A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images

A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images

Amyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:European journal of nuclear medicine and molecular imaging 2024-10, Vol.51 (12), p.3518
Hauptverfasser: Sanaat, Amirhossein, Boccalini, Cecilia, Mathoux, Gregory, Perani, Daniela, Frisoni, Giovanni B, Haller, Sven, Montandon, Marie-Louise, Rodriguez, Cristelle, Giannakopoulos, Panteleimon, Garibotto, Valentina, Zaidi, Habib
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 12
container_start_page 3518
container_title European journal of nuclear medicine and molecular imaging
container_volume 51
creator Sanaat, Amirhossein
Boccalini, Cecilia
Mathoux, Gregory
Perani, Daniela
Frisoni, Giovanni B
Haller, Sven
Montandon, Marie-Louise
Rodriguez, Cristelle
Giannakopoulos, Panteleimon
Garibotto, Valentina
Zaidi, Habib
description Amyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.INTRODUCTIONAmyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.A total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([18F]FBP) or Fluorine-18 Flutemetamol ([18F]FMM), and an [18F]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [18F]FDG from early phase [18F]FBP and [18F]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [18F]FDG as well as eFBP/eFMM to actual [18F]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [18F]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([18F]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [18F]FDG PET and synthetic [18F]FDG P
doi_str_mv 10.1007/s00259-024-06755-1
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_miscellaneous_3066788970</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3066788970</sourcerecordid><originalsourceid>FETCH-proquest_miscellaneous_30667889703</originalsourceid><addsrcrecordid>eNqVi71OwzAURi0EEgX6Akx3ZDFcp01sjwgaYGPoXhlyk6byT_BNBt6eEhhYmb5PR-cIca3wViHqO0YsSiuxWEusdFlKdSIWqlJWajT29M8_FxfMB0RlCmMXYrqHhmgATy7HPnYQUkMe2pSho0jZjd9Qmbp-fILXzRZeguuIoc0pwLHxn3LYO6ZZ8Sm_0eiGPoOLzQ-aRgpHFpKf837Or8RZ6zzT8ncvxU292T48yyGnj4l43IWe38l7FylNvFthVWljrMbVP9QvGoBU9A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3066788970</pqid></control><display><type>article</type><title>A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images</title><source>SpringerLink (Online service)</source><creator>Sanaat, Amirhossein ; Boccalini, Cecilia ; Mathoux, Gregory ; Perani, Daniela ; Frisoni, Giovanni B ; Haller, Sven ; Montandon, Marie-Louise ; Rodriguez, Cristelle ; Giannakopoulos, Panteleimon ; Garibotto, Valentina ; Zaidi, Habib</creator><creatorcontrib>Sanaat, Amirhossein ; Boccalini, Cecilia ; Mathoux, Gregory ; Perani, Daniela ; Frisoni, Giovanni B ; Haller, Sven ; Montandon, Marie-Louise ; Rodriguez, Cristelle ; Giannakopoulos, Panteleimon ; Garibotto, Valentina ; Zaidi, Habib</creatorcontrib><description><![CDATA[Amyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.INTRODUCTIONAmyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.A total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([18F]FBP) or Fluorine-18 Flutemetamol ([18F]FMM), and an [18F]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [18F]FDG from early phase [18F]FBP and [18F]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [18F]FDG as well as eFBP/eFMM to actual [18F]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [18F]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([18F]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [18F]FDG PET and synthetic [18F]FDG PET hypometabolic binary maps.METHODSA total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([18F]FBP) or Fluorine-18 Flutemetamol ([18F]FMM), and an [18F]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [18F]FDG from early phase [18F]FBP and [18F]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [18F]FDG as well as eFBP/eFMM to actual [18F]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [18F]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([18F]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [18F]FDG PET and synthetic [18F]FDG PET hypometabolic binary maps.The clinical evaluation showed that, in comparison to eFBP/eFMM (average of clinical similarity score (CSS) = 1.53), the synthetic [18F]FDG images are quite similar to the actual [18F]FDG images (average of CSS = 2.7) in terms of preserving clinically relevant uptake patterns. The single-subject voxel-wise analyses showed that at the group level, the Dice scores improved by around 13% and 5% when using the DL approach for eFBP and eFMM, respectively. The correlation