Cargando…
Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology
Alzheimer’s disease (AD) is a relatively common senile neurodegenerative disease and the main manifestation of senile dementia. In the pathological changes of AD, the asymmetry of the brain also changes. Therefore, finding an early diagnosis method of AD based on asymmetry is the key to the treatmen...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
De Gruyter
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10476481/ https://www.ncbi.nlm.nih.gov/pubmed/37671100 http://dx.doi.org/10.1515/biol-2022-0690 |
_version_ | 1785100942688911360 |
---|---|
author | Zhang, Xiao Tang, Ning Yin, Yanlin Zhou, Jian Jiang, Rui Sheng, Jinping Zhu, Jing |
author_facet | Zhang, Xiao Tang, Ning Yin, Yanlin Zhou, Jian Jiang, Rui Sheng, Jinping Zhu, Jing |
author_sort | Zhang, Xiao |
collection | PubMed |
description | Alzheimer’s disease (AD) is a relatively common senile neurodegenerative disease and the main manifestation of senile dementia. In the pathological changes of AD, the asymmetry of the brain also changes. Therefore, finding an early diagnosis method of AD based on asymmetry is the key to the treatment of Alzheimer’s. Magnetic resonance (MR) imaging can quantitatively reflect the structural and functional changes of various tissues in the brain. It has the advantages of non-invasive, high spatial resolution, and non-radiation, and has been widely used in the early diagnosis of AD. In this work, asymmetric images were extracted from multiple brain MR images, and different morphological and texture features were extracted. By establishing a feature selection classification integration model, image features in the image were deeply fused to obtain higher and more stable recognition results than before. By filtering image samples, the corresponding sample feature matrix was obtained. Support vector machine was used for classification, and its classification accuracy had improved significantly compared with that before selection. In the experimental data of normal control group and AD group, the accuracy, sensitivity, and specificity of the feature selection algorithm were 93.34, 90.69, and 95.87%, respectively. In the normal control group and the mild cognitive impairment group, the accuracy, sensitivity, and specificity of the feature selection algorithm in this work were 85.31, 79.68, and 88.54%, respectively. On the whole, the classification accuracy of the feature selection algorithm in this work was much higher than that of other items. In addition, from the classification ability and distribution of asymmetric features, it can be seen that this asymmetric feature had a more significant consistent diagnostic role in clinical practice. |
format | Online Article Text |
id | pubmed-10476481 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | De Gruyter |
record_format | MEDLINE/PubMed |
spelling | pubmed-104764812023-09-05 Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology Zhang, Xiao Tang, Ning Yin, Yanlin Zhou, Jian Jiang, Rui Sheng, Jinping Zhu, Jing Open Life Sci Research Article Alzheimer’s disease (AD) is a relatively common senile neurodegenerative disease and the main manifestation of senile dementia. In the pathological changes of AD, the asymmetry of the brain also changes. Therefore, finding an early diagnosis method of AD based on asymmetry is the key to the treatment of Alzheimer’s. Magnetic resonance (MR) imaging can quantitatively reflect the structural and functional changes of various tissues in the brain. It has the advantages of non-invasive, high spatial resolution, and non-radiation, and has been widely used in the early diagnosis of AD. In this work, asymmetric images were extracted from multiple brain MR images, and different morphological and texture features were extracted. By establishing a feature selection classification integration model, image features in the image were deeply fused to obtain higher and more stable recognition results than before. By filtering image samples, the corresponding sample feature matrix was obtained. Support vector machine was used for classification, and its classification accuracy had improved significantly compared with that before selection. In the experimental data of normal control group and AD group, the accuracy, sensitivity, and specificity of the feature selection algorithm were 93.34, 90.69, and 95.87%, respectively. In the normal control group and the mild cognitive impairment group, the accuracy, sensitivity, and specificity of the feature selection algorithm in this work were 85.31, 79.68, and 88.54%, respectively. On the whole, the classification accuracy of the feature selection algorithm in this work was much higher than that of other items. In addition, from the classification ability and distribution of asymmetric features, it can be seen that this asymmetric feature had a more significant consistent diagnostic role in clinical practice. De Gruyter 2023-09-02 /pmc/articles/PMC10476481/ /pubmed/37671100 http://dx.doi.org/10.1515/biol-2022-0690 Text en © 2023 the author(s), published by De Gruyter https://creativecommons.org/licenses/by/4.0/This work is licensed under the Creative Commons Attribution 4.0 International License. |
spellingShingle | Research Article Zhang, Xiao Tang, Ning Yin, Yanlin Zhou, Jian Jiang, Rui Sheng, Jinping Zhu, Jing Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology |
title | Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology |
title_full | Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology |
title_fullStr | Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology |
title_full_unstemmed | Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology |
title_short | Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology |
title_sort | analysis of early diagnosis methods for asymmetric dementia in brain mr images based on genetic medical technology |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10476481/ https://www.ncbi.nlm.nih.gov/pubmed/37671100 http://dx.doi.org/10.1515/biol-2022-0690 |
work_keys_str_mv | AT zhangxiao analysisofearlydiagnosismethodsforasymmetricdementiainbrainmrimagesbasedongeneticmedicaltechnology AT tangning analysisofearlydiagnosismethodsforasymmetricdementiainbrainmrimagesbasedongeneticmedicaltechnology AT yinyanlin analysisofearlydiagnosismethodsforasymmetricdementiainbrainmrimagesbasedongeneticmedicaltechnology AT zhoujian analysisofearlydiagnosismethodsforasymmetricdementiainbrainmrimagesbasedongeneticmedicaltechnology AT jiangrui analysisofearlydiagnosismethodsforasymmetricdementiainbrainmrimagesbasedongeneticmedicaltechnology AT shengjinping analysisofearlydiagnosismethodsforasymmetricdementiainbrainmrimagesbasedongeneticmedicaltechnology AT zhujing analysisofearlydiagnosismethodsforasymmetricdementiainbrainmrimagesbasedongeneticmedicaltechnology |