Ultrasound Journal最新文献

{"title":"Correction: B-mode ultrasound and contrast-enhanced ultrasound-based radiomics interpretable analysis for the prediction of macrotrabecular-massive subtype of hepatocellular carcinoma.","authors":"Dan Lu, Cheng Qin, Li-Fan Wang, Ling-Ling Li, Yu Li, Li-Ping Sun, Hui Shi, Bo-Yang Zhou, Xin Guan, Yao Miao, Hong Han, Jian-Hua Zhou, Hui-Xiong Xu, Chong-Ke Zhao","doi":"10.1186/s13089-025-00468-8","DOIUrl":"10.1186/s13089-025-00468-8","url":null,"abstract":"","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"62"},"PeriodicalIF":2.9,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12647434/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145606397","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":"Effectiveness of traditional, artificial intelligence-assisted, and virtual reality training modalities for focused cardiac ultrasound skill acquisition: a randomised controlled study.","authors":"Yie Hui Lau, Sanchalika Acharyya, Cadence Wei Lin Wee, Huiying Xu, Rafael Pulido Saclolo, Kelly Cao, Wee Kim Fong","doi":"10.1186/s13089-025-00469-7","DOIUrl":"10.1186/s13089-025-00469-7","url":null,"abstract":"<p><strong>Background: </strong>Focused cardiac ultrasound (FCU) is increasingly used as an extension of physical examination to aid diagnosis and clinical decision-making. Emerging educational technologies such as artificial intelligence (AI)-enabled ultrasound devices and virtual reality (VR) simulators offer novel, cost-effective and self-directed approaches for FCU skill acquisition training. Prior studies suggest that VR-based training may be non-inferior to traditional teaching, while AI offers real-time feedback to enhance learning.</p><p><strong>Objective: </strong>This study aimed to evaluate the effectiveness and non-inferiority of AI and VR-assisted training compared to Traditional in-person instruction in achieving competency in FCU image acquisition. Secondary outcomes included time to acquire an optimal apical 4 chamber (A4C) view and self-reported confidence in image acquisition, assessed immediately post-training and at 3-month follow up.</p><p><strong>Methods: </strong>In this single-blind, randomized controlled pilot trial, 66 local medical students with no prior FCU experience were randomised into 3 arms: (1) AI-enabled ultrasound training using the Kosmos system, (2) VR-based stimulator (Vimedix), and (3) Traditional instructor-led teaching. All sessions were 60 min long. Image acquisition of 5 standard FCU views was assessed by blinded evaluators using the Rapid Assessment of Competency in Echocardiography (RACE) score at both time points.</p><p><strong>Results: </strong>Two participants were lost to follow-up (one each from the AI and VR groups). In the first assessment, the Traditional group achieved the highest mean RACE score (15.77), followed by AI (13.39) and VR (13.23). Non-inferiority testing confirmed that both AI (95% CI -∞ to 3.60; p < 0.001) and VR (95% CI -∞ to 3.58; p < 0.001) methods were non-inferior to Traditional instruction. The AI group achieved the shortest mean time to acquire an optimal A4C view (158 ± 99.1 s), followed by the VR (189 ± 94.7 s), and traditional (199 ± 115.1 s), though differences were not statistically significant (p = 0.591). Confidence levels were initially highest in the Traditional group, while the VR group showed higher confidence at 3-month follow-up, particularly in parasternal long-axis view acquisition.</p><p><strong>Conclusions: </strong>AI and VR-based training methods were non-inferior to traditional instruction for FCU skill acquisition. Both modalities show promise as scalable, technology-enabled alternatives in ultrasound education. Trial registration This trial was registered on Clinicaltrials.gov (NCT06355557).</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"61"},"PeriodicalIF":2.9,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12638561/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145565726","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":"Feasibility of point-of-care ultrasound during the emergency department triage: a prospective cohort study.","authors":"Davide Enrici Baion, Chiara Schettino, Lara Vita, Deborah Luison, Stefania Caprioli, Matteo Lombardo, Alberto La Ferrara, Francesca Locascio, Emanuela Galluzzo, Vittoria Ciampi, Aurora Ianiro, Davide Maserin, Francesco Malara, Noemi Urso, Fulvio Morello, Daniele Marchisio, Enrico Lupia, Emanuele Pivetta","doi":"10.1186/s13089-025-00463-z","DOIUrl":"10.1186/s13089-025-00463-z","url":null,"abstract":"<p><strong>Background: </strong>The primary aim of