Aims
Artificial intelligence (AI) provides a powerful tool to extract information from digitised histopathology whole slide images. During the last 5 years, academic and commercial actors have developed new technical solutions for a diverse set of tasks, including tissue segmentation, cell detection, mutation prediction, prognostication and prediction of treatment response. In the light of limited overall resources, it is presently unclear for researchers, practitioners and policymakers which of these topics are stable enough for clinical use in the near future and which topics are still experimental, but worth investing time and effort into.
Methods and results
To identify potentially promising applications of AI in pathology, the research group performed an anonymous online survey of 75 computational pathology domain experts from academia and industry. Participants enrolled in 2021 were queried about their subjective opinion on promising and appealing subfields of computational pathology with a focus upon solid tumours. The results of this survey indicate that the prediction of treatment response directly from routine pathology slides is regarded as the most promising future application. This item was ranked highest in the overall analysis and in subgroups by age and professional background. Furthermore, prediction of genetic alterations, gene expression and survival directly from routine pathology images scored consistently high throughout subgroups.
Conclusions
Together, these data demonstrate a possible direction for the development of computational pathology systems in clinical, academic and industrial research in the near future. The results of the survey could be used to guide future research in academia and industry. Importantly, there are strong interdependencies of the different areas; e.g. AI-driven quality control is useful for an AI-enhanced diagnosis and decision support. Overall, the study shows the need for computational pathology solutions which go beyond workflow automation and provide true new biomarkers for outcome and response prediction. Suggesting more pathologists could be trained in AI to enable them to devise and test their own ideas for new biomarkers. Also, this could help overcome fears of AI, as it was shown in radiology that the more a person knows about AI, the less they fear it.35Â Finally, beyond its powers in image analysis, AI also excels at natural language processing (NLP). Combining vision and language AI models would open the possibility to interact with AI through natural language, which could further improve the integration into clinical workflows.
About this Journal
Histopathology is an international journal intended to be of practical value to surgical and diagnostic histopathologists, and to investigators of human disease who employ histopathological methods. Our primary purpose is to publish advances in pathology, in particular those applicable to clinical practice and contributing to the better understanding of human disease.
