Insights into Imaging最新文献

{"title":"Predicting pediatric age from chest X-rays using deep learning: a novel approach.","authors":"Maolin Li, Jiang Zhao, Huanhuan Liu, Biao Jin, Xuee Cui, Dengbin Wang","doi":"10.1186/s13244-025-02068-5","DOIUrl":"10.1186/s13244-025-02068-5","url":null,"abstract":"<p><strong>Objectives: </strong>Accurate age estimation is essential for assessing pediatric developmental stages and for forensics. Conventionally, pediatric age is clinically estimated by bone age through wrist X-rays. However, recent advances in deep learning enable other radiological modalities to serve as a promising complement. This study aims to explore the effectiveness of deep learning for pediatric age estimation using chest X-rays.</p><p><strong>Materials and methods: </strong>We developed a ResNet-based deep neural network model enhanced with Coordinate Attention mechanism to predict pediatric age from chest X-rays. A dataset comprising 128,008 images was retrospectively collected from two large tertiary hospitals in Shanghai. Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) were employed as main evaluation metrics across age groups. Further analysis was conducted using Spearman correlation and heatmap visualizations.</p><p><strong>Results: </strong>The model achieved an MAE of 5.86 months for males and 5.80 months for females on the internal validation set. On the external test set, the MAE was 7.40 months for males and 7.29 months for females. The Spearman correlation coefficient was above 0.98, indicating a strong positive correlation between the predicted and true age. Heatmap analysis revealed the deep learning model mainly focused on the spine, mediastinum, heart and great vessels, with additional attention given to surrounding bones.</p><p><strong>Conclusions: </strong>We successfully constructed a large dataset of pediatric chest X-rays and developed a neural network model integrated with Coordinate Attention for age prediction. Experiments demonstrated the model's robustness and proved that chest X-rays can be effectively utilized for accurate pediatric age estimation.</p><p><strong>Critical relevance statement: </strong>By integrating pediatric chest X-rays with age data using deep learning, we can provide more support for predicting children's age, thereby aiding in the screening of abnormal growth and development in children.</p><p><strong>Key points: </strong>This study explores whether deep learning could leverage chest X-rays for pediatric age prediction. Trained on over 120,000 images, the model shows high accuracy on internal and external validation sets. This method provides a potential complement for traditional bone age assessment and could reduce radiation exposure.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"184"},"PeriodicalIF":4.5,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12374921/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144952778","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":"Development of a lung perfusion automated quantitative model based on dual-energy CT pulmonary angiography in patients with chronic pulmonary thromboembolism.","authors":"Linfeng Xi, Jianping Wang, Anqi Liu, Yifei Ni, Jie Du, Qiang Huang, Yishan Li, Jing Wen, Hongyi Wang, Shuai Zhang, Yunxia Zhang, Zhu Zhang, Dingyi Wang, Wanmu Xie, Qian Gao, Yong Cheng, Zhenguo Zhai, Min Liu","doi":"10.1186/s13244-025-02067-6","DOIUrl":"10.1186/s13244-025-02067-6","url":null,"abstract":"<p><strong>Objective: </strong>To develop PerAIDE, an AI-driven system for automated analysis of pulmonary perfusion blood volume (PBV) using dual-energy computed tomography pulmonary angiography (DE-CTPA) in patients with chronic pulmonary thromboembolism (CPE).</p><p><strong>Materials and methods: </strong>In this prospective observational study, 32 patients with chronic thromboembolic pulmonary disease (CTEPD) and 151 patients with chronic thromboembolic pulmonary hypertension (CTEPH) were enrolled between January 2022 and July 2024. PerAIDE was developed to automatically quantify three distinct perfusion patterns-normal, reduced, and defective-on DE-CTPA images. Two radiologists independently assessed PBV scores. Follow-up imaging was conducted 3 months after balloon pulmonary angioplasty (BPA).</p><p><strong>Results: </strong>PerAIDE demonstrated high agreement with the radiologists (intraclass correlation coefficient = 0.778) and reduced analysis time significantly (31 ± 3 s vs. 15 ± 4 min, p < 0.001). CTEPH patients had greater perfusion defects than CTEPD (0.35 vs. 0.29, p < 0.001), while reduced perfusion was more prevalent in CTEPD (0.36 vs. 0.30, p < 0.001). Perfusion defects correlated positively with pulmonary vascular resistance (ρ = 0.534) and mean pulmonary artery pressure (ρ = 0.482), and negatively with oxygenation index (ρ = -0.441). PerAIDE effectively differentiated CTEPH from CTEPD (AUC = 0.809, 95% CI: 0.745-0.863). At the 3-month post-BPA, a significant reduction in perfusion defects was observed (0.36 vs. 0.33, p < 0.01).