Academic Radiology最新文献

{"title":"Prediction of Radiation Therapy Induced Cardiovascular Toxicity from Pretreatment CT Images in Patients with Thoracic Malignancy via an Optimal Biomarker Approach.","authors":"Mujun Long, Mostafa Alnoury, Jayaram K Udupa, Yubing Tong, Caiyun Wu, Nicholas Poole, Sutirth Mannikeri, Bonnie Ky, Steven J Feigenberg, Jennifer W Zou, Shannon O'Reilly, Drew A Torigian","doi":"10.1016/j.acra.2025.01.012","DOIUrl":"https://doi.org/10.1016/j.acra.2025.01.012","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Cardiovascular toxicity is a well-known complication of thoracic radiation therapy (RT), leading to increased morbidity and mortality, but existing techniques to predict cardiovascular toxicity have limitations. Predictive biomarkers of cardiovascular toxicity may help to maximize patient outcomes.</p><p><strong>Methods: </strong>The machine learning optimal biomarker (OBM) method was employed to predict development of cardiotoxicity (based on serial echocardiographic measurements of left ventricular ejection fraction and longitudinal strain) from computed tomography (CT) images in patients with thoracic malignancy undergoing RT. Manual segmentations of 10 cardiovascular objects of interest were performed on pre-treatment non-contrast-enhanced CT simulation images in 125 patients with thoracic malignancy (41 who developed cardiotoxicity and 84 who did not after RT). 1078 features describing morphology, image intensity, and texture for each of these objects were extracted and the top 5 features among them that were most uncorrelated and showed the best ability to discriminate between cardiotoxicity/ no cardiotoxicity were determined. The best combination among all possible combinations among these 5 features that yielded the highest accuracy of prediction on a training data set was selected, an SVM classifier was then trained on this combination, and tested for prediction accuracy on an independent data set. Prediction accuracy was quantified for the optimal features derived from each object.</p><p><strong>Results: </strong>The best feature combination based on 5 CT-based features derived from the left ventricle had the highest testing prediction accuracy of 0.88 among all objects. Prediction accuracies over all objects ranged from 0.76-0.88. Heart, Left Atrium, Aortic Arch, Thoracic Aorta, and Descending Thoracic Aorta showed the next best accuracy of 0.84. Most optimal features were texture properties based on the co-occurrence matrix.</p><p><strong>Conclusion: </strong>It is feasible to predict future cardiotoxicity following RT with high accuracy in individual patients with thoracic malignancy from available pre-treatment CT images via machine learning techniques.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054125","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}

{"title":"Machine Learning Model for Risk Stratification of Papillary Thyroid Carcinoma Based on Radiopathomics.","authors":"Xiaoling Liu, Jiao Yao, Di Wang, Weihan Xiao, Wang Zhou, Lin Li, Fanding He, Yujie Luo, Mengyao Xiao, Ziqing Yang, Guixiang Yang, Xiachuan Qin","doi":"10.1016/j.acra.2024.12.062","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.062","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>This study aims to develop a radiopathomics model based on preoperative ultrasound and fine-needle aspiration cytology (FNAC) images to enable accurate, non-invasive preoperative risk stratification for patients with papillary thyroid carcinoma (PTC). The model seeks to enhance clinical decision-making by optimizing preoperative treatment strategies.</p><p><strong>Methods: </strong>A retrospective analysis was conducted on data from PTC patients who underwent thyroidectomy between October 2022 and May 2024 across six centers. Based on lymph node dissection outcomes, patients were categorized into high-risk and low-risk groups. Initially, a clinical predictive model was established based on the maximum diameter of the thyroid nodules. Radiomics features were extracted from preoperative two-dimensional ultrasound images, and pathomics features were extracted from 400x magnification H&E-stained tumor cell images from FNAC. The most predictive radiomics and pathomics features were identified through univariate analysis, Pearson correlation analysis and LASSO algorithm. The most valuable radiopathomics features were then selected by combining these predictive features. Finally, machine learning with the XGBoost algorithm was employed to construct radiomics, pathomics, and radiopathomics models. The performance of the models was evaluated using the area under the curve (AUC), decision curve analysis, accuracy, specificity, sensitivity, positive predictive value, and negative predictive value.</p><p><strong>Results: </strong>A total of 688 PTC patients were included, with 344 classified as intermediate/high-risk and 344 as low-risk. The multimodal radiopathomics model demonstrated excellent predictive performance, with AUCs of 0.886 (95% CI: 0.829-0.924) and 0.828 (95% CI: 0.751-0.879) in two external validation cohorts, significantly outperforming the clinical model (AUCs of 0.662 and 0.601), radiomics model (AUCs of 0.702 and 0.697), and pathomics model (AUCs of 0.741 and 0.712).</p><p><strong>Conclusion: </strong>The radiopathomics model exhibits significant advantages in accurately predicting preoperative risk stratification in PTC patients. Its application is expected to reduce unnecessary lymph node dissection surgeries, optimize treatment strategies, and improve therapeutic outcomes.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054114","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}

