Pub Date : 2024-09-23DOI: 10.1016/j.ejrad.2024.111743
Ziwei Zhang , Jiawei Wang , Yu Li , Chen Liang , He Sui , Zhaoshu Huang , Xia Zhu , Lisha Nie , Lingling Song
Purpose
To demonstrate the clinical applicability of zero echo time magnetic resonance imaging (ZTE MRI) in bone assessment of the sacroiliac joint in ankylosing spondylitis.
Method
Between January 2021 and November 2021, twenty-one ankylosing spondylitis patients underwent clinically indicated MRI including ZTE sequence, in addition, all patients underwent a CT scan covering the sacroiliac joints within 6 months of the MRI examination. The sensitivity, specificity, and accuracy of ZTE MRI were calculated using CT as the reference standard. Cohen’s κappa tests were applied to assess the agreement of positive imaging findings (including erosions, osteosclerosis, bony cystic changes, and joint space changes) between MRI and CT as well as the inter-reader agreement for the grading of sacroiliitis in AS patients.
Results
There was no statistical significance between ZTE MRI and CT in detecting of ankylosing spondylitis(p＞0.05). The consistency of the diagnosis of positive imaging findings between ZTE MRI and CT was moderate to excellent (ranging from 0.611 to 0.889), and the consistency of the scores of positive imaging was good to excellent (ranging from 0.857 to 0.979).
Conclusions
ZTE MRI provides “CT-like” contrast for bony changes of the sacroiliac joint in ankylosing spondylitis and could simplify and reduce costs for some AS patients when both MRI and CT are typically required.
{"title":"Bone assessment of the sacroiliac joint in ankylosing spondylitis: Comparison between computed tomography and zero echo time MRI","authors":"Ziwei Zhang , Jiawei Wang , Yu Li , Chen Liang , He Sui , Zhaoshu Huang , Xia Zhu , Lisha Nie , Lingling Song","doi":"10.1016/j.ejrad.2024.111743","DOIUrl":"10.1016/j.ejrad.2024.111743","url":null,"abstract":"<div><h3>Purpose</h3><div>To demonstrate the clinical applicability of zero echo time magnetic resonance imaging (ZTE MRI) in bone assessment of the sacroiliac joint in ankylosing spondylitis.</div></div><div><h3>Method</h3><div>Between January 2021 and November 2021, twenty-one ankylosing spondylitis patients underwent clinically indicated MRI including ZTE sequence, in addition, all patients underwent a CT scan covering the sacroiliac joints within 6 months of the MRI examination. The sensitivity, specificity, and accuracy of ZTE MRI were calculated using CT as the reference standard. Cohen’s κappa tests were applied to assess the agreement of positive imaging findings (including erosions, osteosclerosis, bony cystic changes, and joint space changes) between MRI and CT as well as the inter-reader agreement for the grading of sacroiliitis in AS patients.</div></div><div><h3>Results</h3><div>There was no statistical significance between ZTE MRI and CT in detecting of ankylosing spondylitis(p＞0.05). The consistency of the diagnosis of positive imaging findings between ZTE MRI and CT was moderate to excellent (ranging from 0.611 to 0.889), and the consistency of the scores of positive imaging was good to excellent (ranging from 0.857 to 0.979).</div></div><div><h3>Conclusions</h3><div>ZTE MRI provides “CT-like” contrast for bony changes of the sacroiliac joint in ankylosing spondylitis and could simplify and reduce costs for some AS patients when both MRI and CT are typically required.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111743"},"PeriodicalIF":3.2,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142327458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-21DOI: 10.1016/j.ejrad.2024.111753
Umut Asfuroğlu , Berrak Barutcu Asfuroğlu , Halil Özer , Mehmet Arda İnan , Murat Uçar
Purpose
This study aims to evaluate the diagnostic performance of curvilinear and linear measurement methods in different magnetic resonance imaging (MRI) sequences for detecting extraprostatic extension (EPE) in prostate cancer, and to evaluate the added value of apparent diffusion coefficient (ADC) in detecting EPE.
Methods
A retrospective analysis was conducted on 84 patients who underwent multiparametric MRI (mp-MRI) prior to radical prostatectomy between January 2019 and February 2022. Tumor contact length (TCL) was assessed curvilinearly and linearly on T2-weighted imaging (T2WI), ADC maps, and dynamic contrast-enhanced (DCE) MRI by two radiologists. MRI-based EPE positivity was defined as a curvilinear or linear contact length of >15 mm. Statistical comparisons were conducted using chi-squared and independent samples t-tests, with interreader agreement evaluated using weighted κ statistics. Univariate and multivariate logistic regression identified independent predictors of EPE, and two prediction models were constructed. Diagnostic performance was assessed using receiver operator characteristic (ROC) curve analysis.
