Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel disease

PurposeThis study aims to develop hippocampal texture model for predicting cognitive impairment in middle-aged patients with cerebral small vessel disease (CSVD).MethodsThe dataset included 145 CSVD patients (Age, 52.662 ± 5.151) and 99 control subjects (Age, 52.576±4.885). An Unet-based deep learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Zheng, Xiaoyan Qin, Ronghua Mu, Peng Yang, Bingqin Huang, Zhixuan Song, Xiqi Zhu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in Neurology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fneur.2025.1462636/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1823859415244079104
author Wei Zheng
Xiaoyan Qin
Ronghua Mu
Peng Yang
Bingqin Huang
Bingqin Huang
Zhixuan Song
Xiqi Zhu
Xiqi Zhu
author_facet Wei Zheng
Xiaoyan Qin
Ronghua Mu
Peng Yang
Bingqin Huang
Bingqin Huang
Zhixuan Song
Xiqi Zhu
Xiqi Zhu
author_sort Wei Zheng
collection DOAJ
description PurposeThis study aims to develop hippocampal texture model for predicting cognitive impairment in middle-aged patients with cerebral small vessel disease (CSVD).MethodsThe dataset included 145 CSVD patients (Age, 52.662 ± 5.151) and 99 control subjects (Age, 52.576±4.885). An Unet-based deep learning neural network model was developed to automate the segmentation of the hippocampus. Features were extracted for each subject, and the least absolute shrinkage and selection operator (LASSO) method was used to select radiomic features. This study also included the extraction of total intracranial volume, gray matter, white matter, cerebrospinal fluid, white matter hypertensit, and hippocampus volume. The performance of the models was assessed using the areas under the receiver operating characteristic curves (AUCs). Additionally, decision curve analysis (DCA) was conducted to justify the clinical relevance of the study, and the DeLong test was utilized to compare the areas under two correlated receiver operating characteristic (ROC) curves.ResultsNine texture features of the hippocampus were selected to construct radiomics model. The AUC values of the brain volume, radiomics, and combined models in the test set were 0.593, 0.843, and 0.817, respectively. The combination model of imaging markers and hippocampal texture did not yield improved a better diagnosis compared to the individual model (p > 0.05).ConclusionThe hippocampal texture model is a surrogate imaging marker for predicting cognitive impairment in middle-aged CSVD patients.
format Article
id doaj-art-9f1ed62f0bee4b77b61bd5c5baecd62d
institution Kabale University
issn 1664-2295
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurology
spelling doaj-art-9f1ed62f0bee4b77b61bd5c5baecd62d2025-02-11T05:10:26ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-02-011610.3389/fneur.2025.14626361462636Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel diseaseWei Zheng0Xiaoyan Qin1Ronghua Mu2Peng Yang3Bingqin Huang4Bingqin Huang5Zhixuan Song6Xiqi Zhu7Xiqi Zhu8Department of Radiology, Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Guilin, ChinaDepartment of Radiology, Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Guilin, ChinaDepartment of Radiology, Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Guilin, ChinaDepartment of Radiology, Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Guilin, ChinaDepartment of Radiology, Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Guilin, ChinaGraduate School, Guilin Medical University, Guilin, ChinaPhilips (China) Investment Co., Ltd., Guangzhou Branch, Guangzhou, ChinaDepartment of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise, ChinaLife Science and Clinical Medicine Research Center, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise, ChinaPurposeThis study aims to develop hippocampal texture model for predicting cognitive impairment in middle-aged patients with cerebral small vessel disease (CSVD).MethodsThe dataset included 145 CSVD patients (Age, 52.662 ± 5.151) and 99 control subjects (Age, 52.576±4.885). An Unet-based deep learning neural network model was developed to automate the segmentation of the hippocampus. Features were extracted for each subject, and the least absolute shrinkage and selection operator (LASSO) method was used to select radiomic features. This study also included the extraction of total intracranial volume, gray matter, white matter, cerebrospinal fluid, white matter hypertensit, and hippocampus volume. The performance of the models was assessed using the areas under the receiver operating characteristic curves (AUCs). Additionally, decision curve analysis (DCA) was conducted to justify the clinical relevance of the study, and the DeLong test was utilized to compare the areas under two correlated receiver operating characteristic (ROC) curves.ResultsNine texture features of the hippocampus were selected to construct radiomics model. The AUC values of the brain volume, radiomics, and combined models in the test set were 0.593, 0.843, and 0.817, respectively. The combination model of imaging markers and hippocampal texture did not yield improved a better diagnosis compared to the individual model (p > 0.05).ConclusionThe hippocampal texture model is a surrogate imaging marker for predicting cognitive impairment in middle-aged CSVD patients.https://www.frontiersin.org/articles/10.3389/fneur.2025.1462636/fullcerebral small vessel diseasecognitive impairmentmagnetic resonance imagingprediction modelradiomics
spellingShingle Wei Zheng
Xiaoyan Qin
Ronghua Mu
Peng Yang
Bingqin Huang
Bingqin Huang
Zhixuan Song
Xiqi Zhu
Xiqi Zhu
Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel disease
Frontiers in Neurology
cerebral small vessel disease
cognitive impairment
magnetic resonance imaging
prediction model
radiomics
title Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel disease
title_full Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel disease
title_fullStr Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel disease
title_full_unstemmed Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel disease
title_short Prediction models for cognitive impairment in middle-aged patients with cerebral small vessel disease
title_sort prediction models for cognitive impairment in middle aged patients with cerebral small vessel disease
topic cerebral small vessel disease
cognitive impairment
magnetic resonance imaging
prediction model
radiomics
url https://www.frontiersin.org/articles/10.3389/fneur.2025.1462636/full
work_keys_str_mv AT weizheng predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT xiaoyanqin predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT ronghuamu predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT pengyang predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT bingqinhuang predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT bingqinhuang predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT zhixuansong predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT xiqizhu predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease
AT xiqizhu predictionmodelsforcognitiveimpairmentinmiddleagedpatientswithcerebralsmallvesseldisease