Black box no more: A cross-sectional multi-disciplinary survey for exploring governance and guiding adoption of AI in medical imaging and radiotherapy in the UK.

BACKGROUND: Medical 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. METHODS: This 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. RESULTS: Among 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.

Strategies to improve the magnetic resonance imaging experience for autistic individuals: a cross-sectional study exploring parents and carers' experiences.

BACKGROUND: Autistic individuals encounter numerous barriers in accessing healthcare, including communication difficulties, sensory sensitivities, and a lack of appropriate adjustments. These issues are particularly acute during MRI scans, which involve confined spaces, loud noises, and the necessity to remain still. There remains no unified approach to preparing autistic individuals for MRI procedures. METHODS: A cross-sectional online survey was conducted with parents and carers of autistic individuals in the UK to explore their experiences, barriers, and recommendations concerning MRI scans. The survey collected demographic information and experiential accounts of previous MRI procedures. Quantitative data were analysed descriptively, while key themes were identified within the qualitative data through inductive thematic analysis. RESULTS: Sixteen parents/carers participated. The majority reported difficulties with communication, inadequate pre-scan preparation, and insufficient adjustments during MRI scans for their autistic children. Key barriers included an overwhelming sensory environment, radiographers' limited understanding of autism, and anxiety stemming from uncertainties about the procedure. Recommended improvements encompassed accessible communication, pre-visit familiarisation, noise-reduction and sensory adaptations, staff training on autism, and greater flexibility to meet individual needs. CONCLUSIONS: There is an urgent need to enhance MRI experiences for autistic individuals. This can be achieved through improved staff knowledge, effective communication strategies, thorough pre-scan preparation, and tailored reasonable adjustments. Co-producing clear MRI guidelines with the autism community could standardise sensitive practices. An individualised approach is crucial for reducing anxiety and facilitating participation. Empowering radiographers through autism-specific education and incorporating insights from autistic individuals and their families could transform MRI experiences and outcomes.

Responsible AI practice and AI education are central to AI implementation: a rapid review for all medical imaging professionals in Europe.

Artificial intelligence (AI) has transitioned from the lab to the bedside, and it is increasingly being used in healthcare. Radiology and Radiography are on the frontline of AI implementation, because of the use of big data for medical imaging and diagnosis for different patient groups. Safe and effective AI implementation requires that responsible and ethical practices are upheld by all key stakeholders, that there is harmonious collaboration between different professional groups, and customised educational provisions for all involved. This paper outlines key principles of ethical and responsible AI, highlights recent educational initiatives for clinical practitioners and discusses the synergies between all medical imaging professionals as they prepare for the digital future in Europe. Responsible and ethical AI is vital to enhance a culture of safety and trust for healthcare professionals and patients alike. Educational and training provisions for medical imaging professionals on AI is central to the understanding of basic AI principles and applications and there are many offerings currently in Europe. Education can facilitate the transparency of AI tools, but more formalised, university-led training is needed to ensure the academic scrutiny, appropriate pedagogy, multidisciplinarity and customisation to the learners' unique needs are being adhered to. As radiographers and radiologists work together and with other professionals to understand and harness the benefits of AI in medical imaging, it becomes clear that they are faced with the same challenges and that they have the same needs. The digital future belongs to multidisciplinary teams that work seamlessly together, learn together, manage risk collectively and collaborate for the benefit of the patients they serve.

Toward Autism-Friendly Magnetic Resonance Imaging: Exploring Autistic Individuals' Experiences of Magnetic Resonance Imaging Scans in the United Kingdom, a Cross-Sectional Survey.

Background: Autistic individuals might undergo a magnetic resonance imaging (MRI) examination for clinical concerns or research. Increased sensory stimulation, lack of appropriate environmental adjustments, or lack of streamlined communication in the MRI suite may pose challenges to autistic patients and render MRI scans inaccessible. This study aimed at (i) exploring the MRI scan experiences of autistic adults in the United Kingdom; (ii) identifying barriers and enablers toward successful and safe MRI examinations; (iii) assessing autistic individuals' satisfaction with MRI service; and (iv) informing future recommendations for practice improvement. Methods: We distributed an online survey to the autistic community on social media, using snowball sampling. Inclusion criteria were: being older than 16, have an autism diagnosis or self-diagnosis, self-reported capacity to consent, and having had an MRI scan in the United Kingdom. We used descriptive statistics for demographics, inferential statistics for group comparisons/correlations, and content analysis for qualitative data. Results: We received 112 responses. A total of 29.6% of the respondents reported not being sent any information before the scan. Most participants (68%) confirmed that radiographers provided detailed information on the day of the examination, but only 17.1% reported that radiographers offered some reasonable environmental adjustments. Only 23.2% of them confirmed they disclosed their autistic identity when booking MRI scanning. We found that quality of communication, physical environment, patient emotions, staff training, and confounding societal factors impacted their MRI experiences. Autistic individuals rated their overall MRI experience as neutral and reported high levels of claustrophobia (44.8%). Conclusion: This study highlighted a lack of effective communication and coordination of care, either between health care services or between patients and radiographers, and lack of reasonable adjustments as vital for more accessible and person-centered MRI scanning for autistic individuals. Enablers of successful scans included effective communication, adjusted MRI environment, scans tailored to individuals' needs/preferences, and well-trained staff.

