RadiographyPub Date : 2025-05-05DOI: 10.1016/j.radi.2025.102962
Y. Cheng , L. Cao , L. Zhang , Y. Cheng , G. Fan , J. Li , L. Chen , T. Qu , Y. Li , J. Guo
{"title":"Detection and measurement of urinary stones on virtual monoenergetic images derived from rapid tube voltage switching dual-energy CT","authors":"Y. Cheng , L. Cao , L. Zhang , Y. Cheng , G. Fan , J. Li , L. Chen , T. Qu , Y. Li , J. Guo","doi":"10.1016/j.radi.2025.102962","DOIUrl":"10.1016/j.radi.2025.102962","url":null,"abstract":"<div><h3>Introduction</h3><div>We aimed to assess urinary stone detection and measurement, which are important indicators for treatment, using virtual monoenergetic (VM) images derived from rapid tube voltage switching dual-energy CT (rsDECT).</div></div><div><h3>Methods</h3><div>Forty-eight urinary stones placed in a 32-cm diameter phantom filled with saline and 38 patients with 95 urinary stones underwent rsDECT scans with CTDIvol of 5 mGy for phantoms and 8.1 ± 2.5 mGy for patients. VM images at energies from 40 to 100 keV were generated. Stone detection rate, detection confidence level (1–4 points), and size measurement deviation (digital caliper as gold standards) on VM images were recorded and compared.</div></div><div><h3>Results</h3><div>All stones could be detected in phantoms on VM images of all energies with one urinary stone missed in patients on VM images above 70 keV. Stones with size equal to or greater than 2 mm were detectable with highest confidence (4 points) on all VM images, while the detection confidence for stones with size smaller than 2 mm was higher on the low-energy images (40–60 keV). In addition, stone length and width measurement values decreased with the increased energy level, and high-energy VM images provided better agreements with digital caliper.</div></div><div><h3>Conclusion</h3><div>VM images in low-dose rsDECT can be used to detect urinary stones with high efficacy. Low-energy VM images provide higher detection confidence for small stones, while higher-energy images are more accurate in size measurements.</div></div><div><h3>Implications for practice</h3><div>Low-dose DECT should be used for detecting and characterizing small urinary stones in clinical practice to ensure high efficacy, and the low-energy and high-energy VM images in DECT should be optimized for stone detection and size measurement, respectively.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 4","pages":"Article 102962"},"PeriodicalIF":2.5,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143904477","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}
RadiographyPub Date : 2025-05-05DOI: 10.1016/j.radi.2025.102956
R. Appleyard , S. Etty , B. Snaith , J. Nightingale
{"title":"The imaging support workforce: Stakeholder perceptions of role, impact and career progression","authors":"R. Appleyard , S. Etty , B. Snaith , J. Nightingale","doi":"10.1016/j.radi.2025.102956","DOIUrl":"10.1016/j.radi.2025.102956","url":null,"abstract":"<div><h3>Introduction</h3><div>Demand for imaging continues to rise, placing significant challenges on an already-stretched radiography workforce. Enhancing the capability and capacity of the Support Worker and Assistant Practitioner (SWAP) workforce is a potential solution, yet little evidence exists about their deployment. This study explored imaging department stakeholder perceptions in NHS institutions across England regarding SWAP roles and responsibilities, their contribution to service provision, and potential for career progression.</div></div><div><h3>Methods</h3><div>This qualitative study is the final phase of a multi-stage explanatory mixed methods study investigating the utilisation of the imaging SWAP workforce. A case study approach included semi-structured interviews (service/modality leads) and focus groups (SWAPs) across nine NHS Trusts. Sampling was evidence-based and purposive, aiming for representative diversity in SWAP utilisation levels, geographical spread and department size. Thematic analysis was conducted within and across cases.</div></div><div><h3>Results</h3><div>The SWAP workforce was consistently recognised as crucial for maintaining operational efficiency and enhancing patient care. Four overarching themes emerged: (1) operational efficiency and service impact, where SWAPs were critical in optimising workflows; (2) roles and responsibilities, recognising both role clarity and ambiguity leading to role strain; (3) career progression, support, and training, highlighting opportunities yet significant barriers to advancement; and (4) workforce dynamics and job satisfaction, where high job satisfaction contrasted with challenges in role stability and professional recognition.</div></div><div><h3>Conclusion</h3><div>SWAPs significantly enhance imaging service delivery. Despite their substantial contributions, SWAPs face challenges in role clarity and career progression that can impact on inherently high job satisfaction.</div></div><div><h3>Implications for practice</h3><div>A high level of variation in SWAP deployment is confirmed; a structured framework is required to guide implementation of effective deployment models. Moving from SWAP rotational models to static modality deployment may enhance consistency, team dynamics and job satisfaction.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 4","pages":"Article 102956"},"PeriodicalIF":2.5,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143904478","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}