</p><p><strong>Conclusion: </strong>CTEPD and CTEPH exhibit distinct perfusion phenotypes on DE-CTPA. PerAIDE reliably quantifies perfusion abnormalities and correlates strongly with clinical and hemodynamic markers of CPE severity.</p><p><strong>Trial registration: </strong>ClinicalTrials.gov, NCT06526468. Registered 28 August 2024- Retrospectively registered, https://clinicaltrials.gov/study/NCT06526468?cond=NCT06526468&rank=1 .</p><p><strong>Critical relevance statement: </strong>PerAIDE is a dual-energy computed tomography pulmonary angiography (DE-CTPA) AI-driven system that rapidly and accurately assesses perfusion blood volume in patients with chronic pulmonary thromboembolism, effectively distinguishing between CTEPD and CTEPH phenotypes and correlating with disease severity and therapeutic response.</p><p><strong>Key points: </strong>Right heart catheterization for definitive diagnosis of chronic pulmonary thromboembolism (CPE) is invasive. PerAIDE-based perfusion defects correlated with disease severity to aid CPE-treatment assessment. CTEPH demonstrates severe perfusion defects, while CTEPD displays predominantly reduced perfusion. PerAIDE employs a U-Net-based adaptive threshold method, which achieves alignment with and faster processing relative to manual evaluation.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"182"},"PeriodicalIF":4.5,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12361028/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144873019","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":"Controversies in contrast-enhanced ultrasound (CEUS): pregnancy, paediatric, abdominal trauma, complex renal cysts, and endovascular aortic repair follow-up.","authors":"Paul S Sidhu, Dirk Andre Clevert, Annamaria Deganello, Maciej Piskunowicz, Vito Cantisani, Thomas Fischer","doi":"10.1186/s13244-025-02055-w","DOIUrl":"10.1186/s13244-025-02055-w","url":null,"abstract":"<p><p>The use of contrast-enhanced ultrasound (CEUS) in clinical practice is theoretically limited to the licensed indications: focal liver lesions, breast, peripheral arterial system, and the heart. In reality, there has been a continuous expansion of the deployment of CEUS examinations to many other organs and body parts over the last 20 years. Many of these applications are a natural extension of the diagnostic capabilities of the CEUS examination, used to achieve a better imaging outcome. These applications have been supported by guidelines issued by scientific societies, detailing the application, accuracy, and safety of the clinical performance. Nevertheless, there are some areas in which it remains more difficult to establish the use of CEUS in the diagnostic pathway. In the pregnant patient, CEUS is an ideal examination-a natural extension of B-mode ultrasound, avoiding ionising radiation and iodinated contrast. The contrast agents used in ultrasound do not cross the placental barrier. Ultrasound in the paediatric patient is used widely, and extending this to a CEUS examination improves diagnostic capabilities, avoiding less child-friendly imaging techniques. The parent can be in the room at the time of the ultrasound examination. Other aspects of CEUS usage are hampered by the lack of physician engagement despite the proven advantages of the technique, the reduction in the morbidity associated with CT and MR imaging, particularly the contrast agents used in these modalities. Complex renal cyst classification, follow-up of blunt abdominal trauma and the surveillance following placement of an aortic stent graft are all areas of potential benefit to the diagnosis. All these are better imaged on a CEUS examination. Furthermore, cost savings can be achieved using CEUS, mostly by alleviating downstream costs of CT and MR imaging. CRITICAL RELEVANCE STATEMENT: CEUS use outside licensed uses is becoming established, driven by the unique ability to achieve diagnostic standards safely and with patient acceptability, pushing the boundaries in areas of abdominal trauma, pregnancy, paediatrics, aortic implants, and complex renal cysts. KEY POINTS: CEUS has a narrow range of licensed applications in medical imaging, but is used widely. An exclusively intravascular agent allows assessment of vascular flow at the capillary level. CEUS is extremely safe and can be used in many areas that require repeated high-resolution imaging.