论文标题
脑肿瘤分割的模态学习
Modality-Pairing Learning for Brain Tumor Segmentation
论文作者
论文摘要
使用深度学习方法从多模式磁共振图像（MRI）进行自动脑肿瘤分割起着在协助诊断和治疗脑肿瘤的重要作用。但是，以前的方法主要忽略了不同方式之间的潜在关系。在这项工作中，我们提出了一种用于脑肿瘤分割的新型端到端模态学习方法。并行的分支旨在利用不同的模态特征，并利用一系列层连接来捕获模式之间的复杂关系和丰富的信息。我们还使用一致性损失来最大程度地减少两个分支之间的预测差异。此外，还采用了学习率热身策略来解决训练不稳定和早期合身的问题。最后，我们使用多种模型的平均合奏和一些后处理技术来获得最终结果。我们的方法在Brats 2020在线测试数据集上进行了测试，获得了有希望的分割性能，整个肿瘤，肿瘤核心和增强肿瘤的平均骰子得分分别为0.891、0.842、0.816。我们赢得了针对肿瘤细分任务的Brats 2020挑战的第二名。
Automatic brain tumor segmentation from multi-modality Magnetic Resonance Images (MRI) using deep learning methods plays an important role in assisting the diagnosis and treatment of brain tumor. However, previous methods mostly ignore the latent relationship among different modalities. In this work, we propose a novel end-to-end Modality-Pairing learning method for brain tumor segmentation. Paralleled branches are designed to exploit different modality features and a series of layer connections are utilized to capture complex relationships and abundant information among modalities. We also use a consistency loss to minimize the prediction variance between two branches. Besides, learning rate warmup strategy is adopted to solve the problem of the training instability and early over-fitting. Lastly, we use average ensemble of multiple models and some post-processing techniques to get final results. Our method is tested on the BraTS 2020 online testing dataset, obtaining promising segmentation performance, with average dice scores of 0.891, 0.842, 0.816 for the whole tumor, tumor core and enhancing tumor, respectively. We won the second place of the BraTS 2020 Challenge for the tumor segmentation task.
