Academic Radiology最新文献

筛选
英文 中文
Renal Transplant Survival Prediction From Unsupervised Deep Learning-Based Radiomics on Early Dynamic Contrast-Enhanced MRI. 基于无监督深度学习的早期动态增强MRI放射组学肾移植生存预测。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-23 DOI: 10.1016/j.acra.2025.05.001
Léo Milecki, Sylvain Bodard, Vicky Kalogeiton, Florence Poinard, Anne-Marie Tissier, Idris Boudhabhay, Jean-Michel Correas, Dany Anglicheau, Maria Vakalopoulou, Marc-Olivier Timsit
{"title":"Renal Transplant Survival Prediction From Unsupervised Deep Learning-Based Radiomics on Early Dynamic Contrast-Enhanced MRI.","authors":"Léo Milecki, Sylvain Bodard, Vicky Kalogeiton, Florence Poinard, Anne-Marie Tissier, Idris Boudhabhay, Jean-Michel Correas, Dany Anglicheau, Maria Vakalopoulou, Marc-Olivier Timsit","doi":"10.1016/j.acra.2025.05.001","DOIUrl":"https://doi.org/10.1016/j.acra.2025.05.001","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>End-stage renal disease is characterized by an irreversible decline in kidney function. Despite a risk of chronic dysfunction of the transplanted kidney, renal transplantation is considered the most effective solution among available treatment options. Clinical attributes of graft survival prediction, such as allocation variables or results of pathological examinations, have been widely studied. Nevertheless, medical imaging is clinically used only to assess current transplant status. This study investigated the use of unsupervised deep learning-based algorithms to identify rich radiomic features that may be linked to graft survival from early dynamic contrast-enhanced magnetic resonance imaging data of renal transplants.</p><p><strong>Materials and methods: </strong>A retrospective cohort of 108 transplanted patients (mean age 50 +/- 15, 67 men) undergoing systematic magnetic resonance imaging follow-up examinations (2013 to 2015) was used to train deep convolutional neural network models based on an unsupervised contrastive learning approach. 5-year graft survival analysis was performed from the obtained artificial intelligence radiomics features using penalized Cox models and Kaplan-Meier estimates.</p><p><strong>Results: </strong>Using a validation set of 48 patients (mean age 54 +/- 13, 30 men) having 1-month post-transplantation magnetic resonance imaging examinations, the proposed approach demonstrated promising 5-year graft survival capability with a 72.7% concordance index from the artificial intelligence radiomics features. Unsupervised clustering of these radiomics features enabled statistically significant stratification of patients (p=0.029).</p><p><strong>Conclusion: </strong>This proof-of-concept study exposed the promising capability of artificial intelligence algorithms to extract relevant radiomics features that enable renal transplant survival prediction. Further studies are needed to demonstrate the robustness of this technique, and to identify appropriate procedures for integration of such an approach into multimodal and clinical settings.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144144320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep Learning and Radiomic Signatures Associated with Tumor Immune Heterogeneity Predict Microvascular Invasion in Colon Cancer. 与肿瘤免疫异质性相关的深度学习和放射学特征预测结肠癌微血管侵袭。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-23 DOI: 10.1016/j.acra.2025.05.006
Jianye Jia, Jiahao Wang, Yongxian Zhang, Genji Bai, Lei Han, Yantao Niu
{"title":"Deep Learning and Radiomic Signatures Associated with Tumor Immune Heterogeneity Predict Microvascular Invasion in Colon Cancer.","authors":"Jianye Jia, Jiahao Wang, Yongxian Zhang, Genji Bai, Lei Han, Yantao Niu","doi":"10.1016/j.acra.2025.05.006","DOIUrl":"https://doi.org/10.1016/j.acra.2025.05.006","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>This study aims to develop and validate a deep learning radiomics signature (DLRS) that integrates radiomics and deep learning features for the non-invasive prediction of microvascular invasion (MVI) in patients with colon cancer (CC). Furthermore, the study explores the potential association between DLRS and tumor immune heterogeneity.