Journal of Medical Imaging and Radiation Sciences最新文献

{"title":"Message from the Guest Editor: Artificial Intelligence Revisited","authors":"Nikolaos Stogiannos","doi":"10.1016/j.jmir.2025.102117","DOIUrl":"10.1016/j.jmir.2025.102117","url":null,"abstract":"","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102117"},"PeriodicalIF":2.0,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145265518","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":"Radiographers' perspectives on triage systems: Exploring workflow impacts and enhancement opportunities in resource-constrained radiology departments","authors":"Rumbidzai N. Dewere ,&nbsp;Bornface Chinene","doi":"10.1016/j.jmir.2025.102118","DOIUrl":"10.1016/j.jmir.2025.102118","url":null,"abstract":"<div><h3>Introduction</h3><div>Efficient radiology triage systems are crucial for healthcare quality in resource-constrained settings, yet Zimbabwe’s quaternary hospitals face significant challenges, including staff shortages, outdated equipment, and inconsistent protocols. While existing literature addresses workflow optimization in high-resource settings, few studies examine triage systems in African referral hospitals. This study aimed to explore radiographers’ experiences of triage-related inefficiencies and their recommendations for improvement in Zimbabwe’s radiology departments.</div></div><div><h3>Methods</h3><div>A qualitative exploratory design was employed, using semi-structured interviews with 12 radiographers from two quaternary hospitals in Harare. Participants were purposively sampled based on experience and direct triage involvement. Thematic analysis was conducted using NVivo 12 to identify key challenges and solutions. Trustworthiness was ensured through member checking, thick description, and reflexivity.</div></div><div><h3>Findings</h3><div>Four major themes were created 1) patient safety concerns, including preventable deaths due to delay;s 2) staff well-being, with burnout linked to high workloads and emotional strain 3) workflow disruption from unclear protocols and conflicts; and 4) institutional credibility risks from poor service quality. Radiographers proposed three key solutions 1) staffing enhancements; 2) equipment upgrades; and 3) standardized protocols for mass casualty events.</div></div><div><h3>Conclusions</h3><div>This study highlights the systemic impact of triage inefficiencies on patient care and radiographer well-being in Zimbabwe’s resource-limited settings. The proposed solutions—staffing improvements, equipment investments, and protocol standardization—offer actionable pathways for strengthening radiology services. These findings underscore triage reform as both an operational and strategic priority for LMIC healthcare systems, with implications for policymakers, administrators, and global health practitioners.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102118"},"PeriodicalIF":2.0,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145260382","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":"Multi-class deep learning architecture for COVID-19, tuberculosis, and pneumonia classification using chest X-ray images","authors":"Sameer Srivastava,&nbsp;Eshanee Ghosh,&nbsp;Abhinav Kumar,&nbsp;Parthiv Chahar,&nbsp;Arpit Utkarsh,&nbsp;Raghavendra Mishra","doi":"10.1016/j.jmir.2025.102115","DOIUrl":"10.1016/j.jmir.2025.102115","url":null,"abstract":"<div><div>Advancements in medical imaging and deep learning have enabled the development of intelligent systems that assist clinicians in diagnosing complex pulmonary diseases. This study addresses the growing concern over lung abnormalities caused by diseases such as COVID-19, tuberculosis (TB), and pneumonia. We propose a convolutional neural network (CNN)-based multi-class classification framework that uses chest X-ray images to automatically detect COVID-19, TB, pneumonia, and normal conditions. The original publicly available dataset exhibited class imbalance, with significantly fewer COVID-19 cases compared to other categories. To address this, the Synthetic Minority Oversampling Technique (SMOTE) are applied at the feature level, generating a balanced dataset of 6,000 chest X-ray images equally distributed across the four classes. The preprocessing techniques have been used to enhance model generalisation, including image normalization, augmentation, and resizing. We evaluated multiple deep learning architectures, including ResNet-50, EfficientNet, DenseNet, and VGG-19. Among these, VGG-19 achieved the highest test accuracy of 97.5%, with precision, recall, and F1-score all exceeding 96% across classes. This unified deep learning pipeline integrates data preprocessing, feature extraction, and classification. The proposed model is intended as a research framework and is currently non-clinical; however, it demonstrates promising potential and could be further explored for assisting radiologists in diagnostic decision-making.