背景:通常报道室间隔的T2*值用于对重型地中海贫血的心肌铁负荷进行分级,隔膜的自动分割可以缩短分析时间并减少观察者之间的变异性。
目的:开发一种基于深度学习的方法,用于从黑血MR图像中自动分割隔膜,用于地中海贫血患者的心肌T2*测量。
方法:回顾性。
方法:来自两个中心的146名输血依赖性地中海贫血患者进行心脏MR检查。来自中心1(1.5T)的数据被分配到训练(100次检查)和内部测试(20次检查)集合;来自中心2的数据被分配到外部测试集合(26次检查;10次在1.5T,16次在3.0T)。
■1.5T和3.0T,多回波梯度回波序列。
结果:构建并训练了用于隔膜分割的改良注意力U-Net,并在看不见的内部和外部数据集上评估其性能。T2*通过拟合平均隔膜信号来测量,通过自动和手动方法分别分段。
方法:使用Dice系数评估手动和自动隔膜分割之间的一致性,和T2*一致性使用Bland-Altman图和变异系数(CoV)进行评估。
结果:内部数据集上基于深度网络的隔膜分割的中值Dice系数为0.90[0.05],外部1.5T数据集上的0.82[0.10],和外部3.0T数据集上的0.86[0.14]。使用自动分割的T2*测量值与手动分割的测量值相对应,平均差为0.02(95%LoA:-0.74至0.79)毫秒,0.43(95%LoA:-2.1至3.0)毫秒,在三个数据集上和0.36(95%LoA:-0.72至1.4)毫秒。两种方法之间的CoV为3.1%,7.0%,内部和两个外部数据集上的6.1%,分别。
结论:建议的隔膜分割产生的心肌T2*测量结果与手动分割获得的结果高度一致。这种自动方法可以促进数据处理并避免在实践中依赖于操作者的可变性。
方法:4技术效果:第一阶段。
BACKGROUND: The T2* value of interventricular septum is routinely reported for grading myocardial iron load in thalassemia major, and automatic segmentation of septum could shorten analysis time and reduce interobserver variability.
OBJECTIVE: To develop a deep learning-based method for automatic septum segmentation from black-blood MR images for the myocardial T2* measurement of thalassemia patients.
METHODS: Retrospective.
METHODS: One hundred forty-six transfusion-dependent thalassemia patients with cardiac MR examinations from two centers. Data from Center 1 (1.5 T) were assigned to the training (100 examinations) and internal testing (20 examinations) sets; data from Center 2 were assigned to the external testing set (26 examinations; 10 at 1.5 T and 16 at 3.0 T).
UNASSIGNED: 1.5 T and 3.0 T, multiecho gradient-echo sequence.
RESULTS: A modified attention U-Net for septum segmentation was constructed and trained, and its performance evaluated on unseen internal and external datasets. T2* was measured by fitting the average septum signal, separately segmented by automatic and manual methods.
METHODS: Agreement between manual and automatic septum segmentations was assessed with the Dice coefficient, and T2* agreement was assessed using the Bland-Altman plot and the coefficient of variation (CoV).
RESULTS: The median Dice coefficient of deep network-based septum segmentation was 0.90 [0.05] on the internal dataset, 0.82 [0.10] on the external 1.5 T dataset, and 0.86 [0.14] on the external 3.0 T dataset. T2* measurements using automatic segmentation corresponded with those from manual segmentation, with a mean difference of 0.02 (95% LoA: -0.74 to 0.79) msec, 0.43 (95% LoA: -2.1 to 3.0) msec, and 0.36 (95% LoA: -0.72 to 1.4) msec on the three datasets. The CoVs between the two methods were 3.1%, 7.0%, and 6.1% on the internal and two external datasets, respectively.
CONCLUSIONS: The proposed septum segmentation yielded myocardial T2* measurements which were highly consistent with those obtained by manual segmentation. This automatic approach may facilitate data processing and avoid operator-dependent variability in practice.
METHODS: 4 TECHNICAL EFFICACY: Stage 1.