</p><p><strong>Materials and methods: </strong>This study is a multi-center retrospective study that included a total of 1007 patients with colon cancer (CC) from three medical centers and The Cancer Genome Atlas (TCGA-COAD) database. Patients from Medical Centers 1 and 2 were divided into a training cohort (n = 592) and an internal validation cohort (n = 255) in a 7:3 ratio. Medical Center 3 (n = 135) and the TCGA-COAD database (n = 25) were used as external validation cohorts. Radiomics and deep learning features were extracted from contrast-enhanced venous-phase CT images. Feature selection was performed using machine learning algorithms, and three predictive models were developed: a radiomics model, a deep learning (DL) model, and a combined deep learning radiomics (DLR) model. The predictive performance of each model was evaluated using multiple metrics, including the area under the curve (AUC), sensitivity, and specificity. Additionally, differential gene expression analysis was conducted on RNA-seq data from the TCGA-COAD dataset to explore the association between the DLRS and tumor immune heterogeneity within the tumor microenvironment.</p><p><strong>Results: </strong>Compared to the standalone radiomics and deep learning models, DLR fusion model demonstrated superior predictive performance. The AUC for the internal validation cohort was 0.883 (95% CI: 0.828-0.937), while the AUC for the external validation cohort reached 0.855 (95% CI: 0.775-0.935). Furthermore, stratifying patients from the TCGA-COAD dataset into high-risk and low-risk groups based on the DLRS revealed significant differences in immune cell infiltration and immune checkpoint expression between the two groups (P < 0.05).</p><p><strong>Conclusion: </strong>The contrast-enhanced CT-based DLR fusion model developed in this study effectively predicts the MVI status in patients with CC. This model serves as a non-invasive preoperative assessment tool and reveals a potential association between the DLRS and immune heterogeneity within the tumor microenvironment, providing insights to optimize individualized treatment strategies.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144144315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep Learning-Based Multimodal Feature Interaction-Guided Fusion: Enhancing the Evaluation of EGFR in Advanced Lung Adenocarcinoma. 基于深度学习的多模态特征交互引导融合:增强晚期肺腺癌EGFR的评估。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-22 DOI: 10.1016/j.acra.2025.04.071
Junhui Xu, Bao Feng, Xiangmeng Chen, Fei Wu, Yu Liu, Zhaole Yu, Senliang Lu, Xiaobei Duan, Xiaojuan Chen, Kunwei Li, Weibin Zhang, Xisheng Dai
{"title":"Deep Learning-Based Multimodal Feature Interaction-Guided Fusion: Enhancing the Evaluation of EGFR in Advanced Lung Adenocarcinoma.","authors":"Junhui Xu, Bao Feng, Xiangmeng Chen, Fei Wu, Yu Liu, Zhaole Yu, Senliang Lu, Xiaobei Duan, Xiaojuan Chen, Kunwei Li, Weibin Zhang, Xisheng Dai","doi":"10.1016/j.acra.2025.04.071","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.071","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The aim of this study is to develop a deep learning-based multimodal feature interaction-guided fusion (DL-MFIF) framework that integrates macroscopic information from computed tomography (CT) images with microscopic information from whole-slide images (WSIs) to predict the epidermal growth factor receptor (EGFR) mutations of primary lung adenocarcinoma in patients with advanced-stage disease.</p><p><strong>Materials and methods: </strong>Data from 396 patients with lung adenocarcinoma across two medical institutions were analyzed. The data from 243 cases were divided into a training set (n=145) and an internal validation set (n=98) in a 6:4 ratio, and data from an additional 153 cases from another medical institution were included as an external validation set. All cases included CT scan images and WSIs. To integrate multimodal information, we developed the DL-MFIF framework, which leverages deep learning techniques to capture the interactions between radiomic macrofeatures derived from CT images and microfeatures obtained from WSIs.