Loading…
Prognostic value of combining clinical factors, 18F-FDG PET-based intensity, volumetric features, and deep learning predictor in patients with EGFR-mutated lung adenocarcinoma undergoing targeted therapies: a cross-scanner and temporal validation study
Objective To investigate the prognostic value of 18 F-FDG PET-based intensity, volumetric features, and deep learning (DL) across different generations of PET scanners in patients with epidermal growth factor receptor (EGFR)-mutated lung adenocarcinoma receiving tyrosine kinase inhibitor (TKI) treat...
Saved in:
| Published in: | Annals of nuclear medicine 2024-08, Vol.38 (8), p.647-658 |
|---|---|
| Main Authors: | , , , , , |
| 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-c233t-9c19c0e5e5d584656e99fb7a0df3cf6dbe297950e8d4026fe13bfd19b26fa27f3 |
| container_end_page | 658 |
| container_issue | 8 |
| container_start_page | 647 |
| container_title | Annals of nuclear medicine |
| container_volume | 38 |
| creator | Lue, Kun-Han Chen, Yu-Hung Chu, Sung-Chao Lin, Chih-Bin Wang, Tso-Fu Liu, Shu-Hsin |
| description | Objective
To investigate the prognostic value of
18
F-FDG PET-based intensity, volumetric features, and deep learning (DL) across different generations of PET scanners in patients with epidermal growth factor receptor (EGFR)-mutated lung adenocarcinoma receiving tyrosine kinase inhibitor (TKI) treatment.
Methods
We retrospectively analyzed the pre-treatment
18
F-FDG PET of 217 patients with advanced-stage lung adenocarcinoma and actionable EGFR mutations who received TKI as first-line treatment. Patients were separated into analog (
n
= 166) and digital (
n
= 51) PET cohorts.
18
F-FDG PET-derived intensity, volumetric features, ResNet-50 DL of the primary tumor, and clinical variables were used to predict progression-free survival (PFS). Independent prognosticators were used to develop prediction model. Model was developed and validated in the analog and digital PET cohorts, respectively.
Results
In the analog PET cohort, female sex, stage IVB status, exon 19 deletion, SUV
max
, metabolic tumor volume, and positive DL prediction independently predicted PFS. The model devised from these six prognosticators significantly predicted PFS in the analog (HR = 1.319,
p
|
| doi_str_mv | 10.1007/s12149-024-01936-2 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3051423502</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3051423502</sourcerecordid><originalsourceid>FETCH-LOGICAL-c233t-9c19c0e5e5d584656e99fb7a0df3cf6dbe297950e8d4026fe13bfd19b26fa27f3</originalsourceid><addsrcrecordid>eNp9kk2LFDEQhhtRcFz9A54CXjxs1nz0pzdZZ2aFBRdZz011UpnN0p20SXpl_rsH0zOC4MFT5fC8T6XgLYq3nF1xxpoPkQtedpSJkjLeyZqKZ8WGt3VJ61LK58WGdbykDW-bl8WrGB8ZE23Vik3x6y74g_MxWUWeYFyQeEOUnwbrrDsQNeapYCQGVPIhXhLe7uju857cbe_pABE1sS6hizYdL8mTH5cJU8gyg5CWgDkBThONOJMRIZysc0BtV1_OkhmSRZci-WnTA9nud9_otCRI2TwuGQaNzisIyjo_AVmcxnDwqyZBOODKpQcMMFuMHwkQFXyMNCpwDsNpecJp9iEfkQ-0Oq_zjsS06OPr4oWBMeKbP_Oi-L7b3l_f0Nuv-y_Xn26pElIm2ineKYYVVrpqy7qqsevM0ADTRipT6wFF13QVw1aXTNQGuRyM5t2Q3yAaIy-K92fvHPyPBWPqJxsVjiM49EvsJat4KWTFREbf_YM--iW4_LtMtRVnUvIqU-JMnY4NaPo52AnCseesXwvRnwvR50L0p0L0q1qeQzHD7oDhr_o_qd_UM78a</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3085103315</pqid></control><display><type>article</type><title>Prognostic value of combining clinical factors, 18F-FDG PET-based intensity, volumetric features, and deep learning predictor in patients with EGFR-mutated lung adenocarcinoma undergoing targeted therapies: a cross-scanner and temporal validation study</title><source>Springer Nature</source><creator>Lue, Kun-Han ; Chen, Yu-Hung ; Chu, Sung-Chao ; Lin, Chih-Bin ; Wang, Tso-Fu ; Liu, Shu-Hsin</creator><creatorcontrib>Lue, Kun-Han ; Chen, Yu-Hung ; Chu, Sung-Chao ; Lin, Chih-Bin ; Wang, Tso-Fu ; Liu, Shu-Hsin</creatorcontrib><description>Objective
To investigate the prognostic value of
18
F-FDG PET-based intensity, volumetric features, and deep learning (DL) across different generations of PET scanners in patients with epidermal growth factor receptor (EGFR)-mutated lung adenocarcinoma receiving tyrosine kinase inhibitor (TKI) treatment.
