Academic Radiology最新文献

{"title":"Diagnostic Efficacy of Ventilation-Perfusion Single Photo Emission Computed Tomography/Computed Tomography for Pulmonary Hypertension due to Fibrinous Mediastinitis.","authors":"Hui-Ting Li, Feng-Xian Zhang, Su-Gang Gong, Qin-Hua Zhao, Ci-Jun Luo, Hong-Ling Qiu, Jing He, Jin-Ming Liu, Lan Wang, Yang-Chun Chen","doi":"10.1016/j.acra.2024.11.026","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.026","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Comprehensive data on the use of ventilation-perfusion single-photo emission computed tomography/computed tomography (V/Q SPECT/CT), an established diagnostic tool for chronic thromboembolic pulmonary hypertension, in identifying pulmonary hypertension secondary to fibrinous mediastinitis (PH-FM) is scarce. This study aimed to assess its diagnostic efficacy for PH-FM.</p><p><strong>Materials and methods: </strong>Patients with PH due to pulmonary artery stenosis were assessed using V/Q SPECT/CT, computed tomography pulmonary angiography (CTPA), and digital subtraction pulmonary angiography (PAG). Abnormal mediastinal or hilar features identified by V/Q SPECT/CT, correlating with perfusion defects, were used to diagnose PH-FM. Final clinical diagnosis is recognized as the gold standard for this study. Diagnostic accuracy was compared using receiver operating characteristic (ROC) analysis and Cohen's kappa coefficient to evaluate agreement among the imaging methods.</p><p><strong>Results: </strong>Among the patients included, 21 had PH-FM, and 76 had PH associated with non-FM. V/Q SPECT/CT showed higher sensitivity (90%), specificity (95%), and accuracy (94%) for detecting PH-FM compared to CTPA (sensitivity 86%, specificity 92%, accuracy 91%) and PAG (sensitivity 62%, specificity 87%, accuracy 81%). The areas under the ROC curve for V/Q SPECT/CT, CTPA, and PAG were 0.93, 0.89, and 0.74, respectively. V/Q SPECT/CT achieved better agreement with the gold standard than CTPA or PAG (κ=0.82, κ=0.69 and κ=0.49, respectively).</p><p><strong>Conclusion: </strong>V/Q SPECT/CT demonstrates superior diagnostic efficacy and accuracy compared to CTPA and PAG in diagnosing PH-FM.</p><p><strong>Clinical relevance statement: </strong>Compared to computed tomography pulmonary angiography and digital subtraction pulmonary angiography, ventilation-perfusion single-photo emission computed tomography/computed tomography demonstrates superior diagnostic efficiency for pulmonary hypertension secondary to fibrinous mediastinitis, leading to improved early detection and accuracy, thus optimizing diagnostic pathways.</p><p><strong>Key points: </strong></p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866060","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":"The quality and accuracy of radiomics model in diagnosing osteoporosis: a systematic review and meta-analysis.","authors":"Jianan Chen, Song Liu, Youxi Lin, Wenjun Hu, Huihong Shi, Nianchun Liao, Miaomiao Zhou, Wenjie Gao, Yanbo Chen, Peijie Shi","doi":"10.1016/j.acra.2024.11.065","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.065","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The purpose of this study is to conduct a meta-analysis to evaluate the diagnostic performance of current radiomics models for diagnosing osteoporosis, as well as to assess the methodology and reporting quality of these radiomics studies.</p><p><strong>Methods: </strong>According to PRISMA guidelines, four databases including MEDLINE, Web of Science, Embase and the Cochrane Library were searched systematically to select relevant studies published before July 18, 2024. The articles that used radiomics models for diagnosing osteoporosis were considered eligible. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool and radiomics quality score (RQS) were used to assess the quality of included studies. The pooled diagnostic odds ratio (DOR), sensitivity, specificity, area under the summary receiver operator characteristic curve (AUC) were calculated to estimated diagnostic efficiency of pooled model.</p><p><strong>Results: </strong>A total of 25 studies were included, of which 24 provided usable data that were utilized for the meta-analysis, including 1553 patients with osteoporosis and 2200 patients without osteoporosis. The mean RQS score of included studies was 11.48 ± 4.92, with an adherence rate of 31.89%. The pooled DOR, sensitivity and specificity for model to diagnose osteoporosis were 81.72 (95% CI: 51.08 - 130.73), 0.90 (95% CI: 0.87-0.93) and 0.90 (95% CI: 0.87-0.93), respectively. The AUC was 0.96, indicating a high diagnostic capability. Subgroup analysis revealed that the use of different imaging modalities to construct radiomics models might be one source of heterogeneity. Radiomics models built using CT images and deep learning algorithms demonstrated higher diagnostic accuracy for osteoporosis.