Loading…
Predicting Amyloid Pathology in Mild Cognitive Impairment Using Radiomics Analysis of Magnetic Resonance Imaging
Background: Noninvasive identification of amyloid-β (Aβ) is important for better clinical management of mild cognitive impairment (MCI) patients. Objective: To investigate whether radiomics features in the hippocampus in MCI improve the prediction of cerebrospinal fluid (CSF) Aβ42 status when integr...
Saved in:
| Published in: | Journal of Alzheimer's disease 2021-01, Vol.79 (2), p.483-491 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c449t-fbc42fe85c1d837c9738e70128d947217aa1d9854d090e59117aebfa72827f893 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c449t-fbc42fe85c1d837c9738e70128d947217aa1d9854d090e59117aebfa72827f893 |
| container_end_page | 491 |
| container_issue | 2 |
| container_start_page | 483 |
| container_title | Journal of Alzheimer's disease |
| container_volume | 79 |
| creator | Park, Yae Won Choi, Dongmin Park, Mina Ahn, Sung Jun Ahn, Sung Soo Suh, Sang Hyun Lee, Seung-Koo |
| description | Background:
Noninvasive identification of amyloid-β (Aβ) is important for better clinical management of mild cognitive impairment (MCI) patients.
Objective:
To investigate whether radiomics features in the hippocampus in MCI improve the prediction of cerebrospinal fluid (CSF) Aβ42 status when integrated with clinical profiles.
Methods:
A total of 407 MCI subjects from the Alzheimer’s Disease Neuroimaging Initiative were allocated to training (n = 324) and test (n = 83) sets. Radiomics features (n = 214) from the bilateral hippocampus were extracted from magnetic resonance imaging (MRI). A cut-off of |
| doi_str_mv | 10.3233/JAD-200734 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2471458760</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sage_id>10.3233_JAD-200734</sage_id><sourcerecordid>2478784870</sourcerecordid><originalsourceid>FETCH-LOGICAL-c449t-fbc42fe85c1d837c9738e70128d947217aa1d9854d090e59117aebfa72827f893</originalsourceid><addsrcrecordid>eNptkVtLJDEQhYOs7Hh78QcsgX1QhNbceip5HMbbiLIi-txkknRvhu5k7PQI8-_N7LgKy9ZLFeE7p0gdhI4pOeeM84u7yWXBCAEudtAelVAWUhH5Lc9cQsEkwAjtp7QghHCi4Dsa8VzAx3QPLR97Z70ZfGjwpFu30Vv8qIffsY3NGvuAH3xr8TQ2wQ_-zeFZt9S-71wY8EvaiJ609bHzJuFJ0O06-YRjjR90E9zgDX5yKQYdzEapmyw4RLu1bpM7-ugH6OX66nl6W9z_uplNJ_eFEUINRT03gtVOloZaycEo4NIBoUxaJYBR0JpaJUthiSKuVDS_uHmtgUkGtVT8AJ1ufZd9fF25NFSdT8a1rQ4urlLFBFBRShiTjP78B13EVZ9_84eSIIWEDXW2pUwfU-pdXS173-l-XVFSbXKocg7VNocM__iwXM07Zz_Rv4fPwMkWSLpxX_v-Y_UORoiOEg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2478784870</pqid></control><display><type>article</type><title>Predicting Amyloid Pathology in Mild Cognitive Impairment Using Radiomics Analysis of Magnetic Resonance Imaging</title><source>SAGE:Jisc Collections:SAGE Journals Read and Publish 2023-2024:2025 extension (reading list)</source><creator>Park, Yae Won ; Choi, Dongmin ; Park, Mina ; Ahn, Sung Jun ; Ahn, Sung Soo ; Suh, Sang Hyun ; Lee, Seung-Koo</creator><creatorcontrib>Park, Yae Won ; Choi, Dongmin ; Park, Mina ; Ahn, Sung Jun ; Ahn, Sung Soo ; Suh, Sang Hyun ; Lee, Seung-Koo ; Alzheimer’s Disease Neuroimaging Initiative</creatorcontrib><description>Background:
Noninvasive identification of amyloid-β (Aβ) is important for better clinical management of mild cognitive impairment (MCI) patients.