Methods
We retrospectively analyzed the pre-treatment
18
F-FDG PET of 217 patients with advanced-stage lung adenocarcinoma and actionable EGFR mutations who received TKI as first-line treatment. Patients were separated into analog (
n
= 166) and digital (
n
= 51) PET cohorts.
18
F-FDG PET-derived intensity, volumetric features, ResNet-50 DL of the primary tumor, and clinical variables were used to predict progression-free survival (PFS). Independent prognosticators were used to develop prediction model. Model was developed and validated in the analog and digital PET cohorts, respectively.
Results
In the analog PET cohort, female sex, stage IVB status, exon 19 deletion, SUV
max
, metabolic tumor volume, and positive DL prediction independently predicted PFS. The model devised from these six prognosticators significantly predicted PFS in the analog (HR = 1.319,
p
< 0.001) and digital PET cohorts (HR = 1.284,
p
= 0.001). Our model provided incremental prognostic value to staging status (c-indices = 0.738 vs. 0.558 and 0.662 vs. 0.598 in the analog and digital PET cohorts, respectively). Our model also demonstrated a significant prognostic value for overall survival (HR = 1.198,
p
< 0.001, c-index = 0.708 and HR = 1.256,
p
= 0.021, c-index = 0.664 in the analog and digital PET cohorts, respectively).
Conclusions
Combining
18
F-FDG PET-based intensity, volumetric features, and DL with clinical variables may improve the survival stratification in patients with advanced EGFR-mutated lung adenocarcinoma receiving TKI treatment. Implementing the prediction model across different generations of PET scanners may be feasible and facilitate tailored therapeutic strategies for these patients.</description><identifier>ISSN: 0914-7187</identifier><identifier>ISSN: 1864-6433</identifier><identifier>EISSN: 1864-6433</identifier><identifier>DOI: 10.1007/s12149-024-01936-2</identifier><language>eng</language><publisher>Singapore: Springer Nature Singapore</publisher><subject>Adenocarcinoma ; Cancer ; Deep learning ; Epidermal growth factor receptors ; Growth factors ; Imaging ; Independent variables ; Kinases ; Lung cancer ; Lungs ; Medicine ; Medicine & Public Health ; Nuclear Medicine ; Original Article ; Patients ; Positron emission ; Positron emission tomography ; Prediction models ; Predictions ; Radiology ; Scanners ; Survival ; Tumors ; Tyrosine ; Tyrosine kinase inhibitors</subject><ispartof>Annals of nuclear medicine, 2024-08, Vol.38 (8), p.647-658</ispartof><rights>The Author(s), under exclusive licence to The Author(s) under exclusive licence to The Japanese Society of Nuclear Medicine 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>The Author(s), under exclusive licence to The Author(s) under exclusive licence to The Japanese Society of Nuclear Medicine 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2024. The Author(s), under exclusive licence to The Author(s) under exclusive licence to The Japanese Society of Nuclear Medicine.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c233t-9c19c0e5e5d584656e99fb7a0df3cf6dbe297950e8d4026fe13bfd19b26fa27f3</cites><orcidid>0000-0002-9227-0731</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,778,782,27911,27912</link.rule.ids></links><search><creatorcontrib>Lue, Kun-Han</creatorcontrib><creatorcontrib>Chen, Yu-Hung</creatorcontrib><creatorcontrib>Chu, Sung-Chao</creatorcontrib><creatorcontrib>Lin, Chih-Bin</creatorcontrib><creatorcontrib>Wang, Tso-Fu</creatorcontrib><creatorcontrib>Liu, Shu-Hsin</creatorcontrib><title>Prognostic value of combining clinical factors, 18F-FDG PET-based intensity, volumetric features, and deep learning predictor in patients with EGFR-mutated lung adenocarcinoma undergoing targeted therapies: a cross-scanner and temporal validation study</title><title>Annals of nuclear medicine</title><addtitle>Ann Nucl Med</addtitle><description>Objective
To investigate the prognostic value of
18
F-FDG PET-based intensity, volumetric features, and deep learning (DL) across different generations of PET scanners in patients with epidermal growth factor receptor (EGFR)-mutated lung adenocarcinoma receiving tyrosine kinase inhibitor (TKI) treatment.
