Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR Imaging
PurposeTo investigate whether the combination of radiomics derived from brain high-resolution T1-weighted imaging and automatic machine learning could diagnose subcortical ischemic vascular cognitive impairment with no dementia (SIVCIND) accurately.MethodsA total of 116 right-handed participants inv...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-04-01
|
Series: | Frontiers in Oncology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.852726/full |
_version_ | 1811285276696248320 |
---|---|
author | Bo Liu Bo Liu Shan Meng Jie Cheng Yan Zeng Daiquan Zhou Xiaojuan Deng Lianqin Kuang Xiaojia Wu Lin Tang Haolin Wang Huan Liu Chen Liu Chuanming Li |
author_facet | Bo Liu Bo Liu Shan Meng Jie Cheng Yan Zeng Daiquan Zhou Xiaojuan Deng Lianqin Kuang Xiaojia Wu Lin Tang Haolin Wang Huan Liu Chen Liu Chuanming Li |
author_sort | Bo Liu |
collection | DOAJ |
description | PurposeTo investigate whether the combination of radiomics derived from brain high-resolution T1-weighted imaging and automatic machine learning could diagnose subcortical ischemic vascular cognitive impairment with no dementia (SIVCIND) accurately.MethodsA total of 116 right-handed participants involving 40 SIVCIND patients and 76 gender-, age-, and educational experience-matched normal controls (NM) were recruited. A total of 7,106 quantitative features from the bilateral thalamus, hippocampus, globus pallidus, amygdala, nucleus accumbens, putamen, caudate nucleus, and 148 areas of the cerebral cortex were automatically calculated from each subject. Six methods including least absolute shrinkage and selection operator (LASSO) were utilized to lessen the redundancy of features. Three supervised machine learning approaches of logistic regression (LR), random forest (RF), and support vector machine (SVM) employing 5-fold cross-validation were used to train and establish diagnosis models, and 10 times 10-fold cross-validation was used to evaluate the generalization performance of each model. Correlation analysis was performed between the optimal features and the neuropsychological scores of the SIVCIND patients.ResultsThirteen features from the right amygdala, right hippocampus, left caudate nucleus, left putamen, left thalamus, and bilateral nucleus accumbens were included in the optimal subset. Among all the three models, the RF produced the highest diagnostic performance with an area under the receiver operator characteristic curve (AUC) of 0.990 and an accuracy of 0.948. According to the correlation analysis, the radiomics features of the right amygdala, left caudate nucleus, left putamen, and left thalamus were found to be significantly correlated with the neuropsychological scores of the SIVCIND patients.ConclusionsThe combination of radiomics derived from brain high-resolution T1-weighted imaging and machine learning could diagnose SIVCIND accurately and automatically. The optimal radiomics features are mostly located in the right amygdala, left caudate nucleus, left putamen, and left thalamus, which might be new biomarkers of SIVCIND. |
first_indexed | 2024-04-13T02:41:46Z |
format | Article |
id | doaj.art-f3be2337866f41aeb93e299985fc5dd4 |
institution | Directory Open Access Journal |
issn | 2234-943X |
language | English |
last_indexed | 2024-04-13T02:41:46Z |
publishDate | 2022-04-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Oncology |
spelling | doaj.art-f3be2337866f41aeb93e299985fc5dd42022-12-22T03:06:11ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-04-011210.3389/fonc.2022.852726852726Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR ImagingBo Liu0Bo Liu1Shan Meng2Jie Cheng3Yan Zeng4Daiquan Zhou5Xiaojuan Deng6Lianqin Kuang7Xiaojia Wu8Lin Tang9Haolin Wang10Huan Liu11Chen Liu12Chuanming Li13Department of Radiology, Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, Third Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, The Second People’s Hospital of Jiulongpo District, Chongqing, ChinaDepartment of Ultrasound, Chongqing Maternal and Child Health Hospital, Chongqing, ChinaDepartment of Radiology, Third Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, Third Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, Third Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, Third Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaMedical Data Science Academy, Chongqing Medical University, Chongqing, ChinaDepartment of Data Analysis, GE Healthcare, Shanghai, ChinaDepartment of Radiology, The First Affiliated Hospital of Army Medical University, Chongqing, ChinaDepartment of Radiology, Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaPurposeTo investigate whether the