Objective:
To investigate whether radiomics features in the hippocampus in MCI improve the prediction of cerebrospinal fluid (CSF) Aβ42 status when integrated with clinical profiles.
Methods:
A total of 407 MCI subjects from the Alzheimer’s Disease Neuroimaging Initiative were allocated to training (n = 324) and test (n = 83) sets. Radiomics features (n = 214) from the bilateral hippocampus were extracted from magnetic resonance imaging (MRI). A cut-off of <192 pg/mL was applied to define CSF Aβ42 status. After feature selection, random forest with subsampling methods were utilized to develop three models with which to predict CSF Aβ42: 1) a radiomics model; 2) a clinical model based on clinical profiles; and 3) a combined model based on radiomics and clinical profiles. The prediction performances thereof were validated in the test set. A prediction model using hippocampus volume was also developed and validated.
Results:
The best-performing radiomics model showed an area under the curve (AUC) of 0.674 in the test set. The best-performing clinical model showed an AUC of 0.758 in the test set. The best-performing combined model showed an AUC of 0.823 in the test set. The hippocampal volume model showed a lower performance, with an AUC of 0.543 in the test set.
Conclusion:
Radiomics models from MRI can help predict CSF Aβ42 status in MCI patients and potentially triage the patients for invasive and costly Aβ tests.</description><identifier>ISSN: 1387-2877</identifier><identifier>EISSN: 1875-8908</identifier><identifier>DOI: 10.3233/JAD-200734</identifier><identifier>PMID: 33337361</identifier><language>eng</language><publisher>London, England: SAGE Publications</publisher><subject>Alzheimer's disease ; Amyloid ; Artificial intelligence ; Cerebrospinal fluid ; Cognitive ability ; Feature extraction ; Hippocampus ; Impairment ; Magnetic resonance imaging ; Medical imaging ; Neurodegenerative diseases ; Neuroimaging ; Prediction models ; Radiomics ; Resonance ; Test sets</subject><ispartof>Journal of Alzheimer's disease, 2021-01, Vol.79 (2), p.483-491</ispartof><rights>2021 – IOS Press. All rights reserved</rights><rights>Copyright IOS Press BV 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c449t-fbc42fe85c1d837c9738e70128d947217aa1d9854d090e59117aebfa72827f893</citedby><cites>FETCH-LOGICAL-c449t-fbc42fe85c1d837c9738e70128d947217aa1d9854d090e59117aebfa72827f893</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27898,27899</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33337361$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Park, Yae Won</creatorcontrib><creatorcontrib>Choi, Dongmin</creatorcontrib><creatorcontrib>Park, Mina</creatorcontrib><creatorcontrib>Ahn, Sung Jun</creatorcontrib><creatorcontrib>Ahn, Sung Soo</creatorcontrib><creatorcontrib>Suh, Sang Hyun</creatorcontrib><creatorcontrib>Lee, Seung-Koo</creatorcontrib><creatorcontrib>Alzheimer’s Disease Neuroimaging Initiative</creatorcontrib><title>Predicting Amyloid Pathology in Mild Cognitive Impairment Using Radiomics Analysis of Magnetic Resonance Imaging</title><title>Journal of Alzheimer's disease</title><addtitle>J Alzheimers Dis</addtitle><description>Background:
Noninvasive identification of amyloid-β (Aβ) is important for better clinical management of mild cognitive impairment (MCI) patients.
Objective:
To investigate whether radiomics features in the hippocampus in MCI improve the prediction of cerebrospinal fluid (CSF) Aβ42 status when integrated with clinical profiles.
Methods:
A total of 407 MCI subjects from the Alzheimer’s Disease Neuroimaging Initiative were allocated to training (n = 324) and test (n = 83) sets. Radiomics features (n = 214) from the bilateral hippocampus were extracted from magnetic resonance imaging (MRI). A cut-off of <192 pg/mL was applied to define CSF Aβ42 status. After feature selection, random forest with subsampling methods were utilized to develop three models with which to predict CSF Aβ42: 1) a radiomics model; 2) a clinical model based on clinical profiles; and 3) a combined model based on radiomics and clinical profiles. The prediction performances thereof were validated in the test set. A prediction model using hippocampus volume was also developed and validated.