this study was to evaluate the feasibility of adding point-of-care ultrasound (POCUS) during the Emergency Department (ED) triage process. This prospective study enrolled two cohorts of adult patients presenting to the ED for a selected group of acute symptoms, previously selected on the basis of the presumed utility of POCUS during triage evaluation. The ED triage process was performed as recommended by the hospital guidelines or by including a nurse-performed POCUS evaluation. Only urgent or less codes were considered eligible for the study. The timing of all evaluations was recorded along with the opinion of the nurses involved in the study on the impact of POCUS results on the triage process. After ED discharge, the most appropriate triage code was determined by independent review of the triage data.</p><p><strong>Results: </strong>A total of 312 patients were enrolled, 101 of whom were evaluated with the hospital standard triage process. Nine nurses with expertise in both ED triage and POCUS were involved in the study. The majority of the enrolled patients were deferrable or minor urgency (about 60% in both groups). The median time needed for the triage evaluation was 180 seconds (range 540), 90 seconds longer in the POCUS group than in the standard triage group (p < 0.01). Net reclassification index of POCUS-implemented compared with standard triage protocol was 8% and 5% for urgent and less urgent cases.</p><p><strong>Conclusions: </strong>This small single site study suggests that POCUS is feasible during the ED triage and it is potentially useful by triage nurses. However, future studies are needed to confirm POCUS potential usefulness for a more accurate triage process.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"60"},"PeriodicalIF":2.9,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12630473/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145551311","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":"Intraoperative elastography and spinal surgery: a systematic review of current and future applications in clinical and preclinical models.","authors":"Parker Dhillon, Brian Fabian Saway, Audrey Galimba, Rishishankar Suresh, Thomas Eckert, Max J Kerensky, Vikas N Vattipally, Patrick Kramer, Nicholas Theodore, Sunil Patel, Stephen Kalhorn","doi":"10.1186/s13089-025-00462-0","DOIUrl":"10.1186/s13089-025-00462-0","url":null,"abstract":"<p><strong>Background: </strong>While conventional imaging provides excellent structural detail of the spine, it cannot assess the mechanical properties of spinal tissue in real time. Ultrasound elastography (USE) is an emerging modality that quantifies tissue stiffness, offering a potential solution to this diagnostic gap. This review synthesizes the current evidence for the use of USE in spinal pathology.</p><p><strong>Main body: </strong>A systematic review of the PubMed, Cochrane, and Web of Science databases was conducted in accordance with PRISMA guidelines, yielding seven primary studies, three clinical and four preclinical, published between 2015 and 2024. These studies, comprising preclinical and clinical data, demonstrate USE's ability to provide real-time, quantitative feedback. Key applications identified include quantifying tension relief in tethered cord syndrome, differentiating spinal tumors from healthy tissue based on stiffness values, and assessing the biomechanical severity of acute and chronic spinal cord injury. Shear wave elastography (SWE) was the predominant modality, proving superior to strain elastography (SE) for spinal applications.</p><p><strong>Conclusion: </strong>USE is a powerful adjunct to traditional spinal imaging, providing unique functional data that can enhance intraoperative surgical precision and decision-making. While challenges such as depth penetration and operator standardization remain, continued research and technological innovation position USE to significantly improve diagnostic accuracy and surgical outcomes in spinal disease management.