Results
A total of 32 (38%) and 52 (62%) patients with EPE and non-EPE, respectively, were included in this study. Patients with EPE demonstrated significantly larger tumor sizes, lower ADC values, and lower ADC ratios than those without EPE (p < 0.001). The curvilinear and linear TCL measurements for each sequence exhibited statistically significant correlations with EPE for both readers, with strong interreader agreement. Curvilinear TCL (c-TCL) and linear TCL (l-TCL) on DCE-MRI showed higher area under the curve (AUC) values than the other measurements for EPE prediction (reader 1: 0.815 and 0.803, reader 2: 0.746 and 0.713, respectively). However, there was no statistically significant difference between c-TCL and l-TCL. Multivariable models with mean ADC value improved predictive performance. Model 2 (ADC, ISUP, and c-TCL on DCE images) surpassed model 1 (ADC and c-TCL on DCE images) with an AUC of 0.919 and 0.874, respectively.
Conclusion
DCE-MRI demonstrated superior performance in predicting EPE compared to other sequences. Linear and curvilinear measurements had comparable diagnostic performance. Being more practical and easier, radiologists may use l-TCL measurement in daily practice. The mean ADC value provided additional diagnostic value.
{"title":"A comparative analysis of techniques for measuring tumor contact length in predicting extraprostatic extension","authors":"Umut Asfuroğlu , Berrak Barutcu Asfuroğlu , Halil Özer , Mehmet Arda İnan , Murat Uçar","doi":"10.1016/j.ejrad.2024.111753","DOIUrl":"10.1016/j.ejrad.2024.111753","url":null,"abstract":"<div><h3>Purpose</h3><div>This study aims to evaluate the diagnostic performance of curvilinear and linear measurement methods in different magnetic resonance imaging (MRI) sequences for detecting extraprostatic extension (EPE) in prostate cancer, and to evaluate the added value of apparent diffusion coefficient (ADC) in detecting EPE.</div></div><div><h3>Methods</h3><div>A retrospective analysis was conducted on 84 patients who underwent multiparametric MRI (mp-MRI) prior to radical prostatectomy between January 2019 and February 2022. Tumor contact length (TCL) was assessed curvilinearly and linearly on T2-weighted imaging (T2WI), ADC maps, and dynamic contrast-enhanced (DCE) MRI by two radiologists. MRI-based EPE positivity was defined as a curvilinear or linear contact length of >15 mm. Statistical comparisons were conducted using chi-squared and independent samples t-tests, with interreader agreement evaluated using weighted κ statistics. Univariate and multivariate logistic regression identified independent predictors of EPE, and two prediction models were constructed. Diagnostic performance was assessed using receiver operator characteristic (ROC) curve analysis.</div></div><div><h3>Results</h3><div>A total of 32 (38%) and 52 (62%) patients with EPE and non-EPE, respectively, were included in this study. Patients with EPE demonstrated significantly larger tumor sizes, lower ADC values, and lower ADC ratios than those without EPE (p < 0.001). The curvilinear and linear TCL measurements for each sequence exhibited statistically significant correlations with EPE for both readers, with strong interreader agreement. Curvilinear TCL (c-TCL) and linear TCL (l-TCL) on DCE-MRI showed higher area under the curve (AUC) values than the other measurements for EPE prediction (reader 1: 0.815 and 0.803, reader 2: 0.746 and 0.713, respectively). However, there was no statistically significant difference between c-TCL and l-TCL. Multivariable models with mean ADC value improved predictive performance. Model 2 (ADC, ISUP, and c-TCL on DCE images) surpassed model 1 (ADC and c-TCL on DCE images) with an AUC of 0.919 and 0.874, respectively.</div></div><div><h3>Conclusion</h3><div>DCE-MRI demonstrated superior performance in predicting EPE compared to other sequences. Linear and curvilinear measurements had comparable diagnostic performance. Being more practical and easier, radiologists may use l-TCL measurement in daily practice. The mean ADC value provided additional diagnostic value.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111753"},"PeriodicalIF":3.2,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142359564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-21DOI: 10.1016/j.ejrad.2024.111720
Jie Zhou , Gang Dong , Xiang Jing , Guanghui Huang , Zhen Wang , Mengfan Peng , Yan Zhou , Xiaoling Yu , Jie Yu , Zhiyu Han , Fangyi Liu , Hongjian Gao , Yubo Zhang , Zhigang Cheng , Xin Ye , Ping Liang
Objective
This study aims to assess the feasibility, effectiveness, and safety of image-guided percutaneous microwave ablation (PMWA) for unresectable pancreatic cancer.