Methods
We retrospectively analyzed the pre-treatment
18
F-FDG PET of 217 patients with advanced-stage lung adenocarcinoma and actionable EGFR mutations who received TKI as first-line treatment. Patients were separated into analog (
n
= 166) and digital (
n
= 51) PET cohorts.
18
F-FDG PET-derived intensity, volumetric features, ResNet-50 DL of the primary tumor, and clinical variables were used to predict progression-free survival (PFS). Independent prognosticators were used to develop prediction model. Model was developed and validated in the analog and digital PET cohorts, respectively.
Results
In the analog PET cohort, female sex, stage IVB status, exon 19 deletion, SUV
max
, metabolic tumor volume, and positive DL prediction independently predicted PFS. The model devised from these six prognosticators significantly predicted PFS in the analog (HR = 1.319,
p
< 0.001) and digital PET cohorts (HR = 1.284,
p
= 0.001). Our model provided incremental prognostic value to staging status (c-indices = 0.738 vs. 0.558 and 0.662 vs. 0.598 in the analog and digital PET cohorts, respectively). Our model also demonstrated a significant prognostic value for overall survival (HR = 1.198,
p
< 0.001, c-index = 0.708 and HR = 1.256,
p
= 0.021, c-index = 0.664 in the analog and digital PET cohorts, respectively).
Conclusions
Combining
18
F-FDG PET-based intensity, volumetric features, and DL with clinical variables may improve the survival stratification in patients with advanced EGFR-mutated lung adenocarcinoma receiving TKI treatment. Implementing the prediction model across different generations of PET scanners may be feasible and facilitate tailored therapeutic strategies for these patients.</description><subject>Adenocarcinoma</subject><subject>Cancer</subject><subject>Deep learning</subject><subject>Epidermal growth factor receptors</subject><subject>Growth factors</subject><subject>Imaging</subject><subject>Independent variables</subject><subject>Kinases</subject><subject>Lung cancer</subject><subject>Lungs</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Nuclear Medicine</subject><subject>Original Article</subject><subject>Patients</subject><subject>Positron emission</subject><subject>Positron emission tomography</subject><subject>Prediction models</subject><subject>Predictions</subject><subject>Radiology</subject><subject>Scanners</subject><subject>Survival</subject><subject>Tumors</subject><subject>Tyrosine</subject><subject>Tyrosine kinase inhibitors</subject><issn>0914-7187</issn><issn>1864-6433</issn><issn>1864-6433</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kk2LFDEQhhtRcFz9A54CXjxs1nz0pzdZZ2aFBRdZz011UpnN0p20SXpl_rsH0zOC4MFT5fC8T6XgLYq3nF1xxpoPkQtedpSJkjLeyZqKZ8WGt3VJ61LK58WGdbykDW-bl8WrGB8ZE23Vik3x6y74g_MxWUWeYFyQeEOUnwbrrDsQNeapYCQGVPIhXhLe7uju857cbe_pABE1sS6hizYdL8mTH5cJU8gyg5CWgDkBThONOJMRIZysc0BtV1_OkhmSRZci-WnTA9nud9_otCRI2TwuGQaNzisIyjo_AVmcxnDwqyZBOODKpQcMMFuMHwkQFXyMNCpwDsNpecJp9iEfkQ-0Oq_zjsS06OPr4oWBMeKbP_Oi-L7b3l_f0Nuv-y_Xn26pElIm2ineKYYVVrpqy7qqsevM0ADTRipT6wFF13QVw1aXTNQGuRyM5t2Q3yAaIy-K92fvHPyPBWPqJxsVjiM49EvsJat4KWTFREbf_YM--iW4_LtMtRVnUvIqU-JMnY4NaPo52AnCseesXwvRnwvR50L0p0L0q1qeQzHD7oDhr_o_qd_UM78a</recordid><startdate>20240801</startdate><enddate>20240801</enddate><creator>Lue, Kun-Han</creator><creator>Chen, Yu-Hung</creator><creator>Chu, Sung-Chao</creator><creator>Lin, Chih-Bin</creator><creator>Wang, Tso-Fu</creator><creator>Liu, Shu-Hsin</creator><general>Springer Nature Singapore</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QP</scope><scope>7TK</scope><scope>K9.