Insights into Imaging最新文献

{"title":"The MR quality landscape in Europe.","authors":"Simone Busoni, Anna Pichiecchio, Lara Cristiano, Andrew England, Edwin H G Oei, Peter Lundberg, Michelle C Williams, Francesco Santini, Emanuele Neri","doi":"10.1186/s13244-026-02280-x","DOIUrl":"https://doi.org/10.1186/s13244-026-02280-x","url":null,"abstract":"<p><strong>Objectives: </strong>Over the last few years, with the introduction of advanced MR imaging techniques, increasing exam demand and the growth of multi-center clinical trials and artificial intelligence (AI)-driven analysis, it has become increasingly difficult to guarantee image quality across time and institutions. Quality Assurance (QA) and Quality Control (QC) programs have therefore become essential. The aim of the survey was to map how MRI QA and QC are implemented in routine clinical practice and, where applicable, in research settings, across Europe, to identify the points where harmonization, coordination, or further education is needed.</p><p><strong>Materials and methods: </strong>An anonymous survey was distributed between October and December 2024 through ESR, EFOMP, EFRS member societies and ESMRMB to healthcare professionals, addressing five broad categories: characteristics of participants and their institutions, national MRI QA/QC guidelines/legislation and awareness, local organization for MRI QA, local (institute level) organization for MRI system performance QCs, conventional imaging QCs and qMRI QCs.</p><p><strong>Results: </strong>269 responses were obtained from 37 different countries. Respondents were radiologists (52%), followed by Medical Physics Experts/Physicists/Engineers (30%), and radiographers (17%). Only a few countries have mandated national legislation addressing MRI QA/QC, while many others rely on voluntary guidelines or lack formal protocols. Most respondents recognized the importance of robust QA/QC programs. There is a strong consensus among respondents on the need for harmonized guidelines from organizations like ESR, multidisciplinary collaboration, and easily accessible training.</p><p><strong>Conclusions: </strong>The European landscape regarding MRI quality is very heterogeneous, with different regulations across countries, and different penetration of MRI QA and QC training and regulation. The European Society of Radiology is optimally positioned with partners to play an active role in the harmonization of MRI quality education and practices across Europe, and we propose the development of a set of recommendations for MRI quality control and assurance.</p><p><strong>Critical relevance statement: </strong>There is scope for raising awareness of both MRI Quality Control (QC) and Quality Assurance (QA) issues and improvement in these fields to ensure patient safety, reduce diagnostic errors, and allow more patients to benefit from MR imaging.</p><p><strong>Key points: </strong>Our survey of MRI QA and QC practices across Europe revealed significant heterogeneity in regulations and practices between countries and institutions. There is a widespread lack of awareness and implementation of MRI quality guidelines. The ESR MR Safety and Quality Committee advocates for the standardization and enhancement of MRI quality training for all professionals involved in this issue.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147837497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gender equity in radiology and radiology research: a survey by the European Society of Radiology.","authors":"Anna D'Angelo, Elisabetta Giannotti, Minerva Becker, Chiara Giraudo, Camilla Panico, Anagha P Parkar, Anouk van der Hoorn, Pascal A T Baltzer, Diana Giannarelli, Ritse M Mann, Marion Smits, Paola Clauser","doi":"10.1186/s13244-026-02281-w","DOIUrl":"10.1186/s13244-026-02281-w","url":null,"abstract":"<p><strong>Objectives: </strong>Gender equity in medicine remains a topic of increasing attention. The aim was to investigate if gender influences the radiology profession, with a focus on career progression, leadership roles, work-life balance, research activity and perceived barriers.</p><p><strong>Materials and methods: </strong>An anonymous online survey consisting of 22 questions was distributed by the European Society of Radiology (ESR) to its members between October and December 2024. The survey covered demographics, work schedules, family responsibilities, career development, leadership roles, research involvement, and perceived personal experiences. Quantitative data were analyzed using descriptive statistics, chi-square test, and rate differences with confidence intervals. Open-ended responses were explored qualitatively using thematic analysis.