</p><p><strong>Results: </strong>Compared to other classification models, the DL-MFIF model achieved significantly higher area under the curve (AUC) values. Specifically, the model outperformed others on both the internal validation set (AUC=0.856, accuracy=0.750) and the external validation set (AUC=0.817, accuracy=0.708). Decision curve analysis (DCA) demonstrated that the model provided superior net benefits(range 0.15-0.87). Delong's test for external validation confirmed the statistical significance of the results (P<0.05).</p><p><strong>Conclusion: </strong>The DL-MFIF model demonstrated excellent performance in evaluating and distinguishing the EGFR in patients with advanced lung adenocarcinoma. This model effectively aids radiologists in accurately classifying EGFR mutations in patients with primary lung adenocarcinoma, thereby improving treatment outcomes for this population.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Effect of Incidence Sites on Light Distribution at Different Wavelengths During Transcranial Photobiomodulation. 经颅光生物调节中入射部位对不同波长光分布的影响。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-22 DOI: 10.1016/j.acra.2025.04.076
Bowen Zhang, Songqi Yang, Meihua Piao, Polun Chang, Ting Li
{"title":"Effect of Incidence Sites on Light Distribution at Different Wavelengths During Transcranial Photobiomodulation.","authors":"Bowen Zhang, Songqi Yang, Meihua Piao, Polun Chang, Ting Li","doi":"10.1016/j.acra.2025.04.076","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.076","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Transcranial photobiomodulation (tPBM) has emerged as a promising noninvasive therapeutic technique for neurological diseases, such as Alzheimer's Disease and Stroke. However, the optimal incidence site for precise stimulation remains unclear. To address this, we aimed to employ the high-resolution Visible Chinese Human (VCH) dataset and Monte Carlo simulation to identify the most suitable incidence site.</p><p><strong>Materials and methods: </strong>Monte Carlo model for photon migration in voxelized media (MCVM) was applied to visualize and compare the photon distribution across different incidence sites. We selected four representative incidence sites in the frontal, parietal, occipital, and temporal lobes and simulated photon propagation at four wavelengths commonly used in tPBM studies: 660 nm, 810 nm, 980 nm, and 1064 nm.</p><p><strong>Results: </strong>For each wavelength, the light source incident from prefrontal lobe had the deepest penetration depth (7 cm, 7 cm, 5 cm, 5 cm for 660 cm, 810 nm, 980 nm, 1064 nm, respectively) and the widest irradiation range (15%, 20%, 13%, 14% of brain for 660 cm, 810 nm, 980 nm, 1064 nm, respectively), while that incident from temporal lobe ensured the highest photon fluence reaching brain parenchyma. When the same light source (the input power was normalized to 1) was respectively applied at four incidence sites, ∼1×10<sup>-3</sup> 1/cm<sup>2</sup> of photon fluence reached brain parenchyma for prefrontal lobe, ∼7.5×10<sup>-5</sup> 1/cm<sup>2</sup> for parietal lobe, ∼1.5×10<sup>-3</sup> 1/cm<sup>2</sup> for occipital lobe, and ∼2.8×10<sup>-2</sup> 1/cm<sup>2</sup> for temporal lobe. To achieve similar photon fluence reaching brain parenchyma across all brain regions during whole-brain tPBM stimulation, we recommended setting the input power ratios of light source at four sites as ∼17:280:20:1 (prefrontal: parietal: occipital: temporal) for 660 nm light, ∼22:250:18:1 for 810 nm, ∼60:1450:20:1 for 980 nm, and ∼54:830:17:1 for 1064 nm.</p><p><strong>Conclusion: </strong>From the perspective of photon delivery to the brain, the prefrontal and temporal lobes were two more optimal locations for light source placement. This study provided a theoretical strategy for optimizing incidence sites in tPBM.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep Learning Image Reconstruction (DLIR) Algorithm to Maintain High Image Quality and Diagnostic Accuracy in Quadruple-low CT Angiography of Children with Pulmonary Sequestration: A Case Control Study. 深度学习图像重建(DLIR)算法在肺隔离儿童四倍低CT血管造影中保持高图像质量和诊断准确性:一项病例对照研究。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-22 DOI: 10.1016/j.acra.2025.05.005