</scope><scope>NAPCQ</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-9227-0731</orcidid></search><sort><creationdate>20240801</creationdate><title>Prognostic value of combining clinical factors, 18F-FDG PET-based intensity, volumetric features, and deep learning predictor in patients with EGFR-mutated lung adenocarcinoma undergoing targeted therapies: a cross-scanner and temporal validation study</title><author>Lue, Kun-Han ; Chen, Yu-Hung ; Chu, Sung-Chao ; Lin, Chih-Bin ; Wang, Tso-Fu ; Liu, Shu-Hsin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c233t-9c19c0e5e5d584656e99fb7a0df3cf6dbe297950e8d4026fe13bfd19b26fa27f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adenocarcinoma</topic><topic>Cancer</topic><topic>Deep learning</topic><topic>Epidermal growth factor receptors</topic><topic>Growth factors</topic><topic>Imaging</topic><topic>Independent variables</topic><topic>Kinases</topic><topic>Lung cancer</topic><topic>Lungs</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Nuclear Medicine</topic><topic>Original Article</topic><topic>Patients</topic><topic>Positron emission</topic><topic>Positron emission tomography</topic><topic>Prediction models</topic><topic>Predictions</topic><topic>Radiology</topic><topic>Scanners</topic><topic>Survival</topic><topic>Tumors</topic><topic>Tyrosine</topic><topic>Tyrosine kinase inhibitors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lue, Kun-Han</creatorcontrib><creatorcontrib>Chen, Yu-Hung</creatorcontrib><creatorcontrib>Chu, Sung-Chao</creatorcontrib><creatorcontrib>Lin, Chih-Bin</creatorcontrib><creatorcontrib>Wang, Tso-Fu</creatorcontrib><creatorcontrib>Liu, Shu-Hsin</creatorcontrib><collection>CrossRef</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Premium</collection><collection>MEDLINE - Academic</collection><jtitle>Annals of nuclear medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lue, Kun-Han</au><au>Chen, Yu-Hung</au><au>Chu, Sung-Chao</au><au>Lin, Chih-Bin</au><au>Wang, Tso-Fu</au><au>Liu, Shu-Hsin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prognostic value of combining clinical factors, 18F-FDG PET-based intensity, volumetric features, and deep learning predictor in patients with EGFR-mutated lung adenocarcinoma undergoing targeted therapies: a cross-scanner and temporal validation study</atitle><jtitle>Annals of nuclear medicine</jtitle><stitle>Ann Nucl Med</stitle><date>2024-08-01</date><risdate>2024</risdate><volume>38</volume><issue>8</issue><spage>647</spage><epage>658</epage><pages>647-658</pages><issn>0914-7187</issn><issn>1864-6433</issn><eissn>1864-6433</eissn><abstract>Objective
To investigate the prognostic value of
18
F-FDG PET-based intensity, volumetric features, and deep learning (DL) across different generations of PET scanners in patients with epidermal growth factor receptor (EGFR)-mutated lung adenocarcinoma receiving tyrosine kinase inhibitor (TKI) treatment.
