Frontiers in radiology最新文献

{"title":"Editorial: Based models and machine learning on CT, MRI and PET-CT in head and neck cancer diagnosis, staging and outcome prediction.","authors":"Emma Gangemi, Marco Panfili, Antonello Vidiri","doi":"10.3389/fradi.2026.1963901","DOIUrl":"10.3389/fradi.2026.1963901","url":null,"abstract":"","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1963901"},"PeriodicalIF":4.0,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13550135/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148914625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable multimodal learning for integrating neuroimaging and genetic data in Alzheimer's disease.","authors":"Kun Zhao, Siyuan Dai, Yingying Zhang, Guodong Liu, Pengfei Gu, Chenghua Lin, Paul M Thompson, Alex Leow, Heng Huang, Lifang He, Liang Zhan, Haoteng Tang","doi":"10.3389/fradi.2026.1912277","DOIUrl":"10.3389/fradi.2026.1912277","url":null,"abstract":"<p><strong>Introduction: </strong>Early detection of Alzheimer's disease (AD) requires models that combine brain structure changes with genetic risk, but existing methods struggle to align these different data types.</p><p><strong>Methods: </strong>We present R-GenIMA, an interpretable multimodal large language model that pairs a region-of-interest vision transformer with genetic prompting to jointly analyze structural MRI and single nucleotide polymorphisms (SNPs). Each brain region becomes a visual token and SNP profiles are encoded as structured text, letting the model link regional atrophy to genetic factors through cross-modal attention. Tested on the ADNI cohort, R-GenIMA performs well in classifying four groups: normal cognition, subjective memory concerns, mild cognitive impairment, and AD.</p><p><strong>Results: </strong>Beyond accuracy, it produces biologically meaningful explanations, identifying stage-specific brain regions and genes. The model consistently highlighted known AD risk genes (APOE, BIN1, CLU, RBFOX1) and revealed stage-specific patterns: striatal involvement in subjective decline, frontotemporal changes in early impairment, and broad network disruption in AD.</p><p><strong>Discussion: </strong>These results show that interpretable multimodal AI can integrate imaging and genetics to reveal disease mechanisms, providing a foundation for clinical tools that enable earlier risk assessment and inform precision treatment in Alzheimer's disease.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1912277"},"PeriodicalIF":4.0,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13547260/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148907881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experience in the management of lymphatic leakage using lipiodol lymphangiography and a temperature-sensitive liquid agent embolization.","authors":"Bin Chen, Yuanhai Tu, Ximan Huang, Guiyuan Zhang, Keyu Tang, Haitao Dai, Yonghui Huang, Run Lin","doi":"10.3389/fradi.2026.1910524","DOIUrl":"10.3389/fradi.2026.1910524","url":null,"abstract":"<p><strong>Objective: </strong>Evaluate the safety and efficacy of a temperature-sensitive liquid embolic agent in the management of lymphatic leakage.</p><p><strong>Methods: </strong>Patients with lymphatic leakage who underwent interventional treatment in our center from September 2023 to April 2025 were retrospectively analyzed. The patient underwent percutaneous inguinal lymph node puncture, and iodized oil was used for lymphography. After lymphography, Chiba needle was used to puncture the breach under the guidance of DSA or CT, and temperature-sensitive liquid embolic agent (TempSLE) was used for direct injection embolization. The drainage volume or urine volume was mainly observed after procedure. The clinical success rate was defined as chest and abdominal drainage volume less than 100 mL/ day or urine chylous test negative for 3 consecutive days.</p><p><strong>Results: </strong>A total of 44 patients were included in this study. The main symptoms were chylous ascites in 26 cases, chylothorax in 12 cases, chylopericardium in 2 cases, and chyluria in 4 cases. Twenty-two patients had lymphatic leakage after surgical operation, mainly including Whipple procedures, spinal internal fixation and gynecological surgery. The remaining 22 cases were unexplained and spontaneous lymphatic leakage. Lipiodol lymphography was successfully performed in 44 patients, and embolization of lymphatic vessels using TempSLE were performed in 26 patients. The technique success rate was 100%, and clinical effective rate was 55.6% (lymphography alone group) and 84.6% (TempSLE group). No major complications were found in both groups.