中国CT和MRI杂志
中國CT和MRI雜誌
중국CT화MRI잡지
CHINESE JOURNAL OF CT AND MRI
2014年
3期
11-14
,共4页
段阳%杨本强%刘文源%徐猛%李延锋%刘宇
段暘%楊本彊%劉文源%徐猛%李延鋒%劉宇
단양%양본강%류문원%서맹%리연봉%류우
磁共振成像%图像分割%多发硬化
磁共振成像%圖像分割%多髮硬化
자공진성상%도상분할%다발경화
Magnetic Renounce Imaging%Imaging Segmentation%Multiple Sclerosis
目的:采用不同序列间组合提高自动图像分割技术对MS病变容积测量。材料和方法以手动分割的病灶容积为金标准,比较不同序列(M,MPRAGE;F,FLAIR;D,DIR;T2,T2WI)间所组合的不同通道(二、三和四通道)的自动分割技术测量MS病灶容积特点。结果二通道(M+T2\M+D\M+F)的敏感性、特异性和精确性分别为:41.8%\33.3%\63.4%、82.2%\93.9%\93.6%和82.1%\99.0%\98.9%;三通道(M+T2+D/M+D+F/M+F+T2)的敏感性、特异性和精确性分别为:40.4%\64.8%\62.5%、87.1%/99.1%/98.6%和86.9%/98.9%/98.5%;四通道(M+T2+D/M+D+F/M+F+T2)的敏感性、特异性和精确性分别为:74.4%、97.0%和96.9%。结论采用四通道图像自动分割技术对MS病灶容积测量较佳。
目的:採用不同序列間組閤提高自動圖像分割技術對MS病變容積測量。材料和方法以手動分割的病竈容積為金標準,比較不同序列(M,MPRAGE;F,FLAIR;D,DIR;T2,T2WI)間所組閤的不同通道(二、三和四通道)的自動分割技術測量MS病竈容積特點。結果二通道(M+T2\M+D\M+F)的敏感性、特異性和精確性分彆為:41.8%\33.3%\63.4%、82.2%\93.9%\93.6%和82.1%\99.0%\98.9%;三通道(M+T2+D/M+D+F/M+F+T2)的敏感性、特異性和精確性分彆為:40.4%\64.8%\62.5%、87.1%/99.1%/98.6%和86.9%/98.9%/98.5%;四通道(M+T2+D/M+D+F/M+F+T2)的敏感性、特異性和精確性分彆為:74.4%、97.0%和96.9%。結論採用四通道圖像自動分割技術對MS病竈容積測量較佳。
목적:채용불동서렬간조합제고자동도상분할기술대MS병변용적측량。재료화방법이수동분할적병조용적위금표준,비교불동서렬(M,MPRAGE;F,FLAIR;D,DIR;T2,T2WI)간소조합적불동통도(이、삼화사통도)적자동분할기술측량MS병조용적특점。결과이통도(M+T2\M+D\M+F)적민감성、특이성화정학성분별위:41.8%\33.3%\63.4%、82.2%\93.9%\93.6%화82.1%\99.0%\98.9%;삼통도(M+T2+D/M+D+F/M+F+T2)적민감성、특이성화정학성분별위:40.4%\64.8%\62.5%、87.1%/99.1%/98.6%화86.9%/98.9%/98.5%;사통도(M+T2+D/M+D+F/M+F+T2)적민감성、특이성화정학성분별위:74.4%、97.0%화96.9%。결론채용사통도도상자동분할기술대MS병조용적측량교가。
Objective To improve automated technique in MS lesion volume measurement. MaterialsandMethods To compare lesion volume of multiple channels automated segmentation with that of manual segmentation in different sequences of 3D high resolution MRI: (MPRAGE, T2WI, FLAIR and DIR). Results the sensitivity of M+T2/M+T2+D, M+D/M+D+F, M+F/M+F+T2 and M+F+T2+D were 41.8/40.4%, 33.3/64.8%, 63.4/62.5%, 74.4%; the specificity were 82.2/87.1%, 93.9/99.1%, 99.0/98.6%, 97.0% and the accuracy were 82.1/86.9%, /93.6/98.9%, 98.9/98.5%, 96.9%. Conclusion In automated segmentation, the four channels automated segmentation is the best measurement way in MS lesion volume.