Clinical Imaging最新文献

{"title":"Does ACR TI-RADS increase efficacy of thyroid ultrasounds?","authors":"S.J.C. van der Burg ,&nbsp;M.J. Van Rietschoten ,&nbsp;N.A. 't Hart ,&nbsp;M. de Rooij ,&nbsp;G.S. Mijnhout ,&nbsp;A.B. Francken","doi":"10.1016/j.clinimag.2025.110510","DOIUrl":"10.1016/j.clinimag.2025.110510","url":null,"abstract":"<div><h3>Background</h3><div>The American College of Radiology Thyroid Imaging Results and Data System (ACR TI-RADS) is a risk stratification system (RSS) to assess ultrasounds of thyroid nodules. This study aims to evaluate if the implementation of ACR TI-RADS reduces fine needle aspiration cytology (FNAC) of benign nodules.</div></div><div><h3>Material &amp; methods</h3><div>All patients diagnosed with a thyroid nodule, and who received an ultrasound between January 2018 and February 2020 were included. Period I included patients undergoing ultrasound before implementation of ACR TI-RADS and period II after implementation. The impact of ACR TI-RADS on the number of FNACs with the accompanying cytological results and guideline concordance were analyzed.</div></div><div><h3>Results</h3><div>In this study, 787 patients and 889 ultrasounds were included. Of these ultrasounds, 403 were performed in period I and 486 in period II. The proportion of ultrasounds leading to FNAC decreased significantly since implementation (51.6 % vs. 43.6 %, <em>p</em> = 0.018) while the proportion of benign cytology results decreased significantly as well (84.4 % vs. 73.6 %, <em>p</em> = 0.020). Furthermore, since ACR TI-RADS implementation, physicians followed the accompanying guidelines on follow-up in 70.4 % of the cases.</div></div><div><h3>Conclusion</h3><div>A decrease of FNAC of benign thyroid nodules was observed since implementation of ACR TI-RADS and this RSS was easily implemented in our clinic.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"124 ","pages":"Article 110510"},"PeriodicalIF":1.8,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultimate focus: applications of the Churchill Method in radiology","authors":"Steven P. Rowe ,&nbsp;Kristen H. Rowe ,&nbsp;Maureen Kohi ,&nbsp;Elliot K. Fishman ,&nbsp;Darren Moore","doi":"10.1016/j.clinimag.2025.110507","DOIUrl":"10.1016/j.clinimag.2025.110507","url":null,"abstract":"<div><div>The Churchill Method evolved as an approach to shooting sporting clays; essentially, successfully shooting the clay as it followed its multi-dimensional trajectory could be distilled into a simplified task, with well-trained instinct taking over to allow achievement of the more complex overall task. The simplified task might be ultimate focus on finding the leading edge of the target – with instinctive hand-eye coordination handling everything else including bringing the barrel into alignment. If the instinct is not present, the Churchill Method will not work – and practice and repetition must be utilized in order for there to be success with the overall goal. Those ideas can inform multiple aspects of radiology practice, from day-to-day, hands-on procedures to long-term career building. Regarding procedures, the Churchill Method can instruct us to keep our focus on the screen or monitor, while letting our honed instincts guide our hands to where they need to be for maximal efficacy. In the context of diagnostic imaging, fleeting ultimate focus can intersect with specific, high-yield areas of the anatomy in instinctively defined search patterns. As for career building, the Churchill Method suggests that ultimate focus on the next paper or the next grant or the next important talk can instinctively allow us to achieve our long-term career goals. With the rapid rise of artificial intelligence (AI), approaches such as the Churchill Method that can maximize human achievement are important to ensure that human endeavor remains relevant as many tasks begin to fall under the AI umbrella.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110507"},"PeriodicalIF":1.8,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144088962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A review of explainable AI techniques and their evaluation in mammography for breast cancer screening","authors":"Noora Shifa,&nbsp;Moutaz Saleh,&nbsp;Younes Akbari,&nbsp;Sumaya Al Maadeed","doi":"10.1016/j.clinimag.2025.110492","DOIUrl":"10.1016/j.clinimag.2025.110492","url":null,"abstract":"<div><div>Explainable AI (XAI) methods are gaining prominence in medical imaging, addressing the critical need for transparency and trust in AI-driven diagnostic tools. Mammography, as the cornerstone of early breast cancer detection, holds immense potential for improving outcomes when