combination of radiomics derived from brain high-resolution T1-weighted imaging and automatic machine learning could diagnose subcortical ischemic vascular cognitive impairment with no dementia (SIVCIND) accurately.MethodsA total of 116 right-handed participants involving 40 SIVCIND patients and 76 gender-, age-, and educational experience-matched normal controls (NM) were recruited. A total of 7,106 quantitative features from the bilateral thalamus, hippocampus, globus pallidus, amygdala, nucleus accumbens, putamen, caudate nucleus, and 148 areas of the cerebral cortex were automatically calculated from each subject. Six methods including least absolute shrinkage and selection operator (LASSO) were utilized to lessen the redundancy of features. Three supervised machine learning approaches of logistic regression (LR), random forest (RF), and support vector machine (SVM) employing 5-fold cross-validation were used to train and establish diagnosis models, and 10 times 10-fold cross-validation was used to evaluate the generalization performance of each model. Correlation analysis was performed between the optimal features and the neuropsychological scores of the SIVCIND patients.ResultsThirteen features from the right amygdala, right hippocampus, left caudate nucleus, left putamen, left thalamus, and bilateral nucleus accumbens were included in the optimal subset. Among all the three models, the RF produced the highest diagnostic performance with an area under the receiver operator characteristic curve (AUC) of 0.990 and an accuracy of 0.948. According to the correlation analysis, the radiomics features of the right amygdala, left caudate nucleus, left putamen, and left thalamus were found to be significantly correlated with the neuropsychological scores of the SIVCIND patients.ConclusionsThe combination of radiomics derived from brain high-resolution T1-weighted imaging and machine learning could diagnose SIVCIND accurately and automatically. The optimal radiomics features are mostly located in the right amygdala, left caudate nucleus, left putamen, and left thalamus, which might be new biomarkers of SIVCIND.https://www.frontiersin.org/articles/10.3389/fonc.2022.852726/fullsubcortical ischemic vascular cognitive impairment with no dementiadiagnosisradiomicshigh-resolution T1-weighted imagingmachine learning |
spellingShingle | Bo Liu Bo Liu Shan Meng Jie Cheng Yan Zeng Daiquan Zhou Xiaojuan Deng Lianqin Kuang Xiaojia Wu Lin Tang Haolin Wang Huan Liu Chen Liu Chuanming Li Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR Imaging Frontiers in Oncology subcortical ischemic vascular cognitive impairment with no dementia diagnosis radiomics high-resolution T1-weighted imaging machine learning |
title | Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR Imaging |
title_full | Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR Imaging |
title_fullStr | Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR Imaging |
title_full_unstemmed | Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR Imaging |
title_short | Diagnosis of Subcortical Ischemic Vascular Cognitive Impairment With No Dementia Using Radiomics of Cerebral Cortex and Subcortical Nuclei in High-Resolution T1-Weighted MR Imaging |
title_sort | diagnosis of subcortical ischemic vascular cognitive impairment with no dementia using radiomics of cerebral cortex and subcortical nuclei in high resolution t1 weighted mr imaging |
topic | subcortical ischemic vascular cognitive impairment with no dementia diagnosis radiomics high-resolution T1-weighted imaging machine learning |
url | https://www.frontiersin.org/articles/10.3389/fonc.2022.852726/full |
work_keys_str_mv | AT boliu diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT boliu diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT shanmeng diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT jiecheng diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT yanzeng diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT daiquanzhou diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT xiaojuandeng diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT lianqinkuang diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT xiaojiawu diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT lintang diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT haolinwang diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT huanliu diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT chenliu diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging AT chuanmingli diagnosisofsubcorticalischemicvascularcognitiveimpairmentwithnodementiausingradiomicsofcerebralcortexandsubcorticalnucleiinhighresolutiont1weightedmrimaging |