{"title":"对脑磁共振成像分析中海马体积估算的成熟分割方法和基于深度学习的分割方法进行比较评估。","authors":"Hsi-Chun Wang, Chia-Sho Chen, Chung-Chin Kuo, Teng-Yi Huang, Kuei-Hong Kuo, Tzu-Chao Chuang, Yi-Ru Lin, Hsiao-Wen Chung","doi":"10.1002/nbm.5169","DOIUrl":null,"url":null,"abstract":"<p><p>In this study, our objective was to assess the performance of two deep learning-based hippocampal segmentation methods, SynthSeg and TigerBx, which are readily available to the public. We contrasted their performance with that of two established techniques, FreeSurfer-Aseg and FSL-FIRST, using three-dimensional T1-weighted MRI scans (n = 1447) procured from public databases. Our evaluation focused on the accuracy and reproducibility of these tools in estimating hippocampal volume. The findings suggest that both SynthSeg and TigerBx are on a par with Aseg and FIRST in terms of segmentation accuracy and reproducibility, but offer a significant advantage in processing speed, generating results in less than 1 min compared with several minutes to hours for the latter tools. In terms of Alzheimer's disease classification based on the hippocampal atrophy rate, SynthSeg and TigerBx exhibited superior performance. In conclusion, we evaluated the capabilities of two deep learning-based segmentation techniques. The results underscore their potential value in clinical and research environments, particularly when investigating neurological conditions associated with hippocampal structures.</p>","PeriodicalId":19309,"journal":{"name":"NMR in Biomedicine","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Comparative assessment of established and deep learning-based segmentation methods for hippocampal volume estimation in brain magnetic resonance imaging analysis.\",\"authors\":\"Hsi-Chun Wang, Chia-Sho Chen, Chung-Chin Kuo, Teng-Yi Huang, Kuei-Hong Kuo, Tzu-Chao Chuang, Yi-Ru Lin, Hsiao-Wen Chung\",\"doi\":\"10.1002/nbm.5169\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In this study, our objective was to assess the performance of two deep learning-based hippocampal segmentation methods, SynthSeg and TigerBx, which are readily available to the public. We contrasted their performance with that of two established techniques, FreeSurfer-Aseg and FSL-FIRST, using three-dimensional T1-weighted MRI scans (n = 1447) procured from public databases. Our evaluation focused on the accuracy and reproducibility of these tools in estimating hippocampal volume. The findings suggest that both SynthSeg and TigerBx are on a par with Aseg and FIRST in terms of segmentation accuracy and reproducibility, but offer a significant advantage in processing speed, generating results in less than 1 min compared with several minutes to hours for the latter tools. In terms of Alzheimer's disease classification based on the hippocampal atrophy rate, SynthSeg and TigerBx exhibited superior performance. In conclusion, we evaluated the capabilities of two deep learning-based segmentation techniques. The results underscore their potential value in clinical and research environments, particularly when investigating neurological conditions associated with hippocampal structures.</p>\",\"PeriodicalId\":19309,\"journal\":{\"name\":\"NMR in Biomedicine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"NMR in Biomedicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1002/nbm.5169\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/5/7 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"BIOPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"NMR in Biomedicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/nbm.5169","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/7 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"BIOPHYSICS","Score":null,"Total":0}
Comparative assessment of established and deep learning-based segmentation methods for hippocampal volume estimation in brain magnetic resonance imaging analysis.
In this study, our objective was to assess the performance of two deep learning-based hippocampal segmentation methods, SynthSeg and TigerBx, which are readily available to the public. We contrasted their performance with that of two established techniques, FreeSurfer-Aseg and FSL-FIRST, using three-dimensional T1-weighted MRI scans (n = 1447) procured from public databases. Our evaluation focused on the accuracy and reproducibility of these tools in estimating hippocampal volume. The findings suggest that both SynthSeg and TigerBx are on a par with Aseg and FIRST in terms of segmentation accuracy and reproducibility, but offer a significant advantage in processing speed, generating results in less than 1 min compared with several minutes to hours for the latter tools. In terms of Alzheimer's disease classification based on the hippocampal atrophy rate, SynthSeg and TigerBx exhibited superior performance. In conclusion, we evaluated the capabilities of two deep learning-based segmentation techniques. The results underscore their potential value in clinical and research environments, particularly when investigating neurological conditions associated with hippocampal structures.
期刊介绍:
NMR in Biomedicine is a journal devoted to the publication of original full-length papers, rapid communications and review articles describing the development of magnetic resonance spectroscopy or imaging methods or their use to investigate physiological, biochemical, biophysical or medical problems. Topics for submitted papers should be in one of the following general categories: (a) development of methods and instrumentation for MR of biological systems; (b) studies of normal or diseased organs, tissues or cells; (c) diagnosis or treatment of disease. Reports may cover work on patients or healthy human subjects, in vivo animal experiments, studies of isolated organs or cultured cells, analysis of tissue extracts, NMR theory, experimental techniques, or instrumentation.