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"59"},"PeriodicalIF":2.9,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12630497/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145551266","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":"The effect of Peyton's four-step method for teaching point-of-care ultrasound psychomotor skills: an experimental study.","authors":"Michael Breunig, Ryan Kingsley, Darrell Schroeder, Jason Kraus, Corbin Plooster, Tiffany Galush, Laura Boldenow, Taryn Ragaisis, Hannah Regan, Will M Schouten, Raheel Shafay, Meltiady Issa, Deanne T Kashiwagi","doi":"10.1186/s13089-025-00466-w","DOIUrl":"10.1186/s13089-025-00466-w","url":null,"abstract":"<p><strong>Background: </strong>Medical education commonly utilizes the \"see one, do one\" two-step approach for teaching psychomotor skills; however, recent evidence suggests that Peyton's four-step method leads to superior learning. There is limited evidence, and almost no high-quality studies, specifically evaluating the effect of Peyton's Four‑Step method on long-term retention of ultrasound/POCUS procedural skills. The purpose of this research project was to evaluate the effectiveness of Peyton's four-step method on teaching the POCUS psychomotor skills of image acquisition to novice learners. Additionally, this research project assessed the influence of Peyton's four-step method at three different points in time during the skill acquisition phase, in the setting of ongoing deliberate skill practice.</p><p><strong>Methods: </strong>A single-blinded, repeated measures interventional study based on experimental design was completed. Physician Assistant students from one large academic medical center were randomized into a control group (using the two-step method) and intervention group (using Peyton's four-step method). Students were taught POCUS of the aorta, bladder, heart, lungs, and kidneys. Students' POCUS skills were assessed during the immediate, intermediate, and delayed learning phases. At each assessment, an organ-specific score and a total score were obtained. Scores were compared using a Wilcoxon rank sum test. An ordinal logistic regression analysis was performed using a generalized linear mixed model with a multinomial distribution and cumulative logit link function to assess the overall effect of Peyton's four-step method.</p><p><strong>Results: </strong>Students who were taught using Peyton's method were found to have an increased likelihood of higher total scores compared to those taught using usual instruction (OR = 4.2, p = 0.003). Peyton's method was found to have increased likelihood of higher scores for cardiac (OR = 2.3, p = 0.032), lung (OR = 2.5, p = 0.034), and kidney (OR = 3.0, p = 0.015). Student performance statistically improved with Peyton's four-step method during the immediate (p = 0.031) and delayed (p = 0.011) skill acquisition phases, but not in the intermediate phase.</p><p><strong>Conclusion: </strong>Peyton's four-step method improves overall psychomotor skill acquisition for POCUS. Peyton's four-step method specifically improved psychomotor skills in the immediate skill acquisition phase and the delayed skill acquisition phase. The benefit of Peyton's four-step method was more prominent in POCUS applications with higher complexity.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"58"},"PeriodicalIF":2.9,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12605846/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145490608","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":"Predicting neonatal RDS with fetal pulmonary artery doppler: a diagnostic performance and ROC curve analysis.","authors":"Ishan Kumar, Karan Kukreja, Ashok Kumar, Priyanka Aggarwal, Shikha Sachan, Ashish Verma","doi":"10.1186/s13089-025-00456-y","DOIUrl":"10.1186/s13089-025-00456-y","url":null,"abstract":"<p><strong>Study design: </strong>Prospective observational diagnostic accuracy study.</p><p><strong>Methods: </strong>This study evaluated Doppler parameters of the fetal main pulmonary artery (MPA) as potential non-invasive predictors of RDS and to assess their relationship with gestational age and postnatal respiratory outcomes. Pulsed-wave Doppler of the fetal MPA was performed and Doppler indices-pulsatility index (PI), resistance index (RI), peak systolic velocity (PSV), and acceleration time/ejection time ratio (At/Et)-were recorded over three cardiac cycles and averaged. Values were compared after delivery between neonates with and without RDS.</p><p><strong>Results: </strong>In normally developing fetuses, PI and RI decreased while At/Et increased with advancing gestational age. In contrast, fetuses who developed RDS showed persistently low At/Et and elevated PI and RI values. Cutoff values of At/Et < 0.24, RI > 0.8, and PI > 2.16 were effective in predicting RDS. The severity of RDS was associated with greater deviations from these values. Altered Doppler indices were found to be independent predictors of RDS in preterm neonates.</p><p><strong>Conclusion: </strong>Fetal MPA Doppler parameters serve as reliable, non-invasive predictors of RDS and the severity of RDS in preterm neonates.