Results:
The best-performing radiomics model showed an area under the curve (AUC) of 0.674 in the test set. The best-performing clinical model showed an AUC of 0.758 in the test set. The best-performing combined model showed an AUC of 0.823 in the test set. The hippocampal volume model showed a lower performance, with an AUC of 0.543 in the test set.
Conclusion:
Radiomics models from MRI can help predict CSF Aβ42 status in MCI patients and potentially triage the patients for invasive and costly Aβ tests.</description><subject>Alzheimer's disease</subject><subject>Amyloid</subject><subject>Artificial intelligence</subject><subject>Cerebrospinal fluid</subject><subject>Cognitive ability</subject><subject>Feature extraction</subject><subject>Hippocampus</subject><subject>Impairment</subject><subject>Magnetic resonance imaging</subject><subject>Medical imaging</subject><subject>Neurodegenerative diseases</subject><subject>Neuroimaging</subject><subject>Prediction models</subject><subject>Radiomics</subject><subject>Resonance</subject><subject>Test sets</subject><issn>1387-2877</issn><issn>1875-8908</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNptkVtLJDEQhYOs7Hh78QcsgX1QhNbceip5HMbbiLIi-txkknRvhu5k7PQI8-_N7LgKy9ZLFeE7p0gdhI4pOeeM84u7yWXBCAEudtAelVAWUhH5Lc9cQsEkwAjtp7QghHCi4Dsa8VzAx3QPLR97Z70ZfGjwpFu30Vv8qIffsY3NGvuAH3xr8TQ2wQ_-zeFZt9S-71wY8EvaiJ609bHzJuFJ0O06-YRjjR90E9zgDX5yKQYdzEapmyw4RLu1bpM7-ugH6OX66nl6W9z_uplNJ_eFEUINRT03gtVOloZaycEo4NIBoUxaJYBR0JpaJUthiSKuVDS_uHmtgUkGtVT8AJ1ufZd9fF25NFSdT8a1rQ4urlLFBFBRShiTjP78B13EVZ9_84eSIIWEDXW2pUwfU-pdXS173-l-XVFSbXKocg7VNocM__iwXM07Zz_Rv4fPwMkWSLpxX_v-Y_UORoiOEg</recordid><startdate>20210101</startdate><enddate>20210101</enddate><creator>Park, Yae Won</creator><creator>Choi, Dongmin</creator><creator>Park, Mina</creator><creator>Ahn, Sung Jun</creator><creator>Ahn, Sung Soo</creator><creator>Suh, Sang Hyun</creator><creator>Lee, Seung-Koo</creator><general>SAGE Publications</general><general>IOS Press BV</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TK</scope><scope>7U7</scope><scope>C1K</scope><scope>NAPCQ</scope><scope>7X8</scope></search><sort><creationdate>20210101</creationdate><title>Predicting Amyloid Pathology in Mild Cognitive Impairment Using Radiomics Analysis of Magnetic Resonance Imaging</title><author>Park, Yae Won ; Choi, Dongmin ; Park, Mina ; Ahn, Sung Jun ; Ahn, Sung Soo ; Suh, Sang Hyun ; Lee, Seung-Koo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c449t-fbc42fe85c1d837c9738e70128d947217aa1d9854d090e59117aebfa72827f893</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Alzheimer's disease</topic><topic>Amyloid</topic><topic>Artificial intelligence</topic><topic>Cerebrospinal fluid</topic><topic>Cognitive ability</topic><topic>Feature extraction</topic><topic>Hippocampus</topic><topic>Impairment</topic><topic>Magnetic resonance imaging</topic><topic>Medical imaging</topic><topic>Neurodegenerative diseases</topic><topic>Neuroimaging</topic><topic>Prediction models</topic><topic>Radiomics</topic><topic>Resonance</topic><topic>Test sets</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Park, Yae Won</creatorcontrib><creatorcontrib>Choi, Dongmin</creatorcontrib><creatorcontrib>Park, Mina</creatorcontrib><creatorcontrib>Ahn, Sung Jun</creatorcontrib><creatorcontrib>Ahn, Sung Soo</creatorcontrib><creatorcontrib>Suh, Sang Hyun</creatorcontrib><creatorcontrib>Lee, Seung-Koo</creatorcontrib><creatorcontrib>Alzheimer’s Disease Neuroimaging Initiative</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Neurosciences Abstracts</collection><collection>Toxicology Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Nursing & Allied Health Premium</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of Alzheimer's disease</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Park, Yae Won</au><au>Choi, Dongmin</au><au>Park, Mina</au><au>Ahn, Sung Jun</au><au>Ahn, Sung Soo</au><au>Suh, Sang Hyun</au><au>Lee, Seung-Koo</au><aucorp>Alzheimer’s Disease Neuroimaging Initiative</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting Amyloid Pathology in Mild Cognitive Impairment Using Radiomics Analysis of Magnetic Resonance Imaging</atitle><jtitle>Journal of Alzheimer's disease</jtitle><addtitle>J Alzheimers Dis</addtitle><date>2021-01-01</date><risdate>2021</risdate><volume>79</volume><issue>2</issue><spage>483</spage><epage>491</epage><pages>483-491</pages><issn>1387-2877</issn><eissn>1875-8908</eissn><abstract>Background:
Noninvasive identification of amyloid-β (Aβ) is important for better clinical management of mild cognitive impairment (MCI) patients.