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102115"},"PeriodicalIF":2.0,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145260305","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":"VR training for pediatric MRI for exam anxiety: A meta-analysis","authors":"Thomas Saliba,&nbsp;Yasser Aleman-Gomez,&nbsp;David Rotzinger","doi":"10.1016/j.jmir.2025.102113","DOIUrl":"10.1016/j.jmir.2025.102113","url":null,"abstract":"<div><h3>Background</h3><div>MRI exams can provoke significant anxiety due to the procedure’s length, noise, and potential for claustrophobia. This meta-analysis examines whether virtual reality (VR) mock MRIs can effectively reduce pre-exam anxiety in patients, offering a more accessible alternative to traditional mock scanners.</div></div><div><h3>Methods</h3><div>We followed PRISMA 2020 guidelines to conduct a meta-analysis of randomized controlled trials evaluating the effect of VR mock MRIs on anxiety levels in patients scheduled for MRI exams. After screening literature from PubMed, EMBASE, and ScienceDirect, six studies were identified, of which four focused on pediatric populations. Data extraction, quality assessment (Jadad and Delphi scales), and statistical analysis were conducted. The data was normalized and a random-effects model used to assess anxiety reduction using Hedges' g.</div></div><div><h3>Results</h3><div>The meta-analysis revealed that VR mock MRIs did not significantly reduce anxiety before the MRI (<em>p</em> = 0.08), but approached significance for pre-VR and post-MRI anxiety in the intervention group (<em>p</em> = 0.06). Furthermore, no significant differences were observed in anxiety levels post-MRI or when compared with control groups. High heterogeneity was present, likely due to variations in study methodologies, VR interventions, and participant characteristics.</div></div><div><h3>Discussion</h3><div>VR mock MRI was shown to not significantly reduce pre-exam anxiety. However, though there were promising results for pre-VR to post-MRI anxiety, the high heterogeneity and limited studies indicates the need for further research. However, the results may be affected by the meta-analysis being underpowered due to the lack of studies.</div></div><div><h3>Conclusion</h3><div>This meta-analysis did not show any effect of VR mock MRIs to reduce pre-exam anxiety in patients. More studies necessary to fully evaluate the question and provide more data for further analysis.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102113"},"PeriodicalIF":2.0,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145208847","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":"Experiences of Zambian radiographers undertaking mammography","authors":"T. Muwowo,&nbsp;L. Mokoena,&nbsp;F. Bhyat","doi":"10.1016/j.jmir.2025.102091","DOIUrl":"10.1016/j.jmir.2025.102091","url":null,"abstract":"<div><h3>Background</h3><div>Mammography is an imaging technique that uses X-rays to create detailed breast tissue images, essential for the early detection of breast cancer and improved patient outcomes. In Zambia, radiographers develop their mammography skills mainly through on-the-job training, with experienced radiographers mentoring juniors to enhance their confidence and proficiency. This collaborative approach aims to improve breast cancer detection in the region.</div></div><div><h3>Objective</h3><div>Given the limited body of research on the experiences of radiographers in Zambia who perform mammography procedures, this study aimed to explore and describe the lived experiences of radiographers involved in mammography imaging within both private and public diagnostic radiography facilities in Zambia.</div></div><div><h3>Participants and research setting/Methods</h3><div>A qualitative phenomenological approach was adopted, employing purposive and snowball sampling strategies to recruit participants. Data were collected through semi-structured, one-on-one telephone interviews with diagnostic radiographers from four of the seven hospitals in Zambia that offer mammography services. A total of twelve interviews were conducted, with data collection continuing until data saturation was achieved. Ethical principles and trustworthiness criteria were rigorously observed throughout the study.</div></div><div><h3>Results</h3><div>The study’s findings revealed three main themes: (i) Lack of adequate training in mammography. This theme highlights the challenges faced by radiographers due to the absence of formalized and specialized training in mammography. (ii) Barriers to providing quality mammography. In this theme, participants identified several obstacles that hinder the delivery of quality mammography services. These include limited access to mammography equipment, a shortage of radiologists, and a lack of breast cancer education. (iii) Strategies for improving mammography services. This theme reflects the participants’ recommendations for enhancing mammography services in Zambia, including digital imaging technology, expanding clinical training opportunities for radiographers, and the establishment of a postgraduate training programme in mammography.