Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC
Objective Tumor metabolic phenotype can be assessed with integrated image pattern analysis of 18 F-fluoro-deoxy-glucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT), called radiomics. This study was performed to assess the prognostic value of radiomics PET parameters in head and n...
Gespeichert in:
| Veröffentlicht in: | Annals of nuclear medicine 2021-03, Vol.35 (3), p.370-377 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 377 |
|---|---|
| container_issue | 3 |
| container_start_page | 370 |
| container_title | Annals of nuclear medicine |
| container_volume | 35 |
| creator | Yoon, Hyukjin Ha, Seunggyun Kwon, Soo Jin Park, Sonya Youngju Kim, Jihyun O, Joo Hyun Yoo, Ie Ryung |
| description | Objective
Tumor metabolic phenotype can be assessed with integrated image pattern analysis of
18
F-fluoro-deoxy-glucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT), called radiomics. This study was performed to assess the prognostic value of radiomics PET parameters in head and neck squamous cell carcinoma (HNSCC) patients.
Methods
18
F-fluoro-deoxy-glucose (FDG) PET/CT data of 215 patients from HNSCC collection free database in The Cancer Imaging Archive (TCIA), and 122 patients in Seoul St. Mary’s Hospital with baseline FDG PET/CT for locally advanced HNSCC were reviewed. Data from TCIA database were used as a training cohort, and data from Seoul St. Mary’s Hospital as a validation cohort. With the training cohort, primary tumors were segmented by Nestles’ adaptive thresholding method. Segmental tumors in PET images were preprocessed using relative resampling of 64 bins. Forty-two PET parameters, including conventional parameters and texture parameters, were measured. Binary groups of homogeneous imaging phenotypes, clustered by K-means method, were compared for overall survival (OS) and disease-free survival (DFS) by log-rank test. Selected individual radiomics parameters were tested along with clinical factors, including age and sex, by Cox-regression test for OS and DFS, and the significant parameters were tested with multivariate analysis. Significant parameters on multivariate analysis were again tested with multivariate analysis in the validation cohort.
Results
A total of 119 patients, 70 from training, and 49 from validation cohort, were included in the study. The median follow-up period was 62 and 52 months for the training and the validation cohort, respectively. In the training cohort. binary groups with different metabolic radiomics phenotypes showed significant difference in OS (
p
= 0.036), and borderline difference in DFS (
p
= 0.086). Gray-Level Non-Uniformity for zone (GLNU
GLZLM
) was the most significant prognostic factor for both OS (hazard ratio [HR] 3.1, 95% confidence interval [CI] 1.4–7.3,
p
= 0.008) and DFS (HR 4.5, CI 1.3–16,
p
= 0.020). Multivariate analysis revealed GLNU
GLZLM
as an independent prognostic factor for OS (HR 3.7, 95% CI 1.1–7.5,
p
= 0.032). GLNU
GLZLM
remained as an independent prognostic factor in the validation cohort (HR 14.8. 95% CI 3.3–66,
p
|
| doi_str_mv | 10.1007/s12149-021-01586-8 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmed_primary_33554314</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2492678206</sourcerecordid><originalsourceid>FETCH-LOGICAL-c465t-f79097c93676f3c64d3dd80228ebdeef5fa3718ad06a50cc55bc713b8f71f6573</originalsourceid><addsrcrecordid>eNqNkU1rFTEUhoMo9lr9Ay4k4EaQ0Xwns5SxX1DaQus6ZDLJNWUmuSYzyv33xk5toQtxEU7gPO_hPe8B4C1GnzBC8nPBBLO2QQQ3CHMlGvUMbLASrBGM0udgg1rMGomVPACvSrlFiCiuyEtwQCnnjGK2AddXOW1jKnOw8KcZFweTh_MypQwnN5s-jbURJrMNcQt3311M837nYL-Hx19P4NXRDcxmCGkKtsAQ4enFdde9Bi-8GYt7c18Pwbfjo5vutDm_PDnrvpw3lgk-N162qJW2pUIKT61gAx0GhQhRrh-c89wbWs2bAQnDkbWc91Zi2isvsRdc0kPwYZ27y-nH4sqsp1CsG0cTXVqKJkxJRurjFX3_BL1NS47VXaVaIqQiSFSKrJTNqZTsvN7lunvea4z0n8j1Grmukeu7yLWqonf3o5d-csOD5G_GFVAr8Mv1yRcbXLTuAUMICcxlvVj9IdyF2cwhxS4tca7Sj_8vrTRd6VKJuHX5ccl_-P8NuHCq9Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2492678206</pqid></control><display><type>article</type><title>Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC</title><source>MEDLINE</source><source>SpringerNature Journals</source><source>Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /></source><creator>Yoon, Hyukjin ; Ha, Seunggyun ; Kwon, Soo Jin ; Park, Sonya Youngju ; Kim, Jihyun ; O, Joo Hyun ; Yoo, Ie Ryung</creator><creatorcontrib>Yoon, Hyukjin ; Ha, Seunggyun ; Kwon, Soo Jin ; Park, Sonya Youngju ; Kim, Jihyun ; O, Joo Hyun ; Yoo, Ie Ryung</creatorcontrib><description>Objective
Tumor metabolic phenotype can be assessed with integrated image pattern analysis of
18
F-fluoro-deoxy-glucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT), called radiomics. This study was performed to assess the prognostic value of radiomics PET parameters in head and neck squamous cell carcinoma (HNSCC) patients.
