Journal of Medical Imaging and Radiation Sciences最新文献

{"title":"Embedding social accountability in radiography education and practice: A call to lead, educate, and serve","authors":"Wiam Elshami , Mohamed Abuzaid , Mohamed H. Taha","doi":"10.1016/j.jmir.2025.102030","DOIUrl":"10.1016/j.jmir.2025.102030","url":null,"abstract":"","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102030"},"PeriodicalIF":1.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144604310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable artificial intelligence for pneumonia classification: Clinical insights into deformable prototypical part network in pediatric chest x-ray images","authors":"Elmira Yazdani ,&nbsp;Aryan Neizehbaz ,&nbsp;Najme Karamzade-Ziarati ,&nbsp;Saeed Reza Kheradpisheh","doi":"10.1016/j.jmir.2025.102023","DOIUrl":"10.1016/j.jmir.2025.102023","url":null,"abstract":"<div><h3>Background</h3><div>Pneumonia detection in chest X-rays (CXR) increasingly relies on AI-driven diagnostic systems. However, their “black-box” nature often lacks transparency, underscoring the need for interpretability to improve patient outcomes. This study presents the first application of the Deformable Prototypical Part Network (D-ProtoPNet), an ante-hoc interpretable deep learning (DL) model, for pneumonia classification in pediatric patients' CXR images. Clinical insights were integrated through expert radiologist evaluation of the model's learned prototypes and activated image patches, ensuring that explanations aligned with medically meaningful features.</div></div><div><h3>Methods</h3><div>The model was developed and tested on a retrospective dataset of 5,856 CXR images of pediatric patients, ages 1–5 years. The images were originally acquired at a tertiary academic medical center as part of routine clinical care and were publicly hosted on a Kaggle platform. This dataset comprised anterior-posterior images labeled normal, viral, and bacterial. It was divided into 80 % training and 20 % validation splits, and utilised in a supervised five-fold cross-validation. Performance metrics were compared with the original ProtoPNet, utilising ResNet50 as the base model. An experienced radiologist assessed the clinical relevance of the learned prototypes, patch activations, and model explanations.</div></div><div><h3>Results</h3><div>The D-ProtoPNet achieved an accuracy of 86 %, precision of 86 %, recall of 85 %, and AUC of 93 %, marking a 3 % improvement over the original ProtoPNet. While further optimisation is required before clinical use, the radiologist praised D-ProtoPNet's intuitive explanations, highlighting its interpretability and potential to aid clinical decision-making.</div></div><div><h3>Conclusion</h3><div>Prototypical part learning offers a balance between classification performance and explanation quality, but requires improvements to match the accuracy of black-box models. This study underscores the importance of integrating domain expertise during model evaluation to ensure the interpretability of XAI models is grounded in clinically valid insights.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102023"},"PeriodicalIF":1.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a novel mask balloon immobilization system for reducing intra-fractional setup errors in spinal stereotactic body radiation therapy","authors":"Kamimura Kazushi,&nbsp;Yoshihiro Ueda,&nbsp;Masaru Isono,&nbsp;Shoki Inui,&nbsp;Yuya Nitta,&nbsp;Seiya Murata,&nbsp;Hayate Washio,&nbsp;Koji Konishi","doi":"10.1016/j.jmir.2025.102016","DOIUrl":"10.1016/j.jmir.2025.102016","url":null,"abstract":"<div><h3>Background</h3><div>Accurate immobilization is vital in spinal stereotactic body radiation therapy (SBRT) to minimize intra-fractional setup errors (IntraSE) and optimize therapeutic outcomes. Traditional methods, such as evacuated cushions, may lack sufficient stability, highlighting the need for improved systems. This study evaluates the accuracy and efficacy of a mask-balloon immobilization system, combining a body mask and a specialized balloon, for spinal SBRT.</div></div><div><h3>Methods</h3><div>Seventy-five patients undergoing spinal SBRT for thoracic or lumbar metastases were analyzed. Of these, 40 patients were immobilized using an evacuated cushion, while 35 used the mask balloon system. Cone-beam computed tomography (CBCT) scans were acquired three times during treatment, and the bony anatomy registration measured translational setup errors in anterior-posterior (AP), superior-inferior (SI), and right-left (RL) directions.