Journal of Medical Radiation Sciences最新文献

Introduction: Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related mortality worldwide. Despite advancements in early detection and treatment, postsurgical recurrence remains a significant challenge, occurring in 30%-55% of patients within 5 years after surgery. This review analysed existing studies on the utilisation of artificial intelligence (AI), incorporating CT, PET, and clinical data, for predicting recurrence risk in early-stage NSCLCs.

Methods: A literature search was conducted across multiple databases, focusing on studies published between 2018 and 2024 that employed radiomics, machine learning, and deep learning based on preoperative positron emission tomography (PET), computed tomography (CT), and PET/CT, with or without clinical data integration. Sixteen studies met the inclusion criteria and were assessed for methodological quality using the METhodological RadiomICs Score (METRICS).

Results: The reviewed studies demonstrated the potential of radiomics and AI models in predicting postoperative recurrence risk. Various approaches showed promising results, including handcrafted radiomics features, deep learning models, and multimodal models combining different imaging modalities with clinical data. However, several challenges and limitations were identified, such as small sample sizes, lack of external validation, interpretability issues, and the need for effective multimodal imaging techniques.

Conclusions: Future research should focus on conducting larger, prospective, multicentre studies, improving data integration and interpretability, enhancing the fusion of imaging modalities, assessing clinical utility, standardising methodologies, and fostering collaboration among researchers and institutions. Addressing these aspects will advance the development of robust and generalizable AI models for predicting postsurgical recurrence risk in early-stage NSCLC, ultimately improving patient care and outcomes.

Introduction: Magnetic resonance imaging (MRI) is a widely used diagnostic modality in healthcare settings, but it carries inherent safety risks. Understanding healthcare providers' knowledge of MRI safety is crucial for ensuring patient and staff safety. This study aimed to assess MRI safety knowledge among physicians and nurses and explore factors influencing this knowledge.

Methods: A cross-sectional study was conducted among 387 nonimaging healthcare practitioners: physicians and nurses, from different healthcare sectors in Jeddah city. A structured questionnaire assessed their understanding of basic MRI concepts, projectile hazards and contrast media risks. Statistical analyses, including Student's t-test and ANOVA, were used to examine differences in knowledge scores.

Results: Participants showed limited or poor knowledge across all MRI safety domains, including basic concepts, projectile hazards and contrast media risks, with domain knowledge scores of 31.8%, 33.7% and 32.3%, respectively. Factors having an impact on knowledge of MRI safety were the type of healthcare sector, qualification, work experience, attending workshops and whether the education curriculum included MRI safety (p ≤ 0.05).

Conclusions: The study highlighted substantial deficits in MRI safety knowledge among nonimaging healthcare practitioners: physicians and nurses. Addressing these gaps through targeted education and training programs is essential for improving patient and staff safety in MRI settings.

Introduction: The COVID-19 pandemic has had a significant and ongoing impact on health care, particularly for medical radiation science (MRS) professionals. There exist many studies that describe the negative effects of clinical placement restrictions and access to universities on the well-being of all health professional students during the pandemic. There also exists evidence of changes to MRS student teaching and impacts to students and academic clinical educators; however, there exists a paucity of research that investigates how changes have affected the performance of students within the clinical environment and entering the workforce. This study surveyed workplace MRS clinical educators within Australia to gather their perspectives regarding the impact of COVID-19 on student clinical education.

Methods: A descriptive study comprising an online structured survey of 44 questions was provided to Medical Imaging and Radiation Therapy Clinical Educators across Australia.

Results: A total of 55 survey responses were received. Of note, respondents described heavy reductions to student intake capacity, losses of clinical placement time, a noted theory-practice gap and possibility of sites 'failing to fail' students. Negative impacts to all domains of MRPBA professional capabilities, as well as a perceived unpreparedness to meet the MRPBA capabilities were described. There was general agreement that graduating students will require supportive periods upon entry into the profession.

Conclusion: This study highlights the considerable impact of changes to the education and training of MRS students in response to COVID-19. The results pose a real concern for a generation of MRS students affected by the COVID-19 pandemic.