</p><p><strong>Results: </strong>Among 830 respondents, 657 completed the questionnaire (63.3% female, 35.3% male, 1.3% others). Women more frequently reported caregiving responsibilities beyond childcare (4.1% vs 3%), longer parental leave (46.2% vs 21.5%), and experiences of harassing behaviors at work. Men held a higher proportion of leadership roles (33.2% vs 25.2%). Respondents involved in research were more likely to work > 30% extra hours (47.2% vs 29.0%). Although research activity rates were similar across genders, women more often reported barriers to attending conferences and a lack of protected research time. Career fulfillment increased with age among men but decreased among women. Gender was considered a career disadvantage by 44.5% of women versus 9.5% of men.</p><p><strong>Conclusion: </strong>The survey reveals perceived gender disparities in radiology, particularly in leadership access, work conditions, and career satisfaction. Addressing structural barriers and promoting supportive workplace policies are essential to achieving true gender equity in the field.</p><p><strong>Critical relevance statement: </strong>Despite improvements in the last few decades, gender inequity remains present in radiology. Variability between geographical regions suggests that key critical areas can be addressed to promote improvement and support a more equitable professional environment.</p><p><strong>Key points: </strong>Perceived gender disparities in radiology are present across career progression, leadership roles, and work-life balance. Women were significantly more likely than men to perceive gender as a career disadvantage (44.5% vs 9.5%; p < 0.0001 35.0% [95% CI: 28.9 to 41.1]). They reported slightly higher caregiving responsibilities and longer parental leave. Structural inequalities impact gender equity in radiology, requiring targeted institutional and cultural changes.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13149819/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147837504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing radiology workflows through collaborative AI-assisted chest X-ray reporting using large vision-language models: a proof-of-concept study.","authors":"Chantal Pellegrini, Ege Özsoy, Florian T Gassert, Alexander W Marka, Maximilian Strenzke, Matthias Keicher, Marcus R Makowski, Nassir Navab","doi":"10.1186/s13244-026-02292-7","DOIUrl":"10.1186/s13244-026-02292-7","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate whether collaborative assistance from an artificial intelligence-based tool that proposes partial radiology report content can improve reporting efficiency and radiologist satisfaction in chest X-ray interpretation, without compromising report quality.</p><p><strong>Materials and methods: </strong>In a retrospective study, three radiologists reported 50 MIMIC-CXR chest X-rays twice, once with artificial intelligence (AI) assistance and once without. A specialized large vision-language model (LVLM) provided real-time suggestions, which could be accepted, modified or rejected. The study evaluated writing time, suggestion acceptance, report length and quality and assessed usability and suggestion quality on a 5-point Likert-scale questionnaire. Statistical analysis used paired t-tests or Wilcoxon signed-rank tests based on normality.</p><p><strong>Results: </strong>AI assistance reduced mean writing time by 7.80% (p = 0.08), with significant gains for complex reports (18.34%, p < 0.001). Efficiency improvements correlated with suggestion acceptance and were user-dependent, with benefits up to 27.24% (CI: [17.34, 37.14], p < 0.001) for radiologists with high acceptance. Report quality and length remained stable, indicating preserved diagnostic accuracy without degradation. Radiologists rated the tool highly for ease of use (mean: 4.33) and desired regular use (mean: 4), noting minimal errors (mean: 1.67).</p><p><strong>Conclusion: </strong>Collaborative AI assistance with an LVLM can improve reporting efficiency if well adopted, particularly for complex cases, without compromising quality, and is well-received by radiologists. These exploratory findings suggest potential to optimize radiology workflows through collaborative reporting and warrant prospective validation in clinical settings.</p><p><strong>Critical relevance statement: </strong>This study critically evaluates a collaborative AI-assisted reporting tool for chest X-rays, demonstrating its potential to enhance radiologist efficiency without compromising automatically measured report quality, thereby demonstrating a potential path for practical integration of AI into clinical radiology workflows.</p><p><strong>Key points: </strong>A collaborative vision-language model supported radiology workflow is proposed, and its effectiveness is studied in a user study. Mean writing time for a radiology report decreases with AI support without affecting report quality. The AI-assisted tool was rated highly for usability and integration into clinical workflow, supporting its practical adoption in radiology reporting.