Methods
In this retrospective study, 72 patients from four hospitals were enrolled between November 2009 and October 2022. Descriptive statistics were employed to describe the patients’ characteristics and prognostic factors. The primary endpoint compassed the complete ablation rate (CAR), incidence of complications and the pain relief rate (PRR).
Results
The median age of the 72 patients was 61 (interquartile range (IQR) 52.5–67.0) years, with 62.5 % (45/72) being male. 26 cases received computed tomography (CT) guidance; 46 cases received ultrasound guidance. A total of 74 tumors were identified (2 in 2 patients), with 56.8 % (42/74) at the body and tail, and the rest at the head and neck. Overall, 73 ablation sessions were carried out, achieving a technical success rate (TSR) of 100 %. The CAR was 40.5 % (30/74). The median follow-up time was 4.6 (1–43.4) months. 50 % (36/72) of patients had died with a median overall survival (OS) of 5.6 (1–27) months. Regarding complications, 18.1 % (13/72) of cases were classified as grade I and II, and 9.8 % (7/72) as grade IIIa. Before surgery, 33 patients experienced pain symptoms, and the postoperative PRR was 96.7 % (32/33). The average pain score decreased from 6.3 (4–10) before surgery to 2.0 (0–8) after ablation (P<0.001).
Conclusions
Image-guided PMWA for unresectable pancreatic cancer is safe and feasible, effectively relieving cancer pain and improving patients’ the quality of life.
{"title":"Image-guided percutaneous microwave ablation for unresectable pancreatic cancers: A multicenter retrospective study","authors":"Jie Zhou , Gang Dong , Xiang Jing , Guanghui Huang , Zhen Wang , Mengfan Peng , Yan Zhou , Xiaoling Yu , Jie Yu , Zhiyu Han , Fangyi Liu , Hongjian Gao , Yubo Zhang , Zhigang Cheng , Xin Ye , Ping Liang","doi":"10.1016/j.ejrad.2024.111720","DOIUrl":"10.1016/j.ejrad.2024.111720","url":null,"abstract":"<div><h3>Objective</h3><div>This study aims to assess the feasibility, effectiveness, and safety of image-guided percutaneous microwave ablation (PMWA) for unresectable pancreatic cancer.</div></div><div><h3>Methods</h3><div>In this retrospective study, 72 patients from four hospitals were enrolled between November 2009 and October 2022. Descriptive statistics were employed to describe the patients’ characteristics and prognostic factors. The primary endpoint compassed the complete ablation rate (CAR), incidence of complications and the pain relief rate (PRR).</div></div><div><h3>Results</h3><div>The median age of the 72 patients was 61 (interquartile range (IQR) 52.5–67.0) years, with 62.5 % (45/72) being male. 26 cases received computed tomography (CT) guidance; 46 cases received ultrasound guidance. A total of 74 tumors were identified (2 in 2 patients), with 56.8 % (42/74) at the body and tail, and the rest at the head and neck. Overall, 73 ablation sessions were carried out, achieving a technical success rate (TSR) of 100 %. The CAR was 40.5 % (30/74). The median follow-up time was 4.6 (1–43.4) months. 50 % (36/72) of patients had died with a median overall survival (OS) of 5.6 (1–27) months. Regarding complications, 18.1 % (13/72) of cases were classified as grade I and II, and 9.8 % (7/72) as grade IIIa. Before surgery, 33 patients experienced pain symptoms, and the postoperative PRR was 96.7 % (32/33). The average pain score decreased from 6.3 (4–10) before surgery to 2.0 (0–8) after ablation (P<0.001).</div></div><div><h3>Conclusions</h3><div>Image-guided PMWA for unresectable pancreatic cancer is safe and feasible, effectively relieving cancer pain and improving patients’ the quality of life.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111720"},"PeriodicalIF":3.2,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-21DOI: 10.1016/j.ejrad.2024.111752
Guixiao Xu , Haibin Liu , Dingwei Ling , Yu Li , Nian Lu , Xinyang Li , Yezhuo Zhang , Haoqiang He , Zuhe Huang , Chuanmiao Xie
Purpose
To evaluate the impact of application acquisition and reconstruction with motion suppression (ARMS) technology on improving the image quality of diffusion-weighted Imaging (DWI) for nasopharyngeal carcinoma (NPC), compared to single-shot echo-planar imaging (SS-EPI).
Methods
A total of 90 patients with NPC underwent MR examination, including ARMS DWI and SS-EPI DWI sequences. Both DWI sequences were acquired with b-values 0 and 800 s/mm2. Two radiologists evaluated the visibility of the lesion, geometric distortion, and overall image quality of the two DWI sequences. Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), geometric distortion degree, and apparent diffusion coefficient (ADC) values of the nasopharyngeal lesions were assessed and compared for two sequences. The Wilcoxon signed-rank test was used to compare the quantitative and qualitative parameters of the two sequences.