</p><p><strong>Conclusions: </strong>The application of temperature-sensitive liquid embolic agent (TempSLE) in the treatment of lymphatic leakage was safe and promising.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1910524"},"PeriodicalIF":4.0,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13548310/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148907769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discriminative feature learning for multiclass lung disease classification using contrastive learning.","authors":"Hafiza Akter Munira, Xuan Zhang, Prathish K Rajaraman, Alejandro P Comellas, Eric A Hoffman, Sean B Fain, Jiwoong Choi, Mario Castro, Mark L Schiebler, Elliot Israel, Serpil C Erzurum, Tianbao Yang, Ching-Long Lin","doi":"10.3389/fradi.2026.1824991","DOIUrl":"10.3389/fradi.2026.1824991","url":null,"abstract":"<p><strong>Objectives: </strong>To develop a contrastive learning model for lung disease classification using discriminative CT imaging embeddings.</p><p><strong>Methods: </strong>A total of 1,187 subjects were included: asthma (<i>n</i> = 315), COPD (<i>n</i> = 355), post-COVID-19 (<i>n</i> = 375), and healthy controls (<i>n</i> = 142). Of these, 1,003 subjects had a single visit with similarly protocoled CT scans acquired at total lung capacity (TLC) and residual volume (RV), and 92 (33 asthma and 59 post-COVID-19) completed a follow-up visit, with two scans per visit. We developed a modified contrastive learning model incorporating an expert-conditioned routing network and adaptive temperature scaling to learn discriminative embeddings. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The embeddings were further validated via k-means clustering, and quantitative CT (qCT) metrics were compared across the derived clusters. The embedding space was used to track disease progression or improvement in the follow-up disease subgroup and to evaluate the model's ability to predict qCT metrics, quantified by the coefficient of determination <math><mo>(</mo> <mrow> <msup><mrow><mi>R</mi></mrow> <mn>2</mn></msup> </mrow> <mo>)</mo></math> .</p><p><strong>Results: </strong>The model achieved a macro-AUC of 89.3% (95% CI: 86.5, 91.8; <i>P</i> < 0.001) in differentiating the four classes. Post-COVID-19 emerged as a distinct class from asthma and COPD in the t-SNE embedding space, and its embeddings across two visits captured disease improvement. Additionally, the learned embeddings showed predictive power for several qCT metrics, particularly the Jacobian ( <math> <msup><mrow><mi>R</mi></mrow> <mn>2</mn></msup> </math> =0.61).</p><p><strong>Conclusions: </strong>The proposed model effectively differentiated these three lung diseases and provided meaningful embeddings for phenotype characterization, longitudinal assessment, and qCT metric prediction.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1824991"},"PeriodicalIF":4.0,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13536901/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive value of an AI model integrating MRI radiomics and clinical features for early recurrence of hepatocellular carcinoma prior to radiofrequency ablation.","authors":"Beibei Zhang, Wenhua Li, Jing Tang, Ruixin Li, Xiao Wang, Xiaoming Liu, Tianran Li","doi":"10.3389/fradi.2026.1824091","DOIUrl":"10.3389/fradi.2026.1824091","url":null,"abstract":"<p><strong>Objectives: </strong>This study developed an AI-driven radiomics model fusing pre-radiofrequency ablation (RFA) multi-sequence MRI features and clinical variables to predict early recurrence of hepatocellular carcinoma (HCC) after RFA.</p><p><strong>Methods: </strong>A total of 169 HCC patients who underwent pre-RFA MRI (January 2015-December 2021) were retrospectively enrolled and randomly assigned to a training set (<i>n</i> = 135) and an internal hold-out test set (<i>n</i> = 34) at an 8:2 ratio using stratified sampling (training: 49 recurrent, 86 non-recurrent; test: 12 recurrent, 22 non-recurrent). Radiomics feature selection involved a three-step strategy of variance threshold filtering, SelectKBest, and least absolute shrinkage and selection operator (LASSO) regression. All data preprocessing, feature selection, and model training were performed exclusively within the training set to prevent information leakage. Support vector machine (SVM), logistic regression (LR), and random forest (RF) classifiers were used to construct radiomics-only, clinical-only, and integrated models. Performance was evaluated using ROC curves (AUC as primary metric), calibration curves, Brier scores, Hosmer-Lemeshow test, and decision curve analysis (DCA). The optimal threshold was determined by the Youden index.