World journal of radiology最新文献

{"title":"Cone-beam computed tomography-based radiomic analysis of architectural phenotypes in jaw cysts and tumors using interpretable artificial intelligence models.","authors":"Sivan Sathish, Haritma Nigam, Rupal Gupta","doi":"10.4329/wjr.123757","DOIUrl":"10.4329/wjr.123757","url":null,"abstract":"<p><strong>Background: </strong>Jaw lesions, like cysts and tumors, demonstrate substantial variation in internal architectural organization, spatial heterogeneity, and voxel-level complexity on cone-beam computed tomography (CBCT). Conventional radiological interpretation relies predominantly on subjective visual assessment and may not adequately capture these underlying imaging phenotypes.</p><p><strong>Aim: </strong>To evaluate whether CBCT-derived radiomic features can quantitatively characterize architectural phenotypes of jaw lesions and to assess their discrimination using interpretable artificial intelligence (AI) models.</p><p><strong>Methods: </strong>This retrospective study analyzed 100 histopathologically confirmed jaw lesions using CBCT. Lesions were manually segmented using 3D Slicer and 107 radiomic features were extracted after standardized preprocessing and voxel normalization using PyRadiomics. Lesions were classified into homogeneous fluid-dominant, intermediate septated, and complex heterogeneous phenotypes. Feature stability was assessed using intraclass correlation coefficients, while selection employed false discovery rate (FDR) correction, correlation pruning, and LASSO regression. Logistic regression (LR), support vector machine (SVM), and random forest (RF) models underwent stratified five-fold cross-validation and independent chronological validation.</p><p><strong>Results: </strong>Forty radiomic features demonstrated statistically significant differences among architectural phenotypic groups following FDR correction. Feature reduction yielded a compact radiomic signature predominantly composed of texture-derived descriptors reflecting gray-level non-uniformity, spatial dependence variability, entropy, and structural complexity. The LR model demonstrated the highest performance, achieving an area under the receiver operating characteristic curve of 0.92, with robust discrimination between architectural phenotypes. SVM and RF models demonstrated comparable but lower performance. Lesions categorized within the complex heterogeneous phenotype exhibited significantly elevated texture heterogeneity metrics compared with homogeneous fluid-dominant lesions, supporting the biological relevance of radiomic architectural characterization in differentiating complex jaw pathologies.</p><p><strong>Conclusion: </strong>CBCT-derived radiomic features enable quantitative assessment of internal architectural phenotypes in jaw lesions, particularly patterns related to spatial heterogeneity and structural organization. Texture-based radiomic signatures, when integrated with interpretable AI models, may function as imaging biomarkers for objective lesion characterization and may support future development of biologically informed diagnostic decision-support systems in oral and maxillofacial radiology.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 8","pages":"123757"},"PeriodicalIF":1.2,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527540/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148865733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning in neuroradiology: Recent developments and applications.","authors":"Manos Siderakis, Georgios Velonakis, Nikolaos-Achilleas Arkoudis","doi":"10.4329/wjr.123022","DOIUrl":"10.4329/wjr.123022","url":null,"abstract":"<p><p>Radiology, particularly neuroradiology, has become a major focus of research and industrial investment in artificial intelligence and machine learning (ML). These technologies may help address increasing imaging volumes, workforce shortages, and the need for faster and more consistent interpretation. This article summarizes recent developments in ML applications across neuroradiology. In acute ischemic stroke, ML supports early lesion detection, automated Alberta Stroke Program Early Computed Tomography Score assessment, large-vessel-occlusion detection, infarct core and penumbra estimation, collateral evaluation, workflow prioritization, and outcome prediction. Further applications include cerebral aneurysm detection and prediction of intracerebral hemorrhage expansion and prognosis. In neuro-oncology, current uses include tumor segmentation and classification, molecular-marker prediction, treatment-response assessment, surgical and radiotherapy planning, differentiation of recurrence from pseudoprogression, and prognostication. Additional advances involve image reconstruction, automated quantification, diagnostic classification, and outcome prediction in spine imaging; lesion detection and segmentation in demyelinating disease; and identification and characterization of neurodegenerative disorders. Despite this progress, limited generalizability, insufficient external validation, and poor interpretability remain major barriers to clinical adoption. Explainable artificial intelligence, federated learning, and robust multicenter validation are likely to be central to future clinical implementation.