{"title":"Non-invasive Assessment of Human Epidermal Growth Factor Receptor 2 Expression in Gastric Cancer Based on Deep Learning: A Computed Tomography-based Multicenter Study.","authors":"Zhong-Hui Wu, Xiao-Rong Ren, Yu-Qi Meng, Xin-Yun Wang, Ning-Xin Yang, Xiao-Yu Wang, Gang Ren","doi":"10.1016/j.acra.2024.12.041","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.041","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The expression of human epidermal growth factor receptor 2 (HER2) in gastric cancer is closely associated with its treatment outcomes and prognosis. This study aims to develop and validate a HER2 prediction model based on computed tomography (CT). Additionally, the study evaluates the robustness of the proposed model.</p><p><strong>Materials and methods: </strong>This retrospective study included 1059 patients from three hospitals (A, B, and C), where patients from hospitals A and B formed the training set (720 cases), and patients from hospital C served as the external test set (339 cases). Venous-phase CT radiomic features were extracted, normalized using the Z-score method, and simplified via principal component analysis. Feature selection was performed using recursive feature elimination (RFE), analysis of variance, Relief, and the Kruskal-Wallis (KW) test, followed by modeling using Lasso-regularized logistic regression and Support Vector Machine (SVM) methods. The models were evaluated and validated using the area under the curve (AUC) and decision curve analysis to determine the best-performing model.</p><p><strong>Results: </strong>The positive proportions of HER2 expression were 8.60% (52/658) in the training set and 5.60% (19/320) in the test set. Eight distinct models were developed to predict HER2 expression. Among these, the model utilizing RFE and Lasso-regularized logistic regression (LR-Lasso) exhibited the highest predictive performance, with AUC values of 0.7874 (95% CI: 0.7346-0.8402) in the training set and 0.8033 (95% CI: 0.7288-0.8788) in the test set. Compared to other models, this model provided a greater net benefit on the decision curve analysis. These results suggest that the proposed model can be effectively applied to predict HER2 expression in patients.</p><p><strong>Conclusion: </strong>The HER2 prediction model demonstrated promising performance in predicting HER2 expression in gastric cancer patients.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054117","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}

{"title":"Unlocking Innovation: Promoting Scholarly Endeavors During Radiology Residency.","authors":"John P Karns, Clara Melhem, Arif Musa, Hassan Shaban, Jarrett Weinberger, Foaz Kayali","doi":"10.1016/j.acra.2025.01.009","DOIUrl":"https://doi.org/10.1016/j.acra.2025.01.009","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054128","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}