</p><p><strong>Results: </strong>Alpha-fetoprotein (AFP), platelet count (PLT), and tumor location were identified as independent clinical predictors (all VIF < 5). Of 11,320 extracted features, 61.5% (<i>n</i> = 6,965) achieved ICC > 0.75, and 16 informative radiomics features were ultimately selected (inter-observer Dice = 0.85 ± 0.06). The radiomics-only models showed robust performance (test AUC: SVM = 0.826, LR = 0.830, RF = 0.826), significantly outperforming clinical-only models (test AUC: SVM = 0.688, LR = 0.706, RF = 0.724; <i>P</i> < 0.05). The integrated models achieved further improvement, with the RF-based integrated model demonstrating superior performance (training AUC = 0.975, test AUC = 0.909; <i>P</i> < 0.0083 after Bonferroni correction). Calibration showed good agreement (Brier score = 0.143, Hosmer-Lemeshow <i>P</i> = 0.367), and DCA demonstrated net clinical benefit across threshold probabilities of 15%-70%. At the optimal threshold (0.42), the RF-based integrated model achieved sensitivity = 83.3%, specificity = 90.9%, PPV = 83.3%, NPV = 90.9%, and accuracy = 88.2%.</p><p><strong>Conclusion: </strong>Preoperative MRI-based radiomics features combined with clinical variables effectively predict early post-RFA HCC recurrence. The integrated radiomics-clinical model outperforms both clinical-only and radiomics-only models, with the RF classifier yielding optimal performance, providing a reliable tool for individualized treatment decision-making.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1824091"},"PeriodicalIF":4.0,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13530903/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-interface persistent memory for large language model-assisted radiology research workflows: a Claude-based proof-of-concept technical development.","authors":"Miguel Angarita, Lina M Acosta Buitrago, Juan Manuel Pérez","doi":"10.3389/fradi.2026.1890122","DOIUrl":"10.3389/fradi.2026.1890122","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background and purpose: &lt;/strong&gt;Large language model (LLM)-assisted radiology research and tool-development work is hampered by a practical form of memory loss we term cross-interface fragmentation: project context built in a web-based conversational interface is not available in a local coding-agent environment, and neither environment retains state across sessions. This forces researchers to manually reconstruct context at every session start and every interface transition. This technical development describes the design and a single-user, proof-of-concept functional demonstration of a Claude-based persistent-memory system intended to reduce this fragmentation for the software-engineering and research-organization layer of radiology AI projects. The system is not a clinical tool and does not process patient data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Materials and methods: &lt;/strong&gt;We implemented an end-to-end pipeline integrating a custom web application (Created.app/Supabase), a self-hosted n8n automation server, the Claude API (Anthropic), GitHub version control, and the Obsidian knowledge-management application. A web session is summarized by the Claude API into six structured fields (summary, decisions, pending tasks, artifacts, errors, continuation point) and written as a per-project MEMORY.md file to GitHub; a complementary CLAUDE.md file holds accumulated technical context for the local coding agent. The study design is a single-user, single-operator proof-of-concept engineering validation across three concurrent development projects; no efficacy, usability, or clinical-outcome claim is made.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In functional testing, the pipeline transferred project context between the web and local-coding environments without manual copy-paste of session content. A representative 558-token session (&lt;i&gt;n&lt;/i&gt; = 1 observation) was processed end-to-end with complete six-field extraction; create and edit operations against the GitHub Contents API succeeded across five consecutive runs without overwrite errors. On a fresh launch, the local coding agent read the memory files and reported project identity, prior technical decisions, and pending tasks without user-provided context. Reported timings are single-run observations, not benchmarked measurements.