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13125563/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The 2024 LI-RADS treatment response update: practical reporting after non-radiation and radiation locoregional therapies for hepatocellular carcinoma.","authors":"Jernej Lučev","doi":"10.1186/s13244-026-02290-9","DOIUrl":"https://doi.org/10.1186/s13244-026-02290-9","url":null,"abstract":"<p><p>This review critically appraises the 2024 Liver Imaging Reporting and Data System (LI-RADS) Treatment Response Algorithm (TRA), which introduces separate non-radiation and radiation treatment response pathways and optional MRI ancillary features, and provides evidence-based guidance for clinical implementation. The updated framework addresses key limitations of the prior algorithm, including moderate sensitivity for residual viable hepatocellular carcinoma (HCC), ambiguity of the Equivocal category, and overcalling after radiation therapy. The 2024 update simplifies viability assessment by emphasizing mass-like enhancement as the dominant sign of residual tumor, introduces a radiation-specific Nonprogressing category based on interval behavior, and allows cautious use of diffusion-weighted and T2-weighted MRI ancillary features in selected non-radiation cases. These changes are expected to improve earlier detection of clinically relevant residual disease while reducing false-positive viable calls after radiation-based therapies. Successful implementation requires high-quality imaging, treatment-specific reporting, multidisciplinary review, and awareness of current scope limitations, particularly in patients receiving systemic or combined therapies. CRITICAL RELEVANCE STATEMENT: The LI-RADS v2024 update critically assesses prior flaws by establishing separate non-radiation and radiation treatment response algorithms, directly advancing clinical practice by reducing false-positive viable calls and standardizing surveillance after complex therapies. KEY POINTS: Update resolves inconsistency by establishing separate algorithms for non-radiation and radiation therapies, significantly reducing false-positive \"Viable\" calls after radiation treatment. Viability criteria are streamlined to rely on mass-like enhancement and optionally include DWI/T2 ancillary features, improving sensitivity for early recurrence detection. These ancillary features require cautious interpretation to minimize false-positive viable calls. Viable lesions prompt intervention, while Nonprogressing lesions warrant close, standardized 3-month surveillance to confirm definitive local control. Typically, short-interval follow-up is performed at ~3 months, but the optimal stability threshold remains undefined.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13121681/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Understanding AI risks from its characteristics and NMPA regulation perspectives.","authors":"Yuehua Liu, Wenjin Yu","doi":"10.1186/s13244-026-02283-8","DOIUrl":"https://doi.org/10.1186/s13244-026-02283-8","url":null,"abstract":"<p><p>AI is reshaping medical research and healthcare delivery, yet the translation of AI innovations into clinically approved medical devices remains limited. This article explores the critical role of regulatory frameworks in bridging this translational gap, with a focus on the full-lifecycle supervision model proposed by China's National Medical Products Administration (NMPA). We first outline the inherent characteristics and risks of AI that challenge conventional evaluation approaches. By examining a patient-centered AI ecosystem encompassing academia, industry, and regulatory bodies, we highlight the misalignment between preclinical AI research output and the relatively small number of approved AI medical devices (AIMDs). In response, we provide a systematic mapping between AI characteristics and corresponding regulatory control measures, offering a point-to-point interpretation of the NMPA's approach. We argue that effective evaluation must extend beyond performance metrics to include development processes and non-functional attributes such as safety, usability, and explainability. A structured, actionable checklist is proposed to guide the comprehensive assessment of AIMDs throughout their lifecycle. This framework aims to enhance regulatory clarity, promote safe deployment, and ultimately improve public trust and patient outcomes in the era of AI-powered medicine. CRITICAL RELEVANCE STATEMENT: This framework aims to improve regulatory clarity, supporting safe deployment of AI medical devices, enhancing public trust, and ultimately optimizing patient outcomes in AI-powered healthcare. KEY POINTS: Despite the rapid AI advancement, the number of approved AI medical devices remains disproportionately small, revealing a translational gap. The study identifies several intrinsic characteristics of AI that contribute to regulatory complexity and potential safety risks in clinical practice. A point-to-point mapping is established between AI characteristics and regulatory control measures, providing an interpretation of NMPA full-lifecycle supervision model. A detailed actionable checklist is proposed, extending beyond algorithmic performance, thereby promoting transparent and reproducible AIMDs development. The framework provides a policy-relevant pathway for harmonizing AI innovation with regulatory oversight, fostering patient-centered integration of AI into healthcare.