Methods
18
F-fluoro-deoxy-glucose (FDG) PET/CT data of 215 patients from HNSCC collection free database in The Cancer Imaging Archive (TCIA), and 122 patients in Seoul St. Mary’s Hospital with baseline FDG PET/CT for locally advanced HNSCC were reviewed. Data from TCIA database were used as a training cohort, and data from Seoul St. Mary’s Hospital as a validation cohort. With the training cohort, primary tumors were segmented by Nestles’ adaptive thresholding method. Segmental tumors in PET images were preprocessed using relative resampling of 64 bins. Forty-two PET parameters, including conventional parameters and texture parameters, were measured. Binary groups of homogeneous imaging phenotypes, clustered by K-means method, were compared for overall survival (OS) and disease-free survival (DFS) by log-rank test. Selected individual radiomics parameters were tested along with clinical factors, including age and sex, by Cox-regression test for OS and DFS, and the significant parameters were tested with multivariate analysis. Significant parameters on multivariate analysis were again tested with multivariate analysis in the validation cohort.
Results
A total of 119 patients, 70 from training, and 49 from validation cohort, were included in the study. The median follow-up period was 62 and 52 months for the training and the validation cohort, respectively. In the training cohort. binary groups with different metabolic radiomics phenotypes showed significant difference in OS (
p
= 0.036), and borderline difference in DFS (
p
= 0.086). Gray-Level Non-Uniformity for zone (GLNU
GLZLM
) was the most significant prognostic factor for both OS (hazard ratio [HR] 3.1, 95% confidence interval [CI] 1.4–7.3,
p
= 0.008) and DFS (HR 4.5, CI 1.3–16,
p
= 0.020). Multivariate analysis revealed GLNU
GLZLM
as an independent prognostic factor for OS (HR 3.7, 95% CI 1.1–7.5,
p
= 0.032). GLNU
GLZLM
remained as an independent prognostic factor in the validation cohort (HR 14.8. 95% CI 3.3–66,
p
< 0.001).
