Artificial intelligence-driven 3D MRI of lumbosacral nerve root anomalies: accuracy, incidence, and clinical utility.

IF 2.4 3区医学 Q2 CLINICAL NEUROLOGY

Neuroradiology Pub Date : 2025-03-01 DOI:10.1007/s00234-025-03574-5

Daisuke Ukeba, Ken Nagahama, Katsuhisa Yamada, Yuichiro Abe, Yoshinori Hyugaji, Tsutomu Endo, Takashi Ohnishi, Hiroyuki Tachi, Yuichi Hasegawa, Hideki Sudo, Norimasa Iwasaki

{"title":"Artificial intelligence-driven 3D MRI of lumbosacral nerve root anomalies: accuracy, incidence, and clinical utility.","authors":"Daisuke Ukeba, Ken Nagahama, Katsuhisa Yamada, Yuichiro Abe, Yoshinori Hyugaji, Tsutomu Endo, Takashi Ohnishi, Hiroyuki Tachi, Yuichi Hasegawa, Hideki Sudo, Norimasa Iwasaki","doi":"10.1007/s00234-025-03574-5","DOIUrl":null,"url":null,"abstract":"Purpose: Lumbosacral nerve root anomalies are relatively rare but can be a risk factor for intraoperative nerve injury. However, it is often difficult to evaluate them with preoperative imaging. We developed a software that automatically generates three-dimensional (3D) nerve root images from magnetic resonance (MR) imaging using artificial intelligence (AI). This study aims to evaluate the accuracy and utility of this modality in clinical practice by conducting an epidemiological study of nerve root anomalies.Methods: The incidence and morphology of nerve root anomalies were evaluated in the 3D images of 1,500 patients. The accuracy of the images was evaluated by comparing the images generated automatically using this AI software with those created manually by conventional methods.Results: Of 1,500 cases, 53 (3.5%) had nerve root anomalies with total of 58 nerve root anomalies. With respect to the spinal level, 35 nerve root anomalies were found in the L5-S1 level, the most common (60.3%). As for morphology, 47 nerve roots (81.0%) were of the Neidre-MacNab classification Type 1. The images matched in 1,493 out of 1,500 cases (99.5%) between the two methods, and the remaining 7 cases all had nerve root abnormalities, which were detected as abnormal by the AI software.Conclusion: The MR nerve root 3D imaging provided a 3D visualization and understanding of nerve root morphology, including nerve root anomalies. The AI software enables easy and precise 3D nerve root imaging, which greatly aids in the preoperative evaluation for spinal surgery.","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuroradiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00234-025-03574-5","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: Lumbosacral nerve root anomalies are relatively rare but can be a risk factor for intraoperative nerve injury. However, it is often difficult to evaluate them with preoperative imaging. We developed a software that automatically generates three-dimensional (3D) nerve root images from magnetic resonance (MR) imaging using artificial intelligence (AI). This study aims to evaluate the accuracy and utility of this modality in clinical practice by conducting an epidemiological study of nerve root anomalies.

Methods: The incidence and morphology of nerve root anomalies were evaluated in the 3D images of 1,500 patients. The accuracy of the images was evaluated by comparing the images generated automatically using this AI software with those created manually by conventional methods.

Results: Of 1,500 cases, 53 (3.5%) had nerve root anomalies with total of 58 nerve root anomalies. With respect to the spinal level, 35 nerve root anomalies were found in the L5-S1 level, the most common (60.3%). As for morphology, 47 nerve roots (81.0%) were of the Neidre-MacNab classification Type 1. The images matched in 1,493 out of 1,500 cases (99.5%) between the two methods, and the remaining 7 cases all had nerve root abnormalities, which were detected as abnormal by the AI software.

Conclusion: The MR nerve root 3D imaging provided a 3D visualization and understanding of nerve root morphology, including nerve root anomalies. The AI software enables easy and precise 3D nerve root imaging, which greatly aids in the preoperative evaluation for spinal surgery.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Neuroradiology 医学-核医学

CiteScore

5.30

自引率

3.60%

发文量

214

审稿时长

4-8 weeks

期刊介绍： Neuroradiology aims to provide state-of-the-art medical and scientific information in the fields of Neuroradiology, Neurosciences, Neurology, Psychiatry, Neurosurgery, and related medical specialities. Neuroradiology as the official Journal of the European Society of Neuroradiology receives submissions from all parts of the world and publishes peer-reviewed original research, comprehensive reviews, educational papers, opinion papers, and short reports on exceptional clinical observations and new technical developments in the field of Neuroimaging and Neurointervention. The journal has subsections for Diagnostic and Interventional Neuroradiology, Advanced Neuroimaging, Paediatric Neuroradiology, Head-Neck-ENT Radiology, Spine Neuroradiology, and for submissions from Japan. Neuroradiology aims to provide new knowledge about and insights into the function and pathology of the human nervous system that may help to better diagnose and treat nervous system diseases. Neuroradiology is a member of the Committee on Publication Ethics (COPE) and follows the COPE core practices. Neuroradiology prefers articles that are free of bias, self-critical regarding limitations, transparent and clear in describing study participants, methods, and statistics, and short in presenting results. Before peer-review all submissions are automatically checked by iThenticate to assess for potential overlap in prior publication.