</p><p><strong>Conclusion: </strong>Radiomics models for the diagnosis of osteoporosis have high diagnostic efficacy. In the future, radiomics models for diagnosing osteoporosis will be an efficient instrument to assist clinical doctors in screening osteoporosis patients. However, relevant guidelines should be followed strictly to improve the quality of radiomics studies.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866065","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":"Diagnostic Characteristics and Clinical Relevance of Incidental Hypermetabolic Breast Lesions Detected on ¹⁸F-FDG PET-CT: A Retrospective Evaluation.","authors":"Yasemin Kayadibi, Seyfullah Halit Karagoz, Seda Aladag Kurt, Osman Aykan Kargin, Cansu Guneren, Onur Erdem Sahin, Rauf Hamid, Mehmet Halit Yilmaz","doi":"10.1016/j.acra.2024.11.031","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.031","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>The study aimed to evaluate demographic and radiological characteristics of breast incidentalomas found on 18-fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (¹⁸F-FDG PET-CT) performed for extramammary indications.</p><p><strong>Materials and methods: </strong>A total of 12633 ¹⁸F-FDG PET-CT scans performed between January 1, 2018 and January 1, 2024, were retrospectively reviewed. Breast incidentalomas that had undergone breast imaging, tissue diagnosis, or at least 2-year radiological follow-up were included. Demographic data and lesion size were recorded. Maximum and average standardized uptake values (SUV_max-SUV_avg) and SUV corrected for lean body mass (SUL) were calculated using region of interest (ROI).</p><p><strong>Results: </strong>The inclusion criteria were met in 101 lesions (81 benign and 20 malignant). The most common benign lesion was fibroadenoma (n = 21), followed by stable lesions during follow-up (n = 18) and benign breast parenchyma (n = 11). The most common malignant lesion was invasive ductal carcinoma (n = 11). The diagnostic characteristics of SUV_max≥ 3, SUL_max≥ 2, SUV_avg≥ 0.735, SUL_avg≥ 0.48, and BI-RADS≥ 4 were 75%, 70%, 75%, 70% and 100% for sensitivity, 69%, 69%, 62%, 62% and 67% for specificity, and 69.3%, 68.3%, 62.4%, 61.4% and 73.3% for accuracy, respectively. The highest negative predictive values (NPV) were obtained with BI-RADS and SUV_max (100% and 92%, respectively). No significant difference in malignancy rate was observed for the lesion size and age of the patients (p > 0.05).</p><p><strong>Conclusion: </strong>There is a risk of detecting malignancy in incidental lesions showing ¹⁸F-FDG uptake. Radiological workup must be done, but SUV_max, with a high NPV value, can be used in conjunction with BI-RADS assessment for appropriate patient selection and effective management of resources.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866045","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":"Predicting Intracerebral Hemorrhage Outcomes Using Deep Learning Models to Extract Head CT Imaging Features.","authors":"Seyedmehdi Payabvash","doi":"10.1016/j.acra.2024.12.019","DOIUrl":"https://doi.org/10.1016/j.acra.2024.12.019","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866061","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":"Generative Adversarial Network Based Contrast Enhancement: Synthetic Contrast Brain Magnetic Resonance Imaging.","authors":"Merve Solak, Murat Tören, Berkutay Asan, Esat Kaba, Mehmet Beyazal, Fatma Beyazal Çeliker","doi":"10.1016/j.acra.2024.11.021","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.021","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Magnetic resonance imaging (MRI) is a vital tool for diagnosing neurological disorders, frequently utilising gadolinium-based contrast agents (GBCAs) to enhance resolution and specificity. However, GBCAs present certain risks, including side effects, increased costs, and repeated exposure. This study proposes an innovative approach using generative adversarial networks (GANs) for virtual contrast enhancement in brain MRI, with the aim of reducing or eliminating GBCAs, minimising associated risks, and enhancing imaging efficiency while preserving diagnostic quality.