Modern radiotherapy practice relies on multiple approaches for verification of patient positioning. All of these techniques require experienced radiotherapists who understand the anatomical landmarks and the limitations of the used verification techniques. We explore the feasibility of using Artificial intelligence in assisted patient positions using acquired port images (PFIs) and digital reconstructed radiographs (DRRs). A retrospective study was conducted on patients with brain and aerodigestive tract malignancy who were treated with radiotherapy between 2018 and 2023. A neural network was built to examine and perform auto-correction of the misaligned PFIs and DRRs images. The performance of the neural network was assessed quantitatively by mean-absolute errors (MAE) and mean-squared errors (MSE), and qualitatively by a survey which was sent to 30 experienced medical professionals in the field of radiation therapy. The total number of patients included in this study was 156 patients. 96 of the patients were treated for aerodigestive tract malignancy while the remaining were treated for brain tumours. The neural network achieved MAE of 27.430 and 27.437 for training and validation sets, respectively, and MSE of 0.5505, and 0.5565 for training and validation sets, respectively. Nineteen medical professionals responded to the survey. They reported a median accuracy score of 8 out of 10. Our neural network is just one step further in the automation of modern radiotherapy services by using AI-assisted correction of setup errors. This study demonstrated the potential role of AI in assisting radiotherapists with patient positioning corrections during radiotherapy treatment. Further research is needed to validate the effectiveness of this approach in clinical practice.

This paper harnesses a comprehensive overview and the collective experience of a community of pre- and post-doctoral Radiographers in successfully securing grants to demonstrate what is required as part of an NIHR fellowship application. Developing a research fellowship application requires individuals to expose themselves to critique to improve the content, design and structure of the proposed piece of work. The scale of the project should be carefully considered when developing applications, with the research plan accurately and realistically proposing a suitable amount of work to be undertaken within the timeframe. All fellowship applications comprise several key elements which must be meticulously crafted to address the requirements of the specific call. This is critical because every section of the application undergoes scrutiny by review panels to ensure the funding achieves its maximum impact. The key elements requiring detailed information are themed around Project, Person, Place, Patient and public involvement and engagement (PPIE), the surrounding People, and a training plan. However, a golden thread highlighting inclusive research that is people-centred is required to run through the entire application. NIHR fellowships are an important pathway to enable dedicated clinically relevant research projects for patient/family benefit to be combined with the advancement of an individual's clinical and academic skills. These dedicated funding streams are tailor-made to enable a wide range of healthcare professionals, including Radiographers, to develop into research leaders of the future. Maximising research training opportunities, including research fellowships for the Radiography profession, will offer the completion of clinically relevant research projects alongside the development of the research leaders of the future.

AI-based segmentation techniques in brain MRI have revolutionized neuroimaging by enhancing the accuracy and efficiency of brain structure analysis. These techniques are pivotal for diagnosing neurodegenerative diseases, classifying psychiatric conditions, and predicting brain age. This scoping review synthesizes current methodologies, identifies key trends, and highlights gaps in the use of automatic and semi-automatic segmentation tools in brain MRI, particularly focusing on their application to healthy populations and clinical utility. A scoping review was conducted following Arksey and O'Malley's framework and PRISMA-ScR guidelines. A comprehensive search was performed across six databases for studies published between 2014 and 2024. Studies focused on AI-based brain segmentation in healthy populations, and patients with neurodegenerative diseases, and psychiatric disorders were included, while reviews, case series, and studies without human participants were excluded. Thirty-two studies were included, employing various segmentation tools and AI models such as convolutional neural networks for segmenting gray matter, white matter, cerebrospinal fluid, and pathological regions. FreeSurfer, which utilizes algorithmic techniques, are also commonly used for automated segmentation. AI models demonstrated high accuracy in brain age prediction, neurodegenerative disease classification, and psychiatric disorder subtyping. Longitudinal studies tracked disease progression, while multimodal approaches integrating MRI with fMRI and PET enhanced diagnostic precision. AI-based segmentation techniques provide scalable solutions for neuroimaging, advancing personalized brain health strategies and supporting early diagnosis of neurological and psychiatric conditions. However, challenges related to standardization, generalizability, and ethical considerations remain. The integration of AI tools and algorithm-based methods into clinical workflows can enhance diagnostic accuracy and efficiency, but greater focus on model interpretability, standardization of imaging protocols, and patient consent processes is needed to ensure responsible adoption in practice.