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;A persistent, cross-interface memory layer for LLM-assisted radiology research workflows is technically feasible with currently available components. As a proof of concept it is explicitly limited: single user, Claude-based, text-only, without quantitative extraction-accuracy benchmarking, and dependent on commercial APIs whose cost scales with use (fixed infrastructure plus variable per-session API cost). We discuss a vendor-neutral, open-weights configuration as the recommended direction for cost- and dependency-sensitive settings such as Latin America, and we report that the system has been used in practice to help organize the development of a separate ","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1890122"},"PeriodicalIF":4.0,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148868074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated opportunistic screening for low bone mineral density using routine CT brain imaging.","authors":"Rory Zhang, Nishant Panchal, Heinrik Choong, Charlie Ding, Haotian Huang, Stefan Kachel, Cherie Chiang, Numan Kutaiba, Ruth P Lim","doi":"10.3389/fradi.2026.1901958","DOIUrl":"10.3389/fradi.2026.1901958","url":null,"abstract":"<p><strong>Objectives: </strong>CT brain (CTB) scans are frequently performed in older adults, a population at increased risk of osteoporosis and low bone mineral density (BMD), presenting an opportunity for opportunistic screening. This study aims to evaluate an automated deep learning approach for opportunistic screening of low BMD and osteoporosis from routine CTB imaging.</p><p><strong>Materials and methods: </strong>A single-centre retrospective analysis was conducted on 2,014 patients (mean age 69.7 ± 14.9 years; 61% female) who underwent non-contrast CTB and dual-energy x-ray absorptiometry (DEXA) within one year of each other. A convolutional neural network incorporating automatically selected CTB slices cranial to the lateral ventricles, as well as age and sex, was trained to perform two binary classification tasks: low BMD screening (<i>T</i>-score < -1.0) and osteoporosis screening (<i>T</i>-score ≤ -2.5). Model performance was evaluated on a 10% hold-out test set using AUC, balanced accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, with subgroup analysis by sex.</p><p><strong>Results: </strong>22% of patients scanned had normal BMD, 44% had osteopenia, and 34% had osteoporosis. For low BMD screening, the model achieved an AUC of 0.83 (95% CI: 0.76-0.90), with AUCs of 0.88 in females and 0.76 in males. For osteoporosis screening, the model achieved an AUC of 0.78 (95% CI: 0.72-0.85), with AUCs of 0.78 in females and 0.74 in males.</p><p><strong>Conclusion: </strong>Automated analysis of routine CT brain imaging showed good discriminatory performance for opportunistic low BMD screening, particularly among females. With further validation, this approach could support earlier identification of at-risk individuals using imaging already acquired in routine clinical care.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1901958"},"PeriodicalIF":4.0,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13522152/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148851972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Longitudinal deep learning-based segmentation of multiple sclerosis lesions in a local clinical cohort.","authors":"Amalie Monberg Hindsholm, Annika Reynberg Langkilde, Jette Lautrup Frederiksen, Flemming Littrup Andersen, Henrik B W Larsson, Ulrich Lindberg, Claes Nøhr Ladefoged","doi":"10.3389/fradi.2026.1758276","DOIUrl":"10.3389/fradi.2026.1758276","url":null,"abstract":"<p><strong>Purpose: </strong>Automated monitoring of multiple sclerosis (MS) lesion progression remains challenging in clinical practice. This study evaluates LongiSeg, a longitudinal deep learning architecture, on heterogeneous clinical data to assess its practical value for routine MS radiological monitoring and extends its use for new lesion detection.