</p><p><strong>Material and methods: </strong>In this study, 10,235 images were acquired in a 3.0 Tesla MRI scanner from 81 participants (54 females, 27 males; mean age 35 years, range 19-68 years). T1-weighted and contrast-enhanced images were obtained following the administration of a standard dose of a GBCA. In order to generate \"synthetic\" images for contrast-enhanced T1-weighted, a CycleGAN model, a sub-model of the GAN structure, was trained to process pre- and post-contrast images. The dataset was divided into three subsets: 80% for training, 10% for validation, and 10% for testing. TensorBoard was employed to prevent image deterioration throughout the training phase, and the image processing and training procedures were optimised. The radiologists were presented with a non-contrast input image and asked to choose between a real contrast-enhanced image and synthetic MR images generated by CycleGAN corresponding to this non-contrast MR image (Turing test).</p><p><strong>Results: </strong>The performance of the CycleGAN model was evaluated using a combination of quantitative and qualitative analyses. For the entire dataset, in the test set, the mean square error (MSE) was 0.0038, while the structural similarity index (SSIM) was 0.58. Among the submodels, the most successful model achieved an MSE of 0.0053, while the SSIM was 0.8. The qualitative evaluation was validated through a visual Turing test conducted by four radiologists with varying levels of clinical experience.</p><p><strong>Conclusion: </strong>The findings of this study support the efficacy of the CycleGAN model in generating synthetic contrast-enhanced T1-weighted brain MR images. Both quantitative and qualitative evaluations demonstrated excellent performance, confirming the model's ability to produce realistic synthetic images. This method shows promise in potentially eliminating the need for intravenous contrast agents, thereby minimising the associated risks of their use.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142856162","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":"ARPA-H for Radiologists: Novel Funding Opportunities and Results of a National Survey.","authors":"Yueh Z Lee, Ichiro Ikuta, Anugayathri Jawahar, Josie Wilkinson, Casey Cappelletti, Renee L Cruea, Mai-Lan Ho","doi":"10.1016/j.acra.2024.11.001","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.001","url":null,"abstract":"<p><p>The Advanced Research Projects Agency for Health (ARPA-H) is a new federal agency established by the Biden administration in March 2022 to accelerate US government-funded biomedical and health solutions. ARPA-H has a distinct operating model, leadership structure, and funds flow separate from the National Institutes of Health. In 2023, the Association of Academic Radiology formed a Radiology Research Alliance taskforce to better understand the mission, vision, and guiding principles of ARPA-H and relevance to radiology and biomedical imaging research. This white paper summarizes the findings of the taskforce with particular relevance to radiology & biomedical imaging researchers. The article begins with a background of ARPA-H history, principles, and organization. Next, we describe the application and review process, timelines, and tips for investigators. Subsequently, we summarize recent/upcoming programs and examples of successful awards, highlighting potential opportunities for radiology researchers. Because the agency is not disease or specialty-specific, it is incumbent upon investigators to brainstorm potential funding opportunities. Therefore, the taskforce conducted a national survey of radiology research leaders in collaboration with The Academy for Radiology & Biomedical Imaging Research, designed to identify cutting-edge developments and opportunities for the field, including suitable targets for ARPA-H funding.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142856127","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":"Comparative Efficacy of Non-contrast vs. Contrast-enhanced CT Radiomics in Predicting Coronary Artery Plaques Among Patients with Low Agatston Scores.","authors":"Jianhua Liang, Congcong Lin, Hongliang Qi, Yongkai Lin, Liwei Deng, Jieyao Wu, Chunyang Yang, Zhiyuan He, Jiaqing Li, Hanwei Li, Debin Hu, Hongwen Chen, Yuanzhang Li","doi":"10.1016/j.acra.2024.11.063","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.063","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Patients with a low Agatston score often present with clinical signs and symptoms suggestive of coronary artery disease, despite having minimal calcium deposits. This study aimed to compare the efficacy of low-dose non-contrast cardiac CT with coronary computed tomography angiography (CCTA) in pericoronary adipose tissue (PCAT) radiomics for predicting coronary artery plaques, using CCTA as the reference standard.