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"179"},"PeriodicalIF":4.5,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12356814/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855155","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":"Prognostic and predictive imaging markers of hepatocellular carcinoma: a pictorial essay.","authors":"Claudia Deyirmendjian, Banmeet Padda, Kathryn J Fowler, Victoria Chernyak, Claude B Sirlin, Hanyu Jiang, Kim-Nhien Vu, Joseph R Dadour, Jessica Murphy-Lavallée, Jean-Sébastien Billiard, Damien Olivié, Bich N Nguyen, An Tang","doi":"10.1186/s13244-025-02058-7","DOIUrl":"10.1186/s13244-025-02058-7","url":null,"abstract":"<p><p>Hepatocellular carcinoma (HCC) encompasses a wide array of histopathologic and genetic features that can be broadly categorized as proliferative or non-proliferative HCC to reflect tumor aggressiveness. However, accurately characterizing tumor behavior remains challenging due to the biologic heterogeneity of HCC and limited access to tissue samples. Currently, imaging is used for the diagnosis of HCC using the Liver Imaging Reporting and Data System (LI-RADS) without histologic confirmation in most cases. Emerging data suggest that imaging can provide clinical insight beyond diagnosis and predict patient outcomes by identifying key prognostic features, including those not yet integrated in LI-RADS. Certain CT and MRI features correlate with proliferative and non-proliferative HCC, and may yield prognostic information. Imaging findings such as tumor size, multifocality, and low apparent diffusion coefficient (ADC) have also been associated with microvascular invasion-an independent marker of poor prognosis. Growing data support the role of imaging in predicting treatment responsiveness before therapy initiation, which may influence the selection of a therapeutic agent. The radiologist can offer key clinical information by understanding and describing the prognostic and predictive features in HCC imaging. CRITICAL RELEVANCE STATEMENT: This study provides radiologists with a comprehensive summary of imaging findings associated with HCC prognosis, treatment responsiveness, and microvascular invasion. KEY POINTS: Hepatocellular carcinoma (HCC) is a heterogeneous cancer leading to challenges in diagnosis and management. Tumors can exhibit imaging features associated with proliferative or non-proliferative HCC. Key imaging features can help predict tumor aggressiveness and treatment responsiveness before the therapy is applied. Further research leveraging molecular data and applying machine learning models can improve our understanding of HCC prognostication.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"181"},"PeriodicalIF":4.5,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12356813/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855158","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":"Subspecialisation recognition in European Radiology-follow-up survey by the Accreditation Council in Imaging and European Society of Radiology National Societies Committee.","authors":"Miraude Adriaensen, Paolo Ricci, Christian Loewe, Helmut Prosch, Mitja Rupreht","doi":"10.1186/s13244-025-02054-x","DOIUrl":"10.1186/s13244-025-02054-x","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the status of radiology subspecialisation recognition across Europe, targeting European Society of Radiology (ESR) National Societies.</p><p><strong>Methods: </strong>A questionnaire was distributed to members of the ESR National Societies Committee regarding the recognition of radiology subspecialties in their respective countries.</p><p><strong>Results: </strong>Responses were received from 37 out of 47 countries (78%). Radiology subspecialties are recognised in 25 countries, whereas in 12 countries, they are not. Among 12 countries without recognised subspecialisations, 9 expressed a desire for future recognition. There are large variations between countries regarding the number of officially recognised subspecialities, ranging from 0 to 12.</p><p><strong>Conclusion: </strong>Based on responses from ESR National Societies Committee members, radiology subspecialties are recognised in 25 countries, while 12 countries do not have formal recognition. The majority of countries without recognised subspecialisations express interest in having them acknowledged in the future.</p><p><strong>Critical relevance statement: </strong>This follow-up survey among ESR National Societies presents the recognition status of radiology subspecialisations in Europe. Among the 37 responding countries, there are significant variations in the number of officially recognised subspecialties, ranging from 0 to 12.</p><p><strong>Key points: </strong>Among the 37 ESR National Societies responding countries, between 0 and 12 out of 13 radiology subspecialties are recognised. No country recognises all subspecialties. The majority of countries without recognised subspecialisations would like them to be acknowledged.