Why is this an important issue?: Magnetic resonance imaging (MRI) is an examination that shows human anatomy and may explain the causes of symptoms. Autistic people may need MRI scans for various reasons, such as low back pain, headaches, accidents, or epilepsy. They have known sensitivities to sound, light, smell, or touch and increased anxiety, so the narrow, loud, isolating, unfamiliar MRI environment may be overwhelming to them. If MRI scans are, for these reasons, inaccessible, many autistic people will have to live with long-standing conditions, pain, or other symptoms, or have delayed treatment, with impact on their quality of life, and life expectancy. What was the purpose of this study?: We tried to understand how autistic people perceive MRI examinations, things that work, and the challenges they face. We also asked for their suggestions to improve practice and accessibility. What did we do?: We distributed an online questionnaire to autistic adults through social media. We analyzed the data using appropriate statistical and text analysis methods. What were the results of the study?: We received 112 responses. Autistic people rated their overall MRI experience as average. Nearly a third (29.6%) reported they were not sent any information before MRI, and only 17.1% reported that radiographers offered some reasonable environmental adjustments. Most participants (68%) reported that radiographers provided detailed information on the day of the scan. Only 23.2% of them disclosed their autistic identity when booking MRIs. We found that quality of communication, physical environment, patient emotions, staff training, stigma, and timely autism diagnosis impacted their MRI experiences. What do these findings add to what was already known?: Autistic people MRI scan experiences are at the heart of this project. Our project shows that MRI for common symptoms is often inaccessible by autistic people. We should improve the MRI environment, adjust communication format/content for them, and deliver person-centered care in MRI. Health care professionals should receive relevant training, to understand the challenges autistic people might face and better support them in MRI scanning. What are potential weaknesses in the study?: The pandemic has impacted participant recruitment; therefore, the results of this sample may not reflect the full impact on the wider autistic population or adequately represent the autistic community, due to small size and including only people who could consent.These results come from different centers, so there is a lot of variation in the use of MRI equipment. How will these findings help autistic adults now or in the future?: We outline the main challenges associated with MRI, so autistic adults and their families/carers understand more of what they could expect in future examinations; hopefully, researchers and scanner manufacturers will try to tackle these challenges to make MRI scans truly accessible for autistic people.We shared this knowledge with stakeholders to develop guidelines and started using it in training. We want to ensure that MRI is person-centered and more accessible for autistic patients.

Black box no more: a scoping review of AI governance frameworks to guide procurement and adoption of AI in medical imaging and radiotherapy in the UK.

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.

Radiomics for Alzheimer's Disease: Fundamental Principles and Clinical Applications.

Alzheimer's disease is a neurodegenerative disease with a huge impact on people's quality of life, life expectancy, and morbidity. The ongoing prevalence of the disease, in conjunction with an increased financial burden to healthcare services, necessitates the development of new technologies to be employed in this field. Hence, advanced computational methods have been developed to facilitate early and accurate diagnosis of the disease and improve all health outcomes. Artificial intelligence is now deeply involved in the fight against this disease, with many clinical applications in the field of medical imaging. Deep learning approaches have been tested for use in this domain, while radiomics, an emerging quantitative method, are already being evaluated to be used in various medical imaging modalities. This chapter aims to provide an insight into the fundamental principles behind radiomics, discuss the most common techniques alongside their strengths and weaknesses, and suggest ways forward for future research standardization and reproducibility.

Exploring radiographers' perceptions and knowledge about patient lead shielding: a cross-sectional study in Greece and Cyprus.

The present study aimed to explore radiographers' knowledge, clinical practice and perceptions regarding the use of patient lead shielding in Greece and Cyprus. Qualitative data were analyzed using conceptual content analysis and through the classification of findings into themes and categories. A total of 216 valid responses were received. Most respondents reported not being aware of the patient shielding recommendations issued by the American Association of Physicists in Medicine (67%) or the guidance issued by the British Institute of Radiology (69%). Shielding-related training was generally not provided by radiography departments (74%). Most of them (85%) reported that they need specific guidance on lead shielding practices. Also, 82% of the respondents said that lead shielding should continue to be used outside the pelvic area when imaging pregnant patients. Pediatric patients are the most common patient category to which lead shielding was applied. Significant gaps in relevant training have been identified among radiographers in Greece and Cyprus, highlighting the need for new protocols and provision of adequate training on lead shielding practices. Radiography departments should invest in appropriate shielding equipment and adequately train their staff.

A cross-sectional study of explainable machine learning in Alzheimer's disease: diagnostic classification using MR radiomic features.