analysis results indicated a relatively strong correlation between eFBP/eFMM and [18F]FDG (eFBP: slope = 0.77, R2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R2 = 0.61, P-value < 0.0001). This correlation improved for synthetic [18F]FDG (synthetic [18F]FDG generated from eFBP (slope = 1.00, R2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R2 = 0.72, P-value < 0.0001)).RESULTSThe clinical evaluation showed that, in comparison to eFBP/eFMM (average of clinical similarity score (CSS) = 1.53), the synthetic [18F]FDG images are quite similar to the actual [18F]FDG images (average of CSS = 2.7) in terms of preserving clinically relevant uptake patterns. The single-subject voxel-wise analyses showed that at the group level, the Dice scores improved by around 13% and 5% when using the DL approach for eFBP and eFMM, respectively. The correlation analysis results indicated a relatively strong correlation between eFBP/eFMM and [18F]FDG (eFBP: slope = 0.77, R2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R2 = 0.61, P-value < 0.0001). This correlation improved for synthetic [18F]FDG (synthetic [18F]FDG generated from eFBP (slope = 1.00, R2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R2 = 0.72, P-value < 0.0001)).We proposed a DL model for generating the [18F]FDG from eFBP/eFMM PET images. This method may be used as an alternative for multiple radiotracer scanning in research and clinical settings allowing to adopt the currently validated [18F]FDG PET normal reference databases for data analysis.CONCLUSIONWe proposed a DL model for generating the [18F]FDG from eFBP/eFMM PET images. This method may be used as an alternative for multiple radiotracer scanning in research and clinical settings allowing to adopt the currently validated [18F]FDG PET normal reference databases for data analysis.]]></description><identifier>ISSN: 1619-7089</identifier><identifier>EISSN: 1619-7089</identifier><identifier>DOI: 10.1007/s00259-024-06755-1</identifier><language>eng</language><ispartof>European journal of nuclear medicine and molecular imaging, 2024-10, Vol.51 (12), p.3518</ispartof><rights>2024. The Author(s).</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Sanaat, Amirhossein</creatorcontrib><creatorcontrib>Boccalini, Cecilia</creatorcontrib><creatorcontrib>Mathoux, Gregory</creatorcontrib><creatorcontrib>Perani, Daniela</creatorcontrib><creatorcontrib>Frisoni, Giovanni B</creatorcontrib><creatorcontrib>Haller, Sven</creatorcontrib><creatorcontrib>Montandon, Marie-Louise</creatorcontrib><creatorcontrib>Rodriguez, Cristelle</creatorcontrib><creatorcontrib>Giannakopoulos, Panteleimon</creatorcontrib><creatorcontrib>Garibotto, Valentina</creatorcontrib><creatorcontrib>Zaidi, Habib</creatorcontrib><title>A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images</title><title>European journal of nuclear medicine and molecular imaging</title><description><![CDATA[Amyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.INTRODUCTIONAmyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.A total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([18F]FBP) or Fluorine-18 Flutemetamol ([18F]FMM), and an [18F]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [18F]FDG from early phase [18F]FBP and [18F]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [18F]FDG as well as eFBP/eFMM to actual [18F]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [18F]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([18F]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [18F]FDG PET and synthetic [18F]FDG PET hypometabolic binary maps.METHODSA total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([18F]FBP) or Fluorine-18 Flutemetamol ([18F]FMM), and an [18F]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [18F]FDG from early phase [18F]FBP and [18F]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [18F]FDG as well as eFBP/eFMM to actual [18F]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [18F]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([18F]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [18F]FDG PET and synthetic [18F]FDG PET hypometabolic binary maps.The clinical evaluation showed that, in comparison to eFBP/eFMM (average of clinical similarity score (CSS) = 1.53), the synthetic [18F]FDG images are quite similar to the actual [18F]FDG images (average of CSS = 2.7) in terms of preserving clinically relevant uptake patterns. The single-subject voxel-wise analyses showed that at the group level, the Dice scores improved by around 13% and 5% when using the DL approach for eFBP and eFMM, respectively. The