Insights into Imaging最新文献

{"title":"Swedish national recommendations for MR safety 2026.","authors":"Boel Hansson, Anton Glans, Love Engström Nordin, Karin Åberg, Titti Owman, Cecilia Petersen, Annica Sandberg, Viktor Darhult, Annika Kits, Isabella M Björkman-Burtscher, Johan Kihlberg, Peter Lundberg","doi":"10.1186/s13244-026-02270-z","DOIUrl":"https://doi.org/10.1186/s13244-026-02270-z","url":null,"abstract":"<p><p>This document outlines the Swedish national recommendations for MR safety, developed by the Swedish Alliance for MR Safety (SAMS). Grounded in international guidelines, Swedish legislation, and scientific evidence, these recommendations have been tailored to the Swedish healthcare context while remaining broadly applicable across European systems. The guidelines emphasize universal safety principles in MR practice, including risk prevention, equipment safety, and organizational integration. SAMS adopts a comprehensive, life-cycle approach to MR safety-from planning to decommissioning-addressing clinical, research, and veterinary use. By sharing this English translation, SAMS aims to support international collaboration and provide a foundational model for countries developing or updating their MR safety frameworks, promoting harmonization and improved safety standards across Europe. CRITICAL RELEVANCE STATEMENT: This article presents and critically explores key MR safety issues through Sweden's national MR safety recommendations, illustrating how their evidence-based, life-cycle approach can guide harmonized and high-standard MR safety practices across healthcare systems in Europe. KEY POINTS: The document presents national MR safety guidelines, based on international standards, Swedish law, and scientific evidence. The guidelines cover all stages of MR use, with a focus on risk prevention, equipment safety, and organizational integration. Swedish Alliance for MR Safety (SAMS) supports international cooperation and offers a model for enhancing safety standards across Europe.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109526/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770601","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":"Deep-learning computer-aided detection and classification of prostate lesions on biparametric MRI: comparison with expert readers.","authors":"Deepak Jain, Francisco Restrepo, Kazuya Yasokawa, Efe Ozkaya, Mickael Tordjman, Marc Berns, Alon Slutzky, Julian Franko, Octavia Bane, Heinrich von Busch, Robert Grimm, Ashutosh K Tewari, Sara Lewis, Bachir Taouli","doi":"10.1186/s13244-026-02261-0","DOIUrl":"https://doi.org/10.1186/s13244-026-02261-0","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To assess the performance of a deep learning-based computer-aided detection (DL-CAD) algorithm for prostate lesion detection and classification on biparametric (bp)MRI.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Materials and methods: &lt;/strong&gt;This retrospective, single-center study included men undergoing 3-T MRI of the prostate for suspected prostate cancer (PCa) between July and September of 2022. Using the radiology report as the reference standard, detection performance for high-risk lesions (defined as PI-RADS ≥ 3, 4, 5) by the DL-CAD was evaluated per-patient using sensitivity, specificity, PPV, NPV and AUC; and per-lesion using sensitivity and PPV. Kappa statistics was used to assess per-patient detection and per-lesion classification of PI-RADS ≥ 3 lesions. Clinical and imaging factors associated with discordance between DL-CAD and radiology reports were assessed using Mann-Whitney, Chi-square, and Fisher's exact tests.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;442 adult males (mean age 65 ± 9 years) were assessed. Per-patient sensitivity, specificity, PPV, and NPV for detection of PI-RADS ≥ 4 and 5 lesions were 65.3%/81.2%/62.7%/82.9% and 82.1%/93.8%/65.7%/97.3%, respectively. Per-patient performance for identifying PI-RADS ≥ 3/4/5 lesions was fair-to-excellent: AUC = 0.67 (0.62-0.71)/0.75 (0.71-0.80)/0.92 (0.89-0.96). For detection of PI-RADS ≥ 4 and 5, per-lesion sensitivity was 60.4% and 78.3%, while PPV was 55.0% and 60.3%. Per-patient agreement between DL-CAD and the reference increased with higher PI-RADS scores (kappa = 0.26 (0.18-0.35)/0.46 (0.37-0.55)/0.68 (0.59-0.78)). Agreement on classification of PI-RADS ≥ 3 lesions was moderate (kappa = 0.56 (0.45-0.68)).