[论文解读] ME-Net: Multi-Encoder Net Framework for Brain Tumor Segmentation

Wenbo Zhang, Guang Yang+5 more|arXiv (Cornell University)|Mar 21, 2022

Advanced Neural Network Applications被引用 5

一句话总结

ME-Net 提出了一种用于脑肿瘤分割的3D多编码器U-Net框架，利用四种MRI模态（T1、T1c、T2、FLAIR）进行特征融合，以提升分割精度。该方法引入了一种具有区域特定权重的分类Dice损失，以应对体素不平衡问题，在BraTS 2020验证数据集上，整体肿瘤、肿瘤核心和增强肿瘤的Dice分数分别达到0.702、0.883和0.739。

ABSTRACT

Glioma is the most common and aggressive brain tumor. Magnetic resonance imaging (MRI) plays a vital role to evaluate tumors for the arrangement of tumor surgery and the treatment of subsequent procedures. However, the manual segmentation of the MRI image is strenuous, which limits its clinical application. With the development of deep learning, a large number of automatic segmentation methods have been developed, but most of them stay in 2D images, which leads to subpar performance. Moreover, the serious voxel imbalance between the brain tumor and the background as well as the different sizes and locations of the brain tumor makes the segmentation of 3D images a challenging problem. Aiming at segmenting 3D MRI, we propose a model for brain tumor segmentation with multiple encoders. The structure contains four encoders and one decoder. The four encoders correspond to the four modalities of the MRI image, perform one-to-one feature extraction, and then merge the feature maps of the four modalities into the decoder. This method reduces the difficulty of feature extraction and greatly improves model performance. We also introduced a new loss function named "Categorical Dice", and set different weights for different segmented regions at the same time, which solved the problem of voxel imbalance. We evaluated our approach using the online BraTS 2020 Challenge verification. Our proposed method can achieve promising results in the validation set compared to the state-of-the-art approaches with Dice scores of 0.70249, 0.88267, and 0.73864 for the intact tumor, tumor core, and enhanced tumor, respectively.

研究动机与目标

• 为解决由于高体素不平衡及肿瘤大小/位置可变性带来的3D脑肿瘤MRI分割挑战。
• 通过利用多模态MRI中的3D空间上下文信息，提升基于2D深度学习方法的性能。
• 通过一种新颖的加权损失函数，减轻分类不平衡对肿瘤分割的影响。
• 开发一种多编码器架构，使每种MRI模态独立处理后进行特征融合。

提出的方法

• 该模型采用四个独立的编码器，每个处理一种MRI模态（T1、T1c、T2、FLAIR），以实现模态特定的特征学习。
• 四个编码器的特征被拼接后输入共享解码器，用于分割预测。
• 提出一种新型损失函数——分类Dice，为不同肿瘤区域（整体肿瘤、肿瘤核心、增强肿瘤）分配不同权重，以应对类别不平衡问题。
• 使用BraTS 2020验证数据集，结合标准数据增强技术，进行端到端训练。
• 该架构旨在保留3D体积中的空间上下文信息，从而提升对复杂肿瘤形态的泛化能力。

实验结果

研究问题

• RQ1 与单编码器模型相比，多编码器3D U-Net框架是否能提升脑肿瘤分割性能？
• RQ2 针对多对比MRI数据的肿瘤分割，模态特定的特征提取策略在多大程度上有效？
• RQ3 区域加权的分类Dice损失在多大程度上减轻了体素不平衡对肿瘤分割的影响？
• RQ4 所提出的方法是否在BraTS 2020基准上超越了最先进方法？

主要发现

• ME-Net在整体肿瘤上取得了0.70249的Dice分数，表明在最大肿瘤区域表现出色。
• 该模型在肿瘤核心上达到0.88267的Dice分数，显示出在最具临床意义区域的高精度。
• 对于增强肿瘤，该方法实现了0.73864的Dice分数，表明在检测对比增强区域方面具有鲁棒性。
• 分类Dice损失显著改善了分割效果，通过降低背景体素在训练中的主导作用。
• 多编码器设计优于单编码器基线模型，实现了每种MRI模态更有效的特征学习。
• 该方法在BraTS 2020验证集上位列顶尖模型之中，证实了其最先进性能。