目的探讨联合使用扩散加权成像(DWI)、磁共振波谱成像(MRS)能否提高Kaiser评分对乳腺病变的诊断效能。方法回顾性分析2023年1月至2025年2月于山东大学第八人民医院行乳腺3.0 T MRI平扫及动态对比增强检查、MRS检查的女性患者病例共107例,...目的探讨联合使用扩散加权成像(DWI)、磁共振波谱成像(MRS)能否提高Kaiser评分对乳腺病变的诊断效能。方法回顾性分析2023年1月至2025年2月于山东大学第八人民医院行乳腺3.0 T MRI平扫及动态对比增强检查、MRS检查的女性患者病例共107例,共111个病灶。对每个病灶进行Kaiser评分、表观扩散系数(ADC)值测量、tCho峰判断,以病理为金标准采用应用受试者工作特征(ROC)曲线、Kappa一致性评价对Kaiser评分及Kaiser+ADC+MRS(Kaiser+评分)的诊断效能进行评价,并应用Delong检验对曲线下面积(AUC)进行比较。结果Kaiser评分的AUC为0.938,最佳诊断界值为4分,其敏感性为96.67%(95%CI:88.5%~99.6%)、特异性80.39%(95%CI:66.9%~90.2%);Kaiser+评分AUC为0.969,最佳诊断界值为4分,其敏感性为93.33%(95%CI:83.8%~98.2%)、特异性90.20%(95%CI:78.6%~96.7%);Kaiser+评分的AUC较Kaiser评分提高(P=0.026)。Kappa一致性分析发现Kaiser评分与病理结果的一致性为0.779(95%CI:0.663~0.896),Kaiser+评分与病理结果的一致性为0.837(95%CI:0.663~0.896)。结论联合使用DWI、MRS可以提高Kaiser评分的诊断效能,可以在保证高敏感性的前提下提高诊断的特异性,降低穿刺活检率。展开更多
Large-scale underground projects need accurate in-situ stress information,and the acoustic emission(AE)Kaiser effect method currently offers lower costs and streamlined procedures.In this method,the accuracy and speed...Large-scale underground projects need accurate in-situ stress information,and the acoustic emission(AE)Kaiser effect method currently offers lower costs and streamlined procedures.In this method,the accuracy and speed of Kaiser point identification are important.Thus,this study aims to integrate chaos theory and machine learning for accurately and quickly identifying Kaiser points.An intelligent model of the identification of AE partitioned areas was established by phase space reconstruction(PSR),genetic algorithm(GA),and support vector machine(SVM).Then,the plots of model classification results were made to identify Kaiser points.We refer to this method of identifying Kaiser points as the partitioning plot method based on PSR–GA–SVM(PPPGS).The PSR–GA–SVM model demonstrated outstanding performance,which achieved a 94.37%accuracy rate on the test set,with other evaluation metrics also indicating exceptional performance.The PPPGS identified Kaiser points similar to the tangent-intersection method with greater accuracy.Furthermore,in the feature importance score of the classification model,the fractal dimension extracted by PSR ranked second after accumulated AE count,which confirmed its importance and reliability as a classification feature.The PPPGS was applied to in-situ stress measurement at a phosphate mine in Guizhou Weng'an,China,to validate its practicability,where it demonstrated good performance.展开更多
文摘目的探讨联合使用扩散加权成像(DWI)、磁共振波谱成像(MRS)能否提高Kaiser评分对乳腺病变的诊断效能。方法回顾性分析2023年1月至2025年2月于山东大学第八人民医院行乳腺3.0 T MRI平扫及动态对比增强检查、MRS检查的女性患者病例共107例,共111个病灶。对每个病灶进行Kaiser评分、表观扩散系数(ADC)值测量、tCho峰判断,以病理为金标准采用应用受试者工作特征(ROC)曲线、Kappa一致性评价对Kaiser评分及Kaiser+ADC+MRS(Kaiser+评分)的诊断效能进行评价,并应用Delong检验对曲线下面积(AUC)进行比较。结果Kaiser评分的AUC为0.938,最佳诊断界值为4分,其敏感性为96.67%(95%CI:88.5%~99.6%)、特异性80.39%(95%CI:66.9%~90.2%);Kaiser+评分AUC为0.969,最佳诊断界值为4分,其敏感性为93.33%(95%CI:83.8%~98.2%)、特异性90.20%(95%CI:78.6%~96.7%);Kaiser+评分的AUC较Kaiser评分提高(P=0.026)。Kappa一致性分析发现Kaiser评分与病理结果的一致性为0.779(95%CI:0.663~0.896),Kaiser+评分与病理结果的一致性为0.837(95%CI:0.663~0.896)。结论联合使用DWI、MRS可以提高Kaiser评分的诊断效能,可以在保证高敏感性的前提下提高诊断的特异性,降低穿刺活检率。
基金financially supported by the National Natural Science Foundation of China(Nos.52374107 and 52304165)。
文摘Large-scale underground projects need accurate in-situ stress information,and the acoustic emission(AE)Kaiser effect method currently offers lower costs and streamlined procedures.In this method,the accuracy and speed of Kaiser point identification are important.Thus,this study aims to integrate chaos theory and machine learning for accurately and quickly identifying Kaiser points.An intelligent model of the identification of AE partitioned areas was established by phase space reconstruction(PSR),genetic algorithm(GA),and support vector machine(SVM).Then,the plots of model classification results were made to identify Kaiser points.We refer to this method of identifying Kaiser points as the partitioning plot method based on PSR–GA–SVM(PPPGS).The PSR–GA–SVM model demonstrated outstanding performance,which achieved a 94.37%accuracy rate on the test set,with other evaluation metrics also indicating exceptional performance.The PPPGS identified Kaiser points similar to the tangent-intersection method with greater accuracy.Furthermore,in the feature importance score of the classification model,the fractal dimension extracted by PSR ranked second after accumulated AE count,which confirmed its importance and reliability as a classification feature.The PPPGS was applied to in-situ stress measurement at a phosphate mine in Guizhou Weng'an,China,to validate its practicability,where it demonstrated good performance.