Results
The lesion visibility, geometric distortion, and overall image quality scores were significantly higher in ARMS DWI (all P<0.001). Four small-sized lesions were not visible and four lesions were partially visible in the SS-EPI DWI sequence. Lesion detection rate of ARMS DWI is 100 %, while that of SS-EPI is 95.56 %, P<0.043. The mismatch distance between the fusion images of ARMS DWI and T2WI was smaller than that of SS-EPI DWI and T2WI (all P<0.001). The SNR and CNR of ARMS DWI were lower than that of SS-EPI DWI (114.48 ± 37.89 vs. 202.61 ± 78.84, P<0.001 and 1.81 ± 1.84 vs. 3.29 ± 3.71, P<0.003) while the ADC value was higher (839.19 ± 138.44 × 10−6 mm2/s vs. 788.82 ± 110.96 × 10−6 mm2/s, P<0.002).
Conclusion
ARMS DWI improves the image quality by reducing geometric distortion and magnetic susceptibility artifacts. ARMS DWI is superior to SS-EPI DWI for diagnosing small-sized nasopharyngeal lesions, although it has lower SNR and CNR.
{"title":"Acquisition and reconstruction with motion suppression DWI enhance image quality in nasopharyngeal carcinoma patients: Non-echo-planar DWI comparison with single-shot echo-planar DWI","authors":"Guixiao Xu , Haibin Liu , Dingwei Ling , Yu Li , Nian Lu , Xinyang Li , Yezhuo Zhang , Haoqiang He , Zuhe Huang , Chuanmiao Xie","doi":"10.1016/j.ejrad.2024.111752","DOIUrl":"10.1016/j.ejrad.2024.111752","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the impact of application acquisition and reconstruction with motion suppression (ARMS) technology on improving the image quality of diffusion-weighted Imaging (DWI) for nasopharyngeal carcinoma (NPC), compared to single-shot echo-planar imaging (SS-EPI).</div></div><div><h3>Methods</h3><div>A total of 90 patients with NPC underwent MR examination, including ARMS DWI and SS-EPI DWI sequences. Both DWI sequences were acquired with b-values 0 and 800 s/mm<sup>2</sup>. Two radiologists evaluated the visibility of the lesion, geometric distortion, and overall image quality of the two DWI sequences. Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), geometric distortion degree, and apparent diffusion coefficient (ADC) values of the nasopharyngeal lesions were assessed and compared for two sequences. The Wilcoxon signed-rank test was used to compare the quantitative and qualitative parameters of the two sequences.</div></div><div><h3>Results</h3><div>The lesion visibility, geometric distortion, and overall image quality scores were significantly higher in ARMS DWI (all P<0.001). Four small-sized lesions were not visible and four lesions were partially visible in the SS-EPI DWI sequence. Lesion detection rate of ARMS DWI is 100 %, while that of SS-EPI is 95.56 %, P<0.043. The mismatch distance between the fusion images of ARMS DWI and T2WI was smaller than that of SS-EPI DWI and T2WI (all P<0.001). The SNR and CNR of ARMS DWI were lower than that of SS-EPI DWI (114.48 ± 37.89 vs. 202.61 ± 78.84, P<0.001 and 1.81 ± 1.84 vs. 3.29 ± 3.71, P<0.003) while the ADC value was higher (839.19 ± 138.44 × 10<sup>−6</sup> mm<sup>2</sup>/s vs. 788.82 ± 110.96 × 10<sup>−6</sup> mm<sup>2</sup>/s, P<0.002).</div></div><div><h3>Conclusion</h3><div>ARMS DWI improves the image quality by reducing geometric distortion and magnetic susceptibility artifacts. ARMS DWI is superior to SS-EPI DWI for diagnosing small-sized nasopharyngeal lesions, although it has lower SNR and CNR.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111752"},"PeriodicalIF":3.2,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142359577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Preoperative prediction of the acetabular cup press-fit stability in total hip arthroplasty is necessary for clinical decision-making. This study aims to establish and validate machine learning models to investigate the feasibility of predicting the intraoperative press-fit stability of the acetabular cup in total hip arthroplasty (THA).
Methods
226 patients who underwent primary THA from 2018 to 2022 in our hospital were retrospectively enrolled. Patients were divided into press-fit stable or unstable groups according to the intraoperative pull-out test of the implanted cup. Then, they were randomly assigned to the training or test cohort in an 8:2 ratio. We used 3Dslicer software to segment the region of interest (ROI) of the patient’s bilateral hip X-ray to extract radiomics features. The least absolute shrinkage and selection operator (LASSO) regression was used in our feature selection. Finally, four machine learning models were employed in this study, including support vector machine (SVM), random forest (RF), logistic regression (LR), and XGBoost (XGB). Decision curve analysis (DCA), and receiver operating characteristic (ROC) curves of the models were plotted. The area under the curve (AUC), diagnostic accuracy, sensitivity, and specificity were calculated as well. The AUCs of the four models were compared using the DeLong test.
