Loading…

A combined radiomics and anatomical features model enhances MRI-based recognition of symptomatic nerves in primary trigeminal neuralgia

The diagnosis of primary trigeminal neuralgia (PTN) in radiology lacks the gold standard and largely depends on the identification of neurovascular compression (NVC) using magnetic resonance imaging (MRI) water imaging sequences. However, relying on this imaging sign alone often fails to accurately...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in neuroscience 2024-10, Vol.18, p.1500584
Main Authors: Li, Hongjian, Li, Bing, Zhang, Chuan, Xiao, Ruhui, He, Libing, Li, Shaojie, Yang, Yu-Xin, He, Shipei, Sun, Baijintao, Qiu, Zhiqiang, Yang, Maojiang, Wei, Yan, Xu, Xiaoxue, Yang, Hanfeng
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c350t-efc688a81ca41a6d9bf4be00f0d32629612a2a1919c288c5f6b3005c339cba103
container_end_page
container_issue
container_start_page 1500584
container_title Frontiers in neuroscience
container_volume 18
creator Li, Hongjian
Li, Bing
Zhang, Chuan
Xiao, Ruhui
He, Libing
Li, Shaojie
Yang, Yu-Xin
He, Shipei
Sun, Baijintao
Qiu, Zhiqiang
Yang, Maojiang
Wei, Yan
Xu, Xiaoxue
Yang, Hanfeng
description The diagnosis of primary trigeminal neuralgia (PTN) in radiology lacks the gold standard and largely depends on the identification of neurovascular compression (NVC) using magnetic resonance imaging (MRI) water imaging sequences. However, relying on this imaging sign alone often fails to accurately distinguish the symptomatic side of the nerve from asymptomatic nerves, and may even lead to incorrect diagnoses. Therefore, it is essential to develop a more effective diagnostic tool to aid radiologists in the diagnosis of TN. This study aims to establish a radiomics-based machine learning model integrating multi-region of interest (multiple-ROI) MRI and anatomical data, to improve the accuracy in differentiating symptomatic from asymptomatic nerves in PTN. A retrospective analysis of MRI data and clinical anatomical data was conducted on 140 patients with clinically confirmed PTN. Symptomatic nerves of TN patients were defined as the positive group, while asymptomatic nerves served as the negative group. The ipsilateral Meckel's cavity (MC) was included in both groups. Through dimensionality reduction analysis, four radiomics features were selected from the MC and 24 radiomics features were selected from the trigeminal cisternal segment. Thirteen anatomical features relevant to TN were identified from the literature, and analyzed using univariate logistic regression and multivariate logistic regression. Four features were confirmed as independent risk factors for TN. Logistic regression (LR) models were constructed for radiomics model and clinical anatomy, and a combined model was developed by integrating the radiomics score (Rad-Score) with the clinical anatomy model. The models' performance was evaluated using receiver operating characteristic curve (ROC) curves, calibration curves, and decision curve analysis (DCA). The four independent clinical anatomical factors identified were: degree of neurovascular compression, site of neurovascular compression site, thickness of the trigeminal nerve root, and trigeminal pons angle (TPA). The final combined model, incorporating radiomics and clinical anatomy, achieved an area under the curve (AUC) of 0.91/0.90 (95% CI: 0.87-0.95/0.81-0.96) and an accuracy of approximately 82% in recognizing symptomatic and normal nerves. The combined radiomics and anatomical model provides superior recognition efficiency for the symptomatic nerves in PTN, offering valuable support for radiologists in diagnosing TN.