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;A pre-trained DL-CAD showed good-to-excellent per-patient performance for the detection of PI-RADS ≥ 4 lesions and moderate performance of PI-RADS ≥ 3 lesion classification. Future prospective studies validating the DL algorithm with histopathologic correlation are warranted.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Critical relevance statement: &lt;/strong&gt;A deep learning computer-aided detection (DL-CAD) algorithm showed good-to-excellent per-patient performance for detection of PI-RADS ≥ 4 lesions, moderate performance of PI-RADS ≥ 3 lesion classification and high negative predictive value, which can be applied in the clinic with knowledge of its limitations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Key points: &lt;/strong&gt;Clinical validation of deep learning computer-aided detection (DL-CAD) models for the detection and classification of prostate lesions on MRI is urgently needed. A pre-trained DL-CAD algorithm showed fair-to-excellent per-patient performance for detection of prostate lesions on biparametric MRI, with moderate performance for PI-RADS ≥ 3 lesion classification. Identification of false negatives and false positives of prostate cancer detection DL-CAD algorithms is important for future improvement and clinical deployment. A DL-CAD-based prostate cancer detection algorithm with high NPV ","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13103022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770480","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":"Diagnostic performance of native T1 in grading histologically proven myocardial glycosphingolipid accumulation in Fabry disease.","authors":"Nicola Galea, Livia Marchitelli, Giacomo Pambianchi, Lorenzo Dominici, Luca Conia, Maria Alfarano, Romina Verardo, Marco Francone, Cristina Chimenti, Andrea Frustaci, Carlo Catalano","doi":"10.1186/s13244-026-02262-z","DOIUrl":"https://doi.org/10.1186/s13244-026-02262-z","url":null,"abstract":"<p><strong>Objective: </strong>Fabry disease cardiomyopathy (FD-CM) is a genetic disorder induced by glycosphingolipid accumulation (GSL-A) in cardiac cells, resulting in left ventricular hypertrophy (LVH) and contractile impairment. Native T1 (nT1) mapping by cardiac magnetic resonance (CMR) effectively detects myocardial GSL-A in patients with FD-CM. However, the association between nT1 values and GSL-A severity has not been histologically confirmed. This study aims to assess the capability of nT1 to classify GSL-A burden, using endomyocardial biopsy (EMB) as the reference, and to identify the best matching site for nT1 measurement.</p><p><strong>Materials and methods: </strong>Forty FD-CM subjects undergone CMR and EMB were classified into 4 groups according to GSL-A severity. CMRs were performed using a comprehensive protocol including nT1 and T2 mapping sequences. Global, per-plane, and septal segmental myocardial nT1 and T2 values (excluding late gadolinium enhanced areas) were compared among groups. Correlations between nT1 values, GSL-A and LVH were explored. Statistical analyses used distribution-appropriate tests, including group comparisons, correlation, and ROC analyses.</p><p><strong>Results: </strong>Significant nT1 differences emerged among groups at all measurement sites, with significant negative correlations with GSL-A, particularly in AHA segment 9, the mid-interventricular septum region of interest and midventricular plane (r = -0.741; -0.716; -0.715; p < 0.001). nT1 measured at these locations demonstrated excellent diagnostic accuracy in identifying severe GSL-A (area under the curve: 0.860, 0.903, and 0.895, respectively).</p><p><strong>Conclusion: </strong>Myocardial nT1 values strongly correlate with GSL-A, with midventricular septum measurements providing the best agreement. If supported by further studies, CMR could act as a noninvasive tool for disease staging and risk stratification, helping to identify patients in advanced, higher-risk stages.</p><p><strong>Critical relevance statement: </strong>Native T1 mapping correlates closely with histological glycosphingolipid accumulation in Fabry cardiomyopathy. This noninvasive biomarker may support early disease stratification and guide timely therapeutic intervention.