Research strategies support professionals to create a shared vision and work towards common objectives which can enhance workforce satisfaction, retention and patient experience. Our research aimed to capture the current number of United Kingdom (UK) radiotherapy and diagnostic imaging departments that have a local discipline specific research strategy in place. We also sought to understand the contributing factors to their development, with the aim of generating models of support to enhance future local research strategies. A discipline specific cross-sectional survey was co-developed by the research team, the College of Radiographers (CoR) and our patient and public involvement and engagement representative. Distribution was via the CoR to radiotherapy and imaging departments across the UK. Complete responses were received from 32 radiotherapy and 19 imaging departments, discipline specific strategy numbers were low with only 10 and 3 departments respectively having one in situ. Barriers and enablers to their development as well as disparate motivations and intentions to develop a strategy were evident within and across each discipline. The respondents identified a range of formats and topics to help the development of strategies. Radiographers are keen to develop and implement their own research ideas, however this work is additional to clinical service demand. Removing barriers to research participation is a strategic priority, regional cooperation and coordination may play an increasing role in research engagement, scale and support. Opportunities to increase ownership and confidence in research strategy development should be pursued including template strategies and professional facilitation. A discipline specific strategy would support departments to navigate the complexities of research regulation and policy and overcome the challenges faced by competing priorities.

Hearing loss is a widespread disability, and unfortunately, deaf and hard-of-hearing (DHH) patients often experience unequal healthcare and unmet needs. People with the condition are predisposed to anxiety, fatigue and depression. Communication barriers are a major issue, particularly during magnetic resonance imaging (MRI) scans where clear radiographer-patient communication is crucial for safety and quality imaging. This study aimed to understand the experiences of MRI Radiographers in providing care to DHH patients for MRI scans. A qualitative descriptive phenomenological study design using purposive sampling to gain in-depth insights. The study comprised seven MRI radiographers working clinically at a public hospital in England. Data was collected through semi-structured face-to-face interviews. Audio recordings were transcribed using Microsoft 365 software. The transcripts were coded into categories and further on, into themes using the inductive approach of thematic analysis. The study revealed five key themes: communication barriers and consequences, current approaches to care, satisfaction of care provisions, prospects of technological advancements and training and professional development. The findings show that MRI radiographers encounter distinct and diverse communication difficulties while caring for DHH patients. Radiographers' experiences indicated the need for evidence-based strategies in addressing the communication challenges of DHH individuals. Some participants acknowledged that training and technological interventions could help with providing quality care for the patient group in MRI. The study's findings advocate for inclusiveness in delivering MRI services. It presents compelling evidence for MRI service providers to support radiographers by encouraging training and implementing approaches that guarantee safe, quality, and consistent care for patients with hearing impairments. The diversity of the DHH population's communication needs and lack of comprehensive guidelines are recognised to contribute to the struggle to deliver good care. To mitigate DHH patients' communication challenges, MRI service providers should sufficiently train MRI radiographers, create a supportive environment and promote services that address their needs.

The FORCE initiative, funded by the EU, was created in response to the COVID-19 pandemic's impact on radiography education. It offers a virtual learning environment (VLE) filled with clinical simulation scenarios targeting Diagnostic Imaging, Nuclear Medicine, and Radiotherapy. These scenarios are designed to provide open-access, simulation-based learning (SBL) resources that help radiography undergraduates engage in problem-based learning across relevant clinical knowledge and professional awareness. This study presents the results of an online survey aimed at evaluating the FORCE VLE and SBL resources to guide future development. The survey targeted academic and clinical staff in Radiography and student Radiographers. It was based on the Course Experience Questionnaire (CEQ) and modified to include topics relevant to online learning, using a five-point Likert Scale (LS). The questionnaire consisted of four sections: research information and consent; socio-demographic data; LS-based questions on case structure, content, interactivity, technical aspects, multimedia quality, and overall experience; and open-text responses. Of the 407 invited participants, 109 (27%) responded, with 77% being students and 23% clinical or academic radiographers from 13 countries. English proficiency was reported by 76% of respondents. The median LS was consistently 4 across all categories, indicating high satisfaction. Content analysis of 159 open-text comments revealed 139 positive opinions on the SBL resources. The FORCE VLE SBL resources were highly regarded for their interactivity, applicability, and support in consolidating knowledge and enhancing patient care. Suggestions for improvement were minor, mainly focusing on navigation and specific content preferences. Expanding the availability of online SBL cases could enhance Radiographer education and promote inclusivity across the field.

Advancements in medical imaging with ionizing radiation have significantly transformed the field and enhanced the education and training of medical professionals. A notable development in this educational landscape is the use of social media, which engages millions of users worldwide. This scoping review aims to explore the potential of social media as an educational tool for healthcare professionals and students in medical imaging with ionizing radiation, highlighting its benefits and disadvantages. In March 2024, research was conducted on three databases: PubMed, Scopus, and Web of Science. The research equation combined the terms "Social Media," "Education," and "Medical Imaging." Data extraction was based on PRISMA-ScR guidelines for scoping reviews. Seventeen articles published between 2017 and 2023 were included in this review, all of which were descriptive cross-sectional studies and primarily focused on popular platforms such as Twitter, Facebook, and YouTube. The key advantages of social media use for medical imaging education were accessibility, ease of use, and broad reach, while the main limitation was the potential for misinformation. While there is clear potential to integrate social media into medical imaging education, more must be done to understand their effectiveness. This ongoing process requires the active engagement of all stakeholders. While promising, further research is needed to validate social media as an educational tool. Successfully integrating social media into medical imaging education, thus enhancing learning, communication, and collaboration between healthcare professionals, requires a strong commitment to managing accurate and reliable content sources on social media.