Haoyan Li, Yuchen Zhang, Shan Hua, Ruifang Sun, Yunxian Zhang, Zhi Yang, Yun Peng, Jihang Sun
{"title":"Deep Learning Image Reconstruction (DLIR) Algorithm to Maintain High Image Quality and Diagnostic Accuracy in Quadruple-low CT Angiography of Children with Pulmonary Sequestration: A Case Control Study.","authors":"Haoyan Li, Yuchen Zhang, Shan Hua, Ruifang Sun, Yunxian Zhang, Zhi Yang, Yun Peng, Jihang Sun","doi":"10.1016/j.acra.2025.05.005","DOIUrl":"https://doi.org/10.1016/j.acra.2025.05.005","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>CT angiography (CTA) is a commonly used clinical examination to detect abnormal arteries and diagnose pulmonary sequestration (PS). Reducing the radiation dose, contrast medium dosage, and injection pressure in CTA, especially in children, has always been an important research topic, but few research is proven by pathology. The current study aimed to evaluate the diagnostic accuracy for children with PS in a quadruple-low CTA (4L-CTA: low tube voltage, radiation, contrast medium, and injection flow rate) using deep learning image reconstruction (DLIR) in comparison with routine protocol CTA with adaptive statistical iterative reconstruction-V (ASIR-V) MATERIALS AND METHODS: 53 patients (1.50±1.36years) suspected with PS were enrolled to undergo chest 4L-CTA using 70kVp tube voltage with radiation dose or 0.90 mGy in volumetric CT dose index (CTDIvol) and contrast medium dose of 0.8 ml/kg injected in 16 s. Images were reconstructed using DLIR. Another 53 patients (1.25±1.02years) with a routine dose protocol was used for comparison, and images were reconstructed with ASIR-V. The contrast-to-noise ratio (CNR) and edge-rise distance (ERD) of the aorta were calculated. The subjective overall image quality and artery visualization were evaluated using a 5-point scale (5, excellent; 3, acceptable). All patients underwent surgery after CT, the sensitivity and specificity for diagnosing PS were calculated.</p><p><strong>Results: </strong>4L-CTA reduced radiation dose by 51%, contrast dose by 47%, injection flow rate by 44% and injection pressure by 44% compared to the routine CTA (all p<0.05). Both groups had satisfactory subjective image quality and achieved 100% in both sensitivity and specificity for diagnosing PS. 4L-CTA had a reduced CNR (by 27%, p<0.05) but similar ERD, which reflects the image spatial resolution (p>0.05) compared to the routine CTA. 4L-CTA revealed small arteries with a diameter of 0.8 mm.</p><p><strong>Conclusion: </strong>DLIR ensures the realization of 4L-CTA in children with PS for significant radiation and contrast dose reduction, while maintaining image quality, visualization of small arteries, and high diagnostic accuracy.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Radiology's Surprising Role in the Soviet Resistance: Bone Music. 放射学在苏联抵抗运动中的惊人作用:骨音乐。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-22 DOI: 10.1016/j.acra.2025.04.050
Wyatt D Reed, Molly Beatty, Richard B Gunderman
{"title":"Radiology's Surprising Role in the Soviet Resistance: Bone Music.","authors":"Wyatt D Reed, Molly Beatty, Richard B Gunderman","doi":"10.1016/j.acra.2025.04.050","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.050","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Unraveling Rescue Thrombectomy for Mild Large Vessel Occlusion Stroke Following Medical Management: Insights From a Multicenter Retrospective Study. 医学治疗后轻度大血管闭塞性卒中的急诊血栓切除术:来自多中心回顾性研究的见解
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-21 DOI: 10.1016/j.acra.2025.04.074
Hu Huang, Chunjie Song, Yuanyuan Han
