Liu Michael, Vanguri Rami, Mutasa Simukayi, Ha Richard, Liu Yu-Cheng, Button Terry, Jambawalikar Sachin
Department of Radiology, Columbia University Irving Medical Center, 622 W 168th Street, New York, NY, 10032, USA.
Department of Pathology & Cell Biology, Columbia University, New York, NY, USA.
Comput Biol Med. 2020 Jul;122:103798. doi: 10.1016/j.compbiomed.2020.103798. Epub 2020 May 16.
MRI T2* relaxometry protocols are often used for Liver Iron Quantification in patients with hemochromatosis. Several methods exist to semi-automatically segment parenchyma and exclude vessels for this calculation.
To determine if inclusion of multiple echoes inputs to Convolutional Neural Networks (CNN) improves automated liver and vessel segmentation in MRI T2* relaxometry protocols and to determine if the resultant segmentations agree with manual segmentations for liver iron quantification analysis.
Multi echo Gradient Recalled Echo (GRE) MRI sequence for T2* relaxometry was performed for 79 exams on 31 patients with hemochromatosis for iron quantification analysis. 275 axial liver slices were manually segmented as ground truth masks. A batch normalized U-Net with variable input width to incorporate multiple echoes is used for segmentation, using DICE as the accuracy metric. ANOVA is used to evaluate significance of channel width changes in segmentation accuracy. Linear regression is used to model the relationship of channel width on segmentation accuracy. Liver segmentations are applied to relaxometry data to calculate liver T2* yielding liver iron concentration(LIC) derived from literature based calibration curves. Manual and CNN based LIC values are compared with Pearson correlation. Bland altman plots are used to visualize differences between manual and CNN based LIC values.
Performance metrics are tested on 55 hold out slices. Linear regression indicates that there is a monotonic increase of DICE with increasing channel depth (p = 0.001) with a slope of 3.61e-3. ANOVA indicates a significant increase segmentation accuracy over single channel starting at 3 channels. Incorporation of all channels results in an average DICE of 0.86, an average increase of 0.07 over single channel. The calculated LIC from CNN segmented livers agrees well with manual segmentation (R = 0.998, slope = 0.914, p«0.001), with an average absolute difference 0.27 ± 0.99 mg Fe/g or 1.34 ± 4.3%.
More input echoes yields higher model accuracy until the noise floor. Echos beyond the first three echo times in GRE based T2* relaxometry do not contribute significant information for segmentation of liver for LIC calculation. Deep learning models with three channel width allow for generalization of model to protocols of more than three echoes, effectively a universal requirement for relaxometry. Deep learning segmentations achieve a good accuracy compared with manual segmentations with minimal preprocessing. Liver iron values calculated from hand segmented liver and Neural network segmented liver were not statistically different from each other.
MRI T2* 弛豫测量协议常用于血色素沉着症患者的肝脏铁定量分析。存在多种半自动分割实质组织并排除血管以进行此计算的方法。
确定将多个回波输入卷积神经网络（CNN）是否能改善MRI T2* 弛豫测量协议中的肝脏和血管自动分割，并确定所得分割结果是否与用于肝脏铁定量分析的手动分割结果一致。
对31例血色素沉着症患者进行了79次检查，采用多回波梯度回波（GRE）MRI序列进行T2* 弛豫测量以进行铁定量分析。将275个肝脏轴位切片手动分割为真值掩码。使用具有可变输入宽度以合并多个回波的批归一化U-Net进行分割，使用DICE作为准确性指标。采用方差分析评估分割准确性中通道宽度变化的显著性。使用线性回归对通道宽度与分割准确性的关系进行建模。将肝脏分割应用于弛豫测量数据以计算肝脏T2*，从而根据基于文献的校准曲线得出肝脏铁浓度（LIC）。将手动和基于CNN的LIC值进行Pearson相关性比较。使用Bland Altman图可视化手动和基于CNN的LIC值之间的差异。
在55个留出切片上测试了性能指标。线性回归表明，随着通道深度增加，DICE呈单调增加（p = 0.001），斜率为3.61e - 3。方差分析表明，从3个通道开始，分割准确性比单通道有显著提高。合并所有通道后，平均DICE为0.86，比单通道平均提高0.07。从CNN分割的肝脏计算出的LIC与手动分割结果吻合良好（R = 0.998，斜率 = 0.914，p «0.001），平均绝对差异为0.27±0.99 mg Fe/g或1.34±4.3%。
在达到噪声底限之前，更多的输入回波可提高模型准确性。基于GRE的T2* 弛豫测量中，前三个回波时间之外的回波对用于LIC计算的肝脏分割没有显著贡献。具有三个通道宽度的深度学习模型可将模型推广到多于三个回波的协议，这实际上是弛豫测量的普遍要求。与手动分割相比，深度学习分割在最少预处理的情况下实现了良好的准确性。从手动分割肝脏和神经网络分割肝脏计算出的肝脏铁值在统计学上没有差异。