Results
Twenty-seven valuable radiomics features were determined by dimensionality reduction and selection. Regarding to the DeLong test, the AUC of the XGB model was significantly different from those of the other three models. (p < 0.05). Among all models, the XGB model exhibited the best performance with an AUC of 0.823 (95 % CI: 0.711–0.919) in the test cohort and showed optimal clinical efficacy according to the DCA.
Conclusion
Machine learning models based on X-ray radiomics can accurately predict the intraoperative press-fit stability of implanted cups preoperatively, providing surgeons with valuable information to lower the complication risk in THA.
背景术前预测全髋关节置换术中髋臼杯的压合稳定性对临床决策非常必要。本研究旨在建立和验证机器学习模型，以研究预测全髋关节置换术（THA）中髋臼杯术中压配稳定性的可行性。方法回顾性纳入2018年至2022年在我院接受初次THA的226例患者。根据植入髋臼杯的术中拉出试验，将患者分为压配稳定组和不稳定组。然后，按照 8:2 的比例将他们随机分配到训练组或测试组。我们使用 3Dslicer 软件分割患者双侧髋关节 X 光片的感兴趣区（ROI），提取放射组学特征。在选择特征时，我们使用了最小绝对收缩和选择算子（LASSO）回归法。最后，本研究采用了四种机器学习模型，包括支持向量机（SVM）、随机森林（RF）、逻辑回归（LR）和 XGBoost（XGB）。绘制了各模型的决策曲线分析（DCA）和接收者操作特征曲线（ROC）。同时还计算了曲线下面积（AUC）、诊断准确性、灵敏度和特异性。结果通过降维和选择确定了 27 个有价值的放射组学特征。根据 DeLong 检验，XGB 模型的 AUC 与其他三个模型有显著差异。(P<；0.05）。结论基于 X 射线放射组学的机器学习模型可以在术前准确预测植入杯的术中压合稳定性，为外科医生降低 THA 并发症风险提供有价值的信息。
{"title":"Prediction of intraoperative press-fit stability of the acetabular cup in total hip arthroplasty using radiomics-based machine learning models","authors":"Bin He , Xin Zhang , Shengwang Peng , Dong Zeng , Haicong Chen , Zhenming Liang , Huan Zhong , Hanbin Ouyang","doi":"10.1016/j.ejrad.2024.111751","DOIUrl":"10.1016/j.ejrad.2024.111751","url":null,"abstract":"<div><h3>Background</h3><div>Preoperative prediction of the acetabular cup press-fit stability in total hip arthroplasty is necessary for clinical decision-making. This study aims to establish and validate machine learning models to investigate the feasibility of predicting the intraoperative press-fit stability of the acetabular cup in total hip arthroplasty (THA).</div></div><div><h3>Methods</h3><div>226 patients who underwent primary THA from 2018 to 2022 in our hospital were retrospectively enrolled. Patients were divided into press-fit stable or unstable groups according to the intraoperative pull-out test of the implanted cup. Then, they were randomly assigned to the training or test cohort in an 8:2 ratio. We used 3Dslicer software to segment the region of interest (ROI) of the patient’s bilateral hip X-ray to extract radiomics features. The least absolute shrinkage and selection operator (LASSO) regression was used in our feature selection. Finally, four machine learning models were employed in this study, including support vector machine (SVM), random forest (RF), logistic regression (LR), and XGBoost (XGB). Decision curve analysis (DCA), and receiver operating characteristic (ROC) curves of the models were plotted. The area under the curve (AUC), diagnostic accuracy, sensitivity, and specificity were calculated as well. The AUCs of the four models were compared using the DeLong test.</div></div><div><h3>Results</h3><div>Twenty-seven valuable radiomics features were determined by dimensionality reduction and selection. Regarding to the DeLong test, the AUC of the XGB model was significantly different from those of the other three models. (p < 0.05). Among all models, the XGB model exhibited the best performance with an AUC of 0.823 (95 % CI: 0.711–0.919) in the test cohort and showed optimal clinical efficacy according to the DCA.</div></div><div><h3>Conclusion</h3><div>Machine learning models based on X-ray radiomics can accurately predict the intraoperative press-fit stability of implanted cups preoperatively, providing surgeons with valuable information to lower the complication risk in THA.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111751"},"PeriodicalIF":3.2,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To explore the potential of the deep learning reconstruction (DLR) for ultralow dose calcium scoring CT (CSCT) with simultaneously reduced tube voltage and current.