</div></div><div><h3>Conclusion</h3><div>The study revealed important insights into Zambian radiographers' experiences with mammography, highlighting challenges that may lead to unnecessary procedures and difficulties in accessing services. It also identified opportunities to improve the quality and availability of these services.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102091"},"PeriodicalIF":2.0,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145208835","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":"Letter to editor: Strengthening radiography education through market alignment and practitioner insights","authors":"Parth Aphale,&nbsp;Himanshu Shekhar,&nbsp;Shashank Dokania","doi":"10.1016/j.jmir.2025.102119","DOIUrl":"10.1016/j.jmir.2025.102119","url":null,"abstract":"","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102119"},"PeriodicalIF":2.0,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145202510","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 the psychosocial needs of post-radiotherapy rectal cancer survivors and their caregivers in Hong Kong","authors":"Shing Yau Tam ,&nbsp;Ka Hei Man ,&nbsp;Tsz Shan Lau ,&nbsp;Shimin Zhu ,&nbsp;Vincent WS Leung ,&nbsp;Siu Wa Mak ,&nbsp;Wai Man Tang ,&nbsp;Helen KW Law","doi":"10.1016/j.jmir.2025.102116","DOIUrl":"10.1016/j.jmir.2025.102116","url":null,"abstract":"<div><h3>Background/Objectives</h3><div>Rectal cancer radiotherapy often causes long-term adverse effects impacting patients and caregivers. Psychosocial needs specific to this population, particularly within Hong Kong's unique context, remain understudied. This study aims to investigate the psychosocial needs of rectal cancer patients and caregivers before and after radiotherapy.</div></div><div><h3>Methods</h3><div>This study was a prospective observational study. Rectal cancer patients with radiotherapy and their direct caregivers were recruited from [a hospital], Hong Kong from 2022 to 2023. Psychosocial needs and quality of life were assessed using validated questionnaires: the European Organization for Research and Treatment of Cancer core and colorectal modules for patients, and the CareGiver Oncology Quality of Life questionnaire for caregivers, administered at baseline, 3 months, and 6 months post-radiotherapy.</div></div><div><h3>Results</h3><div>Twenty-four subjects including 13 patients and 11 caregivers were recruited. The mean age of patients and caregivers were 66.3 ± 12.7 years old and 49.8 ± 14.8 years old respectively. Majority of patients worried about their future health before the radiotherapy. Fatigue and sleeping difficulties were commonly reported by the survivors. An improvement in the patients’ overall health and quality of life was discerned as the treatment progressed. Caregivers reported receiving support from friends and healthcare providers. Their emotional and intimate lives were less affected with a positive self-image identified.</div></div><div><h3>Conclusions</h3><div>Rectal cancer radiotherapy survivors faced substantial psychological distress, fatigue and sleeping difficulties. Exercise programs are suggested to address fatigue and distress in survivors. Future large-scale studies should further explore caregiver quality of life and self-image dynamics across the caregiving trajectory.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102116"},"PeriodicalIF":2.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145117635","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":"Enhancing fetal ultrasound with a visual checklist","authors":"Alba Nicolas-Boluda ,&nbsp;Joanne K. Jeffery ,&nbsp;Ayla Shokrzadeh-Bonnet ,&nbsp;Alexandre Alzaghloul ,&nbsp;Clémentine Morisset ,&nbsp;Vianney Debavelaere ,&nbsp;Julie Signeux ,&nbsp;Celia Amabile ,&nbsp;Nicolas Fries ,&nbsp;Frédérique Isnard-Bogillot","doi":"10.1016/j.jmir.2025.102110","DOIUrl":"10.1016/j.jmir.2025.102110","url":null,"abstract":"<div><h3>Objectives</h3><div>Ensuring quality in fetal ultrasound (US) is critical, particularly achieving data completeness evaluation as recommended in the latest guidelines. This study assesses the impact of a visual checklist on the completeness of fetal US exams across the first (T1), second (T2) and third (T3) trimester scans according to the French National Obstetric and Fetal US Conference (CNEOF 2022).</div></div><div><h3>Methods</h3><div>Over six months, three obstetrician-gynecologists from a French women’s health institution, used the visual checklist integrated into Sonio Pro (Sonio, Paris, France). The control group included three other physicians (also obstetrician-gynecologists) from the same facility. Exam completeness was measured by comparing the actual images taken during the exam, with views included in the CNEOF 2016 and 2022 recommendations, hypothesizing that the use of the checklist would reduce the number of missing views.