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"57"},"PeriodicalIF":2.9,"publicationDate":"2025-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12589688/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145446073","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":"Performance and development trends of ultrasound diagnostic systems in military settings: a review.","authors":"Chang Lu, He-Jing Huang","doi":"10.1186/s13089-025-00458-w","DOIUrl":"10.1186/s13089-025-00458-w","url":null,"abstract":"<p><p>With the evolving challenges of modern warfare, battlefield medical support systems are often required to enhance capabilities in rapid response, flexible deployment, and modular integration. Ultrasound diagnostic systems, appreciated for their portability and ability to provide real-time imaging without ionizing radiation, have been investigated for potential use in early injury screening and rapid assessment in combat and pre-hospital settings. This review provides an overview of representative battlefield-adapted ultrasound systems, such as the Sonosite M-Turbo, Edge II, and GE Vscan Extend, and discusses their reported limitations, including issues with deployment reliability, image quality, operational complexity, and telecommunication capability. Emerging technological directions are explored, including artificial intelligence-assisted diagnosis, multimodal integration, adaptation to extreme environments, and integration with unmanned platforms. Furthermore, a conceptual framework is proposed, focusing on areas such as research and development, standardization, deployment at combat nodes, and training infrastructure, which may contribute to future advancements. The goal is to provide insights that could guide the future development and strategic planning of next-generation tactical medical imaging systems.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"54"},"PeriodicalIF":2.9,"publicationDate":"2025-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12583298/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145439408","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":"Erector spinae plane block for acute pain management of pancreatic cancer at the emergency department.","authors":"Osman Adi, Chan Pei Fong, Azma Haryaty Ahmad, Muhamad Rasydan Abd Ghani, Shahridan Fathil","doi":"10.1186/s13089-025-00461-1","DOIUrl":"10.1186/s13089-025-00461-1","url":null,"abstract":"<p><p>Pancreatic cancer is often associated with intractable pain due to tumor invasion of surrounding neural structures and visceral organs. Conventional pain management strategies, including opioids, are often insufficient and associated with significant side effects. The erector spinae plane block (ESPB) is an inter-fascial regional anesthesia technique that can be considered in managing abdominal pain. Besides being a simple block performed, ESPB is also very effective because it provides visceral, somatic and neuropathic pain coverage. This case series highlights the potential role of ESPB as an adjunctive therapy for acute pain management of pancreatic cancer patients at the emergency department, with discussion on its technical aspect, advantages and limitations.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"56"},"PeriodicalIF":2.9,"publicationDate":"2025-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12586832/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145439419","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":"Performance evaluation of the TE Air wireless handheld ultrasound in cardiac applications: a prospective comparative study.","authors":"Beibei Ge, Mingxia Li, Hanlin Cheng, Zhanru Qi, Xiaoxian Wang, Fen Chen, Zhongqing Shi, Guanjun Guo, Chunjie Shan, Jinyang Qi, Shouhua Luo, Fang Xu, Jing Yao","doi":"10.1186/s13089-025-00454-0","DOIUrl":"10.1186/s13089-025-00454-0","url":null,"abstract":"<p><strong>Aim: </strong>To evaluate the reliability and reproducibility of the TE Air wireless handheld ultrasound device in clinical cardiac imaging by comparing its performance with a high-end reference system.</p><p><strong>Methods: </strong>161 patients for good-quality echocardiographic images were included in this prospective study. Each patient underwent sequential imaging using both the TE Air device (Mindray) and the high-end reference device (Philips EPIQ 7 C). Nine standard cardiac views were acquired. Image quality was assessed manually by two blinded echocardiographers and via proprietary AI software, respectively. The following key parameters were analyzed basing on the images: diastolic thickness of interventricular septal (IVSTd) and left ventricular posterior wall (LVPWTd), left ventricular end-diastolic (LVDd) and end-systolic diameter (LVDs), aortic diameter (AOD), left atrial anteroposterior diameter (LAD), Early (E) and late (A) diastolic velocities of the mitral valve in PW mode, as well as early diastolic velocities at the septal (EmS) and lateral (EmL) mitral annulus. Regional wall motion abnormality (RWMA), bicuspid aortic valve (BAV), atrial septal defect (ASD), left ventricular ejection fraction (LVEF) and valvular regurgitation degree were independently evaluated.