Methods
In this prospective study, seventy-five patients (group A) undergoing routine dose CSCT (120kVp/30mAs) were followed by a low dose (120kVp/20mAs) scan and another 81 (group B) were followed by an ultralow dose (80kVp/20mAs) scan. The hybrid iterative reconstruction was used for the routine dose data while the DLR for data of reduced dose. The calcium score and risk categorization were compared, where the correlation was evaluated using the intraclass correlation coefficient (ICC). The noise suppression performance of DLR was characterized by the contrast-to-noise ratio (CNR) between coronary arteries and pericoronary fat.
Results
The effective dose was 0.32 ± 0.03 vs. 0.48 ± 0.05 mSv for the two scans in group A and 0.09 ± 0.01 vs. 0.49 ± 0.05 mSv in group B. No significant difference was found on CACSs within either group (A: p = 0.10, ICC=0.99; B: p = 0.14, ICC=0.99), nor was it different on risk categorization (A: p = 0.32, ICC=0.99; B: p = 0.16, ICC=0.99). The DLR images exhibited higher CNR in both groups (A: p < 0.001; B: p = 0.001).
Conclusions
The DLR allowed reliable calcium scoring in not only low dose CSCT with reduced tube current but ultralow dose CSCT with simultaneously reduced tube voltage and current, showing feasibility to be adopted in routine applications.
{"title":"Ultralow dose coronary calcium scoring CT at reduced tube voltage and current by using deep learning image reconstruction","authors":"Liyong Zhuo , Shijie Xu , Guozhi Zhang , Lihong Xing , Yu Zhang , Zepeng Ma , Jianing Wang , Xiaoping Yin","doi":"10.1016/j.ejrad.2024.111742","DOIUrl":"10.1016/j.ejrad.2024.111742","url":null,"abstract":"<div><h3>Objective</h3><div>To explore the potential of the deep learning reconstruction (DLR) for ultralow dose calcium scoring CT (CSCT) with simultaneously reduced tube voltage and current.</div></div><div><h3>Methods</h3><div>In this prospective study, seventy-five patients (group A) undergoing routine dose CSCT (120kVp/30mAs) were followed by a low dose (120kVp/20mAs) scan and another 81 (group B) were followed by an ultralow dose (80kVp/20mAs) scan. The hybrid iterative reconstruction was used for the routine dose data while the DLR for data of reduced dose. The calcium score and risk categorization were compared, where the correlation was evaluated using the intraclass correlation coefficient (ICC). The noise suppression performance of DLR was characterized by the contrast-to-noise ratio (CNR) between coronary arteries and pericoronary fat.</div></div><div><h3>Results</h3><div>The effective dose was 0.32 ± 0.03 vs. 0.48 ± 0.05 mSv for the two scans in group A and 0.09 ± 0.01 vs. 0.49 ± 0.05 mSv in group B. No significant difference was found on CACSs within either group (A: <em>p</em> = 0.10, ICC=0.99; B: <em>p</em> = 0.14, ICC=0.99), nor was it different on risk categorization (A: <em>p</em> = 0.32, ICC=0.99; B: <em>p</em> = 0.16, ICC=0.99). The DLR images exhibited higher CNR in both groups (A: <em>p</em> < 0.001; B: <em>p</em> = 0.001).</div></div><div><h3>Conclusions</h3><div>The DLR allowed reliable calcium scoring in not only low dose CSCT with reduced tube current but ultralow dose CSCT with simultaneously reduced tube voltage and current, showing feasibility to be adopted in routine applications.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111742"},"PeriodicalIF":3.2,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-19DOI: 10.1016/j.ejrad.2024.111745
Ali Rastegarpour
Rationale and Objectives: There is limited representation of radiologists in the media, which has been proposed to be a factor in the lack of patient awareness towards radiologist. This study is attempt to look into radiology representation in film.
Materials and Methods
The IMDb website was searched for feature films containing the words “radiologist” and “radiology” in the plot summaries. The resulting titles were reviewed for availability, and if available, for content analysis to demonstrate the representation of radiology. Additional medical specialties were also searched for comparison.
Results
Of the 19 titles returned, only 9 were available on major streaming platforms and of those, 7 were available in English or with English subtitles. Among these, due to plot summary writers confusing radiologists with radiology technologists or other non-radiologist physicians, only 3 actually featured radiologists, and one of these was an extremely negative portrayal of radiologists. Only one film featured an accurate portrayal of a radiologist performing the job of a radiologist.
Conclusions
Accurate and positive radiologist representation in film is extremely limited and if public awareness is the goal, conscious effort is needed in this area.
