目的探讨基于MRI征象与影像组学诊断进展期胃癌T3和T4a分期效能的对比分析。方法选取于同济大学附属东方医院庐江分院行MRI检查,经病理结果证实,共计纳入208例胃癌患者,其中T3期96例,T4a期112例。首先应用传统影像学征象判断进展期胃癌...目的探讨基于MRI征象与影像组学诊断进展期胃癌T3和T4a分期效能的对比分析。方法选取于同济大学附属东方医院庐江分院行MRI检查,经病理结果证实,共计纳入208例胃癌患者,其中T3期96例,T4a期112例。首先应用传统影像学征象判断进展期胃癌侵犯浆膜层等征象,比较多序列MRI征象在病理证实T3和T4a期胃癌中表现的差异性;其次按7:3的比例随机分为训练组(n=145)和验证组(n=63),分别从常规T2非抑脂序列及高比值DWI序列(b=1000 s/mm^(2))图像中提取影像组学特征,构建影像组学联合模型;然后分别绘制基于传统MRI征象与影像组学联合模型工作特征(receiver operating characteristic,ROC)曲线,并计算ROC曲线下面积(area under the curve,AUC)、特异度及灵敏度,量化两种诊断方式对胃癌T3和T4a分期的诊断效能。结果传统多序列MRI征象诊断AUC:0.929(95%CI:0.887~0.970),特异度0.912,灵敏度0.916;MRI影像组学联合模型训练组诊断AUC:0.975(95%CI:0.974~0.976),特异度0.946,灵敏度0.956,验证组诊断AUC:0.971(95%CI:0.965~0.974),特异度0.946,灵敏度0.943,均具有统计学意义(P<0.05)。结论基于MRI影像组学模型诊断T3和T4a分期效能高于传统MRI征象,值得临床工作中进一步推广使用。展开更多
Brain tumor is a global issue due to which several people suffer,and its early diagnosis can help in the treatment in a more efficient manner.Identifying different types of brain tumors,including gliomas,meningiomas,p...Brain tumor is a global issue due to which several people suffer,and its early diagnosis can help in the treatment in a more efficient manner.Identifying different types of brain tumors,including gliomas,meningiomas,pituitary tumors,as well as confirming the absence of tumors,poses a significant challenge using MRI images.Current approaches predominantly rely on traditional machine learning and basic deep learning methods for image classification.These methods often rely on manual feature extraction and basic convolutional neural networks(CNNs).The limitations include inadequate accuracy,poor generalization of new data,and limited ability to manage the high variability in MRI images.Utilizing the EfficientNetB3 architecture,this study presents a groundbreaking approach in the computational engineering domain,enhancing MRI-based brain tumor classification.Our approach highlights a major advancement in employing sophisticated machine learning techniques within Computer Science and Engineering,showcasing a highly accurate framework with significant potential for healthcare technologies.The model achieves an outstanding 99%accuracy,exhibiting balanced precision,recall,and F1-scores across all tumor types,as detailed in the classification report.This successful implementation demonstrates the model’s potential as an essential tool for diagnosing and classifying brain tumors,marking a notable improvement over current methods.The integration of such advanced computational techniques in medical diagnostics can significantly enhance accuracy and efficiency,paving the way for wider application.This research highlights the revolutionary impact of deep learning technologies in improving diagnostic processes and patient outcomes in neuro-oncology.展开更多