</p><p><strong>Key points: </strong>Native T1 values are a valid biomarker of glycosphingolipid accumulation in myocardial tissue and correlate with accumulation degree. Midventricular interventricular septum is the preferred site for nT1 measurement, showing the best agreement with glycosphingolipid accumulation at endomyocardial biopsy. The use of native T1 in the setting of suspected cardiac Fabry disease will help to stratify disease severity, without the intrinsic risk of endomyocardial biopsy.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13103178/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770528","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":"Comparative evaluation of large language models for generating CAD-RADS 2.0-compliant diagnostic conclusions in cardiac CT reports.","authors":"Giovanni Lorusso, Giorgio Ruscino, Alessia Spitaleri, Chiara Morelli, Sara Greco, Ilaria Villanova, Nicola Maria Lucarelli, Michele Mariano, Amato Antonio Stabile Ianora, Nicola Maggialetti","doi":"10.1186/s13244-026-02285-6","DOIUrl":"https://doi.org/10.1186/s13244-026-02285-6","url":null,"abstract":"<p><strong>Objectives: </strong>Coronary computed tomography angiography (CCTA) has become a cornerstone in non-invasive CAD diagnosis and risk stratification. To standardize reporting and improve clinical decision-making, the CAD-RADS 2.0 system was introduced. This study evaluates the performance of four LLMs, GPT-4o, Gemini 2.0 Flash, DeepSeek V, and Copilot in generating CAD-RADS 2.0-compliant conclusions from standardized CCTA reports.</p><p><strong>Materials and methods: </strong>A total of 196 anonymized CCTA reports were retrospectively analyzed. Each LLM was prompted to provide CAD-RADS 2.0 classifications and follow-up recommendations. Ground truth labels were assigned by a senior radiologist. Performance metrics (accuracy, precision, recall, F1-score), execution times, and agreement (Cohen's kappa) with expert interpretation were computed. Interobserver agreement between junior and senior radiologists was also assessed.</p><p><strong>Results: </strong>LLMs demonstrated good-to-excellent agreement with expert classifications: DeepSeek V (κ = 0.771), Copilot (κ = 0.761), GPT-4o (κ = 0.759), and Gemini 2.0 Flash (κ = 0.634). DeepSeek V achieved the highest accuracy (91.83%). Intra-model consistency was perfect (κ = 1). However, LLMs failed to assign CAD-RADS modifiers. ChatGPT-4o provided the most accurate follow-up recommendations (71.94%). All LLMs outperformed radiologists in execution time (3-9 s vs. 15-20 s; p < 0.05).</p><p><strong>Conclusions: </strong>Generic LLMs demonstrate promising performance in automating CAD-RADS 2.0 classification from CCTA reports. However, limitations in modifier assignment and recommendation accuracy highlight areas for refinement before clinical integration.</p><p><strong>Critical relevance statement: </strong>This study explores the potential of large language models to facilitate standardized CAD-RADS 2.0 reporting from coronary CT angiography, highlighting a possible avenue to support workflow efficiency and clinical decision-making in non-invasive coronary artery disease evaluation.</p><p><strong>Key points: </strong>LLMs demonstrated strong potential in automating CAD-RADS 2.0-compliant structured reporting for CCTA. LLMs could significantly enhance efficiency in radiological reporting. LLMs need further optimization before clinical integration.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13103109/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770464","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":"Median nerve swelling in RA patients: an 8-year longitudinal MRI-based study.","authors":"Su Wu, Alex Wing Hung Ng, James Francis Griffith, Fan Xiao, Miaoru Zhang, Lai-Shan Tam","doi":"10.1186/s13244-026-02267-8","DOIUrl":"https://doi.org/10.1186/s13244-026-02267-8","url":null,"abstract":"<p><strong>Objectives: </strong>Rheumatoid arthritis (RA) patients are prone to carpal tunnel syndrome (CTS). MRI can accurately detect median nerve swelling associated with CTS as well as evaluate synovial inflammation and structural damage. A median nerve cross-sectional area (CSA) of > 15 mm² is the best MRI diagnostic criterion of CTS. This study investigates the prevalence of median nerve swelling in early RA patients, its relationship to inflammation and structural damage, and long-term outcome following treatment.