计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220200108-6.doi: 10.11896/jsjkx.220200108
戴天虹, 宋洁绮
DAI Tianhong, SONG Jieqi
摘要: 脑胶质瘤是起源于脑神经胶质细胞的原发性肿瘤,发病率约占全部颅内肿瘤的45%,其核磁共振图像(MRI)的精准分割有着非常重要的临床意义。文中提出了一种基于多编码器的脑肿瘤自动分割方法,模型采用U型网络结构,扩充单收缩路径为多路径以深度挖掘不同模态语义信息;提出结合空洞卷积的Inception模块作为网络基础卷积层以获取图像多尺度特征;在网络瓶颈层和解码器中引入轻量型通道注意力Efficient Channel Attention(ECA)模块,使得模型更多地关注与分割相关的信息,忽略通道维度的信息冗余,从而进一步提高网络分割的精确率。在Brain Tumor Segmentation Challenge 2018(BraTS 2018)数据集上进行验证,提出的网络在整体肿瘤、肿瘤核心、增强肿瘤3个区域的平均Dice系数分别为0.880,0.784,0.757,结果表明所提算法实现了准确有效的多模态MRI脑肿瘤分割。
中图分类号:
[1]KAMNITSAS K,LEDIG C,NEWCOMBE V F,et al.Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation[J].Medical Image Analysis,2017,36:61-78. [2]MYRONENKO A.3D MRI brain tumor segmentation using autoencoder regularization[C]//International MICCAI Brainlesion Workshop.Cham:Springer,2018:311-320. [3]ISENSEE F,JAEGER P F,KOHL S A,et al.nnU-Net:a self-configuring method for deep learning-based biomedical image segmentation[J].Nature methods,2021,18(2):203-211. [4]HATAMIZADEH A,TANG Y,NATH V,et al.Unetr:Transformers for 3d medical image segmentation[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision(WACV).2022:574-584. [5]NIE D,WANG L,GAO Y Z,et al.Fully convolutional networks for multi-modality isointense infant brain image segmentation[C]//2016 IEEE 13th International Symposium on Biomedical Imaging(ISBI).IEEE,2016:1342-1345. [6]DOLZ J,AYED I B,DESROSIERS C.Dense multi-path U-Net for ischemic stroke lesion segmentation in multiple image moda-lities[C]//International MICCAI Brainlesion Workshop.Cham:Springer,2018:271-282. [7]WANG G,LI W,OURSELIN S,et al.Automatic brain tumor segmentation based on cascaded convolutional neural networks with uncertainty estimation[J].Frontiers in Computational Neuroscience,2019,13:56. [8]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2018:7132-7141. [9]WANG Q L,WU B G,ZHU P F,et al.ECA-Net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2020:11531-11539. [10]MENZE B H,JAKAB A,BAUER S,et al.The multimodal brain tumor image segmentation benchmark(BRATS)[J].IEEE Transactions on Medical Imaging,2014,34(10):1993-2024. [11]BAKAS S,AKBARI H,SOTIRAS A,et al.Advancing the can-cer genome atlas glioma MRI collections with expert segmentation labels and radiomic features[J].Scientific Data,2017,4(1):1-3. [12]BAKAS S,REYES M,JAKAB A,et al.Identifying the best machine learning algorithms for brain tumor segmentation,progression assessment,and overall survival prediction in the BRATS challenge[J].arXiv:1811.02629,2019. [13]ÇIÇEK Ö,ABDULKADIR A,LIENKAMP S S,et al.3D U-Net:learning dense volumetric segmentation from sparse annotation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Cham:Springer,2016:424-432. [14]MA J,YANG X P.Automatic brain tumor segmentation by exploring the multi-modality complementary information and cascaded 3D lightweight CNNs[C]//International MICCAI Brainlesion Workshop.Cham:Springer,2018:25-36. [15]ALBIOL A,ALBIOL A,ALBIOL F.Extending 2D deep lear-ning architectures to 3D image segmentation problems[C]//International MICCAI Brainlesion Workshop.Cham:Springer,2018:73-82. [16]HU K,GAN Q H,ZHANG Y,et al.Brain tumor segmentation using multi-cascaded convolutional neural networks and conditional random field[J].IEEE Access,2019,7:92615-92629. [17]ZHOU Z,HE Z,JIA Y.AFPNet:A 3D fully convolutional neural network with atrous-convolution feature pyramid for brain tumor segmentation via MRI images[J].Neurocomputing,2020,402:235-244. [18]AKBAR A S,FATICHAH C,SUCIATI N.SDA-UNET2.5D:Shallow Dilated with Attention Unet2.5D for Brain Tumor Segmentation[J].International Journal of Intelligent Engineering and Systems,2022,15(2):135-149. |
|