</div></div><div><h3>Result</h3><div>For the evacuated cushion, the mean ± standard deviation of absolute IntraSE post-first arc was 0.4 ± 0.7 mm (AP), 0.5 ± 0.7 mm (SI), and 0.5 ± 0.6 mm (RL). For the mask-balloon system, the corresponding values were 0.2 ± 0.2 mm, 0.3 ± 0.3 mm, and 0.3 ± 0.3 mm. After treatment completion, the IntraSE values were 0.7 ± 0.9 mm, 0.8 ± 0.9 mm, and 0.9 ± 0.8 mm for the evacuated cushion and 0.4 ± 0.3 mm, 0.4 ± 0.4 mm, and 0.6 ± 0.4 mm for the mask-balloon system. In all three translational directions, the mask-balloon system had a significantly smaller IntraSE than the evacuated cushion (<em>p</em> &lt; 0.0001).</div></div><div><h3>Conclusion</h3><div>The mask-balloon system improves setup accuracy and is a promising immobilization system for spinal SBRT.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102016"},"PeriodicalIF":1.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The A3ReAcH (Autistic, ADHD and AuDHD research accessibility in healthcare) framework: Principles for inclusive healthcare research with autistic, ADHD and AuDHD individuals in radiography and medical radiation technology","authors":"Ben Potts ,&nbsp;Emily Skelton ,&nbsp;Georgia Pavlopoulou ,&nbsp;Themis Karaminis ,&nbsp;Christina Malamateniou","doi":"10.1016/j.jmir.2025.102009","DOIUrl":"10.1016/j.jmir.2025.102009","url":null,"abstract":"<div><h3>Background</h3><div>Autistic, ADHD and AuDHD individuals are often excluded from healthcare/radiography research due to inaccessible methodologies and systemic biases, perpetuating well-documented health inequalities. While researchers can recognise this, they may be unequipped to address it effectively. This narrative review introduces the A3ReAcH (Autistic, ADHD and AuDHD Research Accessibility in Healthcare) framework, which provides practical guidance for designing and conducting accessible, inclusive and participatory research.</div></div><div><h3>Method</h3><div>Two searches of peer-reviewed studies (2019–2024) were conducted using <em>Emcare, MEDLINE, Social Policy and Practice, CINAHL, the Psychology and Behavioral Sciences Collection, Google Scholar,</em> and <em>PubMed</em>. The key themes were identified, and a framework was synthesised that aligns with different stages of the research lifecycle (planning to dissemination).</div></div><div><h3>Results</h3><div>The searches retrieved 86 articles: 54 methodological and 32 original research. Key themes are presented as a 12-item framework. The A3ReAcH framework outlines practical strategies such as diversifying research teams, ensuring equitable power-sharing, prioritising participatory methods, and adapting research designs to neurodivergent needs. It also emphasises the importance of accessible recruitment, fair compensation, and inclusive dissemination. Additionally, it highlights the role of intersectionality in shaping neurodivergent experiences and provides recommendations to reduce systemic barriers in research.</div></div><div><h3>Conclusion</h3><div>All healthcare/radiography research should include and respect neurodivergent experiences. The A3ReAcH framework empowers researchers to produce more equitable and actionable research by including neurodivergent voices and dismantling barriers to participation. By integrating these principles, healthcare/radiography researchers can improve the participant experience, enhance data quality, and drive systemic change in healthcare/radiography research, moving towards findings that genuinely represent the diversity of the population.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102009"},"PeriodicalIF":1.3,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of medical radiation technologist schedules using advanced analytical tools","authors":"Najib Tasleem,&nbsp;Linh Hoang,&nbsp;Aileen Chenmeyer,&nbsp;Moataz Salameh,&nbsp;Tatiana Belimova,&nbsp;Amit Chandhok","doi":"10.1016/j.jmir.2025.102000","DOIUrl":"10.1016/j.jmir.2025.102000","url":null,"abstract":"<div><h3>Introduction/Background</h3><div>Medical imaging departments are facing significant workforce challenges due to a shortage of medical radiation technologists (MRTs), leading to increased wait times and staff burnout. Traditional manual scheduling methods are time-consuming, prone to error, and contribute to staff dissatisfaction. To address these operational challenges and improve clinical workflow, a quality improvement initiative was undertaken to optimize MRT scheduling using advanced analytical tools.