</p><p><strong>Materials and methods: </strong>Retrospective study of early RA patients who underwent clinical, serology, radiography, and dynamic contrast-enhanced MRI of the wrist at baseline, year 1, and year 8. Median nerve cross-sectional area (CSA), median nerve enhancement and perfusion, retinacular bowing, synovial inflammation, structural damage and functional impairment were assessed.</p><p><strong>Results: </strong>81 early RA patients (age: 54 ± 13 years, F/M: 64/17) were studied. Undue median nerve swelling was present in 25 (31%) at baseline and 37 (46%) of 81 ERA patients at year 8. Undue median nerve swelling was moderately (r = 0.634) related to tenosynovitis volume at baseline but was otherwise not related to synovitis and structural damage at either baseline, year 1, or year 8. Median nerve swelling did not regress long-term. At year 8, CTS symptoms were present in about half of RA patients and were not related to median nerve swelling. Functional impairment at year 8 was more frequent in patients with median nerve swelling.</p><p><strong>Conclusion: </strong>Undue median nerve swelling is common in RA patients, is not related to synovitis or structural damage, does not regress with treatment, and is linked to long-term functional impairment.</p><p><strong>Critical relevance statement: </strong>Median nerve swelling, indicative of carpal tunnel syndrome, is common in RA patients, does not regress with reduction in synovitis or tenosynovitis after treatment and is associated with more severe and more frequent systemic functional impairment.</p><p><strong>Key points: </strong>Almost one-third of RA patients fulfilled MRI criteria for carpal tunnel syndrome (CTS) diagnosis at baseline, increasing to almost one-half of patients at year 8. Long-term median nerve swelling is not related to tenosynovitis, synovitis or structural damage. Functional impairment was over twice as common in patients with undue median nerve swelling than those without undue median nerve swelling.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13103215/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770640","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":"Psychological distress links to magnetic resonance enterography abnormalities in Crohn's disease.","authors":"Ruonan Zhang, Yaoqi Ke, Huasong Cai, Yangdi Wang, Lili Huang, Xiaodi Shen, Qingzhu Zheng, Luyao Wu, Qiaochu Zhao, Weikai Zheng, Dailin Li, Ren Mao, Zhoulei Li, Shaochun Lin, Xuehua Li, Zhenpeng Peng","doi":"10.1186/s13244-026-02273-w","DOIUrl":"https://doi.org/10.1186/s13244-026-02273-w","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objectives: &lt;/strong&gt;Emerging evidence underscores psychological distress as a potential modifier of clinical outcomes in Crohn's disease (CD), though its etiological basis remains undetermined. This study investigated associations between psychological distress and intestinal abnormalities identified by magnetic resonance enterography (MRE) through serum neurotransmitter analysis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Materials and methods: &lt;/strong&gt;In this prospective study, 105 patients with CD and 46 healthy controls (HCs) completed the State-Trait Anxiety Inventory (including the STAI-Trait and State scores), the Beck Depression Inventory, and the Perceived Stress Scale to assess psychological distress. CD patients underwent MRE and serum neurotransmitter profiling. 79 patients received repeat MRE and psychological evaluations during follow-up. Statistical analyses included correlation analysis, multivariable logistic regression, and Cox proportional hazards modeling.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;CD patients exhibited higher psychological distress scores vs. HCs (all p &lt; 0.001). Anxiety severity (STAI-Trait score) correlated with CD bowel stricture, perienteric effusion, mural T2WI hyperintensity and hyperenhancement (|r | =0.454-0.606; all p &lt; 0.05). Multivariable analysis showed that STAI-Trait score influenced the odds of perienteric effusion (OR = 1.124, 95% CI [1.007, 1.255], p = 0.036). Longitudinal follow-up demonstrated significantly higher incidence of new-onset perienteric effusion in patients with elevated baseline STAI-Trait scores compared to those with low scores (62.1% vs. 15.4%, p &lt; 0.001), with STAI-Trait being the strongest predictor (HR = 6.986, 95% CI [2.274, 21.465], p &lt; 0.001). Both STAI-Trait score and perienteric effusion showed consistent associations with serum tryptophan and histidine levels (|r | =0.203-0.255; all p &lt; 0.05).