Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint
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 classificat...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-05-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.679847/full |
id |
doaj-132edb2bcfe44670af77d090af6660c9 |
---|---|
record_format |
Article |
spelling |
doaj-132edb2bcfe44670af77d090af6660c92021-05-28T08:34:09ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-05-011510.3389/fnins.2021.679847679847Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local ConstraintXiaoqing Gu0Zongxuan Shen1Jing Xue2Yiqing Fan3Tongguang Ni4School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, ChinaSchool of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, ChinaDepartment of Nephrology, Affiliated Wuxi People’s Hospital of Nanjing Medical University, Wuxi, ChinaViterbi School of Engineering, University of Southern California, Los Angeles, CA, United StatesSchool of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, ChinaBrain 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.https://www.frontiersin.org/articles/10.3389/fnins.2021.679847/fullbrain tumor image classificationmagnetic resonance imagingdictionary learninglocal constraintconvolutional neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaoqing Gu Zongxuan Shen Jing Xue Yiqing Fan Tongguang Ni |
spellingShingle |
Xiaoqing Gu Zongxuan Shen Jing Xue Yiqing Fan Tongguang Ni Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint Frontiers in Neuroscience brain tumor image classification magnetic resonance imaging dictionary learning local constraint convolutional neural network |
author_facet |
Xiaoqing Gu Zongxuan Shen Jing Xue Yiqing Fan Tongguang Ni |
author_sort |
Xiaoqing Gu |
title |
Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint |
title_short |
Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint |
title_full |
Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint |
title_fullStr |
Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint |
title_full_unstemmed |
Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint |
title_sort |
brain tumor mr image classification using convolutional dictionary learning with local constraint |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neuroscience |
issn |
1662-453X |
publishDate |
2021-05-01 |
description |
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. |
topic |
brain tumor image classification magnetic resonance imaging dictionary learning local constraint convolutional neural network |
url |
https://www.frontiersin.org/articles/10.3389/fnins.2021.679847/full |
work_keys_str_mv |
AT xiaoqinggu braintumormrimageclassificationusingconvolutionaldictionarylearningwithlocalconstraint AT zongxuanshen braintumormrimageclassificationusingconvolutionaldictionarylearningwithlocalconstraint AT jingxue braintumormrimageclassificationusingconvolutionaldictionarylearningwithlocalconstraint AT yiqingfan braintumormrimageclassificationusingconvolutionaldictionarylearningwithlocalconstraint AT tongguangni braintumormrimageclassificationusingconvolutionaldictionarylearningwithlocalconstraint |
_version_ |
1721424295405551616 |