RadiographyPub Date : 2025-05-02DOI: 10.1016/j.radi.2025.102965
H. FriedrichNel , J. Garraway
{"title":"Facilitating student engagement and initiative-taking with workplace learning challenges: The change laboratory methodology","authors":"H. FriedrichNel , J. Garraway","doi":"10.1016/j.radi.2025.102965","DOIUrl":"10.1016/j.radi.2025.102965","url":null,"abstract":"<div><h3>Introduction</h3><div>Workplace-based learning (WBL) or Work-integrated learning (WIL) is an important pedagogy that prepares students for the world of work. However, students may experience challenges during their work practice, inhibiting their learning. Through reflecting on their WBL experiences and understanding the historical and systemic nature of challenges they experience, students may be able to take the initiative in raising and potentially addressing some of these challenges. This sort of reflection and initiative-taking can be facilitated by engaging students outside the workplace in a series of structured workshops collectively called a ‘change laboratory’ (CL). This paper reports on the students' engagement in a CL and assesses the potential of the CL in promoting students' initiative-taking in WBL.</div></div><div><h3>Methods</h3><div>Eight structured CL workshop sessions were held with seventeen final-year Bachelor of Radiography Degree students who voluntarily participated in the CL sessions after ethics approval was obtained.</div></div><div><h3>Results</h3><div>Alongside other challenges, qualified radiographers were sometimes dismissive and unsupportive of students’ WBL. To address these and other difficulties, students suggested an improved WBL system focusing on teamwork between students and qualified radiographers to facilitate patient-centred care and student learning.</div></div><div><h3>Conclusion</h3><div>CL is proposed as a valuable tool for students learning about and taking initiative in addressing WBL challenges.</div></div><div><h3>Implication for practice</h3><div>The research is expected to open new avenues for improving radiography students’ WBL experiences at this specific university.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 4","pages":"Article 102965"},"PeriodicalIF":2.5,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899192","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}
RadiographyPub Date : 2025-04-30DOI: 10.1016/j.radi.2025.102963
W. Abdul Razak , A.S. Asamoah
{"title":"Exploring undergraduate medical imaging students’ perception of clinical stressors in Ghana","authors":"W. Abdul Razak , A.S. Asamoah","doi":"10.1016/j.radi.2025.102963","DOIUrl":"10.1016/j.radi.2025.102963","url":null,"abstract":"<div><h3>Introduction</h3><div>Despite the benefits of clinical training, stressors naturally arise during students’ training. These stressors may negatively impact the emotional and psychological wellbeing of the students. There is paucity of literature on the clinical stressors and the challenges faced by medical imaging students in Ghana. This study explored undergraduate medical imaging students’ perceptions of stressors during clinical training and suggested measures that may lessen burn out.</div></div><div><h3>Methods</h3><div>Cross-sectional study design was employed. The study population consisted of 293 medical Imaging students from College of Health and Wellbeing Kintampo (CoH-K), Kwame Nkrumah University of Science and Technology (KNUST), University of Cape Coast (UCC), University for Development Studies (UDS), University of Ghana (UG), and University of Health and Allied Sciences (UHAS). A self-administered questionnaire with closed-ended questions and a section for open remarks was used for data collection and subsequently analysed using IBM SPSS version 26.</div></div><div><h3>Results</h3><div>63.50% were males and final year students were the majority (48.80%). The highest ranked stressor was, <em>‘‘theory to practical”</em> (89.42%) while “<em>sexual harassment from superiors”</em> ranked lowest (0.12%). UCC recorded the highest responses (35.8%). The coping mechanism, <em>“Reflecting on situations and making better plans for future experiences”</em> ranked highest (89.08%) while “<em>taking alcohol or hard drugs”</em> ranked lowest (2.39%).