Conclusions
Baseline FDG PET radiomics contain risk information for survival prognosis in HNSCC patients. The metabolic heterogeneity parameter, GLNU
GLZLM,
may assist clinicians in patient risk assessment as a feasible prognostic factor.</description><identifier>ISSN: 0914-7187</identifier><identifier>ISSN: 1864-6433</identifier><identifier>EISSN: 1864-6433</identifier><identifier>DOI: 10.1007/s12149-021-01586-8</identifier><identifier>PMID: 33554314</identifier><language>eng</language><publisher>Singapore: Springer Singapore</publisher><subject>Adult ; Aged ; Aged, 80 and over ; Cancer ; Computed tomography ; Confidence intervals ; Emission analysis ; Female ; Fluorine isotopes ; Fluorodeoxyglucose F18 ; Glucose ; Head & neck cancer ; Head and Neck Neoplasms - diagnostic imaging ; Head and Neck Neoplasms - metabolism ; Heterogeneity ; Humans ; Image processing ; Image Processing, Computer-Assisted ; Imaging ; Life Sciences & Biomedicine ; Male ; Medical imaging ; Medical prognosis ; Medicine ; Medicine & Public Health ; Metabolism ; Middle Aged ; Multivariate analysis ; Nonuniformity ; Nuclear Medicine ; Original Article ; Parameters ; Patients ; Pattern analysis ; Phenotype ; Phenotypes ; Positron emission ; Positron emission tomography ; Positron Emission Tomography Computed Tomography ; Prognosis ; Radiology ; Radiology, Nuclear Medicine & Medical Imaging ; Radiomics ; Rank tests ; Regression analysis ; Resampling ; Retrospective Studies ; Risk assessment ; Science & Technology ; Squamous cell carcinoma ; Squamous Cell Carcinoma of Head and Neck - diagnostic imaging ; Squamous Cell Carcinoma of Head and Neck - metabolism ; Statistical analysis ; Survival ; Tomography ; Training ; Tumors</subject><ispartof>Annals of nuclear medicine, 2021-03, Vol.35 (3), p.370-377</ispartof><rights>The Japanese Society of Nuclear Medicine 2021</rights><rights>The Japanese Society of Nuclear Medicine 2021.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>14</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000615764300001</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-c465t-f79097c93676f3c64d3dd80228ebdeef5fa3718ad06a50cc55bc713b8f71f6573</citedby><cites>FETCH-LOGICAL-c465t-f79097c93676f3c64d3dd80228ebdeef5fa3718ad06a50cc55bc713b8f71f6573</cites><orcidid>0000-0003-2016-1373</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s12149-021-01586-8$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s12149-021-01586-8$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>315,781,785,27929,27930,39263,41493,42562,51324</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33554314$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yoon, Hyukjin</creatorcontrib><creatorcontrib>Ha, Seunggyun</creatorcontrib><creatorcontrib>Kwon, Soo Jin</creatorcontrib><creatorcontrib>Park, Sonya Youngju</creatorcontrib><creatorcontrib>Kim, Jihyun</creatorcontrib><creatorcontrib>O, Joo Hyun</creatorcontrib><creatorcontrib>Yoo, Ie Ryung</creatorcontrib><title>Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC</title><title>Annals of nuclear medicine</title><addtitle>Ann Nucl Med</addtitle><addtitle>ANN NUCL MED</addtitle><addtitle>Ann Nucl Med</addtitle><description>Objective
Tumor metabolic phenotype can be assessed with integrated image pattern analysis of
18
F-fluoro-deoxy-glucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT), called radiomics. This study was performed to assess the prognostic value of radiomics PET parameters in head and neck squamous cell carcinoma (HNSCC) patients.
Methods
18
F-fluoro-deoxy-glucose (FDG) PET/CT data of 215 patients from HNSCC collection free database in The Cancer Imaging Archive (TCIA), and 122 patients in Seoul St. Mary’s Hospital with baseline FDG PET/CT for locally advanced HNSCC were reviewed. Data from TCIA database were used as a training cohort, and data from Seoul St. Mary’s Hospital as a validation cohort. With the training cohort, primary tumors were segmented by Nestles’ adaptive thresholding method. Segmental tumors in PET images were preprocessed using relative resampling of 64 bins. Forty-two PET parameters, including conventional parameters and texture parameters, were measured. Binary groups of homogeneous imaging phenotypes, clustered by K-means method, were compared for overall survival (OS) and disease-free survival (DFS) by log-rank test. Selected individual radiomics parameters were tested along with clinical factors, including age and sex, by Cox-regression test for OS and DFS, and the significant parameters were tested with multivariate analysis. Significant parameters on multivariate analysis were again tested with multivariate analysis in the validation cohort.
Results
A total of 119 patients, 70 from training, and 49 from validation cohort, were included in the study. The median follow-up period was 62 and 52 months for the training and the validation cohort, respectively. In the training cohort. binary groups with different metabolic radiomics phenotypes showed significant difference in OS (
p
= 0.036), and borderline difference in DFS (
p
= 0.086). Gray-Level Non-Uniformity for zone (GLNU
GLZLM
) was the most significant prognostic factor for both OS (hazard ratio [HR] 3.1, 95% confidence interval [CI] 1.4–7.3,
p
= 0.008) and DFS (HR 4.5, CI 1.3–16,
p
= 0.020). Multivariate analysis revealed GLNU
GLZLM
as an independent prognostic factor for OS (HR 3.7, 95% CI 1.1–7.5,
p
= 0.032). GLNU
GLZLM
remained as an independent prognostic factor in the validation cohort (HR 14.8. 95% CI 3.3–66,
p
< 0.001).