doi_str_mv 10.3389/fnins.2024.1500584
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_843c92dba7784fd59fc27c1c25b2ea16</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_843c92dba7784fd59fc27c1c25b2ea16</doaj_id><sourcerecordid>3128324235</sourcerecordid><originalsourceid>FETCH-LOGICAL-c350t-efc688a81ca41a6d9bf4be00f0d32629612a2a1919c288c5f6b3005c339cba103</originalsourceid><addsrcrecordid>eNpVks9u1DAQxiMEoqXwAhyQj1yy-G_WOaGqKrBSERICiZs1scepq8Re7GylPgGvjbe7rOjBssee7zdj-2uat4yuhND9Bx9DLCtOuVwxRanS8llzzrqOt1KJX89Pa6nPmlel3FHacS35y-ZM9IoJKtV58-eS2DQPIaIjGVxIc7CFQHR1wLKPYCIeYdllLGRODieC8RaireHX75t2gLKXok1jDEtIkSRPysO8rWJYgiUR833NDZFsc5ghP5AlhxHnECs54i7DNAZ43bzwMBV8c5wvmp-frn9cfWlvvn3eXF3etFYourTobac1aGZBMuhcP3g5IKWeOsE73neMAwfWs95yra3y3SDqy1ghejsAo-Ki2Ry4LsGdOXZkEgTzuJHyaCDXtic0WgrbczfAeq2ld6r3lq8ts1wNHIF1lfXxwNruhhmdxbjUyzyBPj2J4daM6d4wpiQTUlbC-yMhp987LIuZQ7E4TRAx7YoRjGvBJReqpvJDqs2plIz-VIdRs7eDebSD2dvBHO1QRe_-7_Ak-ff_4i99-bW-</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3128324235</pqid></control><display><type>article</type><title>A combined radiomics and anatomical features model enhances MRI-based recognition of symptomatic nerves in primary trigeminal neuralgia</title><source>Open Access: PubMed Central</source><source>Publicly Available Content Database</source><creator>Li, Hongjian ; Li, Bing ; Zhang, Chuan ; Xiao, Ruhui ; He, Libing ; Li, Shaojie ; Yang, Yu-Xin ; He, Shipei ; Sun, Baijintao ; Qiu, Zhiqiang ; Yang, Maojiang ; Wei, Yan ; Xu, Xiaoxue ; Yang, Hanfeng</creator><creatorcontrib>Li, Hongjian ; Li, Bing ; Zhang, Chuan ; Xiao, Ruhui ; He, Libing ; Li, Shaojie ; Yang, Yu-Xin ; He, Shipei ; Sun, Baijintao ; Qiu, Zhiqiang ; Yang, Maojiang ; Wei, Yan ; Xu, Xiaoxue ; Yang, Hanfeng</creatorcontrib><description>The diagnosis of primary trigeminal neuralgia (PTN) in radiology lacks the gold standard and largely depends on the identification of neurovascular compression (NVC) using magnetic resonance imaging (MRI) water imaging sequences. However, relying on this imaging sign alone often fails to accurately distinguish the symptomatic side of the nerve from asymptomatic nerves, and may even lead to incorrect diagnoses. Therefore, it is essential to develop a more effective diagnostic tool to aid radiologists in the diagnosis of TN. This study aims to establish a radiomics-based machine learning model integrating multi-region of interest (multiple-ROI) MRI and anatomical data, to improve the accuracy in differentiating symptomatic from asymptomatic nerves in PTN. A retrospective analysis of MRI data and clinical anatomical data was conducted on 140 patients with clinically confirmed PTN. Symptomatic nerves of TN patients were defined as the positive group, while asymptomatic nerves served as the negative group. The ipsilateral Meckel's cavity (MC) was included in both groups. Through dimensionality reduction analysis, four radiomics features were selected from the MC and 24 radiomics features were selected from the trigeminal cisternal segment. Thirteen anatomical features relevant to TN were identified from the literature, and analyzed using univariate logistic regression and multivariate logistic regression. Four features were confirmed as independent risk factors for TN. Logistic regression (LR) models were constructed for radiomics model and clinical anatomy, and a combined model was developed by integrating the radiomics score (Rad-Score) with the clinical anatomy model. The models' performance was evaluated using receiver operating characteristic curve (ROC) curves, calibration curves, and decision curve analysis (DCA). The four independent clinical anatomical factors identified were: degree of neurovascular compression, site of neurovascular compression site, thickness of the trigeminal nerve root, and trigeminal pons angle (TPA). The final combined model, incorporating radiomics and clinical anatomy, achieved an area under the curve (AUC) of 0.91/0.90 (95% CI: 0.87-0.95/0.81-0.96) and an accuracy of approximately 82% in recognizing symptomatic and normal nerves. The combined radiomics and anatomical model provides superior recognition efficiency for the symptomatic nerves in PTN, offering valuable support for radiologists in diagnosing TN.