</div></div><div><h3>Conclusion</h3><div>The data highlighted various clinical stressors experienced by students identifying theory to practical gap as the most prominent. It also provided valuable insights into the coping mechanisms adopted by the students to manage clinical stressors, with <em>reflection,</em> support<em>-seeking,</em> and <em>relaxation techniques</em> being prominent strategies.</div></div><div><h3>Implications for practice</h3><div>Institutions of higher education in Ghana should institute measures to improve students’ wellbeing in the clinical areas.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 4","pages":"Article 102963"},"PeriodicalIF":2.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892028","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":"Radiation exposure from PET-patients in other hospital settings","authors":"C. Künnapuu , S.N.A. Al-Jurani , E.L. Veje , P.L. Hansen","doi":"10.1016/j.radi.2025.102964","DOIUrl":"10.1016/j.radi.2025.102964","url":null,"abstract":"<div><h3>Introduction</h3><div>PET/CT scans involve the administration of a radioactive tracer, emitting 511 keV gamma photons. Accordingly, the waiting areas at the department of nuclear medicine are designed to minimize radiation exposure from radioactive PET patients. However, when continuing to other departments right after the scan, PET patients are referred to common waiting rooms. As a result, it is possible for patients, relatives and caretakers, here under pregnant women and children, to unknowingly spend prolonged periods of time adjacent radiation emitting patients.The aim of this study is to examine the radiation dose to patients or accompanying persons from radiation emitting PET patients in hospital waiting rooms.</div></div><div><h3>Methods</h3><div>Dose rates of twenty-four patients were measured directly after micturition following PET scan at distances equivalent to distances between seats in a waiting room at a radiological department. Cumulative doses for a patient sitting close to up to four PET patients at increasing time periods were calculated.</div></div><div><h3>Results</h3><div>Measured dose rates varied from 33.39 to 74.39 μSv/h, with a median of 52.34 μSv/h. Thirty minutes at 30 cm from the lowest measured dose resulted in a cumulative dose of 16.92 μSv. However, 1 h at 30–85 cm from four high emitting patients resulted in an accumulated dose of 134.6 μSv.</div></div><div><h3>Conclusion</h3><div>Patients or accompanying people waiting for prolonged periods of time in waiting rooms with an influx of PET patients may repeatedly unknowingly be subjected to radiation.</div></div><div><h3>Implications for practice</h3><div>This study highlights the need to reassess waiting area protocols to minimize radiation exposure from PET patients. Directing PET patients to specialized waiting areas may protect groups like pregnant women and children. Educating healthcare staff on this will ensure a safer environment.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 4","pages":"Article 102964"},"PeriodicalIF":2.5,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887385","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}
RadiographyPub Date : 2025-04-25DOI: 10.1016/j.radi.2025.102959
K.J. Knight , M. Beasley , J. McConnell , T. O'Regan , C.M. Alexander , T. Donovan , H. Probs , R. Reeve , M. Sharma , K.M. Knapp , H.A. McNair
{"title":"Research culture, barriers and facilitators within the radiography workforce in the UK – results of a national survey","authors":"K.J. Knight , M. Beasley , J. McConnell , T. O'Regan , C.M. Alexander , T. Donovan , H. Probs , R. Reeve , M. Sharma , K.M. Knapp , H.A. McNair","doi":"10.1016/j.radi.2025.102959","DOIUrl":"10.1016/j.radi.2025.102959","url":null,"abstract":"<div><h3>Introduction</h3><div>Research is vital for diagnostic and therapeutic radiographers, providing the evidence base for disease diagnosis, screening, surveillance, radiotherapy planning, delivery, and treatment. Despite its benefits in improving patient outcomes and imaging services, little is known about the research culture barriers and facilitators within the UK radiography workforce.</div></div><div><h3>Methods</h3><div>An online survey with three sections was created, including demographic questions and a validated research and development culture index to measure research capacity, equality, diversity, and inclusivity. The survey was distributed between May and October 2023 to radiographers and nuclear medicine technologists via email and social media. Mixed methods analysis was performed using statistical analysis (R version 4.2.2) and qualitative analysis utilising a coding framework for open-ended responses.