BackgroundMedical Imaging and radiotherapy (MIRT) are at the forefront of artificial intelligence applications. The exponential increase of these applications has made governance frameworks necessary to uphold safe and effective clinical adoption. There is little information about how healthcare practitioners in MIRT in the UK use AI tools, their governance and associated challenges, opportunities and priorities for the future.MethodsThis cross-sectional survey was open from November to December 2022 to MIRT professionals who had knowledge or made use of AI tools, as an attempt to map out current policy and practice and to identify future needs. The survey was electronically distributed to the participants. Statistical analysis included descriptive statistics and inferential statistics on the SPSS statistical software. Content analysis was employed for the open-ended questions.ResultsAmong the 245 responses, the following were emphasised as central to AI adoption: governance frameworks, practitioner training, leadership, and teamwork within the AI ecosystem. Prior training was strongly correlated with increased knowledge about AI tools and frameworks. However, knowledge of related frameworks remained low, with different professionals showing different affinity to certain frameworks related to their respective roles. Common challenges and opportunities of AI adoption were also highlighted, with recommendations for future practice.

Introduction: Artificial Intelligence (AI) has the potential to transform medical imaging and radiotherapy; both fields where radiographers' use of AI tools is increasing. This study aimed to explore the views of those professionals who are now using AI tools. Methods: A small-scale exploratory research process was employed, where qualitative data was obtained from five UK-based participants; all professionals working in medical imaging and radiotherapy who use AI in clinical practice. Five semi-structured interviews were conducted online. Verbatim transcription was performed using an open-source automatic speech recognition model. Conceptual content analysis was performed to analyse the data and identify common themes. Results: Participants spoke about the possibility of AI deskilling staff and changing their roles, they discussed issues around data protection and data sharing strategies, the important role of effective leadership of AI teams, and the seamless integration into workflows. Participants thought that the benefits of adopting AI were smoother clinical workflows, support for the workforce in decision-making, and enhanced patient safety/care. They also highlighted the need for tailored AI education/training, multidisciplinary teamwork and support. Conclusion: Participants who are now using AI tools felt that clinical staff should be empowered to support AI implementation by adopting new and clearly defined roles and responsibilities. They suggest that attention to patient care and safety is a key to successful AI adoption. Despite the increasing adoption of AI, participants in the UK described a gap in knowledge with professionals still needing clear guidance, education and training regarding AI in preparation for more widespread adoption.

INTRODUCTION:Despite the rapid increase of AI-enabled applications deployed in clinical practice, many challenges exist around AI implementation, including the clarity of governance frameworks, usability of validation of AI models, and customisation of training for radiographers. This study aimed to explore the perceptions of diagnostic and therapeutic radiographers, with existing theoretical and/or practical knowledge of AI, on issues of relevance to the field, such as AI implementation, including knowledge of AI governance and procurement, perceptions about enablers and challenges and future priorities for AI adoption. METHODS:An online survey was designed and distributed to UK-based qualified radiographers who work in medical imaging and/or radiotherapy and have some previous theoretical and/or practical knowledge of working with AI. Participants were recruited through the researchers' professional networks on social media with support from the AI advisory group of the Society and College of Radiographers. Survey questions related to AI training/education, knowledge of AI governance frameworks, data privacy procedures, AI implementation considerations, and priorities for AI adoption. Descriptive statistics were employed to analyse the data, and chi-square tests were used to explore significant relationships between variables. RESULTS:In total, 88 valid responses were received. Most radiographers (56.6 %) had not received any AI-related training. Also, although approximately 63 % of them used an evaluation framework to assess AI models' performance before implementation, many (36.9 %) were still unsure about suitable evaluation methods. Radiographers requested clearer guidance on AI governance, ample time to implement AI in their practice safely, adequate funding, effective leadership, and targeted support from AI champions. AI training, robust governance frameworks, and patient and public involvement were seen as priorities for the successful implementation of AI by radiographers. CONCLUSION:AI implementation is progressing within radiography, but without customised training, clearer governance, key stakeholder engagement and suitable new roles created, it will be hard to harness its benefits and minimise related risks. IMPLICATIONS FOR PRACTICE:The results of this study highlight some of the priorities and challenges for radiographers in relation to AI adoption, namely the need for developing robust AI governance frameworks and providing optimal AI training.

Technological advancements in computer science have started to bring artificial intelligence (AI) from the bench closer to the bedside. While there is still lots to do and improve, AI models in medical imaging and radiotherapy are rapidly being developed and increasingly deployed in clinical practice. At the same time, AI governance frameworks are still under development. Clinical practitioners involved with procuring, deploying, and adopting AI tools in the UK should be well-informed about these AI governance frameworks. This scoping review aimed to map out available literature on AI governance in the UK, focusing on medical imaging and radiotherapy. Searches were performed on Google Scholar, Pubmed, and the Cochrane Library, between June and July 2022. Of 4225 initially identified sources, 35 were finally included in this review. A comprehensive conceptual AI governance framework was proposed, guided by the need for rigorous AI validation and evaluation procedures, the accreditation rules and standards, and the fundamental ethical principles of AI. Fairness, transparency, trustworthiness, and explainability should be drivers of all AI models deployed in clinical practice. Appropriate staff education is also mandatory to ensure AI’s safe and responsible use. Multidisciplinary teams under robust leadership will facilitate AI adoption, and it is crucial to involve patients, the public, and practitioners in decision-making. Collaborative research should be encouraged to enhance and promote innovation, while caution should be paid to the ongoing auditing of AI tools to ensure safety and clinical effectiveness.

Introduction: Metastatic (M1) disease in [ 18 F]FDG PET-CT lung cancer reports represent stage IV cancer and will have a major impact on a patient’s treatment pathway. PET-CT reports are free text, and this makes it difficult to retrospectively identify M1 staging in a cohort of patients without manually reading every report. Recent developments in artificial intelligence and natural language processing (NLP) provide new methods to retrieve this information automatically. Accordingly, we created a classifier to identify lung cancer reports that contain M1 disease. Methods: A nuclear medicine physician labelled 1851 PET-CT lung cancer reports from King’s College London and Guy’s and St. Thomas’ PET Centre for M1 status. The task was framed as binary classification and a domain adapted pre-trained language model (GatorTron) was fine-tuned on a training set of 1489 reports. The remaining 362 reports were used for evaluation and testing. As we did not have data from an external centre no individual patient data were present in both training and test sets. Results: An accuracy of 94% and AUROC of 0.97 was achieved on the test set demonstrating the model can differentiate between M0 and M1 staging. Conclusions and future work: M1 status in lung cancer can be extracted from unstructured PET-CT reports using NLP. This has potential applications in retrospective analysis and audit of reports and clinical alert systems. We are acquiring external data to further test the models and are currently developing models which categorise multiple finding types simultaneously using TNM staging.