integrated with AI solutions. However, widespread adoption of AI in clinical settings depends on explainability, which enhances clinicians' confidence in these tools. By exploring various XAI techniques and evaluating their strengths and weaknesses, researchers can significantly advance precision medicine. This review synthesizes existing research on XAI in medical imaging, focusing on mammography, a domain often overlooked in XAI studies. It provides a comparative analysis of XAI techniques employed in mammography, assessing their diagnostic efficacy and identifying research gaps, such as the lack of specialized evaluation frameworks. Additionally, the review examines evaluation methods for XAI in medical imaging and proposes modifications tailored to mammography diagnostics. Insights from XAI advancements in other fields are also explored for their potential to enhance interpretability and clinical relevance in breast cancer detection. The study concludes by highlighting critical research gaps and proposing directions for developing reliable, effective AI models that integrate XAI to transform breast cancer diagnostics.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110492"},"PeriodicalIF":1.8,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparison of performance of DeepSeek-R1 model-generated responses to musculoskeletal radiology queries against ChatGPT-4 and ChatGPT-4o – A feasibility study","authors":"Hasaam Uldin ,&nbsp;Sonal Saran ,&nbsp;Girish Gandikota ,&nbsp;Karthikeyan. P. Iyengar ,&nbsp;Raju Vaishya ,&nbsp;Yogesh Parmar ,&nbsp;Fahid Rasul ,&nbsp;Rajesh Botchu","doi":"10.1016/j.clinimag.2025.110506","DOIUrl":"10.1016/j.clinimag.2025.110506","url":null,"abstract":"<div><h3>Objective</h3><div>Artificial Intelligence (AI) has transformed society and chatbots using Large Language Models (LLM) are playing an increasing role in scientific research. This study aims to assess and compare the efficacy of newer DeepSeek R1 and ChatGPT-4 and 4o models in answering scientific questions about recent research.</div></div><div><h3>Material and methods</h3><div>We compared output generated from ChatGPT-4, ChatGPT-4o, and DeepSeek-R1 in response to ten standardized questions in the setting of musculoskeletal (MSK) radiology. These were independently analyzed by one MSK radiologist and one final-year MSK radiology trainee and graded using a Likert scale from 1 to 5 (1 being inaccurate to 5 being accurate).</div></div><div><h3>Results</h3><div>Five DeepSeek answers were significantly inaccurate and provided fictitious references only on prompting. All ChatGPT-4 and 4o answers were well-written with good content, the latter including useful and comprehensive references.</div></div><div><h3>Conclusion</h3><div>ChatGPT-4o generates structured research answers to questions on recent MSK radiology research with useful references in all our cases, enabling reliable usage. DeepSeek-R1 generates articles that, on the other hand, may appear authentic to the unsuspecting eye but contain a higher amount of falsified and inaccurate information in the current version. Further iterations may improve these accuracies.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110506"},"PeriodicalIF":1.8,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The implementation of artificial intelligence in serial monitoring of post gamma knife vestibular schwannomas: A pilot study","authors":"Manwi Singh ,&nbsp;Noemi Jester ,&nbsp;Samantha Lorr ,&nbsp;Alexis Briano ,&nbsp;Nofrat Schwartz ,&nbsp;Amit Mahajan ,&nbsp;Veronica Chiang ,&nbsp;Steven M. Tommasini ,&nbsp;Daniel H. Wiznia ,&nbsp;Frank D. Buono","doi":"10.1016/j.clinimag.2025.110495","DOIUrl":"10.1016/j.clinimag.2025.110495","url":null,"abstract":"<div><h3>Background</h3><div>Vestibular schwannomas (VS) are benign tumors that can lead to hearing loss, balance issues, and tinnitus. Gamma Knife Radiosurgery (GKS) is a common treatment for VS, aimed at halting tumor growth and preserving neurological function. Accurate monitoring of VS volume before and after GKS is essential for assessing treatment efficacy.</div></div><div><h3>Purpose</h3><div>To evaluate the accuracy of an artificial intelligence (AI) algorithm, originally developed to identify NF2-SWN-related VS, in segmenting non-NF2-SWN-related VS and detecting volume changes pre- and post-GKS. We hypothesize this AI algorithm, trained on NF2-SWN-related VS data, will accurately apply to non-NF2-SWN VS and VS treated with GKS.