Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint

被引:45
作者
Gu, Xiaoqing [1 ]
Shen, Zongxuan [1 ]
Xue, Jing [2 ]
Fan, Yiqing [3 ]
Ni, Tongguang [1 ]
机构
[1] Changzhou Univ, Sch Comp Sci & Artificial Intelligence, Changzhou, Jiangsu, Peoples R China
[2] Nanjing Med Univ, Affiliated Wuxi Peoples Hosp, Dept Nephrol, Wuxi, Jiangsu, Peoples R China
[3] Univ Southern Calif, Viterbi Sch Engn, Los Angeles, CA 90007 USA
基金
中国国家自然科学基金;
关键词
brain tumor image classification; magnetic resonance imaging; dictionary learning; local constraint; convolutional neural network; DISCRIMINATIVE DICTIONARY; MACHINE;
D O I
10.3389/fnins.2021.679847
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Brain tumor image classification is an important part of medical image processing. It assists doctors to make accurate diagnosis and treatment plans. Magnetic resonance (MR) imaging is one of the main imaging tools to study brain tissue. In this article, we propose a brain tumor MR image classification method using convolutional dictionary learning with local constraint (CDLLC). Our method integrates the multi-layer dictionary learning into a convolutional neural network (CNN) structure to explore the discriminative information. Encoding a vector on a dictionary can be considered as multiple projections into new spaces, and the obtained coding vector is sparse. Meanwhile, in order to preserve the geometric structure of data and utilize the supervised information, we construct the local constraint of atoms through a supervised k-nearest neighbor graph, so that the discrimination of the obtained dictionary is strong. To solve the proposed problem, an efficient iterative optimization scheme is designed. In the experiment, two clinically relevant multi-class classification tasks on the Cheng and REMBRANDT datasets are designed. The evaluation results demonstrate that our method is effective for brain tumor MR image classification, and it could outperform other comparisons.
引用
收藏
页数:12
相关论文
共 44 条
[1]   Accurate classification of brain gliomas by discriminate dictionary learning based on projective dictionary pair learning of proton magnetic resonance spectra [J].
Adebileje, Sikiru Afolabi ;
Ghasemi, Keyvan ;
Aiyelabegan, Hammed Tanimowo ;
Rad, Hamidreza Saligheh .
MAGNETIC RESONANCE IN CHEMISTRY, 2017, 55 (04) :318-322
[2]  
Afshar P, 2018, IEEE IMAGE PROC, P3129, DOI 10.1109/ICIP.2018.8451379
[3]   Brain tumor classification and segmentation using sparse coding and dictionary learning [J].
Al-Shaikhli, Saif Dawood Salman ;
Yang, Michael Ying ;
Rosenhahn, Bodo .
BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK, 2016, 61 (04) :413-429
[4]  
Al-Shaikhli SDS, 2014, LECT NOTES COMPUT SC, V8887, P489, DOI 10.1007/978-3-319-14249-4_46
[5]   Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms [J].
Anaraki, Amin Kabir ;
Ayati, Moosa ;
Kazemi, Foad .
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2019, 39 (01) :63-74
[6]   REVIEW: MR elastography of brain tumors [J].
Bunevicius, Adomas ;
Schregel, Katharina ;
Sinkus, Ralph ;
Golby, Alexandra ;
Patz, Samuel .
NEUROIMAGE-CLINICAL, 2020, 25
[7]  
Cai X, 2013, 19TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD'13), P1124
[8]   A survey on brain tumor detection techniques for MR images [J].
Chahal, Prabhjot Kaur ;
Pandey, Shreelekha ;
Goel, Shivani .
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (29-30) :21771-21814
[9]   An Automated Framework for Multi-label Brain Tumor Segmentation based onKernel Sparse Representation [J].
Chen, Xuan ;
Nguyen, Binh P. ;
Chui, Chee-Kong ;
Ong, Sim-Heng .
ACTA POLYTECHNICA HUNGARICA, 2017, 14 (01) :25-43
[10]   Retrieval of Brain Tumors by Adaptive Spatial Pooling and Fisher Vector Representation [J].
Cheng, Jun ;
Yang, Wei ;
Huang, Meiyan ;
Huang, Wei ;
Jiang, Jun ;
Zhou, Yujia ;
Yang, Ru ;
Zhao, Jie ;
Feng, Yanqiu ;
Feng, Qianjin ;
Chen, Wufan .
PLOS ONE, 2016, 11 (06)