{"title":"Unraveling Rescue Thrombectomy for Mild Large Vessel Occlusion Stroke Following Medical Management: Insights From a Multicenter Retrospective Study.","authors":"Hu Huang, Chunjie Song, Yuanyuan Han","doi":"10.1016/j.acra.2025.04.074","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.074","url":null,"abstract":"<p><strong>Background: </strong>Although rescue thrombectomy is performed in mild (National Institutes of Health Stroke Scale ≤ 5) large vessel occlusion (LVO) stroke patients who experience early neurological deterioration (END) following best medical management (BMM), clinical outcomes remain highly variable. This study aimed to identify key determinants influencing outcomes in this population.</p><p><strong>Methods: </strong>We retrospectively analyzed consecutive mild LVO patients who initially received BMM and later underwent rescue thrombectomy for END, across four centers between January 2019 and June 2024. END was defined as an NIHSS increase of ≥ 4 points or a total score of ≥ 6 within the first 24 h, without hemorrhage. Multivariable logistic regression was performed to identify factors associated with outcomes. Receiver operating characteristic curve analysis was performed to assess the predictive performance using the area under the curve (AUC).</p><p><strong>Results: </strong>Among 347 patients with mild LVO who underwent BMM, 66 patients who developed END and underwent rescue thrombectomy were included in this study. Of these, 31 (47.0%) achieved poor outcome (90-day modified Rankin Scale score of 3-6). Multivariable analysis identified prolonged deterioration-to-groin puncture time (OR: 1.79 per 10-minute increase, 95% CI: 1.48-2.54) and basilar artery occlusion (OR: 1.42, 95% CI: 1.16-2.08) were independently associated with poor outcomes. The AUC for predicting poor outcomes was 0.828 for deterioration-to-groin puncture time, 0.690 for basilar artery occlusion, and 0.906 for their combination.</p><p><strong>Conclusion: </strong>Delayed initiation of thrombectomy and basilar artery occlusion were predictors for poor outcomes in patients who underwent rescue thrombectomy after BMM.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Corrigendum to "Ultrasound-Based Deep Learning Radiomics Nomogram for Tumor and Axillary Lymph Node Status Prediction After Neoadjuvant Chemotherapy" [Academic Radiology 32 (2025) 12-23]. “基于超声的肿瘤和腋窝淋巴结状态预测的深度学习放射组学Nomogram新辅助化疗”[学术放射学32(2025)12-23]的更正。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-21 DOI: 10.1016/j.acra.2025.05.010
Yue-Xia Liu, Qing-Hua Liu, Quan-Hui Hu, Jia-Yao Shi, Gui-Lian Liu, Han Liu, Sheng-Chun Shu
{"title":"Corrigendum to \"Ultrasound-Based Deep Learning Radiomics Nomogram for Tumor and Axillary Lymph Node Status Prediction After Neoadjuvant Chemotherapy\" [Academic Radiology 32 (2025) 12-23].","authors":"Yue-Xia Liu, Qing-Hua Liu, Quan-Hui Hu, Jia-Yao Shi, Gui-Lian Liu, Han Liu, Sheng-Chun Shu","doi":"10.1016/j.acra.2025.05.010","DOIUrl":"https://doi.org/10.1016/j.acra.2025.05.010","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Right Ventricular Strain as a Key Feature in Interpretable Machine Learning for Identification of Takotsubo Syndrome: A Multicenter CMR-based Study. 右心室应变作为可解释机器学习识别Takotsubo综合征的关键特征:一项基于多中心cmr的研究。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-21 DOI: 10.1016/j.acra.2025.04.068
Zeliu Du, Hongfei Hu, Chenqi Shen, Jie Mei, Ye Feng, Yechao Huang, Xinyu Chen, Xinyu Guo, Zhanning Hu, Liyan Jiang, Yanping Su, Jumatay Biekan, Lingchun Lyv, TouKun Chong, Cunxue Pan, Kan Liu, Jiansong Ji, Chenying Lu
{"title":"Right Ventricular Strain as a Key Feature in Interpretable Machine Learning for Identification of Takotsubo Syndrome: A Multicenter CMR-based Study.","authors":"Zeliu Du, Hongfei Hu, Chenqi Shen, Jie Mei, Ye Feng, Yechao Huang, Xinyu Chen, Xinyu Guo, Zhanning Hu, Liyan Jiang, Yanping Su, Jumatay Biekan, Lingchun Lyv, TouKun Chong, Cunxue Pan, Kan Liu, Jiansong Ji, Chenying Lu","doi":"10.1016/j.acra.2025.04.068","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.068","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To develop an interpretable machine learning (ML) model based on cardiac magnetic resonance (CMR) multimodal parameters and clinical data to discriminate Takotsubo syndrome (TTS), acute myocardial infarction (AMI), and acute myocarditis (AM), and to further assess the diagnostic value of right ventricular (RV) strain in TTS.</p><p><strong>Materials and methods: </strong>This study analyzed CMR and clinical data of 130 patients from three centers. Key features were selected using least absolute shrinkage and selection operator regression and random forest. Data were split into a training cohort and an internal testing cohort (ITC) in the ratio 7:3, with overfitting avoided using leave-one-out cross-validation and bootstrap methods. Nine ML models were evaluated using standard performance metrics, with Shapley additive explanations (SHAP) analysis used for model interpretation.