</div></div><div><h3>Methods</h3><div>In this retrospective cohort study, we reviewed data from an established Gamma Knife database, identifying 16 patients who underwent GKS for VS and had pre- and post-GKS scans. Contrast-enhanced T1-weighted MRI scans were analyzed with both manual segmentation and the AI algorithm. DICE similarity coefficients were computed to compare AI and manual segmentations, and a paired <em>t</em>-test was used to assess statistical significance. Volume changes for pre- and post-GKS scans were calculated for both segmentation methods.</div></div><div><h3>Results</h3><div>The mean DICE score between AI and manual segmentations was 0.91 (range 0.79–0.97). Pre- and post-GKS DICE scores were 0.91 (range 0.79–0.97) and 0.92 (range 0.81–0.97), indicating high spatial overlap.</div></div><div><h3>Conclusion</h3><div>AI-segmented VS volumes pre- and post-GKS were consistent with manual measurements, with high DICE scores indicating strong spatial overlap. The AI algorithm processed scans within 5 min, suggesting it offers a reliable, efficient alternative for clinical monitoring.</div></div><div><h3>Clinical importance</h3><div>DICE scores showed high similarity between manual and AI segmentations. The pre- and post-GKS VS volume percentage changes were also similar between manual and AI-segmented VS volumes, indicating that our AI algorithm can accurately detect changes in tumor growth.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110495"},"PeriodicalIF":1.8,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Academic influence of American College of Radiology Appropriateness Criteria: a citation analysis of thoracic and cardiac imaging guidelines","authors":"Bradley Kasper ,&nbsp;Christopher M. Walker ,&nbsp;Travis S. Henry ,&nbsp;Constantine Raptis ,&nbsp;Brent P. Little","doi":"10.1016/j.clinimag.2025.110505","DOIUrl":"10.1016/j.clinimag.2025.110505","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the academic impact of the American College of Radiology thoracic and cardiac Appropriateness Criteria (ACR-AC) guideline publications through citation analysis.</div></div><div><h3>Methods</h3><div>The Scopus database was used to collect publication year, version number, and number and identity of citing publications for thoracic and cardiac imaging ACR-AC guideline publications. For each citing article, the journal name and impact factor, publication year, countries of all authors, and language(s) of publication were collected. An article h-index was computed for each ACR-AC guideline.</div></div><div><h3>Results</h3><div>31 thoracic and cardiac ACR-AC guideline publications received 758 citations from 379 journals, with authors representing 62 countries. The median citation count was 15 (range = 1–97) and the median article h-index was 5 (range = 1–19). The most frequent country of authorship of articles citing an ACR-AC guideline publication was the United States, but 66.7 % of authors were from other countries. The median impact factor for the citing journals was 3.0 (range = 0.0–521.6). A majority of the total citations were from “Non-Radiology Journals” (<em>n</em> = 422/758 [55.7 %]) which comprised a majority of all journals represented (<em>n</em> = 295/379 [77.8 %]).</div></div><div><h3>Conclusions</h3><div>Citation characteristics of ACR-AC guideline publications suggest broad multidisciplinary and global academic influence.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110505"},"PeriodicalIF":1.8,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143934941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reviewing superficial bone lesions: What the radiologist needs to know","authors":"Dâmaris Versiani Caldeira Gonçalves ,&nbsp;Isabela Azevedo Nicodemos da Cruz ,&nbsp;Marcelo Astolfi Caetano Nico ,&nbsp;Alípio Gomes Ormond Filho ,&nbsp;Júlio Brandão Guimarães","doi":"10.1016/j.clinimag.2025.110493","DOIUrl":"10.1016/j.clinimag.2025.110493","url":null,"abstract":"<div><div>Superficial bone lesions arise from the outer components of the bone, from the cortex to the periosteum. Such superficial lesions are often challenges during imaging reporting, and their incorrect interpretation may lead to inadequate management. We present a literature review regarding these lesions according to a standardized division into tumoral and non-tumoral lesions. We also provide a guide for their proper assessment on different imaging modalities. Knowledge of the specific imaging features that aid in the determination of the lesion origin and estimation of the risk of malignancy is fundamental for the radiologist to contribute to adequate patient management.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110493"},"PeriodicalIF":1.