High-Performance Method for Brain Tumor Feature Extraction in MRI Using Complex Network.

IF 1.8 4区计算机科学 Q3 ENGINEERING, BIOMEDICAL Applied Bionics and Biomechanics Pub Date : 2023-09-21 eCollection Date: 2023-01-01 DOI:10.1155/2023/8843488

Thanh Han Trong, Hinh Nguyen Van, Luu Vu Dang

{"title":"High-Performance Method for Brain Tumor Feature Extraction in MRI Using Complex Network.","authors":"Thanh Han Trong, Hinh Nguyen Van, Luu Vu Dang","doi":"10.1155/2023/8843488","DOIUrl":null,"url":null,"abstract":"Objective: To localize and distinguish between benign and malignant tumors on MRI.Method: This work proposes a high-performance method for brain tumor feature extraction using a combination of complex network and U-Net architecture. And then, the common machine-learning algorithms are used to discriminate between benign and malignant tumors. Experiments and Results. The dataset of brain MRI of a total of 230 brain tumor patients in which 77 high-grade glioma patients and 153 low-grade glioma patients were processed. The results of classifying benign and malignant tumors achieved an accuracy of 99.84%.Conclusion: The high accuracy of experiment results demonstrates that the use of the complex network and U-Net architecture can significantly improve the accuracy of brain tumor classification. This method could potentially be useful for clinicians in aiding diagnosis and treatment planning for brain tumor patients.","PeriodicalId":8029,"journal":{"name":"Applied Bionics and Biomechanics","volume":"2023 ","pages":"8843488"},"PeriodicalIF":1.8000,"publicationDate":"2023-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10539089/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Bionics and Biomechanics","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1155/2023/8843488","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: To localize and distinguish between benign and malignant tumors on MRI.

Method: This work proposes a high-performance method for brain tumor feature extraction using a combination of complex network and U-Net architecture. And then, the common machine-learning algorithms are used to discriminate between benign and malignant tumors. Experiments and Results. The dataset of brain MRI of a total of 230 brain tumor patients in which 77 high-grade glioma patients and 153 low-grade glioma patients were processed. The results of classifying benign and malignant tumors achieved an accuracy of 99.84%.

Conclusion: The high accuracy of experiment results demonstrates that the use of the complex network and U-Net architecture can significantly improve the accuracy of brain tumor classification. This method could potentially be useful for clinicians in aiding diagnosis and treatment planning for brain tumor patients.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

使用复杂网络的MRI脑肿瘤特征提取的高性能方法。

目的：在MRI上定位和区分良恶性肿瘤。方法：提出了一种将复杂网络和U-Net结构相结合的高性能脑肿瘤特征提取方法。然后，使用常见的机器学习算法来区分良性和恶性肿瘤。实验和结果。对230名脑肿瘤患者的脑MRI数据集进行了处理，其中77名高级胶质瘤患者和153名低级胶质瘤患者。良性和恶性肿瘤的分类结果的准确率达到了99.84%。结论：实验结果的高准确率表明，使用复杂网络和U-Net架构可以显著提高脑肿瘤分类的准确率。这种方法可能对临床医生帮助脑肿瘤患者的诊断和治疗计划有用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Applied Bionics and Biomechanics ENGINEERING, BIOMEDICAL-ROBOTICS

自引率

4.50%

发文量

338

审稿时长

>12 weeks

期刊介绍： Applied Bionics and Biomechanics publishes papers that seek to understand the mechanics of biological systems, or that use the functions of living organisms as inspiration for the design new devices. Such systems may be used as artificial replacements, or aids, for their original biological purpose, or be used in a different setting altogether.