</description><identifier>ISSN: 1662-4548</identifier><identifier>ISSN: 1662-453X</identifier><identifier>EISSN: 1662-453X</identifier><identifier>DOI: 10.3389/fnins.2024.1500584</identifier><identifier>PMID: 39513045</identifier><language>eng</language><publisher>Switzerland: Frontiers Media S.A</publisher><subject>MRI ; multiple-ROI ; Neuroscience ; nomogram ; radiomics ; trigeminal neuralgia</subject><ispartof>Frontiers in neuroscience, 2024-10, Vol.18, p.1500584</ispartof><rights>Copyright © 2024 Li, Li, Zhang, Xiao, He, Li, Yang, He, Sun, Qiu, Yang, Wei, Xu and Yang.</rights><rights>Copyright © 2024 Li, Li, Zhang, Xiao, He, Li, Yang, He, Sun, Qiu, Yang, Wei, Xu and Yang. 2024 Li, Li, Zhang, Xiao, He, Li, Yang, He, Sun, Qiu, Yang, Wei, Xu and Yang</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c350t-efc688a81ca41a6d9bf4be00f0d32629612a2a1919c288c5f6b3005c339cba103</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11541344/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11541344/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,37013,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39513045$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Hongjian</creatorcontrib><creatorcontrib>Li, Bing</creatorcontrib><creatorcontrib>Zhang, Chuan</creatorcontrib><creatorcontrib>Xiao, Ruhui</creatorcontrib><creatorcontrib>He, Libing</creatorcontrib><creatorcontrib>Li, Shaojie</creatorcontrib><creatorcontrib>Yang, Yu-Xin</creatorcontrib><creatorcontrib>He, Shipei</creatorcontrib><creatorcontrib>Sun, Baijintao</creatorcontrib><creatorcontrib>Qiu, Zhiqiang</creatorcontrib><creatorcontrib>Yang, Maojiang</creatorcontrib><creatorcontrib>Wei, Yan</creatorcontrib><creatorcontrib>Xu, Xiaoxue</creatorcontrib><creatorcontrib>Yang, Hanfeng</creatorcontrib><title>A combined radiomics and anatomical features model enhances MRI-based recognition of symptomatic nerves in primary trigeminal neuralgia</title><title>Frontiers in neuroscience</title><addtitle>Front Neurosci</addtitle><description>The diagnosis of primary trigeminal neuralgia (PTN) in radiology lacks the gold standard and largely depends on the identification of neurovascular compression (NVC) using magnetic resonance imaging (MRI) water imaging sequences. However, relying on this imaging sign alone often fails to accurately distinguish the symptomatic side of the nerve from asymptomatic nerves, and may even lead to incorrect diagnoses. Therefore, it is essential to develop a more effective diagnostic tool to aid radiologists in the diagnosis of TN. This study aims to establish a radiomics-based machine learning model integrating multi-region of interest (multiple-ROI) MRI and anatomical data, to improve the accuracy in differentiating symptomatic from asymptomatic nerves in PTN. A retrospective analysis of MRI data and clinical anatomical data was conducted on 140 patients with clinically confirmed PTN. Symptomatic nerves of TN patients were defined as the positive group, while asymptomatic nerves served as the negative group. The ipsilateral Meckel's cavity (MC) was included in both groups. Through dimensionality reduction analysis, four radiomics features were selected from the MC and 24 radiomics features were selected from the trigeminal cisternal segment. Thirteen anatomical features relevant to TN were identified from the literature, and analyzed using univariate logistic regression and multivariate logistic regression. Four features were confirmed as independent risk factors for TN. Logistic regression (LR) models were constructed for radiomics model and clinical anatomy, and a combined model was developed by integrating the radiomics score (Rad-Score) with the clinical anatomy model. The models' performance was evaluated using receiver operating characteristic curve (ROC) curves, calibration curves, and decision curve analysis (DCA). The four independent clinical anatomical factors identified were: degree of neurovascular compression, site of neurovascular compression site, thickness of the trigeminal nerve root, and trigeminal pons angle (TPA). The final combined model, incorporating radiomics and clinical anatomy, achieved an area under the curve (AUC) of 0.91/0.90 (95% CI: 0.87-0.95/0.81-0.96) and an accuracy of approximately 82% in recognizing symptomatic and normal nerves. The combined radiomics and anatomical model provides superior recognition efficiency for the symptomatic nerves in PTN, offering valuable support for radiologists in diagnosing TN.