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"180"},"PeriodicalIF":4.5,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12356789/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855159","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":"Paraspinal muscles and gluteus medius fat infiltration are both associated with lumbar disc herniation.","authors":"Jianping Wang, Zhenhua Zhao, Ding Liang, Xiao Xu, Dingbo Shu","doi":"10.1186/s13244-025-02064-9","DOIUrl":"10.1186/s13244-025-02064-9","url":null,"abstract":"<p><strong>Objectives: </strong>To quantitatively assess the degeneration of paraspinal and pelvic muscles in patients with lumbar disc herniation (LDH) using MRI q-Dixon and to explore their potential association with LDH.</p><p><strong>Materials and methods: </strong>The cross-sectional area (CSA) and proton density fat fraction (PDFF) of the multifidus (MF), erector spinae (ES), psoas major (PM), and gluteus medius (GM), as well as the vertebral bone marrow fat fraction (BMFF), lumbar lordosis (LL), and sacral slope (SS), were measured in both LDH and control groups.</p><p><strong>Results: </strong>A total of 85 LDH patients and 48 controls were included. No significant differences in CSA were observed between groups (all p > 0.05). However, PDFF values were significantly higher in the LDH group for all muscles compared to controls (all p < 0.05). After adjustment, the PDFF differences in MF_L4/5, ES_L4/5, PM_L3/4, and PM_L4/5 remained statistically significant (p < 0.05). Although bilateral muscle asymmetry was observed in several muscles, these differences were no longer significant after adjustment (p > 0.05). No significant differences in VBFF, LL, or SS were found (all p > 0.05).</p><p><strong>Conclusions: </strong>LDH patients exhibit increased fat infiltration in the MF, ES, PM, and GM compared to controls, suggesting a potential association between pelvic and paraspinal muscle degeneration and LDH.</p><p><strong>Critical relevance statement: </strong>The MRI q-Dixon technique effectively and noninvasively detects early degeneration of the paraspinal muscles and GM, indicating their potential association with LDH and enabling more targeted rehabilitation strategies.</p><p><strong>Key points: </strong>Spine and muscle changes affect LDH, but their relationship remains unclear. Fat infiltration is more sensitive than CSA for detecting muscle degeneration. LDH patients exhibit greater paraspinal muscle and GM degeneration.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"176"},"PeriodicalIF":4.5,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12354410/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855156","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":"Computed tomography radiomics to predict microsatellite instability status and immunotherapy response in gastric cancer.","authors":"Zhou Li, Zixuan Ding, Yongping Lian, Yongqing Liu, Lei Wang, Pengbo Hu, Fangyuan Zhang, Yan Luo, Hong Qiu","doi":"10.1186/s13244-025-02050-1","DOIUrl":"10.1186/s13244-025-02050-1","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate a CT radiomics model for predicting microsatellite instability (MSI) status in preoperative gastric cancer (GC) patients and to explore the underlying immune infiltration pattern of the radiomics model.</p><p><strong>Materials and methods: </strong>This study used three retrospective datasets from Tongji Hospital (n = 304, training set), Xiangyang Central Hospital (n = 48, external testing set 1) and public datasets from The Cancer Imaging Archive (TCIA) (n = 43, external testing set 2). The preoperative contrast-enhanced CT images of GC were evaluated. Radiomics features were extracted and selected to construct the radiomics model in the training set, and further validated in the other two external testing sets. The outcome cohort, including 68 advanced unresectable GC patients receiving immunotherapy, was used to assess the predictive value of the radiomics model for treatment response and outcomes. We analyzed RNA-sequencing data from TCIA to investigate the underlying genomics characterization and immune infiltration spectrum of the radiomics model.</p><p><strong>Results: </strong>Four radiomic features were ultimately selected to develop the radiomics model. The model demonstrated good predictive performance for MSI status, achieving AUCs of 0.952, 0.835, and 0.879 in the training set and the two external testing sets, respectively. Radiomics scores (Radscores) was an independent predictor for PFS in the outcome cohort (HR: 0.145; 95% CI: 0.032-0.657; p = 0.012). Radscores were positively correlated with CD8+ T cells (R = 0.74, p = 0.013) and negatively related to M2-type macrophages (R = -0.67, p = 0.028).</p><p><strong>Conclusion: </strong>Our CT radiomics model could effectively predict MSI status and immunotherapy outcomes in GC patients therefore, may act as a potential noninvasive tool for personalized treatment decisions.</p><p><strong>Critical relevance statement: </strong>Our study develops a noninvasive biomarker based on readily available imaging to identify gastric cancer patients who may benefit from immunotherapy. It also reveals biological meanings of the radiomics biomarker, promoting further research into interpretability and clinical application of radiomics.