论文标题
HI-NET：超密集的3D UNET用于脑肿瘤分割
HI-Net: Hyperdense Inception 3D UNet for Brain Tumor Segmentation
论文作者
论文摘要
脑肿瘤分割任务旨在使用多模型MRI图像将组织分为整个肿瘤（WT），肿瘤核（TC）和增强肿瘤（ET）类别。脑肿瘤的定量分析对于临床决策至关重要。尽管手动细分乏味，耗时且主观，但此任务同时对自动分割方法非常具有挑战性。由于具有强大的学习能力，卷积神经网络（CNN）（主要是完全卷积网络）已显示出有希望的脑肿瘤分割。本文通过提出高密度Inception 3D UNET（HI-NET）来进一步促进脑肿瘤分割的性能，该组织通过将3D加权卷积层堆叠在残留构成区块中捕获多尺度信息。我们在分解的卷积层之间使用超密集的连接，借助功能可重复性来提取更多的续文信息。我们使用骰子损失功能来应对类失衡。我们验证了有关多模式脑肿瘤分割挑战（BRATS）2020测试数据集的拟议结构。 Brats 2020测试集的初步结果表明，通过我们提出的方法，ET，WT和TC的骰子（DSC）得分分别为0.79457、0.87494和0.83712。
The brain tumor segmentation task aims to classify tissue into the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) classes using multimodel MRI images. Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time-consuming, and subjective, this task is at the same time very challenging to automatic segmentation methods. Thanks to the powerful learning ability, convolutional neural networks (CNNs), mainly fully convolutional networks, have shown promising brain tumor segmentation. This paper further boosts the performance of brain tumor segmentation by proposing hyperdense inception 3D UNet (HI-Net), which captures multi-scale information by stacking factorization of 3D weighted convolutional layers in the residual inception block. We use hyper dense connections among factorized convolutional layers to extract more contexual information, with the help of features reusability. We use a dice loss function to cope with class imbalances. We validate the proposed architecture on the multi-modal brain tumor segmentation challenges (BRATS) 2020 testing dataset. Preliminary results on the BRATS 2020 testing set show that achieved by our proposed approach, the dice (DSC) scores of ET, WT, and TC are 0.79457, 0.87494, and 0.83712, respectively.