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13121643/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasound-based attenuation imaging for assessing steatosis severity in overweight/obese children: a prospective single-center study.","authors":"Tingting Liu, Murong Chen, Longlong Huang, Yanbing Lin, Shasha Huang, Meixi Chen, Zhe Su, Luyao Zhou, Wenying Zhou","doi":"10.1186/s13244-026-02291-8","DOIUrl":"https://doi.org/10.1186/s13244-026-02291-8","url":null,"abstract":"<p><strong>Objectives: </strong>To prospectively evaluate the correlation between the attenuation imaging (ATI) parameter and hepatic steatosis in overweight (OW)/obese (OB) children, and to establish normal ATI reference values from a prospectively enrolled cohort of healthy children.</p><p><strong>Materials and methods: </strong>A total of 653 prospectively enrolled children were categorized into OW, OB, and normal control groups based on body mass index (BMI). Ultrasonographic hepatic steatosis grading and ATI measurements were independently assessed by two radiologists. Hepatic steatosis was graded visually as none, mild, moderate, or severe.</p><p><strong>Results: </strong>The final study cohort consisted of 97 OW, 292 OB, and 264 control children. Median attenuation coefficient obtained with ATI for normal control group, OW group, and OB group were 0.51, 0.54, and 0.64 dB/cm/MHz, respectively. Statistically significant differences in ATI values were observed among all three groups (all p < 0.001). In the combined OW/OB subgroup, ATI values demonstrated a significant weak to strong positive correlation with age, height, weight, BMI, skin-to-liver distance, serum alanine aminotransferase, aspartate aminotransferase, triglycerides, and uric acid (all p < 0.05). Additionally, ATI values increased stepwise with the severity of hepatic steatosis and showed a statistically significant positive correlation with steatosis grade, with higher grades corresponding to greater ATI values (η² = 0.626, p < 0.001).</p><p><strong>Conclusions: </strong>ATI values exhibit a significant stepwise increase across healthy, OW, and OB pediatric cohorts, and correlate with anthropometric/metabolic profiles and ultrasonographic steatosis severity. This evidence positions ATI as a non-invasive tool to grade severity and monitor treatment response in metabolic-associated steatotic liver disease.</p><p><strong>Critical relevance statement: </strong>ATI shows significant increases across pediatric weight groups, correlating with metabolic profiles and steatosis severity, positioning it as a non-invasive metabolic-associated steatotic liver disease assessment tool.</p><p><strong>Key points: </strong>The ATI value increased significantly in a stepwise manner from healthy controls to OW and OB children, confirming its sensitivity to fat-related liver changes. ATI correlates significantly with most metabolic and anthropometric parameters in OW and OB children, suggesting its utility in reflecting metabolic status. ATI values increase progressively with hepatic steatosis severity and show a strong positive correlation with ultrasonographic steatosis grade.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13121645/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-invasive ultrasound assessment of chronic liver disease: current position and future directions for a \"one-stop\" liver ultrasound approach.","authors":"Paul S Sidhu, Mustafa Secil, Dirke-Andre Clevert, Adrian K P Lim, Maciej Piskunowicz, Paolo Ricci, Thomas Fischer, Vladimir Mitkov, Vito Cantisani, Caroline Ewersten","doi":"10.1186/s13244-026-02279-4","DOIUrl":"https://doi.org/10.1186/s13244-026-02279-4","url":null,"abstract":"<p><p>The integration of the multitude of ultrasound techniques into a \"one-stop\" liver clinic model will revolutionize the management of liver diseases. This approach streamlines patient care by providing immediate imaging assessment, facilitating prompt diagnosis, and expediting treatment plans. The traditional ultrasound methods of B-mode imaging and Doppler techniques have been supplemented by the newer techniques of tissue elastography, fat quantification, and contrast-enhanced ultrasound-termed multiparametric ultrasound. The deployment of these techniques to establish in more detail the underlying status of liver disease has been profound. The encompassing ultrasound techniques have allowed the ultrasound practitioner to establish a comprehensive assessment of liver disease, allowing further accurate management, and negating the need for additional, often more expensive, imaging to establish the diagnosis. This paper explores the implementation, benefits, and challenges of ultrasound-based one-stop liver clinics, emphasizing their impact on patient outcomes and healthcare efficiency. A detailed assessment of the techniques and their position in the diagnostic armamentarium is reviewed with a comprehensive overview established. CRITICAL RELEVANCE STATEMENT: Multiparametric liver ultrasound integrating B-mode, Doppler, CEUS, elastography and fat quantification provides a practical, low-cost one-stop pathway for staging chronic liver disease, assessing portal hypertension surrogates and characterizing incidental lesions, thereby speeding up treatment. KEY POINTS: Ultrasound is the first-line imaging investigation for liver disease, with established criteria on B-mode imaging for steatosis and cirrhosis. Multiparametric ultrasound integrates morphology, hemodynamics, fibrosis, steatosis, and lesion assessment. A one-stop liver ultrasound clinic accelerates decisions and reduces additional imaging.