论文标题
神经结构搜索多模式磁共振成像的神经胶质瘤分割
Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging
论文作者
论文摘要
过去的几年目睹了人工智能在各个医学领域的发展。神经胶质瘤的诊断和治疗是最常见的生存率较低的脑肿瘤之一 - 严重依赖于对磁共振成像（MRI）扫描进行的计算机辅助分割过程。尽管编码器形状的深度学习网络已成为医学成像分析中语义细分任务的事实上的标准样式，但仍需要花费大量精力来设计下采样和上采样块的详细体系结构。在这项工作中，我们提出了基于神经结构搜索（NAS）解决多模式体积MRI扫描的脑肿瘤分割任务的解决方案。三组候选操作分别针对三种基本构建块组成，其中每个操作都用要学习的特定概率参数分配。通过交替更新网络中的操作权重和其他参数，搜索机制最终具有两个最佳结构，用于向上和向下块。此外，开发的解决方案还整合了针对大脑MRI处理的归一化和修补策略。 Brats 2019数据集的广泛比较实验表明，所提出的算法不仅可以减轻制造块架构的压力，而且还具有竞争性的可行性和可扩展性。
Past few years have witnessed the artificial intelligence inspired evolution in various medical fields. The diagnosis and treatment of gliomas -- one of the most commonly seen brain tumors with low survival rate -- rely heavily on the computer assisted segmentation process undertaken on the magnetic resonance imaging (MRI) scans. Although the encoder-decoder shaped deep learning networks have been the de facto standard style for semantic segmentation tasks in medical imaging analysis, enormous effort is still required to be spent on designing the detailed architecture of the down-sampling and up-sampling blocks. In this work, we propose a neural architecture search (NAS) based solution to brain tumor segmentation tasks on multimodal volumetric MRI scans. Three sets of candidate operations are composed respectively for three kinds of basic building blocks in which each operation is assigned with a specific probabilistic parameter to be learned. Through alternately updating the weights of operations and the other parameters in the network, the searching mechanism ends up with two optimal structures for the upward and downward blocks. Moreover, the developed solution also integrates normalization and patching strategies tailored for brain MRI processing. Extensive comparative experiments on the BraTS 2019 dataset demonstrate that the proposed algorithm not only could relieve the pressure of fabricating block architectures but also possesses competitive feasibility and scalability.
