作者:
LI YangDept Neurol
1st Med CenterChinese PLA General HospBeijing 100853
Objective To analyze the clinical data and related literature of sporadic amyotrophic lateral sclerosis(sALs) caused by a new mutation of MATR3 *** A sALs patient with MATR3 gene mutation who was admitted to the Depar...
详细信息
Objective To analyze the clinical data and related literature of sporadic amyotrophic lateral sclerosis(sALs) caused by a new mutation of MATR3 *** A sALs patient with MATR3 gene mutation who was admitted to the department of Neurology, the First Medical Center of Chinese people′s liberation army general hospital was collected. The examination of biochemistry, electromyography, cranial magnetic resonance imaging (MRI) and genetic tests, etc, were performed.
目的评估3种深度学习(DL)算法在子宫内膜癌(EC)术后患者高剂量率近距离放射治疗(high-dose-rate brachytherapy,HDR BT)中,自动分割临床靶区(CTV)的应用结果。方法数据集由306名子宫内膜癌术后患者的计算机断层扫描(CT)图像组成,按比例分为训练集(246例)、验证集(30例)和测试集(30例)。比较3种深度卷积神经网络模型(3D U-Net、3D Res U-Net和V-Net)在CTV分割上的性能。采用定量指标分别为戴斯相似性系数(DsC)、豪斯多夫距离(HD)、豪斯多夫距离第95百分位数(HD95%)和交并比(IoU)。结果在测试阶段中,3D U-Net、3D Res U-Net和V-Net分割CTV得到的DsC平均值分别为0.90±0.07、0.95±0.06和0.95±0.06;HD平均值(mm)分别为2.51±1.70、0.96±1.01和0.98±0.95;HD95%平均值(mm)分别为1.33±1.02、0.65±0.91和0.40±0.72,IoU平均值分别为0.85±0.11、0.91±0.09和0.92±0.09。其中,V-Net分割结果与高级临床医生勾画结果更接近,CTV的分割时间s,节省了临床医生的工作时间。结论V-Net在CTV分割方面表现最佳,定量指标和临床评估均优于其他模型。该方法与基准真实值高度一致,有效减少医生间差异,缩短治疗时间。
暂无评论