This paper proposes a 3D attention-based U-Net architecture for multi-region
segmentation of brain tumors using a single stacked multi-modal volume created
by combining three non-native MRI volumes. The attention mechanism added to the
decoder side of the U-Net helps to improve segmentation accuracy by
de-emphasizing healthy tissues and accentuating malignant tissues, resulting in
better generalization power and reduced computational resources. The method is
trained and evaluated on the BraTS 2021 Task 1 dataset, and demonstrates
improvement of accuracy over other approaches. My findings suggest that the
proposed approach has potential to enhance brain tumor segmentation using
multi-modal MRI data, contributing to better understanding and diagnosis of
brain diseases. This work highlights the importance of combining multiple
imaging modalities and incorporating attention mechanisms for improved accuracy
in brain tumor segmentation.

本文提出了一种基于 3D 注意力的 U-Net 架构，用于使用由三个非本地 MRI 卷积组合而成的单一堆叠的多模态体积进行大脑肿瘤的多区域分割。该方法通过在 U-Net 的解码器端添加注意机制来提高分割精度，从而减少了对健康组织的侧重和突出了恶性组织，提高了泛化能力并减少了计算资源。该方法在 BraTS 2021 任务 1 数据集上进行训练和评估，证明其在精度上优于其他方法。实验结果表明，该方法潜在地提高了使用多模态 MRI 数据进行大脑肿瘤分割的能力，有望为更好地理解和诊断脑部疾病做出贡献。这项工作强调了在大脑肿瘤分割中结合多种成像模式和引入注意机制以提高精度的重要性。

使用基于 3D 注意力机制的 U-Net 进行多类 MRI 脑肿瘤分割

Multiclass MRI Brain Tumor Segmentation using 3D Attention-based U-Net

We present a new algorithm for multi-region segmentation of 2D images with
objects that may partially occlude each other. Our algorithm is based on the
observation hat human performance on this task is based both on prior knowledge
about plausible shapes and taking into account the presence of occluding
objects whose shape is already known - once an occluded region is identified,
the shape prior can be used to guess the shape of the missing part. We capture
the former aspect using a deep learning model of shape; for the latter, we
simultaneously minimize the energy of all regions and consider only unoccluded
pixels for data agreement.
Existing algorithms incorporating object shape priors consider every object
separately in turn and can't distinguish genuine deviation from the expected
shape from parts missing due to occlusion. We show that our method
significantly improves on the performance of a representative algorithm, as
evaluated on both preprocessed natural and synthetic images. Furthermore, on
the synthetic images, we recover the ground truth segmentation with good
accuracy.

该研究提出了一种新的算法，用于 2D 图像的多区域分割，其中的对象可能会部分遮挡，该算法基于观察到人类在此任务上的表现受先前关于可信形状的知识以及考虑到已知遮挡对象的形状的影响 - 一旦识别出遮挡区域，形状先验可以用于猜测缺失部分的形状。

在阴影中，形状先验发挥作用：利用遮挡来改善多区域分割

In the Shadows, Shape Priors Shine: Using Occlusion to Improve  Multi-Region Segmentation

Multi-region segmentation algorithms often have the onus of incorporating
complex anatomical knowledge representing spatial or geometric relationships
between objects, and general-purpose methods of addressing this knowledge in an
optimization-based manner have thus been lacking. This paper presents
Generalized Hierarchical Max-Flow (GHMF) segmentation, which captures simple
anatomical part-whole relationships in the form of an unconstrained hierarchy.
Regularization can then be applied to both parts and wholes independently,
allowing for spatial grouping and clustering of labels in a globally optimal
convex optimization framework. For the purposes of ready integration into a
variety of segmentation tasks, the hierarchies can be presented in run-time,
allowing for the segmentation problem to be readily specified and alternatives
explored without undue programming effort or recompilation.

该论文提出了一种广义分层最大流 (GHMF) 分割算法，该算法可以在全局最优凸优化框架中将解剖学的部分 - 整体关系表现为非约束性分层，从而实现标签的空间分组和聚类，并适应于多种分割任务中。