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;CD patients' psychological state is associated with intestinal morphological changes on MRE. The associations of serum tryptophan and histidine levels with both psychological distress and MRE features provide preliminary support for gut-brain interaction in CD.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Critical relevance statement: &lt;/strong&gt;This study links psychological distress to macro-morphological intestinal changes detectable by MRE, potentially associated with neurotransmitters like tryptophan, thereby advancing our understanding of the emotional factors associated with gut pathophysiology in CD and underscoring the importance of integrated psychological and inflammatory monitoring.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Key points: &lt;/strong&gt;Psychological distress correlates with clinical outcomes in patients with Crohn's disease, but the reason for this association remains largely unexplored. Psychological distress is associated with macro-morphological changes as detected in MR enterography, blood tryptophan and histidine, and longitudinal follow-up further explains this connection. This study provides additiona","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13100207/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770565","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":"Deep learning-based early prediction of carotid plaque response to lipid-lowering therapy using longitudinal multimodal ultrasound imaging.","authors":"Lulu Jiang, Yaning Sun, Wendi Huang, Saisai Wang, Danqin Pan, Yanming Zhang, Mengjie Liang","doi":"10.1186/s13244-026-02286-5","DOIUrl":"https://doi.org/10.1186/s13244-026-02286-5","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to develop and validate a deep learning prediction model using longitudinal multimodal ultrasound imaging for early identification of treatment-sensitive and treatment-resistant carotid plaques in patients receiving lipid-lowering therapy.</p><p><strong>Materials and methods: </strong>This prospective study enrolled 802 patients with vulnerable carotid plaques or stenosis ≥ 50%. Patients underwent serial multimodal ultrasound examinations, including B-mode imaging, superb microvascular imaging, and shear wave elastography at baseline and 3, 6, 9, and 12 months after initiating statin therapy. The dataset was divided into training and testing sets using stratified sampling with data augmentation. A hybrid DL model combining convolutional neural networks and long short-term memory networks analyzed longitudinal imaging sequences integrated with baseline clinical data. Five progressive prediction models were constructed for baseline and each follow-up time point, sharing identical architecture but trained independently on temporal sequences of varying lengths using 5-fold cross-validation. Model performance was assessed for discrimination ability, calibration consistency, and clinical utility.</p><p><strong>Results: </strong>Five progressive prediction models demonstrated characteristic temporal performance patterns, with significant improvement from 3 to 6 months (AUC 0.866), followed by marginal gains. The 6-month model emerged as the most clinically practical assessment time point, achieving high specificity (93.7%) for early therapeutic decisions. Ablation experiments confirmed imaging features as primary predictive determinants, while attention mapping revealed consistent focus on plaque-adjacent regions, validating that treatment response prediction relies on morphological changes within target plaques.</p><p><strong>Conclusion: </strong>A hybrid DL model enables reliable carotid plaque treatment response prediction within six months, optimizing personalized therapy through earlier identification of treatment-resistant patients.</p><p><strong>Critical relevance: </strong>This study validates deep learning algorithms to predict carotid plaque treatment response within six months, advancing clinical radiology practice by enabling earlier therapeutic optimization through objective ultrasound-based assessment.</p><p><strong>Key points: </strong>Conventional imaging requires 12 months to reliably assess plaque treatment response. Deep learning model predicts treatment response at six months with high accuracy. Earlier prediction enables timely therapeutic adjustments for resistant patients.