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13121678/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative MRI of lipid content for assessing fetal adipose tissue development and brown-to-white fat conversion.","authors":"Shuzhen Ma, Yuchen Liu, Chunran Yang, Hongbo Pu, Yangmei Pu, Zaihang Yin, Min Kang","doi":"10.1186/s13244-026-02288-3","DOIUrl":"https://doi.org/10.1186/s13244-026-02288-3","url":null,"abstract":"<p><strong>Objective: </strong>Brown and white adipose tissues in different fetal regions undergo distinct developmental processes. This study aimed to quantitatively evaluate the fetal adipose tissue development of singleton fetuses.</p><p><strong>Materials and methods: </strong>A total of 78 participants were recruited, of whom 42 participants were included in the statistical analyses. Multi-echo water-fat separation (IDEAL-IQ) was performed, and proton density fat fraction (PDFF) and apparent transverse relaxation rate (R2*) values were measured for multiple anatomical regions, including cheeks, occiput, underjaw, neck, back, thorax, abdomen, and thighs. Correlations with gestational age were analyzed, and analysis of covariance (ANCOVA) was conducted by grouping participants into early (28-31 GW), mid (32-34 GW), and late (35-38 GW) gestational stages.</p><p><strong>Results: </strong>PDFF values in all fetal regions showed significant positive correlations with gestational age (p < 0.05). R2* values demonstrated region-specific patterns: no significant correlation was found for the back, while the cheeks showed a negative correlation; other regions showed significant correlations (p < 0.05). ANCOVA revealed significant differences in PDFF and R2* values across multiple regions among the early, mid, and late gestational groups (p < 0.01), indicating distinct stage- and region-specific characteristics of fetal fat deposition and iron metabolism.</p><p><strong>Conclusion: </strong>This study demonstrated that fetal PDFF increases globally with GW, while regional R2* patterns may reflect aspects of metabolic maturation. A change in R2* around approximately 32 weeks in the fetal cheek region may be indicative of an early transition from brown- to white-like adipose tissue. These findings indicate that IDEAL-IQ could be a useful tool for exploring fetal fat development.</p><p><strong>Critical relevance statement: </strong>This study provides quantitative MRI relevant to fetal brown-to-white fat conversion, suggesting a potential role for imaging markers in characterizing metabolic maturation in vivo. These findings may contribute to the development of noninvasive approaches for assessing fetal metabolic status and developmental variability.</p><p><strong>Key points: </strong>PDFF increased with gestational week, indicating progressive fetal fat maturation. Regional R2* patterns varied with gestational age, with changes in the cheek region around ~32 weeks that may be consistent with a transition from brown- to white-like adipose tissue. Fat development followed a \"cheek → trunk → limb\" sequence, showing spatial heterogeneity.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109482/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combined radiomics, PI-RADS, and clinical model improve significant prostate cancer prediction and guide biopsy decision.","authors":"Andreu Antolin, Richard Mast, Nuria Roson, Javier Arce, Ramon Almodovar, Roger Cortada, Anna Alberti, Berta Miro, Olga Mendez, Almudena Maceda, Esther Serrano, Carmen Pietro-de-la-Lastra, Ana Jimenez-Pastor, Anna Nogué-Infante, Manuel Escobar, Enrique Trilla, Juan Morote","doi":"10.1186/s13244-026-02295-4","DOIUrl":"https://doi.org/10.1186/s13244-026-02295-4","url":null,"abstract":"<p><strong>Objectives: </strong>The aim of this study was to develop and validate an MRI radiomics-based predictive model to discriminate significant prostate cancer (sPCa), compare it with PI-RADS, and determine whether incorporating PI-RADS and other clinical variables improves clinical performance.