This correspondence is in response to the article 'Impact of Pre-Examination Video Education in Gd-EOB-DTPA-Enhanced Liver MRI: A Comparative Study' (doi.org/10.1002/jmrs.833). The study provides valuable initial insights into the impact of video-based education. Further research in this area is recommended.

This letter critically evaluates the conclusions drawn by Li et al. (https://doi.org/10.1002/jmrs.773) in their comparison of proton beam therapy (PBT) and photon irradiation for paediatric and young adult patients. While acknowledging the complexities of treatment selection, the authors argue that PBT's benefits, particularly in reducing radiation exposure to organs at risk, should be given greater consideration. The letter calls for a comprehensive, nuanced approach to treatment decisions, emphasising long-term outcomes and the reduction of potential late effects.

Introduction: Quality assurance (QA) in medical imaging ensures consistently high-quality images at acceptable radiation doses. However, the applicability of the chest X-ray (CXR) QA tool in images with pathology, particularly infectious diseases like COVID-19, has not been explored. This study examines the utility of the European Guidelines for image quality in QA of CXRs with varying severity and types of infectious disease.

Methods: A convenient sampling methodology was employed to recruit 25 participants (qualified radiographers: n = 13 and 4th-year undergraduate radiography students: n = 12) to evaluate 70 CXR images using the European Guidelines for image quality in CXRs. The image dataset comprised of COVID-19 and non-COVID-19 cases, which were randomly selected to reflect routine clinical practice variability. Participants independently rated image quality based on 10 criteria in the European guidelines on quality criteria for CXRs using a six-point Likert scale. Image quality ratings of normal and pathological CXR images were compared using a Kruskal-Wallis test. Spearman's ranked order correlation was used to assess the association between quality criteria ratings.

Results: CXRs with no pathology or non-COVID pathologies exhibited statistically higher total QA scores compared to CXRs with COVID-19 and indeterminate COVID-19 (P < 0.001). This trend was evident across various QA factors, especially those associated with patient inspiration. Higher levels of infection corresponded to lower QA ratings. No differences were found between different pathologies regarding the medial border of the scapulae being outside the lung fields.

Conclusions: Severe pathology negatively impacts the technical quality of CXRs with COVID-19 features without necessarily affecting their diagnostic value. The findings emphasise the need to prioritise diagnostic ability over technical quality when evaluating CXRs exhibiting diffuse signs of pathology.

Introduction: Clinical training is crucial for diagnostic radiography students, bridging theoretical knowledge with practical skills. In resource-constrained settings, this training may face unique challenges that might significantly impact learning outcomes and future practice. Despite its importance, the experiences of diagnostic radiography students during clinical placements remain understudied, particularly in Sub-Saharan Africa. This study aimed to explore and describe the experiences of diagnostic radiography students during clinical training at two resource-constrained Sub-Saharan public hospitals.

Methods: A qualitative phenomenological study was conducted using face-to-face, semi-structured interviews with 18 diagnostic radiography students (six each from years 2 to 4) from one participating university. Interviews were audio-recorded, transcribed and analysed using thematic analysis. Trustworthiness was ensured through prolonged engagement, member checking, and researchers' reflexivity. Ethical approval was obtained before data collection commenced.

Results: Three main themes were generated: (1) Clinical Environment Challenges, including equipment shortages and understaffing; (2) Independent Learning and Development, highlighting students' resilience and self-directed learning; and (3) Patient Care Impact, demonstrating students' commitment to quality care despite constraints. Students reported increased confidence and adaptability but also noted negative interactions with healthcare workers and supervision inconsistencies.

Conclusions: Despite significant challenges, diagnostic radiography students demonstrated remarkable resilience and commitment to patient care. However, resource limitations and interprofessional issues pose substantial barriers to optimal learning experiences. These findings highlighted the need for targeted interventions in diagnostic radiography education within resource-constrained settings, including increased investment in equipment and staffing, enhanced interprofessional education, improved supervision models and curriculum enhancements fostering self-directed learning and resilience.