目的分析强直性脊柱炎(A S)骶髂关节磁共振成像(M R I)表现与血清基质金属蛋白酶-3(MMP-3)、肿瘤坏死因子-α(TNF-α)水平的关系。方法选取2016年6月至2019年6月我院收治60例AS患者作为研究对象,并选取同期于我院进行体检的60例健康者...目的分析强直性脊柱炎(A S)骶髂关节磁共振成像(M R I)表现与血清基质金属蛋白酶-3(MMP-3)、肿瘤坏死因子-α(TNF-α)水平的关系。方法选取2016年6月至2019年6月我院收治60例AS患者作为研究对象,并选取同期于我院进行体检的60例健康者作为对照组,均进行MRI检查,并检测血清MMP-3、TNF-α水平,分析MRI表现与血清MMP-3、TNF-α水平的关系。结果观察组累及范围计分、水肿强度计分、水肿深度计分及总评分均显著高于对照组(P<0.05);观察组血清MMP-3、TNF-α水平均显著高于对照组(P<0.05);Pearson相关性分析显示,累及范围计分、水肿强度计分、水肿深度计分与血清MMP-3、TNF-α水平呈正相关性(P<0.05)。结论AS骶髂关节MRI表现与血清MMP-3、TNF-α水平呈正相关,MRI检查和血清MMP-3、TNF-α水平可用于早期诊断AS骶髂关节炎。展开更多
目的:评价磁共振成像(MRI)三维可变翻转角快速自旋回波(3D-sampling perfection with applicationoptimized contrasts by using different filp angle evolutions,3D-SPACE)序列结合不同图像融合技术获得的图像对垂体大腺瘤术前评估的...目的:评价磁共振成像(MRI)三维可变翻转角快速自旋回波(3D-sampling perfection with applicationoptimized contrasts by using different filp angle evolutions,3D-SPACE)序列结合不同图像融合技术获得的图像对垂体大腺瘤术前评估的应用价值。方法:收集中南大学湘雅医院43例术后证实为垂体大腺瘤患者的MRI资料,包括常规MRI平扫+增强、3D-SPACE T2WI和3D-SPACE T1WI+C(增强)的影像资料。3D-SPACE T2WI/3D-SPACE T1WI+C序列分别采用正相+正相、反相+正相、正相+反相、反相+反相以及正相伪彩+正相、正相+正相伪彩6种组合方式融合,由两名放射科高年资主治医生采用半定量方法对不同组合方式图像质量进行评价及比较,得到最佳融合模式;并根据肿瘤对视交叉、动眼神经、海绵窦血管的侵袭程度,按照三级评分制对MRI平扫+增强(常规MRI增强组),3DSPACE T2WI,3D-SPACE T1WI+C及2种3D-SPACE序列融合(融合组)的图像进行评估,以术中观察结果为金标准,采用Fisher概率确切法比较4组图像显示垂体大腺瘤对周围组织侵袭程度与金标准的一致性。结果:Kruskal-Wallis H秩和检验结果显示6种图像融合模式中,以3D-SPACE T1WI+C正相伪彩与3D-SPACE T2WI正相融合图像质量最优(P<0.05)。比较肿瘤对动眼神经侵袭程度I,II,III级关系一致性时,MRI增强组、3D-SPACE T1WI+C组、3DSPACE T2WI组、融合组4组图像差异均无统计学意义(均P>0.05);比较肿瘤对视交叉侵袭程度I级关系一致性时,4组图像差异均无统计学意义(均P>0.05),比较侵袭程度II,III级关系一致性时,融合组图像与3D-SPACE T2WI组差异无统计学意义(P>0.05),但均明显优于常规MRI增强组(均P<0.01)和3D-SPACE T1WI+C组(均P<0.05);比较肿瘤对海绵窦血管侵袭程度I,III级关系一致性时,4组图像差异均无统计学意义(均P>0.05),比较侵袭程度II级关系一致性时,融合组图像与3D-SPACE T1WI+C组差异无统计学意义(P>0.05),但均明显优于常规MRI增强组(均P<0.01)和3D-SPACE T2WI组(均P<0.05)。结论:MRI 3D-SPACE序列结合图像融合技术在显示垂体大腺瘤对颅底血管神经的侵袭程度上明显优于常规MRI序列,在显示肿瘤与视交叉II,III级侵袭关系及肿瘤与海绵窦血管II级侵袭关系上明显优于单独的3D-SPACE序列,对于手术前的风险评估及手术方案的制订有良好的应用前景。展开更多
文摘目的探讨基于MRI征象与影像组学诊断进展期胃癌T3和T4a分期效能的对比分析。方法选取于同济大学附属东方医院庐江分院行MRI检查,经病理结果证实,共计纳入208例胃癌患者,其中T3期96例,T4a期112例。首先应用传统影像学征象判断进展期胃癌侵犯浆膜层等征象,比较多序列MRI征象在病理证实T3和T4a期胃癌中表现的差异性;其次按7:3的比例随机分为训练组(n=145)和验证组(n=63),分别从常规T2非抑脂序列及高比值DWI序列(b=1000 s/mm^(2))图像中提取影像组学特征,构建影像组学联合模型;然后分别绘制基于传统MRI征象与影像组学联合模型工作特征(receiver operating characteristic,ROC)曲线,并计算ROC曲线下面积(area under the curve,AUC)、特异度及灵敏度,量化两种诊断方式对胃癌T3和T4a分期的诊断效能。结果传统多序列MRI征象诊断AUC:0.929(95%CI:0.887~0.970),特异度0.912,灵敏度0.916;MRI影像组学联合模型训练组诊断AUC:0.975(95%CI:0.974~0.976),特异度0.946,灵敏度0.956,验证组诊断AUC:0.971(95%CI:0.965~0.974),特异度0.946,灵敏度0.943,均具有统计学意义(P<0.05)。结论基于MRI影像组学模型诊断T3和T4a分期效能高于传统MRI征象,值得临床工作中进一步推广使用。
