Comparative Assessment of Manual Segmentation of Cerebral Infarction Lesions in Experimental Animals Based on Magnetic Resonance Imaging Using Artificial Intelligence.
I L Gubskiy, D D Namestnikova, E A Cherkashova, I S Gumin, V V Kurilo, V P Chekhonin, K N Yarygin
{"title":"Comparative Assessment of Manual Segmentation of Cerebral Infarction Lesions in Experimental Animals Based on Magnetic Resonance Imaging Using Artificial Intelligence.","authors":"I L Gubskiy, D D Namestnikova, E A Cherkashova, I S Gumin, V V Kurilo, V P Chekhonin, K N Yarygin","doi":"10.1007/s10517-025-06366-2","DOIUrl":null,"url":null,"abstract":"<p><p>The aim of this study was to evaluate the quality of manual segmentation of cerebral infarction lesions in experimental animals with modeled brain infarct based on magnetic resonance imaging compared to an automated artificial intelligence approach. For automated infarct segmentation, an artificial intelligence system with the Swin-UNETR architecture was used, while manual segmentation was performed by four independent researchers. It was shown that manual segmentation exhibits significant variability, especially when small brain infarct lesions are analyzed. The obtained data emphasize the need for standardizing methods and applying automated systems to improve the accuracy and reproducibility of the results.</p>","PeriodicalId":9331,"journal":{"name":"Bulletin of Experimental Biology and Medicine","volume":" ","pages":"514-519"},"PeriodicalIF":0.6000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bulletin of Experimental Biology and Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10517-025-06366-2","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/3/28 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0
Abstract
The aim of this study was to evaluate the quality of manual segmentation of cerebral infarction lesions in experimental animals with modeled brain infarct based on magnetic resonance imaging compared to an automated artificial intelligence approach. For automated infarct segmentation, an artificial intelligence system with the Swin-UNETR architecture was used, while manual segmentation was performed by four independent researchers. It was shown that manual segmentation exhibits significant variability, especially when small brain infarct lesions are analyzed. The obtained data emphasize the need for standardizing methods and applying automated systems to improve the accuracy and reproducibility of the results.
期刊介绍：
Bulletin of Experimental Biology and Medicine presents original peer reviewed research papers and brief reports on priority new research results in physiology, biochemistry, biophysics, pharmacology, immunology, microbiology, genetics, oncology, etc. Novel trends in science are covered in new sections of the journal - Biogerontology and Human Ecology - that first appeared in 2005.
World scientific interest in stem cells prompted inclusion into Bulletin of Experimental Biology and Medicine a quarterly scientific journal Cell Technologies in Biology and Medicine (a new Russian Academy of Medical Sciences publication since 2005). It publishes only original papers from the leading research institutions on molecular biology of stem and progenitor cells, stem cell as the basis of gene therapy, molecular language of cell-to-cell communication, cytokines, chemokines, growth and other factors, pilot projects on clinical use of stem and progenitor cells.
The Russian Volume Year is published in English from April.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