</p><p><strong>Materials and methods: </strong>This retrospective study analyzed 459 patients with suspected coronary artery disease and a coronary artery calcium score < 100 Agatston units, who were treated between June 2021 and December 2023 at a tertiary hospital. Three predictive models for coronary artery plaques were developed: (1) a clinical factor model, (2) a hybrid model integrating clinical factors and CT PCAT radiomics, and (3) a hybrid model integrating clinical factors and CCTA PCAT radiomics. Multivariable logistic regression and receiver operating characteristic curve evaluations were performed to develop and validate predictive models.</p><p><strong>Results: </strong>Both hybrid models showed significant correlations in the training set (r = 0.890, P < 0.001) and the validation set (r = 0.920, P < 0.001). The mean agreement in the training set is 0, with 3.42% (11/322) of the data points outside the 95% CI (-0.18-0.18, P < 0.001). The mean agreement in the validation set is -0.244, with 6.57% (9/137) of the data points outside the 95% CI (-0.443-0.045, P < 0.001).</p><p><strong>Conclusions: </strong>Non-contract CT PCAT radiomics showed comparable efficacy to CCTA PCAT radiomics in predicting coronary artery plaques among patients with low Agatston scores.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142856160","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":"HRS Improves Active Surveillance for Prostate Cancer by Timely Identification of Progression.","authors":"Isabella M Kimbel, Veronica Wallaengen, Evangelia I Zacharaki, Adrian L Breto, Ahmad Algohary, Sophia Carbohn, Sandra M Gaston, Nachiketh Soodana-Prakash, Pedro F S Freitas, Oleksandr N Kryvenko, Patricia Castillo, Matthew C Abramowitz, Chad R Ritch, Bruno Nahar, Mark L Gonzalgo, Dipen J Parekh, Alan Pollack, Sanoj Punnen, Radka Stoyanova","doi":"10.1016/j.acra.2024.11.008","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.008","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Active surveillance (AS) is the preferred management strategy for low-risk prostate cancer. This study aimed to evaluate the impact of Habitat Risk Score (HRS), an automated approach for mpMRI analysis, for early detection of progressors in a prospective AS clinical trial (MAST NCT02242773).</p><p><strong>Materials and methods: </strong>The MAST protocol includes Confirmatory mpMRI ultrasound fusion (MRI-US) biopsy and yearly surveillance MRI-US biopsies for up to 3 years. Clinical and mpMRI data from patients that progressed based on protocol criteria at years 1-3 were reviewed. Patients were classified as \"MRI/HRS Progressors\" if the PI-RADS lesion(s) had been targeted throughout the surveillance and resulted in positive biopsies, or as \"Missed Progressors\" if the lesion(s) were not identified by PI-RADS (\"PI-RADS Miss\") or were missed by the biopsy (\"Needle Miss\"). HRS maps were generated for each patient and evaluated for association with histopathological progression.</p><p><strong>Results: </strong>Of the 34 patients, 15 were classified as \"MRI/HRS Progressors\" and 19 as \"Missed Progressors\" (12 \"PI-RADS Miss\", seven \"Needle Miss\"). In all cases, HRS confirmed the PI-RADS assessment. In the \"PI-RADS Miss\" group, HRS identified the lesions in all patients that were not targeted by biopsy and resulted in patient reclassification. HRS volumes showed clear association with tumor evolution both in terms of volume and aggressiveness over time.</p><p><strong>Conclusion: </strong>HRS volumes can serve as a quantitative biomarker for early detection of progression and lead to timely conversion to treatment, thereby improving patient outcomes and reducing the burden of unnecessary surveillance.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142856167","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":"A Prospective Evaluation of Chemokine Receptor-4 (CXCR4) Overexpression in High-grade Glioma Using ⁶⁸Ga-Pentixafor (Pars-Cixafor™) PET/CT Imaging.","authors":"Habibollah Dadgar, Nasim Norouzbeigi, Majid Assadi, Esmail Jafari, Batool Al-Balooshi, Akram Al-Ibraheem, Abdulredha A Esmail, Fahad Marafi, Mohamad Haidar, Haider Muhsin Al-Alawi, Yehia Omar, Sharjeel Usmani, Andrea Cimini, Maria Ricci, Hossein Arabi, Habib Zaidi","doi":"10.1016/j.acra.2024.11.064","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.064","url":null,"abstract":"<p><strong>Background: </strong>While magnetic resonance imaging (MRI) remains the gold standard for morphological imaging, its ability to differentiate between tumor tissue and treatment-induced changes on the cellular level is insufficient. Notably, glioma cells, particularly glioblastoma multiforme (GBM), demonstrate overexpression of chemokine receptor-4 (CXCR4). This study aims to evaluate the feasibility of non-invasive ⁶⁸Ga-Cixafor™ PET/CT as a tool to improve diagnostic accuracy in patients with high-grade glioma.