</description><subject>MRI</subject><subject>multiple-ROI</subject><subject>Neuroscience</subject><subject>nomogram</subject><subject>radiomics</subject><subject>trigeminal neuralgia</subject><issn>1662-4548</issn><issn>1662-453X</issn><issn>1662-453X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNpVks9u1DAQxiMEoqXwAhyQj1yy-G_WOaGqKrBSERICiZs1scepq8Re7GylPgGvjbe7rOjBssee7zdj-2uat4yuhND9Bx9DLCtOuVwxRanS8llzzrqOt1KJX89Pa6nPmlel3FHacS35y-ZM9IoJKtV58-eS2DQPIaIjGVxIc7CFQHR1wLKPYCIeYdllLGRODieC8RaireHX75t2gLKXok1jDEtIkSRPysO8rWJYgiUR833NDZFsc5ghP5AlhxHnECs54i7DNAZ43bzwMBV8c5wvmp-frn9cfWlvvn3eXF3etFYourTobac1aGZBMuhcP3g5IKWeOsE73neMAwfWs95yra3y3SDqy1ghejsAo-Ki2Ry4LsGdOXZkEgTzuJHyaCDXtic0WgrbczfAeq2ld6r3lq8ts1wNHIF1lfXxwNruhhmdxbjUyzyBPj2J4daM6d4wpiQTUlbC-yMhp987LIuZQ7E4TRAx7YoRjGvBJReqpvJDqs2plIz-VIdRs7eDebSD2dvBHO1QRe_-7_Ak-ff_4i99-bW-</recordid><startdate>20241024</startdate><enddate>20241024</enddate><creator>Li, Hongjian</creator><creator>Li, Bing</creator><creator>Zhang, Chuan</creator><creator>Xiao, Ruhui</creator><creator>He, Libing</creator><creator>Li, Shaojie</creator><creator>Yang, Yu-Xin</creator><creator>He, Shipei</creator><creator>Sun, Baijintao</creator><creator>Qiu, Zhiqiang</creator><creator>Yang, Maojiang</creator><creator>Wei, Yan</creator><creator>Xu, Xiaoxue</creator><creator>Yang, Hanfeng</creator><general>Frontiers Media S.A</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope></search><sort><creationdate>20241024</creationdate><title>A combined radiomics and anatomical features model enhances MRI-based recognition of symptomatic nerves in primary trigeminal neuralgia</title><author>Li, Hongjian ; Li, Bing ; Zhang, Chuan ; Xiao, Ruhui ; He, Libing ; Li, Shaojie ; Yang, Yu-Xin ; He, Shipei ; Sun, Baijintao ; Qiu, Zhiqiang ; Yang, Maojiang ; Wei, Yan ; Xu, Xiaoxue ; Yang, Hanfeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c350t-efc688a81ca41a6d9bf4be00f0d32629612a2a1919c288c5f6b3005c339cba103</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>MRI</topic><topic>multiple-ROI</topic><topic>Neuroscience</topic><topic>nomogram</topic><topic>radiomics</topic><topic>trigeminal neuralgia</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Hongjian</creatorcontrib><creatorcontrib>Li, Bing</creatorcontrib><creatorcontrib>Zhang, Chuan</creatorcontrib><creatorcontrib>Xiao, Ruhui</creatorcontrib><creatorcontrib>He, Libing</creatorcontrib><creatorcontrib>Li, Shaojie</creatorcontrib><creatorcontrib>Yang, Yu-Xin</creatorcontrib><creatorcontrib>He, Shipei</creatorcontrib><creatorcontrib>Sun, Baijintao</creatorcontrib><creatorcontrib>Qiu, Zhiqiang</creatorcontrib><creatorcontrib>Yang, Maojiang</creatorcontrib><creatorcontrib>Wei, Yan</creatorcontrib><creatorcontrib>Xu, Xiaoxue</creatorcontrib><creatorcontrib>Yang, Hanfeng</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>Directory of Open Access Journals</collection><jtitle>Frontiers in neuroscience</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Hongjian</au><au>Li, Bing</au><au>Zhang, Chuan</au><au>Xiao, Ruhui</au><au>He, Libing</au><au>Li, Shaojie</au><au>Yang, Yu-Xin</au><au>He, Shipei</au><au>Sun, Baijintao</au><au>Qiu, Zhiqiang</au><au>Yang, Maojiang</au><au>Wei, Yan</au><au>Xu, Xiaoxue</au><au>Yang, Hanfeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A combined radiomics and anatomical features model enhances MRI-based recognition of symptomatic nerves in primary trigeminal neuralgia</atitle><jtitle>Frontiers in neuroscience</jtitle><addtitle>Front