AI software in the form of deep learning-based automatic detection (DLAD) algorithms for chest X-ray (CXR) interpretation have shown success in early detection of lung cancer (LC), however, there remains uncertainty related to clinical validation. CXRs and their corresponding chest-CT scans were retrospectively collated from a single institution between January 2019-2020. A commercially available AI software was used to evaluate 320 CXRs (<6 years prior-to-diagnosis) from 105 positive LC patients and 103 negative controls. Clinical reports were extracted and coded to correlate against AI findings. Of 105 LC patients, (57[55%] men, median [IQR] age 73[68-83] years), clinical reports identified LC in 64 (61%) whereas AI identified LC in 95 (90%). AI diagnostic (image-level) and prognostic (patient-level) sensitivities were 57.6% and 90.0%, (81% in correct location), respectively. On CXRs performed >12 months prior to LC diagnosis, the AI detected nodules in 24(23%) cases of which 22/24 had negative clinical reports for lung nodule/mass. The potential median reduction in time-to-diagnosis for cases where AI identified nodule(s) on previous CXR, but clinical reports negative, was 193[IQR 42-598] days. Of the 103 'negative' controls (48[47%] men, median [IQR] age 69[61-77] years) 20 patients had a nodule abnormality score above the threshold, generating a false-positive rate of 19%. The AI software showed excellent performance in detecting LCs that initially went undetected on CXR. The algorithm has potential to increase LC detection rates and reduce time-to-diagnosis. Using the AI, in conjunction with a trained observer, could increase reporting accuracy and potentially improve clinical outcomes. This study demonstrated the benefits and pitfalls associated with using AI in a clinical setting. It provides further evidence for utilising decision-support aids within clinical practice.

Ankle injuries that present to the ED with instability of the joint due to multiple fractures/disruption of the mortise need to be re-aligned promptly to minimise complications. A protocol change was introduced whereby mobile radiographs would be performed in the ED resuscitation room during manipulation of a complex ankle injury. The aim of this study was to determine if the overall time to definitive reduction had reduced for these patients, improving patient flow. Data was collected from patients attending the ED with a complex or unstable ankle injury in a UK single-centre over 6-months periods, pre pathway introduction (2019), immediately post change (2021) and 2 years post implementation (2023). In excess of 3000 patients had ankle radiographs performed in each cohort of data collection with an average of 2.9% of injuries categorised as complex or unstable and requiring manipulation, consistent across the cohorts (p=0.246). Increasing compliance with the new pathway was evident over time with a significant time reduction demonstrated from initial ED presentation to final post manipulation imaging if mobile radiographs were obtained with the mean time 113min quicker than those performed in the radiology department in 2023 (p=0.00). Although it takes time to embed new pathways and changes in practice, this study demonstrated that a simple change in imaging provision had a positive impact for patients with a complex ankle injury. Providing post manipulation radiographs in the ED resuscitation room allowed earlier confirmation of restored anatomical alignment for patients with a complex ankle injury and enabled clinicians to perform multiple manipulation attempts, if necessary, under the same sedation episode.

Invasive fungal infections (IFI) in paediatric oncology patients are associated with significant morbidity and mortality. Abdominal ultrasonography is widely used for diagnosis, but its utility remains unclear. We conducted a retrospective cohort study of paediatric oncology patients who were febrile and neutropaenic at Queensland Children's Hospital, Australia, from January 2018 to December 2019. We reviewed abdominal ultrasound (US) examinations requested for suspected IFI, analysing diagnostic yield and associations with clinical variables. There were 94 patients included, 21 of whom did not survive their underlying condition, seven (7.4%) showed evidence of IFI on US. Infections did not demonstrate a predilection for a particular abdominal organ. Fourteen patients had a positive blood culture, with only three confirmed fungal pathogens. Chest computed tomography, performed in 41 of cases had findings suspicious for IFI in 52.3% of these examinations. Abdominal ultrasonography has a low diagnostic yield (7.4%) for new IFI in paediatric oncology patients. However, given the mortality rate in this population, its use may be justified for monitoring known infections and as part of a comprehensive diagnostic approach. US is an effective method of screening for abdominal IFI in paediatric oncology patients who are febrile and neutropaenic. The low diagnostic yield is outweighed by the morbidity and mortality of IFI in this vulnerable patient cohort.