</p><p><strong>Key points: </strong>A CT-based radiomics model was constructed to noninvasively predict gastric cancer (GC) microsatellite instability status. This immune-related radiomics model can effectively predict immunotherapy outcomes in GC. This noninvasive method can serve as a supplement for treatment decisions.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"177"},"PeriodicalIF":4.5,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12354409/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855154","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":"Preoperative ternary classification using DCE-MRI radiomics and machine learning for HCC, ICC, and HIPT.","authors":"Peng Xie, Zhong-Jian Liao, Lu Xie, Junyuan Zhong, Xiaodong Zhang, Wei Yuan, Yujin Yin, Tianxian Chen, Huizhen Lv, Xinglin Wen, Xiaochun Wang, Ling Zhang","doi":"10.1186/s13244-025-02062-x","DOIUrl":"10.1186/s13244-025-02062-x","url":null,"abstract":"<p><strong>Objectives: </strong>This study develops a machine learning model using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics and clinical data to preoperatively differentiate hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and hepatic inflammatory pseudotumor (HIPT), addressing limitations of conventional diagnostics.</p><p><strong>Materials and methods: </strong>This retrospective study included 280 patients (HCC = 160, ICC = 80, HIPT = 40) who underwent DCE-MRI from 2008 to 2024 at three hospitals. Radiomics features and clinical data were extracted and analyzed using LASSO regression and machine learning algorithms (Logistic Regression, Random Forest, and Extreme Gradient Boosting), with class weighting (HCC:ICC:HIPT = 1:2:4) to address class imbalance. Models were compared using macro-average Area Under the Curve (AUC), accuracy, recall, and precision.</p><p><strong>Results: </strong>The fusion model, integrating radiomics and clinical features, achieved an AUC of 0.933 (95% CI: 0.91-0.95) and 84.5% accuracy, outperforming radiomics-only (AUC = 0.856, 72.6%) and clinical-only (AUC = 0.795, 66.7%) models (p < 0.05). Rim enhancement is a key model feature for distinguishing HCC from ICC and HIPT, while hepatic lobe atrophy distinguishes ICC and HIPT from HCC.</p><p><strong>Conclusion: </strong>This study developed a novel preoperative imaging-based model to differentiate HCC, ICC, and HIPT. The fusion model performed exceptionally well, demonstrating superior accuracy in ICC identification, significantly outperforming traditional diagnostic methods (e.g., radiology and biomarkers) and single-modality machine learning models (p < 0.05). This noninvasive approach enhances diagnostic precision and supports personalized treatment planning in liver disease management.</p><p><strong>Critical relevance statement: </strong>This study develops a novel preoperative imaging-based machine learning model to differentiate hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and hepatic inflammatory pseudotumor (HIPT), improving diagnostic accuracy and advancing personalized treatment strategies in clinical radiology.</p><p><strong>Key points: </strong>A machine learning model integrates DCE-MRI radiomics and clinical data for liver lesion differentiation. The fusion model outperforms single-modality models with 0.933 AUC and 84.5% accuracy. This model provides a noninvasive, reliable tool for personalized liver disease diagnosis and treatment planning.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"178"},"PeriodicalIF":4.5,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12354431/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855157","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":"Explanation and Elaboration with Examples for METRICS (METRICS-E3): an initiative from the EuSoMII Radiomics Auditing Group.","authors":"Burak Kocak, Angela Ammirabile, Ilaria Ambrosini, Tugba Akinci D'Antonoli, Alessandra Borgheresi, Armando Ugo Cavallo, Roberto Cannella, Gennaro D'Anna, Oliver Díaz, Fabio M Doniselli, Salvatore Claudio Fanni, Samuele Ghezzo, Kevin B W Groot Lipman, Michail E Klontzas, Andrea Ponsiglione, Arnaldo Stanzione, Matthaios Triantafyllou, Federica Vernuccio, Renato Cuocolo","doi":"10.1186/s13244-025-02061-y","DOIUrl":"10.1186/s13244-025-02061-y","url":null,"abstract":"<p><p>Radiomics research has been hindered by inconsistent and often poor methodological quality, limiting its potential for clinical translation. To address this challenge, the METhodological RadiomICs Score (METRICS) was recently introduced as a tool for systematically assessing study rigor. However, its effective application requires clearer guidance. The METRICS-E3 (Explanation and Elaboration with Examples) resource was developed by the