Objective:
To investigate whether radiomics features in the hippocampus in MCI improve the prediction of cerebrospinal fluid (CSF) Aβ42 status when integrated with clinical profiles.
Methods:
A total of 407 MCI subjects from the Alzheimer’s Disease Neuroimaging Initiative were allocated to training (n = 324) and test (n = 83) sets. Radiomics features (n = 214) from the bilateral hippocampus were extracted from magnetic resonance imaging (MRI). A cut-off of <192 pg/mL was applied to define CSF Aβ42 status. After feature selection, random forest with subsampling methods were utilized to develop three models with which to predict CSF Aβ42: 1) a radiomics model; 2) a clinical model based on clinical profiles; and 3) a combined model based on radiomics and clinical profiles. The prediction performances thereof were validated in the test set. A prediction model using hippocampus volume was also developed and validated.
Results:
The best-performing radiomics model showed an area under the curve (AUC) of 0.674 in the test set. The best-performing clinical model showed an AUC of 0.758 in the test set. The best-performing combined model showed an AUC of 0.823 in the test set. The hippocampal volume model showed a lower performance, with an AUC of 0.543 in the test set.
Conclusion:
Radiomics models from MRI can help predict CSF Aβ42 status in MCI patients and potentially triage the patients for invasive and costly Aβ tests.</abstract><cop>London, England</cop><pub>SAGE Publications</pub><pmid>33337361</pmid><doi>10.3233/JAD-200734</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1387-2877 |
| ispartof | Journal of Alzheimer's disease, 2021-01, Vol.79 (2), p.483-491 |
| issn | 1387-2877 1875-8908 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2471458760 |
| source | SAGE:Jisc Collections:SAGE Journals Read and Publish 2023-2024:2025 extension (reading list) |
| subjects | Alzheimer's disease Amyloid Artificial intelligence Cerebrospinal fluid Cognitive ability Feature extraction Hippocampus Impairment Magnetic resonance imaging Medical imaging Neurodegenerative diseases Neuroimaging Prediction models Radiomics Resonance Test sets |
| title | Predicting Amyloid Pathology in Mild Cognitive Impairment Using Radiomics Analysis of Magnetic Resonance Imaging |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-27T07%3A20%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predicting%20Amyloid%20Pathology%20in%20Mild%20Cognitive%20Impairment%20Using%20Radiomics%20Analysis%20of%20Magnetic%20Resonance%20Imaging&rft.jtitle=Journal%20of%20Alzheimer's%20disease&rft.au=Park,%20Yae%20Won&rft.aucorp=Alzheimer%E2%80%99s%20Disease%20Neuroimaging%20Initiative&rft.date=2021-01-01&rft.volume=79&rft.issue=2&rft.spage=483&rft.epage=491&rft.pages=483-491&rft.issn=1387-2877&rft.eissn=1875-8908&rft_id=info:doi/10.3233/JAD-200734&rft_dat=%3Cproquest_cross%3E2478784870%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c449t-fbc42fe85c1d837c9738e70128d947217aa1d9854d090e59117aebfa72827f893%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2478784870&rft_id=info:pmid/33337361&rft_sage_id=10.3233_JAD-200734&rfr_iscdi=true |