[论文解读] Novel Deep Convolution Neural Network Applied to MRI Cardiac Segmentation.

Clément Zotti, Zhiming Luo+3 more|arXiv (Cornell University)|May 24, 2017

Radiomics and Machine Learning in Medical Imaging参考文献 20被引用 10

一句话总结

该论文提出了一种新型的深度卷积神经网络，用于完全自动化的3D MRI心脏分割，联合分割左心室和右心室腔室以及左心室心外膜。该方法引入了具有形状先验和质心回归的最大后验概率损失，使在ACDC数据集上每体积仅需0.4秒即可实现0.90的平均Dice分数。

ABSTRACT

In this paper, we propose a fully automatic MRI cardiac segmentation method based on a novel deep convolutional neural network (CNN). As opposed to most cardiac segmentation methods which focus on the left ventricle (and especially the left cavity), our method segments both the left ventricular cavity, the left ventricular epicardium, and the right ventricular cavity. The novelty of our network lies in its maximum a posteriori loss function, which is specifically designed for the cardiac anatomy. Our loss function incorporates the cross-entropy of the predicted labels, the predicted contours, a cardiac shape prior, and an a priori term. Our model also includes a cardiac center-of-mass regression module which allows for an automatic shape prior registration. Also, since our method processes raw MR images without any manual preprocessing and/or image cropping, our CNN learns both high-level features (useful to distinguish the heart from other organs with a similar shape) and low-level features (useful to get accurate segmentation results). Those features are learned with a multi-resolution conv-deconv grid architecture which can be seen as an extension of the U-Net. We trained and tested our model on the ACDC MICCAI'17 challenge dataset of 150 patients whose diastolic and systolic images were manually outlined by 2 medical experts. Results reveal that our method can segment all three regions of a 3D MRI cardiac volume in $0.4$ second with an average Dice index of $0.90$, which is significantly better than state-of-the-art deep learning methods.

研究动机与目标

• 开发一种完全自动化的3D MRI心脏结构分割方法，无需人工预处理。
• 通过将心脏特异性解剖先验整合到损失函数中，提高分割精度。
• 通过多分辨率U-Net类架构实现端到端学习，同时捕捉高层和低层特征。
• 通过在原始MR图像上进行训练，消除对图像裁剪或人工预处理的需求。

提出的方法

• 该方法采用受U-Net启发的多分辨率卷积-反卷积网格架构，从原始MRI体积中学习分层特征。
• 采用最大后验概率（MAP）损失函数，整合预测标签的交叉熵、预测轮廓、心脏形状先验以及先验项。
• 心脏质心回归模块可实现形状先验与输入图像的自动配准。
• 网络直接处理原始、未经处理的MR图像，同时学习全局器官级特征和局部边界细节。
• 该架构在ACDC MICCAI'17数据集的150例患者数据上进行端到端训练，包含专家标注的舒张期和收缩期图像。
• 模型被优化为预测三个区域：左心室腔室、左心室心外膜和右心室腔室。

实验结果

研究问题

• RQ1 是否可以通过自定义MAP损失函数的深度CNN，同时提升多个心脏结构的分割精度？
• RQ2 通过质心回归学习的形状先验在无需人工裁剪的情况下，对提升分割鲁棒性的效果如何？
• RQ3 多分辨率U-Net变体在无需预处理的情况下，能够多大程度上从原始MRI中学习高层和低层特征？
• RQ4 将解剖轮廓和形状先验整合到损失函数中，是否能比标准交叉熵损失带来更好的边界精度？
• RQ5 该方法是否能在多样化的临床数据集上实现实时推理速度，同时保持高Dice分数？

主要发现

• 所提出的方法在所有三个心脏结构（左心室腔室、左心室心外膜和右心室腔室）上均实现了0.90的平均Dice分数。
• 该模型仅用0.4秒即可分割一个完整的3D MRI心脏体积，展示了实时推理能力。
• 结合形状先验和轮廓监督的MAP损失函数显著提升了分割精度，相比标准交叉熵损失效果更优。
• 该方法在ACDC MICCAI'17基准数据集上优于当前最先进的深度学习方法。
• 该网络在无需图像裁剪或人工预处理步骤的情况下，对不同患者表现出良好的泛化能力。