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13100238/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770454","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":"Focal intratesticular lesions including spontaneous hematomas in the acute scrotum: the pivotal role of ultrasound and MRI in diagnosis and management-a pictorial review.","authors":"Laurence Rocher, Mariam Hijazi, Fatima Shaito, Chahinez Hani, Omar Bekdache, Emmanuel Arama, Sondes Zaag","doi":"10.1186/s13244-026-02269-6","DOIUrl":"10.1186/s13244-026-02269-6","url":null,"abstract":"<p><p>An acute scrotum with a focal intratesticular lesion represents a diagnostic challenge and may lead to misdiagnosis and inappropriate management, such as unnecessary orchidectomy or empirical antibiotic therapy. In an emergency setting of acute scrotal pain, a wide spectrum of underlying conditions may be encountered, including testicular tumors with necrotic changes, abscesses, infarctions, and spontaneous hematomas. The latter are uncommon and frequently underrecognized entities, carrying a significant risk of mismanagement; therefore, particular emphasis is placed on their imaging features. Multiparametric ultrasound (US), including contrast-enhanced ultrasound and shear wave elastography (SWE), combined with multiparametric enhanced magnetic resonance imaging (MRI), plays a pivotal role in establishing an accurate diagnosis and guiding appropriate treatment decisions. This pictorial review illustrates the broad spectrum of focal intratesticular lesions presenting in the context of acute scrotum, emphasizing the role of imaging in differentiating benign conditions-such as spontaneous hematomas, which can be managed conservatively-from malignant tumors requiring prompt surgery. CRITICAL RELEVANCE STATEMENT: Multiparametric ultrasound and MRI improve the diagnostic accuracy of focal intratesticular lesions in acute scrotum, particularly spontaneous hematomas, helping avoid misdiagnosis and unnecessary surgical intervention. KEY POINTS: Acute scrotum associated with a focal intratesticular lesion is a diagnostic pitfall that may lead to inappropriate management, including unnecessary surgery. Multiparametric ultrasound (including CEUS and elastography) and MRI are complementary for distinguishing benign from malignant lesions and guiding management. Spontaneous testicular hematomas are rare benign entities characterized by T1-weighted image hyperintensity with a hypointense core and no enhancement on subtraction imaging, supporting conservative treatment. Lack of internal enhancement and geographic margins are keys for diagnosing segmental infarction, whereas enhancing thickened or nodular walls and increased stiffness suggest necrotic or hemorrhagic tumors; abscesses typically show dominant inflammatory changes with extra-testicular involvement.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13096303/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147728890","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":"Decoding the association between CT-derived body composition metrics and prognosis in stage II rectal cancer.","authors":"Fengli Jiang, Ziyan Weng, Zhiqing Shao, Qianling Li, Jie Lin, Dening Ma, Xinyi Gao","doi":"10.1186/s13244-026-02276-7","DOIUrl":"10.1186/s13244-026-02276-7","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the prognostic impact of CT-derived body composition metrics and clinical factors, and to develop a prognostic model in patients with stage II rectal cancer.</p><p><strong>Materials and methods: </strong>This retrospective study analyzed consecutive stage II rectal cancer patients who underwent radical surgery. The predictive value of body composition metrics and clinical factors was evaluated. A Cox proportional hazards model-derived nomogram, based on independent risk factors identified through univariate and multivariate analyses, was established and validated to predict overall survival (OS).