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 8","pages":"123022"},"PeriodicalIF":1.2,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527546/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148866117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Size-specific dose estimation in pediatric computed tomography: From dose characterization to individualized optimization.","authors":"Tiao Chen","doi":"10.4329/wjr.124887","DOIUrl":"10.4329/wjr.124887","url":null,"abstract":"<p><p>Pediatric computed tomography (CT) is clinically indispensable for emergency care, neurologic disorders, thoracoabdominal diseases, trauma assessment, and oncologic diagnosis and follow-up. However, children should not be regarded as small adults. They are actively growing and developing, and organs or tissues such as the hematopoietic system, thyroid, breast, gonads, lens, central nervous system, and bone marrow are more sensitive to ionizing radiation. In addition, children have a longer life expectancy, allowing a longer latency window for radiation-related late effects. Epidemiological studies suggest associations between pediatric CT exposure and cumulative-dose-related risks of leukemia, brain tumors, and overall cancer; although the individual absolute risk is generally low, stricter justification, optimization, and dose recording remain necessary in pediatric populations. Conventional volume CT dose index (CTDI_vol) and dose-length product primarily describe scanner output under standard phantom conditions and cannot adequately characterize differences in patient body size, tissue attenuation, organ location, and scan coverage. Size-specific dose estimate (SSDE), which corrects CTDI_vol using a patient-size conversion factor, represents an important intermediate dose descriptor linking scanner output, pediatric body-size characteristics, organ-dose estimation, and scan-protocol optimization. This review focuses on the specific requirements of pediatric CT dose assessment. It summarizes the conceptual evolution of SSDE, the selection of size metrics, applications across examination sites, relationships with organ dose and radiation-risk assessment, pediatric diagnostic reference levels, and future directions in automated dose management. The aim is to provide a conceptual and practical basis for individualized pediatric CT dose optimization.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 8","pages":"124887"},"PeriodicalIF":1.2,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527544/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148866440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vascular complications in percutaneous biliary interventions.","authors":"Fabrizio Acquafredda, Antonio Vizzuso, Stavros Grigoriadis, Giuseppe Di Giovanni, Matteo Renzulli, Emanuela Giampalma, Ioannis Paraskevopoulos, Stavros Spiliopoulos, Riccardo Inchingolo","doi":"10.4329/wjr.119018","DOIUrl":"10.4329/wjr.119018","url":null,"abstract":"<p><p>Percutaneous biliary interventions are indicated for both benign or malignant biliary strictures to treat obstructive jaundice and/or biliary leak. Major vascular complications include active bleeding or more frequently pseudoaneurysm formation, bilio-portal, bilio-venous or arterio-biliary fistulae and intra- or peri-hepatic hematoma. Such adverse events can occur during the procedure itself or, more often, several days to weeks after the initial procedure. Major vascular complications frequently manifest with symptoms of hemobilia (jaundice, pain, melena or hemochezia and reduced serum hemoglobin levels), which in some cases lead to life-threatening hemodynamic compromise. Computed tomography angiography is mandatory to diagnose the cause and site of bleeding, while simultaneously depicting the anatomy, in order to plan the treatment. Covered stents, liquid embolic agents and coils are the commonest devices used, depending on the underlying pathology. Although such complications are rare, they are frequently life-threatening, and require prompt treatment. Therefore, interventional radiologists must be proficient in their management. This narrative minireview aims to outline management strategies of the most frequent intra- or post-procedural vascular complications following biliary interventions.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 8","pages":"119018"},"PeriodicalIF":1.2,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527549/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148866496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiolabeled exosomes for theranostics: Personalized tailored therapy through imaging.","authors":"Soumya Deep Phadikar, Aliza Hyder, Ramya Lakshmi Rajendran, Anand Krishnan, Chae Moon Hong, Prakash Gangadaran, Byeong-Cheol Ahn","doi":"10.4329/wjr.122678","DOIUrl":"10.4329/wjr.122678","url":null,"abstract":"<p><p>Radiolabeled exosomes have emerged as a transformative platform at the intersection of nanomedicine, molecular imaging, and precision theranostics. These nanoscale extracellular vesicles exhibit intrinsic biocompatibility, low immunogenicity, and inherent targeting capabilities, making them highly attractive for