</p><p><strong>Results: </strong>A total of 11 key features were identified. The extreme gradient boosting model showed the best performance, with an area under the curve (AUC) value of 0.94 (95% CI: 0.85-0.97) in the ITC. Right ventricular basal circumferential strain (RVCS-basal) was the most important feature for identifying TTS. Its absolute value was significantly higher in TTS patients than in AMI and AM patients (-9.93%, -5.21%, and -6.18%, respectively, p < 0.001), with values above -6.55% contributing to a diagnosis of TTS.</p><p><strong>Conclusion: </strong>This study developed an interpretable ternary classification ML model for identifying TTS and used SHAP analysis to elucidate the significant value of RVCS-basal in TTS diagnosis. An online calculator (https://lsszxyy.shinyapps.io/XGboost/) based on this model was developed to provide immediate decision support for clinical use.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Serum Carotenoid Concentrations Are Associated with Enlarged Choroid Plexus, Lateral Ventricular Volume, and Perivascular Spaces on Magnetic Resonance Imaging: A Large Cohort Study. 磁共振成像显示血清类胡萝卜素浓度与脉络膜丛、侧室容积和血管周围空间增大有关:一项大型队列研究。
IF 3.8 2区 医学
Academic Radiology Pub Date : 2025-05-20 DOI: 10.1016/j.acra.2025.04.048
Jusei Kudo, Keita Watanabe, Miho Sasaki, Tomohiro Shintaku, Shinya Kakehata, Sera Kasai, Kana Saito, Tatsuya Mikami, Daichi Kokubu, Yusuke Ushida, Masashi Matsuzaka, Shingo Kakeda
{"title":"Serum Carotenoid Concentrations Are Associated with Enlarged Choroid Plexus, Lateral Ventricular Volume, and Perivascular Spaces on Magnetic Resonance Imaging: A Large Cohort Study.","authors":"Jusei Kudo, Keita Watanabe, Miho Sasaki, Tomohiro Shintaku, Shinya Kakehata, Sera Kasai, Kana Saito, Tatsuya Mikami, Daichi Kokubu, Yusuke Ushida, Masashi Matsuzaka, Shingo Kakeda","doi":"10.1016/j.acra.2025.04.048","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.048","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Since carotenoids have various physiological activities, including antioxidant activity, several epidemiological studies have linked the consumption of a carotenoid-rich diet to a decreased risk of neurodegenerative diseases. Increased choroid plexus volume (CPV) and enlarged perivascular spaces (PVS) on brain magnetic resonance imaging (MRI) may be indicators of impaired glymphatic system function. The purpose of this large-scale elderly population study was to assess whether serum concentrations of major carotenoids (α-carotene, β-carotene, cis-lycopene, trans-lycopene, β-cryptoxanthin, zeaxanthin, and lutein) concentrations are associated with CPV, lateral ventricular volume (LVV), and PVS.</p><p><strong>Materials and methods: </strong>This cross-sectional study included 2050 individuals (median age, 69 years; 61.02% females) who underwent 3 T MRI. The imaging characteristics included total intracranial volume (ICV), CPV, LVV, and basal ganglia-enlarged PVS on T2-weighted images.</p><p><strong>Results: </strong>Low serum β-carotene concentration was a significant independent predictor of increased CPV/ICV (p=0.046), increased LVV/ICV (p=0.035), and enlarged PVS (p=0.009) after adjusting for potential confounders (age, sex, body mass index, HbA1c level, systolic blood pressure, smoking history, drinking history, educational history, and Mini-Mental State Examination score, CRP level). Low serum α-carotene concentration was also a significant independent predictor of an enlarged PVS (p=0.014).</p><p><strong>Conclusion: </strong>In this study, β-carotene concentration was associated to the CPV, LVV, and PVS, suggesting that the antioxidant activity of β-carotene may have an important role in maintaining glymphatic system function. Since β-carotene is a dietary carotenoid, our results emphasize the importance of interventions for effective β-carotene intake among elderly people.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144120702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信