</p><p><strong>Results: </strong>The TE Air demonstrated comparable image quality to the high-end reference system in both manual (64.95 ± 1.24 vs. 64.19 ± 1.63, P = 0.28) and AI-based evaluations (65.07 ± 1.02 vs. 63.80 ± 1.68, P = 0.06). Structural measurements showed high inter-device consistency, with ICCs of 0.77/0.74 for IVSTd/LVPWTd, 0.95/0.96 for LVDd/LVDs, and 0.82/0.98 for AOD/LAD (all P < 0.001). Functional parameters also demonstrated strong agreement (ICC: 0.91/0.92 for mitral E/A waves; 0.79/0.85 for EmS/EmL; P < 0.001). The TE Air had sensitivities of 81.8% for RWMA, 100% for ASD and BAV, and 93.5% for LVEF < 50%. Diagnostic agreement was excellent for LVEF (κ = 0.96, P < 0.001) and valvular regurgitation (weighted κ = 0.89, P < 0.001).</p><p><strong>Conclusion: </strong>The TE Air wireless handheld ultrasound device exhibits high agreement with high-end reference device in image quality, measurements, and clinical diagnoses, supporting its potential for widespread use in point-of-care ultrasound (POCUS) clinical applications.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"55"},"PeriodicalIF":2.9,"publicationDate":"2025-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12572465/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145402481","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":"B-mode ultrasound and contrast-enhanced ultrasound-based radiomics interpretable analysis for the prediction of macrotrabecular-massive subtype of hepatocellular carcinoma.","authors":"Dan Lu, Cheng Qin, Li-Fan Wang, Ling-Ling Li, Yu Li, Li-Ping Sun, Hui Shi, Bo-Yang Zhou, Xin Guan, Yao Miao, Hong Han, Jian-Hua Zhou, Hui-Xiong Xu, Chong-Ke Zhao","doi":"10.1186/s13089-025-00452-2","DOIUrl":"10.1186/s13089-025-00452-2","url":null,"abstract":"<p><strong>Background: </strong>This study aimed to develop and validate an interpretable radiomics model using quantitative features from B-mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) for predicting macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC).</p><p><strong>Methods: </strong>From October 2020 to September 2023, 344 patients (mean age: 58.20 ± 10.70 years; 275 men) with surgically resected HCC were retrospectively enrolled from three medical centers. Radiomics features were extracted from BMUS and CEUS, followed by a multiple-step feature selection process. BMUS_R model (based on BMUS radiomics features), BM + CEUS_R model (based on BMUS and CEUS radiomics features) and hybrid_R+C model (integrated clinical indicators and radiomic features) were established. These radiomics models' performance was compared with conventional clinic-radiological (C_C+R) model using area under the receiver operating characteristic curve (AUC). SHapley Additive exPlanations (SHAP) method was used to interpret model performance. The model's potential for predicting recurrence-free survival (RFS) was further analyzed.</p><p><strong>Results: </strong>Among ten distinct machine learning classifiers evaluated, the AdaBoost algorithm demonstrated the highest classification performance. The AUCs of the BM + CEUS_R model for identifying MTM-HCC were higher than the BMUS_R model and the conventional clinic-radiological model in both validation (0.880 vs. 0.720 and 0.658, both p < 0.05) and test sets (0.878 vs. 0.605 and 0.594, both p < 0.05). No statistical differences were observed between the BM + CEUS_R model and the hybrid_R+C model in either set (p > 0.05). Additionally, the AdaBoost-based BM + CEUS_R model showed promising in stratifying early recurrence-free survival, with p < 0.001.</p><p><strong>Conclusion: </strong>The AdaBoost-based BM + CEUS_R model shows promise as a tool for preoperatively identifying MTM-HCC and may also be beneficial in predicting prognosis.</p>","PeriodicalId":36911,"journal":{"name":"Ultrasound Journal","volume":"17 1","pages":"53"},"PeriodicalIF":3.6,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12534629/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145309377","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}