both diagnostic and therapeutic applications. The integration of radiochemistry with exosome biology enables noninvasive, real-time tracking of biodistribution, pharmacokinetics, and target engagement using advanced imaging modalities such as positron emission tomography and single-photon emission computed tomography. This minireview comprehensively summarizes current radiolabeling strategies for exosomes, including direct and indirect approaches, highlighting their advantages, limitations, and impact on vesicle integrity and imaging accuracy. Furthermore, we discuss key imaging platforms, <i>in vivo</i> biodistribution patterns, and pharmacokinetic profiles that influence therapeutic efficacy. Critical challenges such as rapid clearance by the mononuclear phagocyte system, labeling instability, and the lack of standardized protocols are also addressed. Finally, we outline future perspectives focusing on advanced bioengineering, multimodal imaging integration, and clinical translation frameworks. Radiolabeled exosomes represent a promising next-generation theranostic system with the potential to enable personalized, image-guided therapies across oncology and regenerative medicine.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 7","pages":"122678"},"PeriodicalIF":1.2,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13419547/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148631835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a clinical factor-based nomogram for predicting imaging-defined cardiopulmonary abnormality risk in an asymptomatic screening population.","authors":"Zhong-Yun He, Zhi-Wei Zhan, Le-Jiang Zhou, Jun Tang, Chen Chen, Qing-Jun Yang, Qiang Tian, Xiao-Hong Wang","doi":"10.4329/wjr.123894","DOIUrl":"10.4329/wjr.123894","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Chronic cardiopulmonary diseases, including chronic obstructive pulmonary disease, interstitial lung disease, and coronary artery disease, represent a major global health burden. Low-dose computed tomography (LDCT) combined with artificial intelligence (AI) quantitative imaging enables the identification of cardiopulmonary imaging abnormalities in asymptomatic individuals.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Aim: &lt;/strong&gt;To evaluate early risk factors for cardiopulmonary imaging abnormalities in asymptomatic middle-aged and elderly population using single-inspiratory phase LDCT combined with AI-based whole-lung quantitative analysis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A retrospective collection was conducted on 1035 asymptomatic individuals aged ≥ 40 years who underwent routine single-inspiratory-phase LDCT screening at Zhuzhou 331 Hospital in 2025. An AI platform was utilized to automatically extract airway wall area percentage, low-attenuation area percentage, interstitial lung abnormality, and coronary artery calcification score. Based on risk stratification criteria, the population was divided into a high-risk group (&lt;i&gt;n&lt;/i&gt; = 689) and a low-risk group (&lt;i&gt;n&lt;/i&gt; = 346) and randomly stratified into a training set (&lt;i&gt;n&lt;/i&gt; = 724) and a validation set (&lt;i&gt;n&lt;/i&gt; = 311) at a 7:3 ratio. Independent sample &lt;i&gt;t&lt;/i&gt;-test or &lt;i&gt;χ&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; test was applied to analyze between-group differences. Binary logistic regression was used to screen independently associated factors, and a multivariate logistic regression model was constructed after excluding collinear variables using variance inflation factor (VIF &lt; 5), followed by the establishment of a nomogram prediction model. The receiver operating characteristic curve and DeLong test were employed to evaluate model discrimination. The Hosmer-Lemeshow test and calibration curves were used to assess goodness of fit. Decision curve analysis (DCA) was applied to evaluate clinical net benefit, and internal validation was performed using the bootstrap method (1000 resamplings).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Univariate analysis showed that smoking history, abnormal metabolic status, body mass index (BMI), age, and gender were significantly associated with cardiopulmonary imaging-defined high-risk status (&lt;i&gt;P&lt;/i&gt; &lt; 0.05), while work style showed a marginal association in univariate analysis (&lt;i&gt;P&lt;/i&gt; = 0.043) but did not retain statistical significance in the multivariate model (&lt;i&gt;P&lt;/i&gt; = 0.851). After VIF collinearity screening (all VIF &lt; 5) and multivariate logistic regression analysis with forced entry of six candidate variables, smoking history [odds ratio (OR) = 1.968 per level, 95% confidence interval (CI): 1.665-2.325, &lt;i&gt;P&lt;/i&gt; &lt; 0.001], abnormal metabolic status (OR = 3.266, 95%CI: 2.259-4.723, &lt;i&gt;P&lt;/i&gt; &lt; 0.001), BMI (OR = 1.150 per unit, 95%CI: 1.079-1.226, &lt;i&gt;P&lt;/i&gt; &lt; 0.001), and age (OR = 1.028 per year, 95%CI: 1.005-1.052, &lt;i&gt;P&lt;/i&gt; = 0.018) were identified as independently associate","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 