Journal of medical imaging and radiation sciences最新文献

Introduction/background: Artificial intelligence (AI) tools such as ChatGPT-4o are increasingly being explored in education. This study examined the potential of ChatGPT-4o to support reflective practice in medical radiation science (MRS) education. The focus was on the quality of AI-generated reflections in terms of alignment with professional standards, depth, clarity, and practical relevance.

Methods: Four clinical scenarios representing third-year diagnostic radiography placements were used as prompts. ChatGPT-4o generated reflective responses, which were assessed by three reviewers. Reflections were evaluated against the Medical Radiation Practice Board of Australia's professional capability domains and the National Safety and Quality Health Service Standards. Review criteria included clarity, depth, authenticity, and practical relevance. Inter-rater reliability was analysed using intraclass correlation coefficients (ICC) and the Friedman test.

Results: Scenario 3 achieved the highest inter-rater reliability (ICC: moderate to excellent; p = 0.022). Scenario 2 showed the lowest reliability (ICC: poor to fair; p = 0.060). Reflections were consistently well-structured and clear, but often lacked emotional depth, contextual awareness, and person-centered insights. Qualitative feedback identified limitations in empathetic reflection and critical self-awareness.

Discussion: ChatGPT-4o can produce structured reflective responses aligned with professional frameworks. However, its lack of emotional and contextual depth limits its ability to replace authentic reflective practice. Reviewer agreement varied depending on scenario complexity and emotional content.

Conclusion: AI tools such as ChatGPT-4o can assist in structuring reflections in MRS education but should complement, not replace, human-guided reflective learning. Hybrid models combining AI and educator input may enhance both efficiency and authenticity.

Introduction: Magnetic Resonance Imaging (MRI) is indispensable in modern diagnostics, yet its optimal use in resource-limited settings remains understudied. Zimbabwe's healthcare system faces unique challenges, including centralized MRI access and a privatized imaging sector, which may exacerbate utilization disparities. This study aimed to evaluate MRI referral patterns at a major Zimbabwean tertiary center to identify inefficiencies and inform policy improvements.

Methods: A retrospective cross-sectional analysis was conducted on 430 MRI requests (January 2024-March 2025) at Zimbabwe's largest tertiary hospital. Data included demographics, requesting specialties, anatomical regions, clinical indications, and diagnoses. Descriptive statistics and chi-square tests analyzed utilization trends.

Results: Brain (36.28%, n = 156) and spine (32.79%, n = 141) MRIs were most frequent. Notably, 30.47% (n = 131) of requests lacked clinical indications, and 33.95% (n = 146) of scans were normal, which could suggest overuse. Age and gender disparities emerged: peak utilization occurred in 41-65-year-olds (39.07%, n = 168). Males dominated brain MRIs (57.05%, n = 227), and females had more abdominal/spine requests, and these observed differences were statistically significant (χ²_(4df) = 11.15, p = 0.03).

Conclusion: This study highlights systemic inefficiencies in Zimbabwe's MRI use, including unjustified referrals and demographic disparities. Urgent interventions are needed to ensure strict adherence to standardized referral protocols (e.g., ACR criteria), clinician training, and equitable service expansion. Future research should assess cost-effectiveness, appropriateness criteria, and multicenter patterns to optimize resource allocation in low-resource settings. The findings of this study fill a crucial knowledge gap in African radiology literature and provide actionable recommendations for optimizing imaging services in resource-limited settings.

Introduction: Artificial intelligence (AI) has been growing in the field of medical imaging and clinical practice. It is essential to comprehend the perceptions, experiences, and expectations regarding AI implementation among medical radiation technologists (MRTs) working in radiology, nuclear medicine, and radiotherapy. Some global studies tend to inform about AI implementation, but there is almost no information from Central and South American professionals. This study aimed to understand the perceptions of the impact of AI on the MRTs, as well as the varying experiences and expectations these professionals have regarding its implementation.