</p><p><strong>Results: </strong>Among 975 patients (median age 63 years, IQR 55-70 years; 644 [66.1%] males), 183 deaths were recorded during a median follow-up period of 53 months (IQR 33-83 months). Low skeletal muscle density (SMD) (OR = 0.43; 95% CI: 0.20, 0.91), age ≥ 65 years, and CA125 positive (p < 0.05) were risk factors for severe postoperative complications. High visceral-to-subcutaneous adipose ratio (VSR) (OR = 1.33; 95% CI: 1.02, 1.73), body mass index (BMI) > 24.9, and T4 stage (p < 0.05) were risk factors for prolonged hospitalization. After univariate and multivariate analyses, the nomogram based on age, gross type, perineural invasion, lymphovascular invasion, inflammatory burden index, subcutaneous fat area (SFA), and SMD (p < 0.05) exhibited area under the curve values of 0.77/0.62, 0.77/0.62, and 0.75/0.67 at 1-year, 3-year, and 5-year OS in training/validation sets, respectively.</p><p><strong>Conclusions: </strong>In predicting the prognosis of stage II rectal cancer patients, VSR, SFA, and SMD were superior to other body composition metrics. The nomogram integrating body composition metrics and clinical factors showed superior predictive performance for OS compared to a single risk factor alone.</p><p><strong>Critical relevance statement: </strong>CT-derived body composition metrics can predict the prognosis of rectal cancer patients by reflecting the nutritional and metabolic status.</p><p><strong>Key points: </strong>Body composition metrics' prognostic utility in stage II rectal cancer is clear. Body composition metrics are associated with clinical outcomes in stage II rectal cancer. Body composition is a predictive biomarker for stage II rectal cancer.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13096300/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147728895","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":"Equity, diversity, and inclusion: variations in clinical and academic radiology.","authors":"C Kassanje, E H Y Wong, J O Bamidele, A C Offiah","doi":"10.1186/s13244-026-02278-5","DOIUrl":"10.1186/s13244-026-02278-5","url":null,"abstract":"<p><p>Equity, diversity, and inclusion (EDI) are fundamental to achieving fairness and representation in radiological research and practice. This review aims to examine how structural inequities related to race, sex, gender, age, disability, and socioeconomic status shape imaging research, workforce composition, and clinical outcomes. Racial disparities persist through outdated diagnostic assumptions and unequal access to imaging, while the limited representation of minority clinicians in leadership continues to affect research priorities and inclusivity. Similarly, sex and gender inequities also remain, with women being underrepresented in academic and interventional radiology, and transgender and gender diverse individuals often excluded from research and clinical systems. These gaps highlight the importance of inclusive mentorship, equitable leadership opportunities and consistent use of inclusive terminology. Differences in age, disability, and socioeconomic status affect participation and outcomes in imaging research. Older adults, children and people with disabilities are often excluded from imaging datasets, reducing generalisability and limiting the safe application of new technologies such as artificial intelligence. Socioeconomic inequities affect access to timely imaging and distort normative datasets, leading to misinterpretation of results in deprived populations. Inclusive recruitment, adaptive imaging protocols, and explicit consideration of social context in research design are essential to address these disparities. To address this, radiology must prioritise inclusive recruitment, adapt imaging protocols for underrepresented groups, and integrate EDI principles into study design, dataset curation, and peer review. Embedding these practices will enhance scientific validity, ethical integrity, and patient-centred care, ensuring that imaging research truly reflects the diverse populations it serves. CRITICAL RELEVANCE STATEMENT: This review highlights how addressing equity, diversity, and inclusion in radiological research and practice is essential for improving the relevance, accuracy, and fairness of imaging data and emerging technologies across diverse patient populations. KEY POINTS: Persistent gaps in diversity affect fairness within radiological research and clinical practice. Inequities hinder equitable representation and limit the generalisability of radiological findings. Inclusive practices better serve the diverse populations we care for.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"17 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13096468/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147728952","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}