European Society of Medical Imaging Informatics-Radiomics Auditing Group in response. This international initiative provides comprehensive support for users by offering detailed rationales, interpretive guidance, scoring recommendations, and illustrative examples for each METRICS item and condition. Each criterion includes positive examples from peer-reviewed, open-access studies and hypothetical negative examples. In total, the finalized METRICS-E3 includes over 200 examples. The complete resource is publicly available through an interactive website. CRITICAL RELEVANCE STATEMENT: METRICS-E3 offers deeper insights into each METRICS item and condition, providing concrete examples with accompanying commentary and recommendations to enhance the evaluation of methodological quality in radiomics research. KEY POINTS: As a complementary initiative to METRICS, METRICS-E3 is intended to support stakeholders in evaluating the methodological aspects of radiomics studies. In METRICS-E3, each METRICS item and condition is supplemented with interpretive guidance, positive literature-based examples, hypothetical negative examples, and scoring recommendations. The complete METRICS-E3 explanation and elaboration resource is accessible at its interactive website.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"175"},"PeriodicalIF":4.5,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351001/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144834973","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":"Bone reporting and data system on CT (Bone-RADS-CT): a validation study by four readers on 328 cases from three local and two public databases.","authors":"Yue Xing, Defang Ding, Shun Dai, Yangfan Hu, Xianwei Liu, Liangjing Lyu, Guangcheng Zhang, Shiqi Mao, Qian Yin, Junjie Lu, Jiarui Yang, Yang Song, Huan Zhang, Chengzhou Li, Weiwu Yao, Jingyu Zhong","doi":"10.1186/s13244-025-02057-8","DOIUrl":"10.1186/s13244-025-02057-8","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the reproducibility and effectiveness of the bone reporting and data system on CT (Bone-RADS-CT) for incidental solitary bone lesions in adults.</p><p><strong>Materials and methods: </strong>We retrospectively included 328 CT cases from three local and two public databases, respectively. All the cases were histopathologically or clinically confirmed bone lesions, \"do not touch\" lesions with typical appearance, and remained stable for at least 2 years. Each lesion with gender, age, and clinical history was categorized according to the Bone-RADS algorithm by two musculoskeletal radiologists and two non-musculoskeletal radiologists. The Bone-RADS categories were as follows: Bone-RADS-1, likely benign, leave alone; Bone-RADS-2, incomplete assessed on imaging, perform different imaging modality; Bone-RADS-3, intermediate, perform follow-up imaging; Bone-RADS-4, suspicious for malignancy or need for treatment, biopsy and/or oncologic referral. Inter-reader agreement was evaluated. The diagnostic performance of the Bone-RADS-CT for distinguishing positive cases (intermediate or malignant lesions or osteomyelitis) from negative cases (benign lesions), were measured, using histopathology results, clinical diagnosis, or follow-up as a standard reference.</p><p><strong>Results: </strong>There were 223 positive cases and 105 negative cases, respectively. The overall inter-reader agreement between two musculoskeletal and two non-musculoskeletal radiologists were both moderate (weighted kappa 0.553 and 0.403). The diagnostic performance for identifying intermediate or malignant lesions or osteomyelitis ranged according to radiologists with sensitivities of 88.8% to 94.6%, specificities of 42.9% to 71.1%, and accuracies of 78.0% to 86.6%.</p><p><strong>Conclusion: </strong>Bone-RADS-CT is effective for identifying bone lesions that need further treatment, but is only moderately reliable for readers of different specialties and experience.</p><p><strong>Critical relevance statement: </strong>Bone-RADS-CT has been demonstrated to be a reliable algorithm for non-musculoskeletal radiologists and an effective tool for identifying the \"need for treatment\" incidental solitary bone lesions in adults, but still needs improvement in the rating method and category definition.</p><p><strong>Key points: </strong>Bone-RADS-CT has been demonstrated to be reliable and accurate when rated by musculoskeletal radiologists. Bone-RADS-CT achieved moderate agreement for musculoskeletal and non-musculoskeletal radiologists. Bone-RADS-CT presented high sensitivities but low specificities for identifying \"need for treatment\" bone lesions.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"174"},"PeriodicalIF":4.5,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12344047/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144821310","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}