基金supported by the Researchers Supporting Program at King Saud University.Researchers Supporting Project number(RSPD2024R867),King Saud University,Riyadh,Saudi Arabia.
文摘Brain tumor is a global issue due to which several people suffer,and its early diagnosis can help in the treatment in a more efficient manner.Identifying different types of brain tumors,including gliomas,meningiomas,pituitary tumors,as well as confirming the absence of tumors,poses a significant challenge using MRI images.Current approaches predominantly rely on traditional machine learning and basic deep learning methods for image classification.These methods often rely on manual feature extraction and basic convolutional neural networks(CNNs).The limitations include inadequate accuracy,poor generalization of new data,and limited ability to manage the high variability in MRI images.Utilizing the EfficientNetB3 architecture,this study presents a groundbreaking approach in the computational engineering domain,enhancing MRI-based brain tumor classification.Our approach highlights a major advancement in employing sophisticated machine learning techniques within Computer Science and Engineering,showcasing a highly accurate framework with significant potential for healthcare technologies.The model achieves an outstanding 99%accuracy,exhibiting balanced precision,recall,and F1-scores across all tumor types,as detailed in the classification report.This successful implementation demonstrates the model’s potential as an essential tool for diagnosing and classifying brain tumors,marking a notable improvement over current methods.The integration of such advanced computational techniques in medical diagnostics can significantly enhance accuracy and efficiency,paving the way for wider application.This research highlights the revolutionary impact of deep learning technologies in improving diagnostic processes and patient outcomes in neuro-oncology.
文摘目的分析强直性脊柱炎(A S)骶髂关节磁共振成像(M R I)表现与血清基质金属蛋白酶-3(MMP-3)、肿瘤坏死因子-α(TNF-α)水平的关系。方法选取2016年6月至2019年6月我院收治60例AS患者作为研究对象,并选取同期于我院进行体检的60例健康者作为对照组,均进行MRI检查,并检测血清MMP-3、TNF-α水平,分析MRI表现与血清MMP-3、TNF-α水平的关系。结果观察组累及范围计分、水肿强度计分、水肿深度计分及总评分均显著高于对照组(P<0.05);观察组血清MMP-3、TNF-α水平均显著高于对照组(P<0.05);Pearson相关性分析显示,累及范围计分、水肿强度计分、水肿深度计分与血清MMP-3、TNF-α水平呈正相关性(P<0.05)。结论AS骶髂关节MRI表现与血清MMP-3、TNF-α水平呈正相关,MRI检查和血清MMP-3、TNF-α水平可用于早期诊断AS骶髂关节炎。