{"title":"Longitudinal Assessment of Pulmonary Involvement and Prognosis in Different Subtypes of COVID-19 Patients After One Year Using Low-Dose CT: A Prospective Observational Study.","authors":"Jinyang Zhao, Liang Dong, Xue Jiao, Fan Xia, Qi Shan, Jiawen Tang, Sihan Wang, Xiaohong Lyu","doi":"10.1016/j.acra.2025.01.006","DOIUrl":"https://doi.org/10.1016/j.acra.2025.01.006","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Severe COVID-19 typically results in pulmonary sequelae. However, current research lacks clarity on the differences in these sequelae among various clinical subtypes. This study aimed to evaluate the changing lung imaging features and predictive factors in patients with COVID-19 pneumonia in northern China over a 12-month follow-up period after the relaxation of COVID-19 restrictions in 2022.</p><p><strong>Materials and methods: </strong>Imaging and clinically relevant data from three groups (moderate, severe, and critical) of patients with varying severity were prospectively analyzed. Low-dose CT scans were conducted at 3, 6, and 12 months after discharge, with chest CT images evaluated at baseline and each follow-up using qualitative and quantitative analyses. Clinical symptoms and pulmonary function recovery at 12 months were documented. The correlation between lung function and CT results was analyzed. Univariate and multivariable logistic regression analyses were employed to examine factors influencing prognosis, while a post-hoc analysis model was utilized to investigate the relationships among different groups, time points, and chest CT findings.</p><p><strong>Results: </strong>Among the 103 hospitalized patients with COVID-19 pneumonia, 64 completed the 12-month evaluation. The median age was 63.70 ± 12.15%, and 62.5% (40/64) were men. During the follow-up period, while 67.19% (43/64) showed abnormalities, including fibrotic changes in 9.38% (6/64). Multivariable logistic regression identified age ≥ 65 (OR: 8.66; 95% CI: 1.86, 40.34; P = 0.006), length of hospital stays (OR: 1.23; 95% CI: 1.03, 1.47; P = 0.022), and baseline consolidation volume as a percentage of the whole lung (OR: 56.95; 95% CI: 1.198, 2706.782; P = 0.04) as independent risk factors for persistent CT lung abnormalities at 1 year. After 1 year, 34.38% (22/64) of patients still had abnormal lung function, and 9.38% (6/64) had pulmonary fibrosis and restrictive ventilatory dysfunction. The relationship between lung function and CT findings is weak correlation. The mixed model analysis revealed significant differences between groups, particularly between the moderate and severe groups, and significant changes in CT values over time.</p><p><strong>Conclusion: </strong>One year after infection, more than one third of even moderate patients with mild symptoms had persistent pulmonary abnormalities. In our study, fibrotic changes were seen in severe and critically ill patients and remained stable 6 months after discharge from hospital. Imaging parameters can predict the prognosis. The larger the extent of baseline consolidation, the worse the prognosis of elderly patients.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143048709","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}

{"title":"Quantitative and Visual Benefits of Data-Driven Motion Correction on Oncologic PET/CT: A Prospective Cross-sectional Study.","authors":"Semra Ince, M Allan Thomas, Malak Itani, Christopher Swingle, Richard Laforest, Adeel Haq, Genevieve Muñoz, Saeed Ashrafinia, Paul Schleyer, Richard L Wahl, Tyler J Fraum","doi":"10.1016/j.acra.2024.12.016","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.016","url":null,"abstract":"<p><strong>Rationale and objective: </strong>Conventional positron emission tomography (PET) respiratory gating utilizes a fraction of acquired PET counts (i.e., optimal gate [OG]), whereas elastic motion correction with deblurring (EMCD) utilizes all PET counts to reconstruct motion-corrected images without increasing image noise. Our aim was to assess the quantitative and visual impacts of EMCD-based motion correction on FDG-PET and DOTATATE-PET images relative to OG and ungated (UG) images.</p><p><strong>Materials and methods: </strong>This prospective, single-center study enrolled adults undergoing FDG or DOTATATE oncologic PET/CT between June 2020 and October 2022. Subjects underwent a standard-of-care (SOC) PET acquisition while wearing a respiratory gating belt. UG, belt-gating-derived optimal gate (BG-OG), EMCD utilizing belt gating (BG-EMCD), and EMCD utilizing data-driven gating (DDG-EMCD) images were reconstructed. Tracer-avid lesions in the lower chest or upper abdomen were segmented. Quantitative metrics were extracted. Two independent, blinded readers assessed image quality via a 4-point scale and counted lesions on each reconstruction. Differences between reconstructions were assessed via the Wilcoxon signed-rank test (alpha, 0.05).</p><p><strong>Results: </strong>This study enrolled 78 subjects; 36 subjects (mean age, 64.8 years; 20 males) with 136 tracer-avid lesions were analyzed. Data provided are medians across all tracers. Lesion SUV-max was significantly higher (P<0.001) on motion-corrected images (BG-OG: 10.77, BG-EMCD: 10.75, DDG-EMCD: 10.74) than UG images (9.00). Lesion contrast-to-noise ratios (CNRs) were significantly lower (P<0.001) for BG-OG (6.31) and UG images (7.89) than BG-EMCD (9.14) and DDG-EMCD (8.89) images. FDG and DOTATATE subgroup analyses produced similar results. Among motion-corrected images, both readers preferred EMCD-based images to BG-OG images for all tracers (P<0.001) and both subgroups. EMCD-based images occasionally demonstrated more tracer-avid lesions than BG-OG or UG images.</p><p><strong>Conclusion: </strong>EMCD-based motion correction beneficially impacts lesion quantitation (including higher SUVs and CNRs) and overall image quality.</p><p><strong>Clinical impact: </strong>When employed on capable scanners, EMCD can improve the quality of oncologic PET imaging.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143043212","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}