</p><p><strong>Materials and methods: </strong>A retrospective observational study was conducted using a cohort of 1497 MRI cases from 1395 men to develop the models. For each case, the index-lesion PI-RADS score, systematic ± targeted biopsy results, and six additional clinical variables were collected. Prostate biopsy samples served as the reference standard, defining sPCa as Gleason Grade ≥ 7. Handcrafted radiomic features were extracted from automatically segmented prostate glands. Four machine learning models were developed: (1) Radiomics, (2) PI-RADS, (3) PI-RADS + Radiomics, and (4) PI-RADS + Radiomics + Clinical Variables. Model performance and comparisons were evaluated using the area under the curve (AUC), while clinical utility was assessed through the decision curve analysis plot, Clinical Utility plot, and the number of avoided biopsies.</p><p><strong>Results: </strong>The radiomics model did not perform significantly better than PI-RADS in the validation cohort (AUC 0.838 vs. 0.833, p = 0.874). The combination of radiomics, PI-RADS, and clinical variables achieved the highest performance, with an AUC of 0.891 (95% CI: 0.853-0.930), significantly outperforming the other models (p < 0.05). It also showed the highest specificity (29.41%) and biopsy avoidance rate (18.15%), although the differences were not statistically significant (p = 0.313).</p><p><strong>Conclusions: </strong>Incorporating radiomics and clinical variables into PI-RADS enhances its ability to discriminate sPCa, potentially decreasing false positives and unnecessary biopsies.</p><p><strong>Critical relevance statement: </strong>The incorporation of clinical variables and radiomics into PI-RADS enhances its ability to predict significant prostate cancer, helping mitigate some of PI-RADS's current limitations, such as a significant false-positive rate, and might help reduce unnecessary biopsies.</p><p><strong>Key points: </strong>PI-RADS limitations result in overdiagnosis of indolent prostatic lesions and unnecessary biopsies. Radiomics and clinical variables enhance PI-RADS ability to detect significant prostate cancer. Combined clinical-radiological models reduce false positives and help avoid unnecessary biopsies.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13110268/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Grayscale ultrasound radiomics for characterizing subpleural pulmonary lesions: a multicenter prospective study.","authors":"Jiawei Yi, Xinyu Zhao, Ke Bi, Kaiwen Wu, Runhe Xia, Yuning Luo, Yi Li, Mengjun Shen, Yang Cong, Yi Zhang, Yin Wang","doi":"10.1186/s13244-026-02244-1","DOIUrl":"https://doi.org/10.1186/s13244-026-02244-1","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate a radiomics model based on grayscale ultrasound (GSUS) images for characterizing subpleural pulmonary lesions (SPLs).</p><p><strong>Materials and methods: </strong>In this prospective, multicenter study, 738 patients with CT-confirmed SPLs were enrolled from three institutions and assigned to training (n = 407), internal validation (n = 146), and external validation (n = 185) cohorts. A total of 1320 radiomics features were extracted from both lesion and perilesional regions on GSUS images. Feature selection was performed through intra- and inter-class correlation coefficients (ICCs) analyses, Pearson correlation analyses, and least absolute shrinkage and selection operator (LASSO) regression. Clinical-radiomics fusion models were subsequently constructed by integrating selected radiomics features with key clinical variables using multivariate logistic regression. Model performance was evaluated comprehensively using the area under the receiver-operating characteristic curve (AUC), sensitivity, specificity, F1-score, and additional diagnostic metrics.</p><p><strong>Results: </strong>Five predictive models were constructed based on clinical, radiologic, and radiomics features. Among them, the integrated model combining lesion-based radiomics with clinical variables achieved the best diagnostic performance, with AUCs of 0.884 (95% CI: 0.828-0.940) in the internal validation cohort and 0.848 (95% CI: 0.791-0.904) in the external validation cohort. Calibration and decision curve analyses demonstrated good model calibration and favorable clinical utility. The diagnostic accuracy of the model was comparable to that of experienced lung ultrasound radiologists.</p><p><strong>Conclusions: </strong>The GSUS-based radiomics model effectively differentiates between benign and malignant SPLs, demonstrating strong diagnostic performance and promising clinical applicability.</p><p><strong>Critical relevance statement: </strong>The proposed ultrasound-based radiomics model provides a reproducible, noninvasive decision-support tool for characterizing subpleural pulmonary lesions, offering particular value in patients for whom invasive procedures are unsuitable or in settings where CT or biopsy is not readily available.</p><p><strong>Key points: </strong>Accurate characterization of subpleural pulmonary lesions remains challenging using conventional imaging techniques. The grayscale ultrasound radiomics model achieved accuracy comparable to expert radiologists. This model provides a noninvasive and accessible tool when CT or biopsy is limited.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13110262/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}