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiomics-based machine learning in prediction of response to neoadjuvant chemotherapy in osteosarcoma: A systematic review and meta-analysis","authors":"Mohsen Salimi ,&nbsp;Shakiba Houshi ,&nbsp;Ali Gholamrezanezhad ,&nbsp;Pouria Vadipour ,&nbsp;Sharareh Seifi","doi":"10.1016/j.clinimag.2025.110494","DOIUrl":"10.1016/j.clinimag.2025.110494","url":null,"abstract":"<div><h3>Background and aims</h3><div>Osteosarcoma (OS) is the most common primary bone malignancy, and neoadjuvant chemotherapy (NAC) improves survival rates. However, OS heterogeneity results in variable treatment responses, highlighting the need for reliable, non-invasive tools to predict NAC response. Radiomics-based machine learning (ML) offers potential for identifying imaging biomarkers to predict treatment outcomes. This systematic review and meta-analysis evaluated the accuracy and reliability of radiomics models for predicting NAC response in OS.</div></div><div><h3>Methods</h3><div>A systematic search was conducted in PubMed, Embase, Scopus, and Web of Science up to November 2024. Studies using radiomics-based ML for NAC response prediction in OS were included. Pooled sensitivity, specificity, and AUC for training and validation cohorts were calculated using bivariate random-effects modeling, with clinical-combined models analyzed separately. Quality assessment was performed using the QUADAS-2 tool, radiomics quality score (RQS), and METRICS scores.</div></div><div><h3>Results</h3><div>Sixteen studies were included, with 63 % using MRI and 37 % using CT. Twelve studies, comprising 1639 participants, were included in the meta-analysis. Pooled metrics for training cohorts showed an AUC of 0.93, sensitivity of 0.89, and specificity of 0.85. Validation cohorts achieved an AUC of 0.87, sensitivity of 0.81, and specificity of 0.82. Clinical-combined models outperformed radiomics-only models. The mean RQS score was 9.44 ± 3.41, and the mean METRICS score was 60.8 % ± 17.4 %.</div></div><div><h3>Conclusion</h3><div>Radiomics-based ML shows promise for predicting NAC response in OS, especially when combined with clinical indicators. However, limitations in external validation and methodological consistency must be addressed.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110494"},"PeriodicalIF":1.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of interventional radiology awareness: insights from Turkey, the USA, and Europe using Google Trends data","authors":"Ali Dablan,&nbsp;Hamit Özgül,&nbsp;Yiğit Can Kartal,&nbsp;Ali Fuat Tekin","doi":"10.1016/j.clinimag.2025.110491","DOIUrl":"10.1016/j.clinimag.2025.110491","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate public awareness of Interventional Radiology (IR) by analyzing internet search trends across Turkey, the United States (USA), and major European countries (2004–2024), and assess the quality of online IR educational resources.</div></div><div><h3>Materials and methods</h3><div>Google Trends data were analyzed for IR-related terms in five countries. Relative Search Volume (RSV) trends and growth rates were calculated. Top 10 IR-related websites in Turkish were evaluated using DISCERN and Flesch-Kincaid readability tools. Statistical significance was assessed using time series analysis (<em>p</em> &lt; 0.05).</div></div><div><h3>Results</h3><div>The USA showed highest overall IR awareness (RSV:88), while Turkey demonstrated fastest growth (<em>p</em> &lt; 0.001). European countries showed moderate but significant growth in IR-related searches. Procedure-specific searches (ablation, thrombectomy) increased significantly in Turkey post-2014 (p &lt; 0.001). Online IR educational content in Turkish showed limited accessibility (mean Flesch-Kincaid score: 11.2 ± 1.4).</div></div><div><h3>Conclusion</h3><div>Significant regional disparities exist in IR awareness, with established presence in the USA contrasting with rapid growth in Turkey and moderate growth in Europe. Limited accessibility of educational resources, particularly in developing regions, suggests need for targeted interventions to improve IR awareness and enhance adoption of minimally invasive procedures.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110491"},"PeriodicalIF":1.8,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143931558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"I saw the sign: Finding the right track on the crazy (-paving) train","authors":"Rishi R. Shah ,&nbsp;Douglas S. Katz","doi":"10.1016/j.clinimag.2025.110488","DOIUrl":"10.1016/j.clinimag.2025.110488","url":null,"abstract":"","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"123 ","pages":"Article 110488"},"PeriodicalIF":1.8,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}