</div></div><div><h3>Methods</h3><div>A cost-constrained optimization model was developed using Microsoft Excel’s Solver tool. Staffing data from the University Health Network (UHN) medical imaging department served as the basis for model design. Key constraints included staff availability, fairness in shift assignments, overtime cost minimization, and maximum consecutive shifts. The model incorporated full-time, casual, and agency staff, with an emphasis on equitable work distribution and cost control.</div></div><div><h3>Results</h3><div>The optimized scheduling model successfully created a fair, fully staffed 4-week schedule while minimizing costs. Full-time MRTs were assigned 40-hour work weeks without exceeding contractual limits, and agency and casual staff were effectively integrated to prevent overtime. The model reduced the time required to generate schedules and minimized common errors such as double-booking and uneven shift distribution.</div></div><div><h3>Discussion</h3><div>The use of an advanced analytical approach for MRT scheduling demonstrates a practical, scalable solution for healthcare organizations. By aligning shift assignments with operational demands and human resource principles, the initiative supports staff well-being, promotes workplace fairness, and contributes to improved patient care delivery. Importantly, this method is cost-effective and can be adapted to other clinical departments facing similar staffing and scheduling challenges.</div></div><div><h3>Conclusion</h3><div>This quality improvement initiative highlights the potential for healthcare departments to leverage simple yet powerful optimization tools to enhance clinical operations. The successful implementation of an analytical scheduling model in a high-volume medical imaging department underscores the value of evidence-informed process improvements at the frontline of clinical practice.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102000"},"PeriodicalIF":1.3,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144481064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On-call work and sleep quality amongst Radiographers registered in Ireland","authors":"Rachel Callanan ,&nbsp;Andrew England ,&nbsp;Rena Young ,&nbsp;Clare Rainey ,&nbsp;Grainne Curran ,&nbsp;Niamh Moore ,&nbsp;Marie Ryan ,&nbsp;Mark McEntee","doi":"10.1016/j.jmir.2025.101999","DOIUrl":"10.1016/j.jmir.2025.101999","url":null,"abstract":"<div><h3>Background</h3><div>Most radiographers in Ireland take part in an ‘on-call’ system, which includes working at night and out-of-hours to meet service demands. Night working and undertaking overtime are associated with lower sleep quality and reduced wellbeing among healthcare workers. However, a gap exists in the literature regarding the effects on radiographers. This study aimed to establish whether there is an association between the number of on-call shifts worked and participants’ overall perception of sleep quality.</div></div><div><h3>Methods</h3><div>A validated questionnaire was adapted and shared via social media platforms. Section one included demographic information, including the number of years clinically practising and the number of on-call shifts worked per month. Section two contained questions regarding participants’ perception of their sleep quality, and section three sought responses on quality-of-life measures. Correlations in the data were analysed using the Chi-Square test for independence.</div></div><div><h3>Results</h3><div>A total of 95 participants completed the study; 27(29 %) radiographers reported experiencing insufficient sleep over the last month, greater than reports of insufficient sleep of the general population (14.2 %). The Chi-Square test revealed a statistically significant correlation between the number of on-call shifts and the perception of sleep quality (X², 12, <em>n</em> = 95, <em>p</em> = 0.04).