{"title":"Photoacoustic Imaging with Attention-Guided Deep Learning for Predicting Axillary Lymph Node Status in Breast Cancer.","authors":"Guoqiu Li, Shuzhen Tang, Zhibin Huang, Mengyun Wang, Hongtian Tian, Huaiyu Wu, Sijie Mo, Jinfeng Xu, Fajin Dong","doi":"10.1016/j.acra.2024.12.020","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.020","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Preoperative assessment of axillary lymph node (ALN) status is essential for breast cancer management. This study explores the use of photoacoustic (PA) imaging combined with attention-guided deep learning (DL) for precise prediction of ALN status.</p><p><strong>Materials and methods: </strong>This retrospective study included patients with histologically confirmed early-stage breast cancer from 2022 to 2024, randomly divided (8:2) into training and test cohorts. All patients underwent preoperative dual modal photoacoustic-ultrasound (PA-US) examination, were treated with surgery and sentinel lymph node biopsy or ALN dissection, and were pathologically examined to determine the ALN status. Attention-guided DL model was developed using PA-US images to predict ALN status. A clinical model, constructed via multivariate logistic regression, served as the baseline for comparison. Subsequently, a nomogram incorporating the DL model and independent clinical parameters was developed. The performance of the models was evaluated through discrimination, calibration, and clinical applicability.</p><p><strong>Results: </strong>A total of 324 patients (mean age ± standard deviation, 51.0 ± 10.9 years) were included in the study and were divided into a development cohort (n = 259 [79.9%]) and a test cohort (n = 65 [20.1%]). The clinical model incorporating three independent clinical parameters yielded an area under the curve (AUC) of 0.775 (95% confidence interval [CI], 0.711-0.829) in the training cohort and 0.783 (95% CI, 0.654-0.897) in the test cohort for predicting ALN status. In comparison, the nomogram showed superior predictive performance, with an AUC of 0.906 (95% CI, 0.867-0.940) in the training cohort and 0.868 (95% CI, 0.769-0.954) in the test cohort. Decision curve analysis further confirmed the nomogram's clinical applicability, demonstrating a better net benefit across relevant threshold probabilities.</p><p><strong>Conclusion: </strong>This study highlights the effectiveness of attention-guided PA imaging in breast cancer patients, providing novel nomograms for individualized clinical decision-making in predicting ALN node status.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143030175","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}

{"title":"Adjuvant transarterial chemoembolization in resected macrotrabecular-massive hepatocellular carcinoma (ATAC-MACRO): a multicenter real-world retrospective study.","authors":"Qingjun Li, Xu Chang, Jiaye Gu, Yi Yang, Jingzhong Ouyang, Yanzhao Zhou, Hong Zhao, Jinxue Zhou","doi":"10.1016/j.acra.2024.12.053","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.053","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The purpose of this study was to demonstrate the impact of postoperative adjuvant transarterial chemoembolization (TACE) on the prognosis of patients with macrotrabecular-massive hepatocellular carcinoma (MTM-HCC).</p><p><strong>Materials and methods: </strong>This retrospective study used the clinical records of patients with resected MTM-HCC with/without adjuvant TACE at three centers between January 2015 and December 2022. The primary end point was recurrence free survival (RFS). The secondary end points were overall survival (OS) and safety.</p><p><strong>Results: </strong>A total of 559 eligible patients were classified into the adjuvant TACE group and the observation group. After propensity score matching analysis, both RFS (HR 0.62 [95% CI, 0.48 to 0.80]; P < 0.001) and OS (HR 0.59 [95% CI, 0.42 to 0.84]; P = 0.013) in the adjuvant TACE group were significantly better than the observation group. By Cox regression models, mALBI grade, types of hepatectomy, number, satellite lesion, without adjuvant TACE were identified as independent risk factors for RFS, and mALBI grade, number, maximum tumor size, satellite lesion, microvascular invasion, high AFP level, without adjuvant TACE were identified as independent risk factors for OS. The incidence of surgery-related adverse events (AEs) had no significant difference between the two groups (P = 0.609). The majority of AEs associated with adjuvant TACE were grade I (84.4%), and no treatment-related deaths occurred in either group.</p><p><strong>Conclusions: </strong>Adjuvant TACE significantly improved the RFS and OS of patients with resected MTM-HCC with acceptable toxicity.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143030077","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}

