Background： Previous studies showed that combining apparent diffusion coefficient （ADC） value with the Spondyloarthritis Research Consortium of Canada （SPARCC） index value might provide a reliable evaluation of t...Background： Previous studies showed that combining apparent diffusion coefficient （ADC） value with the Spondyloarthritis Research Consortium of Canada （SPARCC） index value might provide a reliable evaluation of the activity of ankylosing spondylitis （AS）, and that contrast-enhanced （CE） magnetic resonance imaging （MRI） is unnecessary. However, the results were based on confirming only a small random sample. This study aimed to assess the role of CE-MRI in differentiating the disease activity of AS by comparingADC value with a large sample. Methods： A total of l 15 patients with AS were enrolled in accordance with Bath AS Disease Activity Index and laboratory indices, and 115 patients were divided into two groups, including active group （n = 69） and inactive group （n 46）. SPARCC, ASI, and ADC values were obtained from the short tau inversion recovery （STIR）, diffusion-weighted imaging （DWI）, and CE-MRI, respectively. One-way analysis of variance and receiver operating characteristic analysis were performed for all parameters. Results： The optimal cutoff values （with sensitivity, specificity, respective area under the curve, positive likelihood ratio, and negative likelihood ratio） for the differentiation between active and inactive groups are as follows： SPARCC = 6 （72.06%, 82.61%, 0.836, 4.14, 0.34）; ASI （%） 153 （80.6%, 84.78%, 0.819, 5.3, 0.23）; ADC value - 1.15 × 10 3 mm2/s （72.73% 81.82%, 0.786, 4, 0.33）. No statistical differences were found among the predictive values of SPARCC, △SI, and ADC. Multivariate analysis showed no significant difference between the combination of SPARCC and ADC values with and without ASI. Conclusions： Using large sample, we concluded that the combination of STIR and DWI would play significant roles in assessing the disease activity, and CE-MRI sequence is not routinely used in imaging of AS to avoid renal fibrosis and aggravation of kidney disease.展开更多
目的:探讨基于钆塞酸二钠增强MRI肝胆期影像组学在肝细胞癌(HCC)病理分化程度中的预测价值。方法:回顾性收集145例经术后病理证实为HCC患者资料,根据病理分级将患者分为低危险组(100例)和高危险组(45例),前者包括高分化(11例)、中-高分...目的:探讨基于钆塞酸二钠增强MRI肝胆期影像组学在肝细胞癌(HCC)病理分化程度中的预测价值。方法:回顾性收集145例经术后病理证实为HCC患者资料,根据病理分级将患者分为低危险组(100例)和高危险组(45例),前者包括高分化(11例)、中-高分化(11例)、中分化(78例)HCC,后者包括低分化(21例)、中-低分化(24例)HCC。所有患者术前2周均行钆塞酸二钠增强MRI检查。通过分析得出对HCC有影响的临床及传统影像学特征,建立临床-影像模型;利用ITK⁃SNAP软件在肝胆特异期图像上手动勾画肿瘤感兴趣区(ROIs),利用FAE(FeAture Explorer V.0.5.5)软件提取特征,使用最大相关最小冗余法对特征降维,通过建立XGBoost二分类模型来预测诊断效能;最终将临床-影像模型与影像组学模型相结合,建立联合模型。采用受试者工作特征(ROC)曲线下面积、准确度、灵敏度、特异度等指标来评价各模型诊断效能。结果:测试组中临床-影像模型、影像组学模型以及联合模型的ROC曲线下面积值分别为0.66、0.70、0.76,准确度分别为63.6%、63.6%、77.3%,灵敏度分别为71.4%、85.7%、57.1%,特异度分别为60.0%、53.3%、86.7%。结论:基于钆塞酸二钠增强MRI肝胆期影像组学的模型在预测HCC病理分化中有一定的价值。展开更多
文摘Background： Previous studies showed that combining apparent diffusion coefficient （ADC） value with the Spondyloarthritis Research Consortium of Canada （SPARCC） index value might provide a reliable evaluation of the activity of ankylosing spondylitis （AS）, and that contrast-enhanced （CE） magnetic resonance imaging （MRI） is unnecessary. However, the results were based on confirming only a small random sample. This study aimed to assess the role of CE-MRI in differentiating the disease activity of AS by comparingADC value with a large sample. Methods： A total of l 15 patients with AS were enrolled in accordance with Bath AS Disease Activity Index and laboratory indices, and 115 patients were divided into two groups, including active group （n = 69） and inactive group （n 46）. SPARCC, ASI, and ADC values were obtained from the short tau inversion recovery （STIR）, diffusion-weighted imaging （DWI）, and CE-MRI, respectively. One-way analysis of variance and receiver operating characteristic analysis were performed for all parameters. Results： The optimal cutoff values （with sensitivity, specificity, respective area under the curve, positive likelihood ratio, and negative likelihood ratio） for the differentiation between active and inactive groups are as follows： SPARCC = 6 （72.06%, 82.61%, 0.836, 4.14, 0.34）; ASI （%） 153 （80.6%, 84.78%, 0.819, 5.3, 0.23）; ADC value - 1.15 × 10 3 mm2/s （72.73% 81.82%, 0.786, 4, 0.33）. No statistical differences were found among the predictive values of SPARCC, △SI, and ADC. Multivariate analysis showed no significant difference between the combination of SPARCC and ADC values with and without ASI. Conclusions： Using large sample, we concluded that the combination of STIR and DWI would play significant roles in assessing the disease activity, and CE-MRI sequence is not routinely used in imaging of AS to avoid renal fibrosis and aggravation of kidney disease.
文摘目的:探讨基于钆塞酸二钠增强MRI肝胆期影像组学在肝细胞癌(HCC)病理分化程度中的预测价值。方法:回顾性收集145例经术后病理证实为HCC患者资料,根据病理分级将患者分为低危险组(100例)和高危险组(45例),前者包括高分化(11例)、中-高分化(11例)、中分化(78例)HCC,后者包括低分化(21例)、中-低分化(24例)HCC。所有患者术前2周均行钆塞酸二钠增强MRI检查。通过分析得出对HCC有影响的临床及传统影像学特征,建立临床-影像模型;利用ITK⁃SNAP软件在肝胆特异期图像上手动勾画肿瘤感兴趣区(ROIs),利用FAE(FeAture Explorer V.0.5.5)软件提取特征,使用最大相关最小冗余法对特征降维,通过建立XGBoost二分类模型来预测诊断效能;最终将临床-影像模型与影像组学模型相结合,建立联合模型。采用受试者工作特征(ROC)曲线下面积、准确度、灵敏度、特异度等指标来评价各模型诊断效能。结果:测试组中临床-影像模型、影像组学模型以及联合模型的ROC曲线下面积值分别为0.66、0.70、0.76,准确度分别为63.6%、63.6%、77.3%,灵敏度分别为71.4%、85.7%、57.1%,特异度分别为60.0%、53.3%、86.7%。结论:基于钆塞酸二钠增强MRI肝胆期影像组学的模型在预测HCC病理分化中有一定的价值。