7","pages":"123894"},"PeriodicalIF":1.2,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13419150/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148621599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive value of second-trimester ophthalmic artery Doppler for identifying women at risk for preeclampsia.","authors":"Rishav Dhiman, Nishant Nayyar, Preeti Takkar, Dinesh Sood, Ankit Shukla","doi":"10.4329/wjr.120995","DOIUrl":"10.4329/wjr.120995","url":null,"abstract":"<p><strong>Background: </strong>Preeclampsia (PE) is a multifactorial hypertensive disorder specific to pregnancy that significantly contributes to maternal and perinatal morbidity and mortality worldwide. According to hospital-based studies, its prevalence in India ranges from 5% to 15%. Despite advances in obstetric care, the early identification of women at risk remains a major clinical challenge. Ophthalmic artery Doppler (OAD), a noninvasive and reproducible imaging technique, provides important information on cerebral autoregulation and maternal vascular resistance with potential exploratory utility in the early detection of PE.</p><p><strong>Aim: </strong>To evaluate the predictive value of maternal OAD indices measured during the second trimester (17-23 weeks of gestation) for the subsequent development of PE in a cohort of initially normotensive pregnant women.</p><p><strong>Methods: </strong>This prospective observational study, conducted from March 2024 to February 2025, enrolled 90 antenatal women in their second trimester with no prior history of hypertension or renal disease. OAD evaluation was performed using the transorbital approach with the Alpinion E-CUBE 8 ultrasound system, and key Doppler indices were recorded. Participants were subsequently followed through the third trimester to assess the development of PE. Statistical analysis was performed using the independent samples <i>t</i>-test for continuous variables, Fisher's exact test for categorical variables, and receiver operating characteristic curve analysis to assess the predictive performance of Doppler parameters.</p><p><strong>Results: </strong>Out of the 90 participants, 8 (8.89%) developed PE during follow-up. The resistive index (<i>P</i> = 0.004), pulsatility index (<i>P</i> = 0.0003), and most notably, the peak ratio (PR) (<i>P</i> < 0.0001) showed statistically significant differences between the normotensive and preeclamptic groups. Among the Doppler parameters, PR demonstrated the best diagnostic performance, with a diagnostic accuracy of 91.11%, sensitivity of 100%, specificity of 90.24%, and area under the receiver operating characteristic curve of 0.90. Elevated PR values were strongly associated with the subsequent development of PE, indicating potential predictive value that requires further validation in larger studies.</p><p><strong>Conclusion: </strong>Maternal OAD measurements, particularly PR, demonstrated significant associations with the subsequent development of PE in this study cohort. Its noninvasive nature, ease of application, and observed diagnostic performance suggest that it may warrant further evaluation as an adjunctive risk stratification tool in antenatal screening protocols, particularly in resource-limited settings. The early detection and management of high-risk pregnancies could be greatly improved by incorporating OAD into standard obstetric care, potentially improving maternal and perinatal outcomes.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 7","pages":"120995"},"PeriodicalIF":1.2,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13419541/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148631847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Role of magnetic resonance in bowel pathologies: Beyond inflammatory bowel disease.","authors":"Carlos Ignacio Gonzalez Baerga, Manuel Menendez Santos, Ruben Gabriel Ortiz Cordero, Oswaldo André Guevara Tirado, Mayur Virarkar, Dheeraj Reddy Gopireddy","doi":"10.4329/wjr.122165","DOIUrl":"10.4329/wjr.122165","url":null,"abstract":"<p><p>Magnetic resonance imaging (MRI) has an established role for identifying and monitoring inflammatory bowel disease. This review summarizes key MRI findings and select technique considerations for bowel pathologies beyond inflammatory bowel disorders, emphasizing how imaging features within this modality can support diagnosis and assist with management. We highlight MRI features of inflammatory and infectious conditions, mechanical obstruction, neoplasms, and mesenteric ischemia. We also discuss how particular imaging techniques may improve diagnostic confidence, including diffusion-weighted imaging when contrast cannot be administered and rapid motion-robust sequences to reduce motion artifacts from peristalsis and breathing.