{"title":"Neurochemical Alterations Linked to Persistent COVID-19-Induced Anosmia: Probing Into Orbitofrontal Cortex by Magnetic Resonance Spectroscopy.","authors":"Mohammad Haghani Dogahe, Abbas Monsef, Elahe Abbaspour, Sahand Karimzadhagh, Sima Fallah Arzpeyma, Alireza Teymouri, Nahal Daneshgar, Shadman Nemati","doi":"10.1016/j.acra.2024.12.042","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.042","url":null,"abstract":"<p><strong>Background: </strong>While many COVID-19-induced anosmia patients recover their sense of smell within a few months, a substantial number of them continue to experience olfactory impairment. In our primary study, the metabolic patterns in orbitofrontal cortex (OFC) were observed to exhibit more alterations than other regions. Hence, this study specifically probes into alterations within OFC region in subjects with persistent COVID-19-induced anosmia.</p><p><strong>Methods: </strong>In a new categorization, 54 subjects were studied as two major groups of COVID-19-related anosmia and normal each of which includes 27 subjects. Iran Recognition-Smell Identification Test (IR-SIT) over a three-month follow-up period was utilized for olfactory function assessment and anosmia diagnosis. Proton Magnetic Resonance Spectroscopy (¹H-MRS) was employed to examine changes of metabolites in OFC, including N-acetyl aspartate (NAA), choline (Cho), and creatine (Cr), as well as their ratios. Additionally, a linear regression was applied to investigate the potential correlation between MRS data and IR-SIT scores.</p><p><strong>Results: </strong>Patients with COVID-19-induced anosmia exhibited a significant reduction in NAA, Cho, and Cr levels in the OFC region compared to the control group. Moreover, NAA/Cho and NAA/Cr ratios were lower in the anosmia patients, whereas the Cho/Cr ratio elevated. The NAA/Cho ratio had the highest linear correlation with IR-SIT scores in anosmia.</p><p><strong>Conclusion: </strong>This study highlights remarkable neurochemical patterns associated with COVID-19-induced anosmia in brain orbitofrontal cortex detectable by proton MRS, shedding light on the link between OFC function impairment and anosmia. The NAA/Cho ratio derived from MRS data emerged as a potential biomarker that correlates with anosmia severity and recovery examination.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143030085","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}

{"title":"Advanced Automated Model for Robust Bone Marrow Segmentation in Whole-body MRI.","authors":"Fabian Bauer, Jessica Kächele, Juliane Bernhard, Marina Hajiyianni, Niels Weinhold, Sandra Sauer, Martin Grözinger, Marc-Steffen Raab, Elias K Mai, Tim F Weber, Hartmut Goldschmidt, Heinz-Peter Schlemmer, Klaus Maier-Hein, Stefan Delorme, Peter Neher, Markus Wennmann","doi":"10.1016/j.acra.2024.12.060","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.060","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To establish an advanced automated bone marrow (BM) segmentation model on whole-body (WB-)MRI in monoclonal plasma cell disorders (MPCD), and to demonstrate its robust performance on multicenter datasets with severe myeloma-related pathologies.</p><p><strong>Materials and methods: </strong>The study cohort comprised multi-vendor, multi-protocol imaging data acquired with varying field strength across 8 different centers. In total, 210 WB-MRIs of 207 MPCD patients were included. An nnU-Net algorithm was established for segmenting the individual bone marrow spaces (BMS) of the spine, pelvis, humeri and femora (advanced segmentation model). For this task, 186 T1-weighted (T1w) WB-MRIs from center 1 were used in the training set. Test sets included 12 T1w WB-MRIs from center 2 (I) and 9 T1w WB-MRIs from centers 3-8 (II). Example cases were included to showcase segmentation performance on T1w WB-MRIs with extensive tumor load. The segmentation accuracy of the advanced segmentation model was compared to a prior established basic segmentation model by calculating Dice scores and using the Wilcoxon signed-rank test.</p><p><strong>Results: </strong>The mean Dice score on the individual BMS was 0.89±0.13 (test set I) and 0.88±0.11 (test set II), significantly higher than the Dice scores of a prior basic model (p<0.05). Dice scores for the BMS of the individual bones ranged from 0.77 to 0.96 (test set I), and 0.81 to 0.95 (test set II). BM altered by myeloma-relevant pathologies, artifacts or low imaging quality was precisely segmented.</p><p><strong>Conclusion: </strong>The advanced model performed reliable, automated segmentations, even on heterogeneously acquired multicenter WB-MRIs with severe pathologies.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143030096","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}