</div></div><div><h3>Results</h3><div>A total of 970 completed surveys were returned: 629 diagnostic radiographers, 306 therapeutic radiographers and 35 nuclear medicine technologists (∼3 % of the UK workforce). Of respondents, 47.4 % had completed or were undertaking a postgraduate qualification and 41.1 % had engaged in research. The barriers to research yielded similar trends over all the radiographers. ‘Lack of protected time at work’, ‘other roles taking priority’ and ‘lack of funding’ being key barriers. The only enablers that scored less than 90 % agreement were ‘research encouraged by manager’, ‘experienced external colleagues able to supervise’, and the ‘desire to prove a theory or hunch’ and ‘research written into the role description’.</div></div><div><h3>Conclusion</h3><div>Research remains underdeveloped in UK radiography roles. This national survey highlights that currently less than half of the UK radiographers have experience in research within their role. Protected time, funding, managerial support, and supervision access are crucial to embedding research into practice.</div></div><div><h3>Implications for practice</h3><div>Greater support is needed for radiographers and managers to overcome barriers and promote radiographer-led research.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 4","pages":"Article 102959"},"PeriodicalIF":2.5,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870186","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}
RadiographyPub Date : 2025-04-24DOI: 10.1016/j.radi.2025.102958
K. Mori , T. Negishi , R. Sekiguchi , M. Suzaki
{"title":"Reduction of radiation exposure in chest radiography using deep learning-based noise reduction processing: A phantom and retrospective clinical study","authors":"K. Mori , T. Negishi , R. Sekiguchi , M. Suzaki","doi":"10.1016/j.radi.2025.102958","DOIUrl":"10.1016/j.radi.2025.102958","url":null,"abstract":"<div><h3>Introduction</h3><div>Intelligent noise reduction (INR), a deep learning-based noise reduction developed by Canon, is used in planar radiography to improve image quality and reduce patient exposure dose. This study aimed to evaluate the reduction of patient exposure dose in planar chest radiography using INR.</div></div><div><h3>Methods</h3><div>We evaluated the visibility of a Lungman phantom with tumor inserts by mean opinion score (MOS) to evaluate the optimal imaging conditions for INR. Furthermore, the optimal imaging conditions for INR were verified through retrospective evaluation using clinical images and the image quality was evaluated by blind/referenceless image spatial quality evaluator (BRISQUE). The individuals were the same 100 patients who had planar chest X-rays taken without INR and with INR, designated as the control and evaluation groups, respectively. Imaging conditions with automatic exposure control in the evaluation group set the radiation dose 32 % lower than that for the control group. The BRISQUE and entrance surface dose (<span><math><mrow><msub><mi>K</mi><mrow><mi>a</mi><mo>,</mo><mi>e</mi></mrow></msub></mrow></math></span>) in each group were compared.</div></div><div><h3>Results</h3><div>Regarding the visibility of the simulated mass, there was no significant difference in MOS when the reference dose was reduced by 33.33 % (<em>p</em> = 0.26). In retrospective evaluation of clinical images, BRISQUE in the control and evaluation groups was 34.35 ± 4.19 and 34.46 ± 4.58 (<em>p</em> = 0.35), respectively. The <span><math><mrow><msub><mi>K</mi><mrow><mi>a</mi><mo>,</mo><mi>e</mi></mrow></msub></mrow></math></span> in the control and evaluation groups were 0.131 ± 0.039 and 0.084 ± 0.024 mGy (<em>p</em> < 0.001).</div></div><div><h3>Conclusion</h3><div>INR reduced patient exposure dose by an average of 35 % without decreasing image quality.</div></div><div><h3>Implications for practice</h3><div>These results indicate that INR can contribute to the reduction of patient radiation dose during chest radiography. The widespread use of this technology may reduce dose indices, including diagnostic reference levels.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 3","pages":"Article 102958"},"PeriodicalIF":2.5,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863767","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}
RadiographyPub Date : 2025-04-24DOI: 10.1016/j.radi.2025.102957
G. Doherty , C. Hughes , J. McConnell , R. Bond , L. McLaughlin , S. McFadden