correlation analysis results indicated a relatively strong correlation between eFBP/eFMM and [18F]FDG (eFBP: slope = 0.77, R2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R2 = 0.61, P-value < 0.0001). This correlation improved for synthetic [18F]FDG (synthetic [18F]FDG generated from eFBP (slope = 1.00, R2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R2 = 0.72, P-value < 0.0001)).RESULTSThe clinical evaluation showed that, in comparison to eFBP/eFMM (average of clinical similarity score (CSS) = 1.53), the synthetic [18F]FDG images are quite similar to the actual [18F]FDG images (average of CSS = 2.7) in terms of preserving clinically relevant uptake patterns. The single-subject voxel-wise analyses showed that at the group level, the Dice scores improved by around 13% and 5% when using the DL approach for eFBP and eFMM, respectively. The correlation analysis results indicated a relatively strong correlation between eFBP/eFMM and [18F]FDG (eFBP: slope = 0.77, R2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R2 = 0.61, P-value < 0.0001). This correlation improved for synthetic [18F]FDG (synthetic [18F]FDG generated from eFBP (slope = 1.00, R2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R2 = 0.72, P-value < 0.0001)).We proposed a DL model for generating the [18F]FDG from eFBP/eFMM PET images. This method may be used as an alternative for multiple radiotracer scanning in research and clinical settings allowing to adopt the currently validated [18F]FDG PET normal reference databases for data analysis.CONCLUSIONWe proposed a DL model for generating the [18F]FDG from eFBP/eFMM PET images. This method may be used as an alternative for multiple radiotracer scanning in research and clinical settings allowing to adopt the currently validated [18F]FDG PET normal reference databases for data analysis.]]></description><issn>1619-7089</issn><issn>1619-7089</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNqVi71OwzAURi0EEgX6Akx3ZDFcp01sjwgaYGPoXhlyk6byT_BNBt6eEhhYmb5PR-cIca3wViHqO0YsSiuxWEusdFlKdSIWqlJWajT29M8_FxfMB0RlCmMXYrqHhmgATy7HPnYQUkMe2pSho0jZjd9Qmbp-fILXzRZeguuIoc0pwLHxn3LYO6ZZ8Sm_0eiGPoOLzQ-aRgpHFpKf837Or8RZ6zzT8ncvxU292T48yyGnj4l43IWe38l7FylNvFthVWljrMbVP9QvGoBU9A</recordid><startdate>20241001</startdate><enddate>20241001</enddate><creator>Sanaat, Amirhossein</creator><creator>Boccalini, Cecilia</creator><creator>Mathoux, Gregory</creator><creator>Perani, Daniela</creator><creator>Frisoni, Giovanni B</creator><creator>Haller, Sven</creator><creator>Montandon, Marie-Louise</creator><creator>Rodriguez, Cristelle</creator><creator>Giannakopoulos, Panteleimon</creator><creator>Garibotto, Valentina</creator><creator>Zaidi, Habib</creator><scope>7X8</scope></search><sort><creationdate>20241001</creationdate><title>A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images</title><author>Sanaat, Amirhossein ; Boccalini, Cecilia ; Mathoux, Gregory ; Perani, Daniela ; Frisoni, Giovanni B ; Haller, Sven ; Montandon, Marie-Louise ; Rodriguez, Cristelle ; Giannakopoulos, Panteleimon ; Garibotto, Valentina ; Zaidi, Habib</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_miscellaneous_30667889703</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sanaat, Amirhossein</creatorcontrib><creatorcontrib>Boccalini, Cecilia</creatorcontrib><creatorcontrib>Mathoux, Gregory</creatorcontrib><creatorcontrib>Perani, Daniela</creatorcontrib><creatorcontrib>Frisoni, Giovanni B</creatorcontrib><creatorcontrib>Haller, Sven</creatorcontrib><creatorcontrib>Montandon, Marie-Louise</creatorcontrib><creatorcontrib>Rodriguez, Cristelle</creatorcontrib><creatorcontrib>Giannakopoulos, Panteleimon</creatorcontrib><creatorcontrib>Garibotto, Valentina</creatorcontrib><creatorcontrib>Zaidi, Habib</creatorcontrib><collection>MEDLINE - Academic</collection><jtitle>European journal of nuclear medicine and molecular imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sanaat, Amirhossein</au><au>Boccalini, Cecilia</au><au>Mathoux, Gregory</au><au>Perani, Daniela</au><au>Frisoni, Giovanni B</au><au>Haller, Sven</au><au>Montandon, Marie-Louise</au><au>Rodriguez, Cristelle</au><au>Giannakopoulos, Panteleimon</au><au>Garibotto, Valentina</au><au>Zaidi, Habib</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images</atitle><jtitle>European journal of nuclear medicine and molecular imaging</jtitle><date>2024-10-01</date><risdate>2024</risdate><volume>51</volume><issue>12</issue><spage>3518</spage><pages>3518-</pages><issn>1619-7089</issn><eissn>1619-7089</eissn><abstract><![CDATA[Amyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.INTRODUCTIONAmyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose ([18F]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [18F]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients.A total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([18F]FBP) or Fluorine-18 Flutemetamol ([18F]FMM), and an [18F]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [18F]FDG from early phase [18F]FBP and [18F]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [18F]FDG as well as eFBP/eFMM to actual [18F]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [18F]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([18F]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [18F]FDG PET and synthetic [18F]FDG PET hypometabolic binary maps.METHODSA total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([18F]FBP) or Fluorine-18 Flutemetamol ([18F]FMM), and an [18F]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [18F]FDG from early phase [18F]FBP and [18F]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [18F]FDG as well as eFBP/eFMM to actual [18F]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [18F]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([18F]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [18F]FDG PET and synthetic [18F]FDG PET hypometabolic binary maps.The clinical evaluation showed that, in comparison to eFBP/eFMM (average of clinical similarity score (CSS) = 1.53), the synthetic [18F]FDG images are quite similar to the actual [18F]FDG images (average of CSS = 2.7) in terms of preserving clinically relevant uptake patterns. The single-subject voxel-wise analyses showed that at the group level, the Dice scores improved by around 13% and 5% when using the DL approach for eFBP and eFMM, respectively. The correlation analysis results indicated a relatively strong correlation between eFBP/eFMM and [18F]FDG (eFBP: slope = 0.77, R2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R2 = 0.61, P-value < 0.0001). This correlation improved for synthetic [18F]FDG (synthetic [18F]FDG generated from eFBP (slope = 1.00, R2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R2 = 0.72, P-value < 0.0001)).RESULTSThe clinical evaluation showed that, in comparison to eFBP/eFMM (average of clinical similarity score (CSS) = 1.53), the synthetic [18F]FDG images are quite similar to the actual [18F]FDG images (average of CSS = 2.7) in terms of preserving clinically relevant uptake patterns. The single-subject voxel-wise analyses showed that at the group level, the Dice scores improved by around 13% and 5% when using the DL approach for eFBP and eFMM, respectively. The correlation analysis results indicated a relatively strong correlation between eFBP/eFMM and [18F]FDG (eFBP: slope = 0.77, R2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R2 = 0.61, P-value < 0.0001). This correlation improved for synthetic [18F]FDG (synthetic [18F]FDG generated from eFBP (slope = 1.00, R2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R2 = 0.72, P-value < 0.0001)).We proposed a DL model for generating the [18F]FDG from eFBP/eFMM PET images. This method may be used as an alternative for multiple radiotracer scanning in research and clinical settings allowing to adopt the currently validated [18F]FDG PET normal reference databases for data analysis.CONCLUSIONWe proposed a DL model for generating the [18F]FDG from eFBP/eFMM PET images. This method may be used as an alternative for multiple radiotracer scanning in research and clinical settings allowing to adopt the currently validated [18F]FDG PET normal reference databases for data analysis.]]></abstract><doi>10.1007/s00259-024-06755-1</doi></addata></record>
fulltext fulltext
identifier ISSN: 1619-7089
ispartof European journal of nuclear medicine and molecular imaging, 2024-10, Vol.51 (12), p.3518
issn 1619-7089
1619-7089
language eng
recordid cdi_proquest_miscellaneous_3066788970
source SpringerLink (Online service)
title A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T06%3A03%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20deep%20learning%20model%20for%20generating%2018FFDG%20PET%20Images%20from%20early-phase%2018FFlorbetapir%20and%2018FFlutemetamol%20PET%20images&rft.jtitle=European%20journal%20of%20nuclear%20medicine%20and%20molecular%20imaging&rft.au=Sanaat,%20Amirhossein&rft.date=2024-10-01&rft.volume=51&rft.issue=12&rft.spage=3518&rft.pages=3518-&rft.issn=1619-7089&rft.eissn=1619-7089&rft_id=info:doi/10.1007/s00259-024-06755-1&rft_dat=%3Cproquest%3E3066788970%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3066788970&rft_id=info:pmid/&rfr_iscdi=true