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 7","pages":"122165"},"PeriodicalIF":1.2,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13420189/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148631789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computed tomography derived morphomics in the prediction of long-term outcomes in acute pancreatitis.","authors":"Sahil Shet, Orla Cliona O'Shea, Ludolf Gavin Arthur De Kock, Eid Kakish, Ronan James Lee, Naomi Ni Chleirigh, Evan O'Broin, David John Ryan, Michael Martin Maher","doi":"10.4329/wjr.118613","DOIUrl":"10.4329/wjr.118613","url":null,"abstract":"<p><strong>Background: </strong>Acute pancreatitis is a common abdominal pathology with significant morbidity and mortality in select patients. Currently, prediction of outcome and prognosis in patients with acute pancreatitis is based on a variety of indices, scores, and criteria calculated from biochemical, clinical, and imaging parameters, but all currently available predictors of outcome have limitations. Analytic morphomics, a quantitative technique that assesses body composition from cross-sectional imaging, may offer a novel approach to outcome prediction.</p><p><strong>Aim: </strong>To evaluate whether analytic morphomics-derived parameters can predict recurrence and mortality after an index episode of acute pancreatitis.</p><p><strong>Methods: </strong>Following ethical approval, a retrospective single-centre study was conducted at Cork University Hospital. Adult patients presenting with acute pancreatitis between January 2012 and December 2013 were included and followed for 10 years. Patients with pancreatic malignancy, equivocal diagnoses, or age < 18 years were excluded. Cases of acute pancreatitis were classified as acute interstitial oedematous pancreatitis or necrotising pancreatitis. Demographic, biochemical, and clinical data were collected, including the modified Glasgow Imrie severity score. Computed tomography examinations were analysed using CoreSlicer for semi-automated segmentation of skeletal muscle and adipose tissue at the L3 vertebral level. Statistical analysis was performed using Microsoft Excel and Jamovi, including the Mann-Whitney <i>U</i> test, Pearson correlation, and logistic regression.</p><p><strong>Results: </strong>Seventy-two patients were included with a median modified Glasgow Imrie severity score of 2. Wall muscle (WM) density correlated inversely with disease severity [WM density (Hounsfield units): <i>r</i> = -0.480, <i>P</i> < 0.001; psoas muscle density (Hounsfield units): <i>r</i> = -0.465, <i>P</i> < 0.001]. Higher WM density and greater subcutaneous fat (SCF) area were associated with reduced 30-day mortality (mean difference 14.4 HU, <i>P</i> = 0.003; 65.3 cm², <i>P</i> = 0.033, respectively) and improved 10-year survival. On multivariate analysis, lower WM density and lower SCF area independently predicted short- and long-term mortality, while no morphomic variables were independently associated with recurrence.</p><p><strong>Conclusion: </strong>Skeletal muscle quality and SCF are protective factors in acute pancreatitis. Integration of morphomics with existing severity scores may enhance prognostication. Larger studies are needed to validate these findings.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 7","pages":"118613"},"PeriodicalIF":1.2,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13420184/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148631844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Letter to the Editor: Potential pitfalls in deep learning-based imaging for spontaneous intracerebral hemorrhage.","authors":"Sachin D Balutkar, Sachin S Bhavthankar, Basavraj S Nagoba","doi":"10.4329/wjr.120076","DOIUrl":"10.4329/wjr.120076","url":null,"abstract":"<p><p>The study by Yang and Li in the <i>World Journal of Radiology</i> reports strong predictive performance for hematoma enlargement, perihematomal edema (PHE) and hospital mortality using hand crafted quantitative radiomics and deep learning models in patients with spontaneous intracerebral haemorrhage (ICH). While the authors report strong predictive performance using quantitative radiomics and deep learning features, several methodological concerns warrant discussion. By letting the deep learning models based on pretrained Convolutional Neural Network (CNN) to detect the density range of 50-400 Hounsfield units, may falsely detect age related and pathological basal ganglionic calcifications as heterogeneity within the ICH. This may lead to increased false positive rates in the prediction of hematoma enlargement. Similarly, by not restricting the density range between 25-35 Hounsfield units for pretrained CNN to detect PHE, may also add bias by falsely detecting age related micro ischaemic areas and chronic lacunar infarcts in basal ganglionic region as PHE. Further, hand crafted quantitative radiomics by trained clinical radiologists will calculate volume of ICH and PHE more accurately as compared to the CNN models using only three consecutive axial slices centered on the maximum haematomal cross-sectional area, as reported in the original study. Hence, an integrated model consisting of hand crafted quantitative radiomics by trained clinical radiologist with deep learning models based on pre trained CNN with the above-mentioned enhancements and a human touch by a trained clinical radiologist to remove the mentioned confounding factors is highly recommended for better outcomes.</p>","PeriodicalId":23819,"journal":{"name":"World journal of radiology","volume":"18 7","pages":"120076"},"PeriodicalIF":1.2,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13419148/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148621645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}