Introduction: Alzheimer's disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atrophy on a late disease stage. Therefore, the main objective of this study is to investigate the necessity of quantitative imaging in the assessment of AD by using machine learning (ML) methods. Nowadays, ML methods are used to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers in the assessment of AD. Methods: In this study radiomic features from both entorhinal cortex and hippocampus were extracted from 194 normal controls (NC), 284 mild cognitive impairment (MCI) and 130 AD subjects. Texture analysis evaluates statistical properties of the image intensities which might represent changes in MRI image pixel intensity due to the pathophysiology of a disease. Therefore, this quantitative method could detect smaller-scale changes of neurodegeneration. Then the radiomics signatures extracted by texture analysis and baseline neuropsychological scales, were used to build an XGBoost integrated model which has been trained and integrated. Results: The model was explained by using the Shapley values produced by the SHAP (SHapley Additive exPlanations) method. XGBoost produced a f1-score of 0.949, 0.818, and 0.810 between NC vs. AD, MC vs. MCI, and MCI vs. AD, respectively. Discussion: These directions have the potential to help to the earlier diagnosis and to a better manage of the disease progression and therefore, develop novel treatment strategies. This study clearly showed the importance of explainable ML approach in the assessment of AD.

Breast MRI: Where are we currently standing?

Breast cancer is the most frequently occurring malignancy among women, having a great impact on society, economy, and healthcare. It is therefore vital to develop effective imaging methods to perform breast screening, diagnosis, and treatment follow-up. Breast MRI is the most efficient method for screening high-risk patients, for breast lesion differentiation and characterization, and for the assessment of response to treatment. Some novel MRI imaging techniques, such as Diffusion Kurtosis Imaging, perfusion imaging, MR Spectroscopy, hybrid PET/MRI imaging, fMRI and ultra-high field MRI imaging offer the capacity to improve the diagnostic accuracy of breast MRI, while reducing unnecessary biopsies. However, any techniques used in breast MRI should be treated with caution, and after a thoughtful consideration of its main strengths and weaknesses. Fast, unenhanced MRI protocols will benefit our patients, improving their overall MRI experience and avoiding the potential risks of contrast media administration. The implementation of AI-based algorithms, using Deep Learning, Convolutional Neural Networks and Radiomics, will certainly increase the superiority of breast MRI and improve patient outcomes, as they can facilitate lesion differentiation, predict response to treatment, reduce unnecessary biopsies, and also reduce scan times and artefacts.

A systematic review of person-centred adjustments to facilitate magnetic resonance imaging for autistic patients without the use of sedation or anaesthesia.

LAY ABSTRACT: Autistic patients often undergo magnetic resonance imaging examinations. Within this environment, it is usual to feel anxious and overwhelmed by noises, lights or other people. The narrow scanners, the loud noises and the long examination time can easily cause panic attacks. This review aims to identify any adaptations for autistic individuals to have a magnetic resonance imaging scan without sedation or anaesthesia. Out of 4442 articles screened, 53 more relevant were evaluated and 21 were finally included in this study. Customising communication, different techniques to improve the environment, using technology for familiarisation and distraction have been used in previous studies. The results of this study can be used to make suggestions on how to improve magnetic resonance imaging practice and the autistic patient experience. They can also be used to create training for the healthcare professionals using the magnetic resonance imaging scanners.

Identifying cardiomegaly in chest X-rays: a cross-sectional study of evaluation and comparison between different transfer learning methods.

BACKGROUND: Cardiomegaly is a relatively common incidental finding on chest X-rays; if left untreated, it can result in significant complications. Using Artificial Intelligence for diagnosing cardiomegaly could be beneficial, as this pathology may be underreported, or overlooked, especially in busy or under-staffed settings. PURPOSE: To explore the feasibility of applying four different transfer learning methods to identify the presence of cardiomegaly in chest X-rays and to compare their diagnostic performance using the radiologists' report as the gold standard. MATERIAL AND METHODS: Two thousand chest X-rays were utilized in the current study: 1000 were normal and 1000 had confirmed cardiomegaly. Of these exams, 80% were used for training and 20% as a holdout test dataset. A total of 2048 deep features were extracted using Google's Inception V3, VGG16, VGG19, and SqueezeNet networks. A logistic regression algorithm optimized in regularization terms was used to classify chest X-rays into those with presence or absence of cardiomegaly. RESULTS: Diagnostic accuracy is reported by means of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), with the VGG19 network providing the best values of sensitivity (84%), specificity (83%), PPV (83%), NPV (84%), and overall accuracy (84,5%). The other networks presented sensitivity at 64.1%-82%, specificity at 77.1%-81.1%, PPV at 74%-81.4%, NPV at 68%-82%, and overall accuracy at 71%-81.3%. CONCLUSION: Deep learning using transfer learning methods based on VGG19 network can be used for the automatic detection of cardiomegaly on chest X-ray images. However, further validation and training of each method is required before application to clinical cases.