{"title":"Radiologist representation in cinema","authors":"Ali Rastegarpour","doi":"10.1016/j.ejrad.2024.111745","DOIUrl":"10.1016/j.ejrad.2024.111745","url":null,"abstract":"<div><p>Rationale and Objectives: There is limited representation of radiologists in the media, which has been proposed to be a factor in the lack of patient awareness towards radiologist. This study is attempt to look into radiology representation in film.</p></div><div><h3>Materials and Methods</h3><p>The IMDb website was searched for feature films containing the words “radiologist” and “radiology” in the plot summaries. The resulting titles were reviewed for availability, and if available, for content analysis to demonstrate the representation of radiology. Additional medical specialties were also searched for comparison.</p></div><div><h3>Results</h3><p>Of the 19 titles returned, only 9 were available on major streaming platforms and of those, 7 were available in English or with English subtitles. Among these, due to plot summary writers confusing radiologists with radiology technologists or other non-radiologist physicians, only 3 actually featured radiologists, and one of these was an extremely negative portrayal of radiologists. Only one film featured an accurate portrayal of a radiologist performing the job of a radiologist.</p></div><div><h3>Conclusions</h3><p>Accurate and positive radiologist representation in film is extremely limited and if public awareness is the goal, conscious effort is needed in this area.</p></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111745"},"PeriodicalIF":3.2,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142272583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-19DOI: 10.1016/j.ejrad.2024.111748
Huayan Zuo , Qiyang Wang , Guoli Bi , Yijin Wang , Guang Yang , Chengxiu Zhang , Yang Song , Yunzhu Wu , Xiarong Gong , Qiu Bi
Purpose
To compare the performance of MRI-based Gaussian mixture model (GMM), K-means clustering, and Otsu unsupervised algorithms in predicting sarcopenia and to develop a combined model by integrating clinical indicators.
Methods
Retrospective analysis was conducted on clinical and lumbar MRI data from 118 patients diagnosed with sarcopenia and 222 patients without the sarcopenia. All patients were randomly divided into training and validation groups in a 7:3 ratio. Regions of interest (ROI), specifically the paravertebral muscles at the L3/4 intervertebral disc level, were delineated on axial T2-weighted images (T2WI). The Gaussian mixture model (GMM), K-means clustering, and Otsu’s thresholding algorithms were employed to automatically segment muscle and adipose tissues at both the cohort and case levels. Subsequently, the mean signal intensity, volumes, and percentages of these tissues were calculated and compared. Logistic regression analyses were conducted to construct models and identify independent predictors of sarcopenia. An combined model was developed by combining the optimal magnetic resonance imaging (MRI) model and clinical predictors. The performance of the constructed model was assessed using receiver operating characteristic (ROC) curve analysis.
Results
Age, BMI, and serum albumin were identified as independent clinical predictors of sarcopenia. The cohort-level GMM demonstrated the best predictive performance both in the training group (AUC=0.840) and validation group (AUC=0.800), while the predictive performance of the other models was lower than that of the clinical model both in the training and validation groups. After combining the cohort-level GMM with the independent clinical predictors, the AUC of the training and validation groups increased to 0.871 and 0.867, respectively.
Conclusion
The cohort-level GMM shows potential in predicting sarcopenia, and the incorporation of independent clinical predictors further increased the performance.
{"title":"Comparison of different MRI-based unsupervised segmentation algorithms in predicting sarcopenia","authors":"Huayan Zuo , Qiyang Wang , Guoli Bi , Yijin Wang , Guang Yang , Chengxiu Zhang , Yang Song , Yunzhu Wu , Xiarong Gong , Qiu Bi","doi":"10.1016/j.ejrad.2024.111748","DOIUrl":"10.1016/j.ejrad.2024.111748","url":null,"abstract":"<div><h3>Purpose</h3><div>To compare the performance of MRI-based Gaussian mixture model (GMM), K-means clustering, and Otsu unsupervised algorithms in predicting sarcopenia and to develop a combined model by integrating clinical indicators.</div></div><div><h3>Methods</h3><div>Retrospective analysis was conducted on clinical and lumbar MRI data from 118 patients diagnosed with sarcopenia and 222 patients without the sarcopenia. All patients were randomly divided into training and validation groups in a 7:3 ratio. Regions of interest (ROI), specifically the paravertebral muscles at the L3/4 intervertebral disc level, were delineated on axial T2-weighted images (T2WI). The Gaussian mixture model (GMM), K-means clustering, and Otsu’s thresholding algorithms were employed to automatically segment muscle and adipose tissues at both the cohort and case levels. Subsequently, the mean signal intensity, volumes, and percentages of these tissues were calculated and compared. Logistic regression analyses were conducted to construct models and identify independent predictors of sarcopenia. An combined model was developed by combining the optimal magnetic resonance imaging (MRI) model and clinical predictors. The performance of the constructed model was assessed using receiver operating characteristic (ROC) curve analysis.</div></div><div><h3>Results</h3><div>Age, BMI, and serum albumin were identified as independent clinical predictors of sarcopenia. The cohort-level GMM demonstrated the best predictive performance both in the training group (AUC=0.840) and validation group (AUC=0.800), while the predictive performance of the other models was lower than that of the clinical model both in the training and validation groups. After combining the cohort-level GMM with the independent clinical predictors, the AUC of the training and validation groups increased to 0.871 and 0.867, respectively.</div></div><div><h3>Conclusion</h3><div>The cohort-level GMM shows potential in predicting sarcopenia, and the incorporation of independent clinical predictors further increased the performance.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111748"},"PeriodicalIF":3.2,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-18DOI: 10.1016/j.ejrad.2024.111746
Hee Ho Chu, Jin Hyoung Kim, Gun Ha Kim, So Yeon Kim, So Jung Lee, Hyung Jin Won, Yong Moon Shin
Purpose
To develop a model for pretreatment prediction of overall survival (OS) after radiofrequency ablation (RFA) for colorectal liver metastasis (CRLM).
