Magnetic Resonance Imaging Estimation of Longitudinal Relaxation Rate Change (ΔR1) in Dual Gradient Echo Sequences Using an Adaptive Model.
Magnetic Resonance Imaging Estimation of Longitudinal Relaxation Rate Change (ΔR1) in Dual Gradient Echo Sequences Using an Adaptive Model.
复制标题
使用自适应模型对双梯度回波序列中的纵向弛豫率变化 (ΔR1) 进行磁共振成像估计。
DOI：
10.1109/ijcnn.2011.6033544
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Ewing,JR
中科院分区：
文献类型：
--
作者：
Bagher-Ebadian,H;Nejad-Davarani,SP;Ali,MM;Brown,S;Makki,M;Jiang,Q;Noll,DC;Ewing,JR
磁共振成像 (MRI) 估计快速脉冲序列中造影剂浓度（例如双梯度回波 (DGE) 成像）具有挑战性。使用 Look-Locker (LL) 技术（反转恢复成像的修改版本）估计的造影剂浓度图作为金标准来训练自适应神经网络 (ANN)。使用从 DGE MRI 数据中提取的一组特征，训练 ANN 来创建基于体素的 CA 浓度时间轨迹估计器。使用 60 倍和 10500 个样本的 K 折交叉验证 (KFCV) 方法，使用六只 Fisher 大鼠的 DGE 和 LL 信息对 ANN 进行训练和测试。 60 倍的接收器算子特征曲线下面积 (AUROC) 用于 ANN 的训练、测试和优化。经过训练和优化后，最佳 ANN (4:7:5:1) 生成的 CA 浓度图与 LL 技术估计的 CA 浓度高度相关 (r = 0.89，P <; 0.0001)。 ANN 做出的估计具有出色的整体性能（AUROC = 0.870）。
Magnetic Resonance Imaging (MRI) estimation of contrast agent concentration in fast pulse sequences such as Dual Gradient Echo (DGE) imaging is challenging. An Adaptive Neural Network (ANN) was trained with a map of contrast agent concentration estimated by Look-Locker (LL) technique (modified version of inversion recovery imaging) as a gold standard. Using a set of features extracted from DGE MRI data, an ANN was trained to create a voxel based estimator of the time trace of CA concentration. The ANN was trained and tested with the DGE and LL information of six Fisher rats using a K-Fold Cross-Validation (KFCV) method with 60 folds and 10500 samples. The Area Under the Receiver Operator Characteristic Curve (AUROC) for 60 folds was used for training, testing and optimization of the ANN. After training and optimization, the optimal ANN (4:7:5:1) produced maps of CA concentration which were highly correlated (r = 0.89, P <; 0.0001) with the CA concentration estimated by the LL technique. The estimation made by the ANN had an excellent overall performance (AUROC = 0.870).