</div></div><div><h3>Conclusion</h3><div>A negative association exists between the amount of on-call work and perceived sleep quality. Radiographers working one or more on-call shifts per week report insufficient sleep more often. On-call patterns should be a consideration for managers and policymakers when setting out staffing rosters and introducing guidelines indicating the maximum number of on-call shifts a radiographer may undertake per month.</div><div>This work may provide a springboard for policymakers, managers and professional bodies to consider the optimal working pattern and compensatory rest considerations for radiographers to ensure adequate workforce provision, recruitment to the profession and retention of existing staff and avoid undesirable economic implications.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 101999"},"PeriodicalIF":1.3,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144320741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Farewell reflections from a medical radiation technologist on a career of learning, leadership and lasting gratitude","authors":"Lisa Pyke","doi":"10.1016/j.jmir.2025.101988","DOIUrl":"10.1016/j.jmir.2025.101988","url":null,"abstract":"","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 101988"},"PeriodicalIF":1.3,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of transformer-based deep learning models for glioma and meningioma classification","authors":"Katerina Nalentzi ,&nbsp;Konstantinos Gerogiannis ,&nbsp;Haralabos Bougias ,&nbsp;Nikolaos Stogiannos ,&nbsp;Periklis Papavasileiou","doi":"10.1016/j.jmir.2025.102008","DOIUrl":"10.1016/j.jmir.2025.102008","url":null,"abstract":"<div><h3>Introduction/Background</h3><div>This study compares the classification accuracy of novel transformer-based deep learning models (ViT and BEiT) on brain MRIs of gliomas and meningiomas through a feature-driven approach. Meta’s Segment Anything Model was used for semi-automatic segmentation, therefore proposing a total neural network-based workflow for this classification task.</div></div><div><h3>Methods</h3><div>ViT and BEiT models were finetuned to a publicly available brain MRI dataset. Gliomas/meningiomas cases (625/507) were used for training and 520 cases (260/260; gliomas/meningiomas) for testing. The extracted deep radiomic features from ViT and BEiT underwent normalization, dimensionality reduction based on the Pearson correlation coefficient (PCC), and feature selection using analysis of variance (ANOVA). A multi-layer perceptron (MLP) with 1 hidden layer, 100 units, rectified linear unit activation, and Adam optimizer was utilized. Hyperparameter tuning was performed via 5-fold cross-validation.</div></div><div><h3>Results</h3><div>The ViT model achieved the highest AUC on the validation dataset using 7 features, yielding an AUC of 0.985 and accuracy of 0.952. On the independent testing dataset, the model exhibited an AUC of 0.962 and an accuracy of 0.904. The BEiT model yielded an AUC of 0.939 and an accuracy of 0.871 on the testing dataset.</div></div><div><h3>Discussion</h3><div>This study demonstrates the effectiveness of transformer-based models, especially ViT, for glioma and meningioma classification, achieving high AUC scores and accuracy. However, the study is limited by the use of a single dataset, which may affect generalizability. Future work should focus on expanding datasets and further optimizing models to improve performance and applicability across different institutions.</div></div><div><h3>Conclusion</h3><div>This study introduces a feature-driven methodology for glioma and meningioma classification, showcasing advancements in the accuracy and model robustness of transformer-based models.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102008"},"PeriodicalIF":1.3,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Radiation Therapist to a transformational healthcare leader: Expanding the MRT horizon","authors":"Yasir Khalid","doi":"10.1016/j.jmir.2025.102001","DOIUrl":"10.1016/j.jmir.2025.102001","url":null,"abstract":"","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102001"},"PeriodicalIF":1.3,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The road less traveled: a journey beyond the image","authors":"Samantha Moraes","doi":"10.1016/j.jmir.2025.102004","DOIUrl":"10.1016/j.jmir.2025.102004","url":null,"abstract":"","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 5","pages":"Article 102004"},"PeriodicalIF":1.3,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}