Method
This retrospective study included 491 patients (median age, 61 years; 348 men) who underwent percutaneous RFA for CRLM between 2000 and 2021. The Kaplan–Meier method was used to estimate OS rates. Independent factors affecting OS were investigated using multivariable Cox regression analysis. Risk scores were assigned to the risk factors and pretreatment prediction models were created using the risk factors.
Results
After RFA, the 5-, 10-, and 20-year OS rates were 44 %, 31 %, and 24 %, respectively, and the median OS was 46 months. Multivariate Cox regression analysis showed that a largest tumor size ≥ 2 cm (P<0.001), positive nodal status of primary tumor (P<0.001), carcinoembryonic antigen level > 30 ng/mL (P=0.049), multiple tumors (P=0.008), and T4 stage of the primary tumor (P=0.029) were independently associated with OS. In patients with a single CRLM, tumor diameter (P<0.001), positive nodal status of primary tumor (P=0.001), disease-free interval <12 months (P=0.045), and subcapsular location (P=0.03) were risk factors affecting OS. According to our prediction models, which included the aforementioned risk factors, OS rates progressively decreased as the risk scores increased, with significantly different OS rates between contiguous groups (P<0.001).
Conclusions
Our prediction models can be used as a prognostic stratification tool in patients with CRLM, and can help select those candidates who will benefit most from RFA.
{"title":"Percutaneous radiofrequency ablation of liver metastases from colorectal cancer: Development of a prognostic score to predict overall survival","authors":"Hee Ho Chu, Jin Hyoung Kim, Gun Ha Kim, So Yeon Kim, So Jung Lee, Hyung Jin Won, Yong Moon Shin","doi":"10.1016/j.ejrad.2024.111746","DOIUrl":"10.1016/j.ejrad.2024.111746","url":null,"abstract":"<div><h3>Purpose</h3><div>To develop a model for pretreatment prediction of overall survival (OS) after radiofrequency ablation (RFA) for colorectal liver metastasis (CRLM).</div></div><div><h3>Method</h3><div>This retrospective study included 491 patients (median age, 61 years; 348 men) who underwent percutaneous RFA for CRLM between 2000 and 2021. The Kaplan–Meier method was used to estimate OS rates. Independent factors affecting OS were investigated using multivariable Cox regression analysis. Risk scores were assigned to the risk factors and pretreatment prediction models were created using the risk factors.</div></div><div><h3>Results</h3><div>After RFA, the 5-, 10-, and 20-year OS rates were 44 %, 31 %, and 24 %, respectively, and the median OS was 46 months. Multivariate Cox regression analysis showed that a largest tumor size ≥ 2 cm (P<0.001), positive nodal status of primary tumor (P<0.001), carcinoembryonic antigen level > 30 ng/mL (P=0.049), multiple tumors (P=0.008), and T4 stage of the primary tumor (P=0.029) were independently associated with OS. In patients with a single CRLM, tumor diameter (P<0.001), positive nodal status of primary tumor (P=0.001), disease-free interval <12 months (P=0.045), and subcapsular location (P=0.03) were risk factors affecting OS. According to our prediction models, which included the aforementioned risk factors, OS rates progressively decreased as the risk scores increased, with significantly different OS rates between contiguous groups (P<0.001).</div></div><div><h3>Conclusions</h3><div>Our prediction models can be used as a prognostic stratification tool in patients with CRLM, and can help select those candidates who will benefit most from RFA.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111746"},"PeriodicalIF":3.2,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142312253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号