{"title":"Integrating AI into medical imaging curricula: Insights from UK HEIs","authors":"G. Doherty , C. Hughes , J. McConnell , R. Bond , L. McLaughlin , S. McFadden","doi":"10.1016/j.radi.2025.102957","DOIUrl":"10.1016/j.radi.2025.102957","url":null,"abstract":"<div><h3>Introduction</h3><div>With artificial intelligence (AI) becoming increasingly integrated into medical imaging, the Health and Care Professions Council (HCPC) updated its Standards of Proficiency for Radiographers in Autumn 2023. These changes require clinicians to be both competent and confident in operating AI and related technologies within their role. Responsibility for meeting these standards extends beyond individual clinicians to higher education institutions (HEIs), which play a crucial role in preparing future professionals. This study examines the current and planned provision of AI education for medical imaging students and staff, identifying potential challenges in its implementation.</div></div><div><h3>Methods</h3><div>An electronic survey was developed and hosted on the Joint Information Systems Committee (JISC) platform. It was disseminated in April 2023 by the Society of Radiographers to UK HEIs offering medical imaging programmes.</div></div><div><h3>Results</h3><div>24 HEIs responded, with representation from all four UK nations. Of these, 71 % (<em>n = 17</em>) had already integrated AI into their curriculum. Reported challenges included timetabling constraints and the need to upskill staff. 21 % (n = 5) indicated that AI would be incorporated following course revalidation in the 2024/25 academic year, while the remaining two HEIs were unaware of planned changes.</div></div><div><h3>Conclusion</h3><div>Most UK HEIs have begun integrating AI education into medical imaging programmes. However, significant disparities exist in the depth and scope of AI content across institutions. Further efforts are needed to develop a comprehensive and standardised AI curriculum for medical imaging in the UK.</div></div><div><h3>Implications for practice</h3><div>This study highlights key areas for improvement in AI education within medical imaging programmes. Further research into content and delivery methods is essential to ensure radiography professionals adequately equipped to navigate the evolving clinical environment.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 3","pages":"Article 102957"},"PeriodicalIF":2.5,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863761","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}
RadiographyPub Date : 2025-04-23DOI: 10.1016/j.radi.2025.102961
E.N. Onwuharine , M. Asaduzzaman , A. James Clark , M. Raseta
{"title":"Predictive modelling for prostate cancer aggressiveness using non-invasive MRI techniques","authors":"E.N. Onwuharine , M. Asaduzzaman , A. James Clark , M. Raseta","doi":"10.1016/j.radi.2025.102961","DOIUrl":"10.1016/j.radi.2025.102961","url":null,"abstract":"<div><h3>Introduction</h3><div>Magnetic Resonance Imaging (MRI) plays a crucial role in the diagnosis of prostate cancer (Pca). This study aimed to improve the diagnostic accuracy of MRI in distinguishing between prostate tumours of Grade Group (GG)2 versus GGs3–5 and GG2 versus GG3 only, using predictive models.</div></div><div><h3>Methods</h3><div>Double Inversion Recovery MRI (DIR-MRI) and Multiparametric MRI (mpMRI) scans from 53 patients (mean age: 67 years) acquired between January 2015 and January 2017 were retrospectively analysed. The suspected PCa lesions identified on MRI were correlated with biopsy targets and GGs. Lesion-to-normal ratios (LNRs) of potential PCa lesions were calculated using the Siemens Healthineers Syngo.via Picture Archiving and Communication System (PACS) by drawing Regions of Interest (ROIs) around the lesions and corresponding normal tissue to measure their respective signal intensities. Prediction models were developed using the R statistical package CARRoT, integrating MRI-derived variables and baseline patient characteristics to reliably classify PCa GGs.</div></div><div><h3>Results</h3><div>The developed predictive models achieved high diagnostic performance, with Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.86 and 0.91 upon 1000 cross-validations, respectively.</div></div><div><h3>Conclusion</h3><div>We present explainable and rigorously cross-validated models that differentiate less aggressive from more aggressive PCa based on T2 LNR and the tumuor short axis measured on axial T2-weighted MRI (Dimension B). In contrast to existing models, which often lack validation (internal or external) or rely on non-explainable Artificial Intelligence techniques, our models offer greater clinical applicability.</div></div><div><h3>Implications for practice</h3><div>These models provide a robust, explainable tool for clinicians to accurately distinguish between less and more aggressive PCa, utilizing T2 LNR and axial T2 tumuor dimensions. By addressing limitations in existing predictive models, they offer potential for improved clinical decision-making.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 3","pages":"Article 102961"},"PeriodicalIF":2.5,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863766","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}