Methods
We retrospectively analyzed the pre-treatment
18
F-FDG PET of 217 patients with advanced-stage lung adenocarcinoma and actionable EGFR mutations who received TKI as first-line treatment. Patients were separated into analog (
n
= 166) and digital (
n
= 51) PET cohorts.
18
F-FDG PET-derived intensity, volumetric features, ResNet-50 DL of the primary tumor, and clinical variables were used to predict progression-free survival (PFS). Independent prognosticators were used to develop prediction model. Model was developed and validated in the analog and digital PET cohorts, respectively.
Results
In the analog PET cohort, female sex, stage IVB status, exon 19 deletion, SUV
max
, metabolic tumor volume, and positive DL prediction independently predicted PFS. The model devised from these six prognosticators significantly predicted PFS in the analog (HR = 1.319,
p
< 0.001) and digital PET cohorts (HR = 1.284,
p
= 0.001). Our model provided incremental prognostic value to staging status (c-indices = 0.738 vs. 0.558 and 0.662 vs. 0.598 in the analog and digital PET cohorts, respectively). Our model also demonstrated a significant prognostic value for overall survival (HR = 1.198,
p
< 0.001, c-index = 0.708 and HR = 1.256,
p
= 0.021, c-index = 0.664 in the analog and digital PET cohorts, respectively).
Conclusions
Combining
18
F-FDG PET-based intensity, volumetric features, and DL with clinical variables may improve the survival stratification in patients with advanced EGFR-mutated lung adenocarcinoma receiving TKI treatment. Implementing the prediction model across different generations of PET scanners may be feasible and facilitate tailored therapeutic strategies for these patients.</abstract><cop>Singapore</cop><pub>Springer Nature Singapore</pub><doi>10.1007/s12149-024-01936-2</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-9227-0731</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0914-7187 |
| ispartof | Annals of nuclear medicine, 2024-08, Vol.38 (8), p.647-658 |
| issn | 0914-7187 1864-6433 1864-6433 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_3051423502 |
| source | Springer Nature |
| subjects | Adenocarcinoma Cancer Deep learning Epidermal growth factor receptors Growth factors Imaging Independent variables Kinases Lung cancer Lungs Medicine Medicine & Public Health Nuclear Medicine Original Article Patients Positron emission Positron emission tomography Prediction models Predictions Radiology Scanners Survival Tumors Tyrosine Tyrosine kinase inhibitors |
| title | Prognostic value of combining clinical factors, 18F-FDG PET-based intensity, volumetric features, and deep learning predictor in patients with EGFR-mutated lung adenocarcinoma undergoing targeted therapies: a cross-scanner and temporal validation study |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T17%3A37%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=Prognostic%20value%20of%20combining%20clinical%20factors,%2018F-FDG%20PET-based%20intensity,%20volumetric%20features,%20and%20deep%20learning%20predictor%20in%20patients%20with%20EGFR-mutated%20lung%20adenocarcinoma%20undergoing%20targeted%20therapies:%20a%20cross-scanner%20and%20temporal%20validation%20study&rft.jtitle=Annals%20of%20nuclear%20medicine&rft.au=Lue,%20Kun-Han&rft.date=2024-08-01&rft.volume=38&rft.issue=8&rft.spage=647&rft.epage=658&rft.pages=647-658&rft.issn=0914-7187&rft.eissn=1864-6433&rft_id=info:doi/10.1007/s12149-024-01936-2&rft_dat=%3Cproquest_cross%3E3051423502%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c233t-9c19c0e5e5d584656e99fb7a0df3cf6dbe297950e8d4026fe13bfd19b26fa27f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3085103315&rft_id=info:pmid/&rfr_iscdi=true |