Introduction: Emotional intelligence (EI) is described as the ability to recognise and understand one's own emotions and the emotions of others, and empathically manage emotional responses. While historically not emphasised in undergraduate allied health sciences training, it is increasingly considered an essential graduate trait. This scoping review synthesises existing research on EI outcomes, specifically in undergraduate allied health professions students.

Method: Four databases were searched in February 2024 using keywords relating to EI and empathy to identify studies published in English from 1990. Eligible studies needed to include assessment and reported outcomes using validated EI tools in health professions students.

Results: A total of 163 papers met the inclusion criteria. Many studies employed a cross-sectional design (n = 115). Most studies (n = 135) focused on undergraduate students studying medicine (n = 62), nursing (n = 80) and dentistry (n = 13), with some studies (n = 21) evaluating more than one discipline. Many studies investigated one discipline only (n = 64 for nursing, n = 50 for medicine) using no comparator undergraduate degree. The most common EI models evaluated from this review were ability-based (n = 77), followed by trait-based models (n = 36) and mixed social-emotional competence (n = 35). Ability model evaluations of EI most commonly utilised the Schutte Self-Report Emotional Intelligence Test (SSEIT) (n = 44) and the Mayer-Salovey-Caruso Emotional Intelligence Test (MSCEIT) (n = 24).

Conclusion: Research on EI among undergraduate allied health fields is limited. Existing literature reveals there is some consensus on the importance of EI in healthcare education, but there is considerable variability in how EI is measured. Studies suggest higher levels of EI may correlate with improved student professional skill development in clinical reasoning, empathy and stress management.

Introduction: The application of artificial intelligence (AI) in radiation therapy holds promise for addressing challenges, such as healthcare staff shortages, increased efficiency and treatment planning variations. Increased AI adoption has the potential to standardise treatment protocols, enhance quality, improve patient outcomes, and reduce costs. However, drawbacks include impacts on employment and algorithmic biases, making it crucial to navigate trade-offs. A discrete choice experiment (DCE) was undertaken to examine the AI-related characteristics radiation oncology professionals think are most important for adoption in radiation therapy treatment planning.

Methods: Radiation oncology professionals completed an online discrete choice experiment to express their preferences about AI systems for radiation therapy planning which were described by five attributes, each with 2-4 levels: accuracy, automation, exploratory ability, compatibility with other systems and impact on workload. The survey also included questions about attitudes to AI. Choices were modelled using mixed logit regression.

Results: The survey was completed by 82 respondents. The results showed they preferred AI systems that offer the largest time saving, and that provide explanations of the AI reasoning (both in-depth and basic). They also favoured systems that provide improved contouring precision compared with manual systems. Respondents emphasised the importance of AI systems being cost-effective, while also recognising AI's impact on professional roles, responsibilities, and service delivery.

Conclusions: This study provides important information about radiation oncology professionals' priorities for AI in treatment planning. The findings from this study can be used to inform future research on economic evaluations and management perspectives of AI-driven technologies in radiation therapy.

Introduction: Artificial intelligence (AI) is being used increasingly in image interpretation tasks. Human reliance on technology and bias can cause decision errors. A checklist, used with the AI to mitigate against such biases, may optimise the use of AI technologies and promote good decision hygiene. A checklist to aid radiographic image interpretation for radiographers using AI for image interpretation was formed. This study investigates the effect of a checklist for musculoskeletal (MSK) radiographic image assessment when using AI interpretive assistance.

Methods: Radiographers were asked to interpret five MSK examinations with AI feedback. They were then provided with the checklist and asked to reinterpret the same five examinations with the AI feedback (n = 140 interpretations). During the interpretation sessions, participants were asked to provide a diagnosis and a confidence level on the diagnosis provided. Participants were then asked to complete a questionnaire to gain feedback on the use of the checklist.

Results: Fourteen radiographers were recruited. Nine participants found the checklist alongside the AI most useful and five participants found the AI element to be most useful on its own. Five participants found the AI feedback to be useful as it helped to critique the radiographic image interpretation more closely and rethink their own initial diagnosis.

Conclusion: The checklist for use with AI in MSK image interpretation contained useful elements to the user, but further developments can be made to enhance its use in clinical practice.