There has been particular interest in the deployment of digital pathology (DP) and artificial intelligence (AI) in the diagnosis of prostate cancer, but little is known about the views of the public on their use. Prostate Cancer UK supporters were invited to an online survey which included quantitative and qualitative questions exploring views on the use of DP and AI in histopathological assessment. A total of 1276 responses to the survey were analysed (response rate 12.5%). Most respondents were supportive of DP (87%, 1113/1276) and of testing AI in clinical practice as a diagnostic adjunct (83%, 1058/1276). Respondents saw DP as potentially increasing workflow efficiency, facilitating research, education/training and fostering clinical discussions between clinician and patient. Some respondents raised concerns regarding data security, reliability and the need for human oversight. Among those who were unsure about AI, information was requested regarding its performance and others wanted to defer the decision to use it to an expert. Although most are in favour of its use, some are unsure, and their concerns could be addressed with more information or better communication. A small minority (<1%) are not in favour of the testing of the use of AI in histopathology for reasons which are not easily addressed.
Aim: we describe our experience of validating departmental pathologists for digital pathology reporting, based on the UK Royal College of Pathologists (RCPath) “Best Practice Recommendations for Implementing Digital Pathology (DP),” at a large academic teaching hospital that scans 100% of its surgical workload. We focus on Stage 2 of validation (prospective experience) prior to full validation sign-off. Methods and results: twenty histopathologists completed Stage 1 of the validation process and subsequently completed Stage 2 validation, prospectively reporting a total of 3777 cases covering eight specialities. All cases were initially viewed on digital whole slide images (WSI) with relevant parameters checked on glass slides, and discordances were reconciled before the case was signed out. Pathologists kept an electronic log of the cases, the preferred reporting modality used, and their experiences. At the end of each validation, a summary was compiled and reviewed with a mentor. This was submitted to the DP Steering Group who assessed the scope of cases and experience before sign-off for full validation. A total of 1.3% (49/3777) of the cases had a discordance between WSI and glass slides. A total of 61% (30/49) of the discordances were categorised as a minor error in a supplementary parameter without clinical impact. The most common reasons for diagnostic discordances across specialities included identification and grading of dysplasia, assessment of tumour invasion, identification of small prognostic or diagnostic objects, interpretation of immunohistochemistry/special stains, and mitotic count assessment. Pathologists showed similar mean diagnostic confidences (on Likert scale from 0 to 7) with a mean of 6.8 on digital and 6.9 on glass slide reporting. Conclusion: we describe one of the first real-world experiences of a department-wide effort to implement, validate, and roll out digital pathology reporting by applying the RCPath Recommendations for Implementing DP. We have shown a very low rate of discordance between WSI and glass slides.
Deep learning (DL) has the potential to deliver significant clinical benefits. In recent years, an increasing number of DL-based systems have been approved by the relevant regulators, e.g. FDA. Although obtaining regulatory approvals is a prerequisite to deploy such systems for real world use, it may not be sufficient. Regulatory approvals give confidence in the development process for such systems, but new hazardous events can arise depending on how the systems have been deployed in the intended clinical pathways or how they have been used with other systems in complex healthcare settings. These kinds of events can be difficult to predict during the development process. Indeed, most health systems and hospitals require self-verification before deploying a diagnostic medical device, which could be viewed as an additional safety measure. This shows that it is important to carry on assuring the safety of such systems in deployment. In this work, we address this urgent need based on the experience of a prospective study in UK hospitals as part of the ARTICULATE PRO project. In particular, the system considered in this work is developed by Paige for prostate cancer diagnosis, which has obtained FDA approval in the US and UKCA marks in the UK. The methodology presented in this work starts by mapping out the clinical workflow within which the system has been deployed, then carries out hazard and risk analysis based on the clinical workflow, and finally presents a deployment safety case, which provides a basis for deployment and continual monitoring of the safety of this system in use. In this work we systematically address the emergence of new hazardous events from the deployment and to present a way to continually assure the safety of a regulatorily approved system in use.