</p><p><strong>Methods: </strong>In this retrospective analysis, a database of histopathology-confirmed glioma patients with MRI findings consistent with high-grade gliomas was utilized. Within 2 weeks of their MRI, these patients underwent ⁶⁸Ga-Cixafor™ PET/CT scans to assess CXCR4 expression. Both visual scoring based on established criteria and semi-quantitative measures including maximum standardized uptake value (SUV_max) and tumor-to-background ratios (TBR) were calculated to analyze the PET/CT data.</p><p><strong>Results: </strong>Our retrospective study enrolled 29 histologically confirmed glioma patients with MRI findings consistent with high-grade gliomas. All patients underwent ⁶⁸Ga-Cixafor™ PET/CT scans within 2 weeks of their MRI, specifically at one-hour post-injection time point. Visual assessment based on a standardized scoring system identified 27 positive scans out of 29 (93.1%). Median SUV_max was 2.31 (range: 0.49-9.96) and median TBR was 20 (range: 6.12-124.5). Pathological analysis revealed 5 grade III (17.24%) and 24 grade IV (82.75%) lesions among the 29 patients. Notably, the median SUV_max of grade IV lesions (2.85) was significantly higher than grade III lesions (1.27) (P=0.02). Conversely, there was no significant difference in median TBR between grade IV (20) and grade III (22.37). These findings support the correlation between high CXCR4 expression, particularly in high-grade gliomas, and elevated uptake of ⁶⁸Ga-Pentixafor. While areas with high uptake showed CXCR4 expression, areas with low uptake did not exhibit noticeable expression (data not shown).</p><p><strong>Conclusion: </strong>This study demonstrated that ⁶⁸Ga-Cixafor™ PET exhibits a TBR with minimal cortical uptake, significantly enhancing glioma detection compared to conventional imaging methods. This, combined with the potential therapeutic capabilities of CXCR4-targeting radiopharmaceuticals, highlights the promise of ⁶⁸Ga-Cixafor™ as a valuable tool for not only improved glioma diagnosis but also personalized treatment strategies.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142848359","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":"Interpretable Deep-learning Model Based on Superb Microvascular Imaging for Noninvasive Diagnosis of Interstitial Fibrosis in Chronic Kidney Disease.","authors":"Xiachuan Qin, Xiaoling Liu, Weihan Xiao, Qi Luo, Linlin Xia, Chaoxue Zhang","doi":"10.1016/j.acra.2024.11.067","DOIUrl":"https://doi.org/10.1016/j.acra.2024.11.067","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To develop an interpretable deep learning (XDL) model based on superb microvascular imaging (SMI) for the noninvasive diagnosis of the degree of interstitial fibrosis (IF) in chronic kidney disease (CKD).</p><p><strong>Methods: </strong>We included CKD patients who underwent renal biopsy, two-dimensional ultrasound, and SMI examinations between May 2022 and October 2023. Based on the pathological IF score, they were divided into two groups: minimal-mild IF (≤25%) and moderate-severe IF (>25%). An XDL model based on the SMI while establishing an ultrasound radiomics model and a color doppler ultrasonography (CDUS) model as the control group. The utility of the proposed model was evaluated using the receiver operating characteristic curve (ROC) and decision curve analysis.</p><p><strong>Results: </strong>In total, 365 CKD patients were included herein. In the validation group, AUCs of the ROC curves for the DL, ultrasound radiomics, and CDUS models were 0.854, 0.784, and 0.745, respectively. In the test group, AUCs of the ROC curve for the DL ultrasound radiomics, and CDUS models were 0.824, 0.792, and 0.752, respectively. The pie chart and heat map based on Shapley additive explanations (SHAP) provided substantial interpretability for the model.</p><p><strong>Conclusion: </strong>Compared with the ultrasound radiomics and CDUS models, the DL model based on the SMI had higher accuracy in the noninvasive judgment of the degree of IF in CKD patients. Pie and heat maps based on Shapley can explain which image regions are helpful in diagnosing the degree of IF.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142848371","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}