is a specific issue in this field. Addressing this issue of explainability, the rapidly evolving research field of explainable AI (XAI) has developed many techniques and methods to make black‐box machine‐learning systems more transparent. These XAI methods are a first step towards making black‐box AI systems understandable by humans. However, we argue that an explanation interface must complement these explainable models to make their results useful to human stakeholders and achieve a high level of causability, i.e. a high level of causal understanding by the user. This is especially relevant in the medical field since explainability and causability play a crucial role also for compliance with regulatory requirements. We conclude by promoting the need for novel user interfaces for AI applications in pathology, which enable contextual understanding and allow the medical expert to ask interactive ‘what‐if’‐questions. In pathology, such user interfaces will not only be important to achieve a high level of causability. They will also be crucial for keeping the human‐in‐the‐loop and bringing medical experts' experience and conceptual knowledge to AI processes.