Neurosci</addtitle><date>2024-10-24</date><risdate>2024</risdate><volume>18</volume><spage>1500584</spage><pages>1500584-</pages><issn>1662-4548</issn><issn>1662-453X</issn><eissn>1662-453X</eissn><abstract>The diagnosis of primary trigeminal neuralgia (PTN) in radiology lacks the gold standard and largely depends on the identification of neurovascular compression (NVC) using magnetic resonance imaging (MRI) water imaging sequences. However, relying on this imaging sign alone often fails to accurately distinguish the symptomatic side of the nerve from asymptomatic nerves, and may even lead to incorrect diagnoses. Therefore, it is essential to develop a more effective diagnostic tool to aid radiologists in the diagnosis of TN. This study aims to establish a radiomics-based machine learning model integrating multi-region of interest (multiple-ROI) MRI and anatomical data, to improve the accuracy in differentiating symptomatic from asymptomatic nerves in PTN. A retrospective analysis of MRI data and clinical anatomical data was conducted on 140 patients with clinically confirmed PTN. Symptomatic nerves of TN patients were defined as the positive group, while asymptomatic nerves served as the negative group. The ipsilateral Meckel's cavity (MC) was included in both groups. Through dimensionality reduction analysis, four radiomics features were selected from the MC and 24 radiomics features were selected from the trigeminal cisternal segment. Thirteen anatomical features relevant to TN were identified from the literature, and analyzed using univariate logistic regression and multivariate logistic regression. Four features were confirmed as independent risk factors for TN. Logistic regression (LR) models were constructed for radiomics model and clinical anatomy, and a combined model was developed by integrating the radiomics score (Rad-Score) with the clinical anatomy model. The models' performance was evaluated using receiver operating characteristic curve (ROC) curves, calibration curves, and decision curve analysis (DCA). The four independent clinical anatomical factors identified were: degree of neurovascular compression, site of neurovascular compression site, thickness of the trigeminal nerve root, and trigeminal pons angle (TPA). The final combined model, incorporating radiomics and clinical anatomy, achieved an area under the curve (AUC) of 0.91/0.90 (95% CI: 0.87-0.95/0.81-0.96) and an accuracy of approximately 82% in recognizing symptomatic and normal nerves. The combined radiomics and anatomical model provides superior recognition efficiency for the symptomatic nerves in PTN, offering valuable support for radiologists in diagnosing TN.</abstract><cop>Switzerland</cop><pub>Frontiers Media S.A</pub><pmid>39513045</pmid><doi>10.3389/fnins.2024.1500584</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1662-4548
ispartof Frontiers in neuroscience, 2024-10, Vol.18, p.1500584
issn 1662-4548
1662-453X
1662-453X
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_843c92dba7784fd59fc27c1c25b2ea16
source Open Access: PubMed Central; Publicly Available Content Database
subjects MRI
multiple-ROI
Neuroscience
nomogram
radiomics
trigeminal neuralgia
title A combined radiomics and anatomical features model enhances MRI-based recognition of symptomatic nerves in primary trigeminal neuralgia
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T09%3A10%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20combined%20radiomics%20and%20anatomical%20features%20model%20enhances%20MRI-based%20recognition%20of%20symptomatic%20nerves%20in%20primary%20trigeminal%20neuralgia&rft.jtitle=Frontiers%20in%20neuroscience&rft.au=Li,%20Hongjian&rft.date=2024-10-24&rft.volume=18&rft.spage=1500584&rft.pages=1500584-&rft.issn=1662-4548&rft.eissn=1662-453X&rft_id=info:doi/10.3389/fnins.2024.1500584&rft_dat=%3Cproquest_doaj_%3E3128324235%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c350t-efc688a81ca41a6d9bf4be00f0d32629612a2a1919c288c5f6b3005c339cba103%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3128324235&rft_id=info:pmid/39513045&rfr_iscdi=true