1
|
Wan C, Fang L, Cao S, Luo J, Jiang Y, Wei Y, Lv C, Si W. Research on classification algorithm of cerebral small vessel disease based on convolutional neural network. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022. [DOI: 10.3233/jifs-213212] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/07/2022]
Abstract
The investigation on brain magnetic resonance imaging (MRI) of cerebral small vessel disease (CSVD) classification algorithm based on deep learning is particularly important in medical image analyses and has not been reported. This paper proposes an MRI classification algorithm based on convolutional neural network (MRINet), for accurately classifying CSVD and improving the classification performance. The working method includes five main stages: fabricating dataset, designing network model, configuring the training options, training model and testing performance. The actual training and testing datasets of MRI of CSVD are fabricated, the MRINet model is designed for extracting more detailedly features, a smooth categorical-cross-entropy loss function and Adam optimization algorithm are adopted, and the appropriate training parameters are set. The network model is trained and tested in the fabricated datasets, and the classification performance of CSVD is fully investigated. Experimental results show that the loss and accuracy curves demonstrate the better classification performance in the training process. The confusion matrices confirm that the designed network model demonstrates the better classification results, especially for luminal infarction. The average classification accuracy of MRINet is up to 80.95% when classifying MRI of CSVD, which demonstrates the superior classification performance over others. This work provides a sound experimental foundation for further improving the classification accuracy and enhancing the actual application in medical image analyses.
Collapse
Affiliation(s)
- Chenxia Wan
- College of Information and Communication Engineering, Harbin Engineering University, Harbin, China
| | - Liqun Fang
- Forth Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Shaodong Cao
- Forth Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Jiaji Luo
- College of Information and Communication Engineering, Harbin Engineering University, Harbin, China
| | - Yijing Jiang
- Forth Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Yuanxiao Wei
- Forth Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Cancan Lv
- Forth Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Weijian Si
- College of Information and Communication Engineering, Harbin Engineering University, Harbin, China
| |
Collapse
|
2
|
Liu X, Ye Y, Gao X, Wang Z. 3D Printing in Cranioplasty for Giant Cranial Deformity with Multi-Dimensional Nuclear Magnetic Simulation. JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS 2021. [DOI: 10.1166/jmihi.2021.3741] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
This article is based on 3D printing technology, through multi-dimensional nuclear magnetic stimulation to the in-depth study of the application of plastic surgery in patients with giant cranial deformity cranial reduction, first of all, patients with CT scan of the brain, based on
CT data for 3D reconstruction, 3D geometric modeling, using 3D printing Prepare multiple skull 1:1 scale, solid models, perform surgical planning and drills, determine the surgical plan (related parameters such as surgical time, cranial cavity volume, frontal plane ratio, anterior-posterior
diameter, left-right diameter, head-to-height ratio, etc.), it can increase the patient’s speed and stride, and complete a variety of material tests. The 3D printing group had lower pain VAS scores at 1 h and 24 h after surgery than the traditional data group. The same data observed
from different dimensions may yield different results, but also enable people to understand the nature of things more comprehensively and clearly. It was statistically significant (P < 0.05). The postoperative swelling of the 3D printing group was less than that of the customary
group, and the difference was statistically significant (P < 0.05). Through 12 months of follow up observation, the power of 3D printing is higher than that of the habitual group, and the difference is statistically significant (P < 0.05). This technology has an important
guiding significance in future related treatment technology.
Collapse
Affiliation(s)
- Xiyao Liu
- Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen Fujian, 361001, China
| | - Yongzao Ye
- Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen Fujian, 361001, China
| | - Xin Gao
- Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen Fujian, 361001, China
| | - Zhanxiang Wang
- Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen Fujian, 361001, China
| |
Collapse
|