</p><p><strong>Methods: </strong>We trained LongiSeg on 470 patients from a diverse clinical cohort acquired across 15 scanner types (both 1.5T and 3T) with mixed 2D/3D T2w FLAIR sequences. We trained and evaluated models for both cross-sectional lesion segmentation and new lesion detection. Performance was compared against a single-timepoint nnU-Net on a cross-sectional test cohort consisting of 67 patients as well as 22 patients presenting with new lesions.</p><p><strong>Results: </strong>LongiSeg achieved superior cross-sectional segmentation performance compared to single-timepoint nnU-Net on the clinical test set (<i>n</i> = 67, T2w FLAIR input, DSC: 0.684 ± 0.124 vs. DSC: 0.665 ± 0.144). LongiSeg for new lesion detection obtained a low performance on the small clinical test cohort (<i>n</i> = 22, DSC: 0.260, 95%CI: 0.143-0.383).</p><p><strong>Conclusion: </strong>LongiSeg demonstrated moderate improvements in cross-sectional MS lesion segmentation. However, the added complexity of processing longitudinal scans may not be justified by these modest gains. For new lesion segmentation, performance was low, especially in cases with few lesions.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1758276"},"PeriodicalIF":4.0,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13506831/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148835370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of 80 kVp combined with deep learning reconstruction algorithm in overweight patients coronary CT angiography: reduced radiation dose and contrast agent dose.","authors":"Hangge Pan, Qiushuang Zhang, Jianrong Ding, Jingli Pan, Aiyun Sun","doi":"10.3389/fradi.2026.1876684","DOIUrl":"10.3389/fradi.2026.1876684","url":null,"abstract":"<p><strong>Background: </strong>Coronary CT angiography (CCTA) has become a key imaging technique for clinical screening of coronary artery disease (CAD). Overweight patients have a higher prevalence of CAD, however, they face increased risks of radiation exposure and contrast-induced nephropathy during CCTA examinations. This study aimed to explore the feasibility of an 80 kVp scanning protocol combined with deep learning image reconstruction (DLIR) algorithm to reducing radiation dose and contrast agent dose in overweight patients with CCTA.</p><p><strong>Methods: </strong>A prospective study was conducted on 100 overweight patients who underwent CCTA, randomly divided into two groups of 50 patients each. The scanning tube voltage of group A was 80 kVp, the dose of contrast agent was calculated as BMI×0.14 mL/s×9s, and H-strength DLIR(DLIR-H) was used for image reconstruction. The voltage of group B was 100 kVp, the contrast agent dose was calculated as BMI×0.18 mL/s×9s and the image was reconstruction by 50% adaptive statistical iterative reconstruction-Veo (ASIR-V50%). Radiation dose, contrast agent dose, injection rate, subjective and objective image quality were compared.</p><p><strong>Results: </strong>Compared to Group B, Group A exhibited significantly lower values for radiation dose (2.85 ± 0.46 vs.4.46 ± 0.69 mSv), contrast agent dose (34.62 ± 2.05 vs. 43.64 ± 1.91 mL) and injection rate (3.83 ± 0.22 vs. 4.84 ± 0.21 mL/s) (all <i>P</i> < 0.001), representing reductions of 36.02%, 20.67% and 20.87%, respectively. Inter-reader agreement for subjective scores were excellent (<i>к</i> between 0.89 and 1.00). Group A demonstrated significantly lower background noise compared to Group B (15.46 ± 2.82 vs. 21.60 ± 4.36 HU, <i>P</i> < 0.001). The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of major coronary arteries were significantly better in Group A compared to Group B (both <i>P</i> < 0.05), except for the SNR of left circumflex artery.</p><p><strong>Conclusions: </strong>In overweight patients undergoing CCTA, the 80 kVp protocol combined DLIR-H effectively reduced the radiation dose, contrast agent dose and injection rate while ensuring image quality compared to the 100 kVp combined ASIR-V50% scanning protocol.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1876684"},"PeriodicalIF":4.0,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13501517/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148815199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Emerging fast medical imaging techniques in radiology.","authors":"Zhifeng Chen, Zhicheng Peng, Mingfeng Jiang, Jianfeng Zhou, Lijun Lu, Xiaoyun Liang","doi":"10.3389/fradi.2026.1948195","DOIUrl":"https://doi.org/10.3389/fradi.2026.1948195","url":null,"abstract":"","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1948195"},"PeriodicalIF":4.0,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13485880/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}