Methods: An online survey was conducted among Central and South American MRTs for the collection of qualitative data concerning the primary perceptions regarding the implementation of AI in radiology, nuclear medicine, and radiotherapy. The analysis considered descriptive statistics in closed-ended questions and dimension codification for open-ended responses.

Results: A total of 398 valid responses were obtained, and it was determined that 98.5% (n = 392) of the respondents agreed with the implementation of AI in clinical practice. The primary contributions of AI that were identified were the optimization of processes, greater diagnostic accuracy, and the possibility of job expansion. On the other hand, concerns were raised regarding the delay in providing training opportunities and limited avenues for learning in this domain, the displacement of roles, and dehumanization in clinical practice. This sample of participants likely represents mostly professionals who have more AI knowledge than others. It is therefore important to interpret these results with caution.

Discussion: Our findings indicate strong professional confidence in AI's capacity to improve imaging quality while maintaining patient safety standards. However, user resistance may disturb implementation efforts. Our results highlight the dual need for (a) comprehensive professional training programs and (b) user education initiatives that demonstrate AI's clinical value in radiology. We therefore recommend a carefully structured, phased AI implementation approach, guided by evidence-based guidelines and validated training protocols from existing research.

Conclusion: AI is already present in medical imaging, but its effective implementations depend on building acceptance and trust through education and training, enabling MRTs to use it safely for patient benefit.

Introduction: This case report details the first in-vivo use of continuous glucose monitoring (CGM) technology by a therapeutic radiographer working in magnetic resonance image (MRI) guided radiotherapy with type 1 diabetes (T1D) at our institution. As adoption rates of this device increase, understanding how they perform in MR environments is important for staff working in MR specific roles.

Case and outcomes: For a single member of an MRI guided radiotherapy team with type I diabetes, daily CGM readings in mmol/L were recorded for 4 months when working in all areas of an Elekta Unity MR Linac (Elekta AB, Sweden). These measurements were compared to the mean daily self-monitoring blood glucose (SMBG) readings taken at 2-hour intervals whilst in work over a 4-month testing period. A cloud-based diabetes management system demonstrated successful data transmission as 96% of BG readings had been received from the CGM across all areas of working. A Pearson correlation coefficient of CGM and SMBG readings showed a positive correlation (r = 0.70) and a paired T-Test indicated no significant differences (p = 0.63), indicating CGM reliability in this MR Linac environments across 122 days of testing.

Conclusion: This case highlights the feasibility and safety of using the Freestyle Libre 2 CGM (FreeStyle Libre 2, Abbott Diabetes Care) for an individual with T1D working in an MR Linac. The data presented here is specific to this scenario and serves as informative guidance for healthcare professionals. Further research and standardisation efforts are needed to enhance the compatibility of non-invasive CGMs in MRI environments.

Introduction: Policymakers wish to extend access to medical records, including medical imaging. Appreciating how patients might review radiographs could be key to establishing future training needs for healthcare professionals and how image sharing could be integrated into practice.

Method: A pilot study in the UK using a survey was distributed to adult participants via the online research platform Prolific. All subjects were without prior professional healthcare experience. Participants reviewed ten radiographs (single projection only) and were asked a two-stage question. Firstly, if the radiograph was 'normal' or 'abnormal' and secondly, if they had answered 'abnormal', to identify the abnormality from a pre-determined list featuring generic terms for pathologies.

Results: Fifty participants completed the survey. A mean of 65.8 % of participants were able to correctly identify if radiographs were normal or abnormal. Results in relation to the identification of a pathology were not as positive, but still notable with a mean of 46.4 % correctly identifying abnormalities. Qualitative data demonstrated that members of the public are enthralled with reviewing radiographs and intrigued to understand their performance in identifying abnormalities.

Conclusion: In the pilot, members of the public could identify if a radiograph is normal or abnormal to a reasonable standard. Further detailed interpretation of images requires supportive intervention. This pilot study suggests that patients can participate in image sharing as part of their care. Image sharing may be beneficial to the therapeutic relationship, aiding patient understanding and enhancing consultations between healthcare professional and patient. Further research is indicated.