</div></div><div><h3>Results</h3><div>Out of 336 exams (including: 111 T1, 117 T2 and 108 T3) the checklist was used on 206 exams (80 T1, 78 T2 and 48 T3). The use of the visual checklist significantly reduced the number of missing images across all exam types and recommendations, with the number of complete exams increasing notably. Specifically, the completion rate of T2 exams doubled under the CNEOF 2022 protocol, when the visual checklist was used. For the most frequently missed “placenta insertion” and “axial kidneys” views in T2 exams, the use of the visual checklist increased the capture rates from 70 % to 87 % and 74 % to 97 %, respectively. Missing views dropped from 0,39 to 0,06 on average for CNEOF 2022 T2 exams after implementing the checklist.</div></div><div><h3>Conclusions</h3><div>The use of a visual checklist markedly enhanced exam completeness, proving potential benefit for compliance with evolving guidelines and, ultimately, for patient care.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102110"},"PeriodicalIF":2.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145117634","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":"Response to Letter to the Editor: “Mammogram Interpretation Under Ideal Conditions? Evaluating the Generalizability of Radiography Advanced Practitioners’ Performance”","authors":"Noelle Clerkin ,&nbsp;Chantal Ski ,&nbsp;Patrick Brennan ,&nbsp;Ruth Strudwick","doi":"10.1016/j.jmir.2025.102111","DOIUrl":"10.1016/j.jmir.2025.102111","url":null,"abstract":"","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102111"},"PeriodicalIF":2.0,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104716","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":"Machine learning and deep learning approaches in MRI for quantifying and staging fatty liver disease: A systematic review","authors":"Mohammadreza Elhaie ,&nbsp;Abolfazl Koozari ,&nbsp;Hossein Koohi ,&nbsp;Qurain T. Alqurain","doi":"10.1016/j.jmir.2025.102112","DOIUrl":"10.1016/j.jmir.2025.102112","url":null,"abstract":"<div><h3>Background</h3><div>Fatty liver disease, encompassing non-alcoholic fatty liver disease (NAFLD) and alcohol-related liver disease (ALD), affects ∼25% of adults globally. Magnetic resonance imaging (MRI), particularly proton density fat fraction (PDFF), is the non-invasive gold standard for hepatic steatosis quantification, but its clinical use is limited by cost, protocol variability, a analysis time. Machine learning (ML) and deep learning (DL) techniques, including convolutional neural networks (CNNs) and generative adversarial networks (GANs), show promise in enhancing MRI-based quantification and staging.</div></div><div><h3>Objective</h3><div>To systematically review the diagnostic accuracy, reproducibility, and clinical utility of ML and DL techniques applied to MRI for quantifying and staging hepatic steatosis in fatty liver disease.</div></div><div><h3>Methods</h3><div>This systematic review was registered in PROSPERO (CRD420251121056) and adhered to PRISMA guidelines, searching PubMed, Cochrane Library, Scopus, IEEE Xplore, Web of Science, Google Scholar, and grey literature for studies on ML/DL applications in MRI for fatty liver disease. Eligible studies involved human participants with suspected/confirmed NAFLD, NASH, or ALD, using ML/DL (e.g., CNNs, GANs) on MRI data (e.g., PDFF, Dixon MRI). Outcomes included diagnostic accuracy (sensitivity, specificity, area under the curve (AUC)), reproducibility (intraclass correlation coefficient (ICC), Dice), and clinical utility (e.g., treatment planning). Two reviewers screened studies, extracted data, and assessed risk of bias using QUADAS-2. Narrative synthesis and meta-analysis (where feasible) were conducted.</div></div><div><h3>Results</h3><div>From 2550 records, 15 studies (<em>n</em> = 25–1038) were included, using CNNs, GANs, radiomics, and dictionary learning on PDFF, chemical shift-encoded MRI, or Dixon MRI. Diagnostic accuracy was high (AUC 0.85–0.97, <em>r</em> = 0.94–0.99 vs. biopsy/MRS), with reproducibility metrics robust (ICC 0.94–0.99, Dice 0.87–0.94). Efficiency improved significantly (e.g., processing &lt;0.16 s/slice, scan time &lt;1 min). Clinical utility included virtual biopsies, surgical planning, and treatment monitoring. Limitations included small sample sizes, single-center designs, and vendor variability.</div></div><div><h3>Conclusion</h3><div>ML and DL enhance MRI-based hepatic steatosis assessment, offering high accuracy, reproducibility, and efficiency. CNNs excel in segmentation/PDFF quantification, while GANs and radiomics aid free-breathing MRI and NASH staging. Multi-center studies and standardization are needed for clinical integration.</div></div>","PeriodicalId":46420,"journal":{"name":"Journal of Medical Imaging and Radiation Sciences","volume":"56 6","pages":"Article 102112"},"PeriodicalIF":2.0,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104715","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}