Conclusions
Baseline FDG PET radiomics contain risk information for survival prognosis in HNSCC patients. The metabolic heterogeneity parameter, GLNU
GLZLM,
may assist clinicians in patient risk assessment as a feasible prognostic factor.</description><subject>Adult</subject><subject>Aged</subject><subject>Aged, 80 and over</subject><subject>Cancer</subject><subject>Computed tomography</subject><subject>Confidence intervals</subject><subject>Emission analysis</subject><subject>Female</subject><subject>Fluorine isotopes</subject><subject>Fluorodeoxyglucose F18</subject><subject>Glucose</subject><subject>Head & neck cancer</subject><subject>Head and Neck Neoplasms - diagnostic imaging</subject><subject>Head and Neck Neoplasms - metabolism</subject><subject>Heterogeneity</subject><subject>Humans</subject><subject>Image processing</subject><subject>Image Processing, Computer-Assisted</subject><subject>Imaging</subject><subject>Life Sciences & Biomedicine</subject><subject>Male</subject><subject>Medical imaging</subject><subject>Medical prognosis</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Metabolism</subject><subject>Middle Aged</subject><subject>Multivariate analysis</subject><subject>Nonuniformity</subject><subject>Nuclear Medicine</subject><subject>Original Article</subject><subject>Parameters</subject><subject>Patients</subject><subject>Pattern analysis</subject><subject>Phenotype</subject><subject>Phenotypes</subject><subject>Positron emission</subject><subject>Positron emission tomography</subject><subject>Positron Emission Tomography Computed Tomography</subject><subject>Prognosis</subject><subject>Radiology</subject><subject>Radiology, Nuclear Medicine & Medical Imaging</subject><subject>Radiomics</subject><subject>Rank tests</subject><subject>Regression analysis</subject><subject>Resampling</subject><subject>Retrospective Studies</subject><subject>Risk assessment</subject><subject>Science & Technology</subject><subject>Squamous cell carcinoma</subject><subject>Squamous Cell Carcinoma of Head and Neck - diagnostic imaging</subject><subject>Squamous Cell Carcinoma of Head and Neck - metabolism</subject><subject>Statistical analysis</subject><subject>Survival</subject><subject>Tomography</subject><subject>Training</subject><subject>Tumors</subject><issn>0914-7187</issn><issn>1864-6433</issn><issn>1864-6433</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>HGBXW</sourceid><sourceid>EIF</sourceid><recordid>eNqNkU1rFTEUhoMo9lr9Ay4k4EaQ0Xwns5SxX1DaQus6ZDLJNWUmuSYzyv33xk5toQtxEU7gPO_hPe8B4C1GnzBC8nPBBLO2QQQ3CHMlGvUMbLASrBGM0udgg1rMGomVPACvSrlFiCiuyEtwQCnnjGK2AddXOW1jKnOw8KcZFweTh_MypQwnN5s-jbURJrMNcQt3311M837nYL-Hx19P4NXRDcxmCGkKtsAQ4enFdde9Bi-8GYt7c18Pwbfjo5vutDm_PDnrvpw3lgk-N162qJW2pUIKT61gAx0GhQhRrh-c89wbWs2bAQnDkbWc91Zi2isvsRdc0kPwYZ27y-nH4sqsp1CsG0cTXVqKJkxJRurjFX3_BL1NS47VXaVaIqQiSFSKrJTNqZTsvN7lunvea4z0n8j1Grmukeu7yLWqonf3o5d-csOD5G_GFVAr8Mv1yRcbXLTuAUMICcxlvVj9IdyF2cwhxS4tca7Sj_8vrTRd6VKJuHX5ccl_-P8NuHCq9Q</recordid><startdate>20210301</startdate><enddate>20210301</enddate><creator>Yoon, Hyukjin</creator><creator>Ha, Seunggyun</creator><creator>Kwon, Soo Jin</creator><creator>Park, Sonya Youngju</creator><creator>Kim, Jihyun</creator><creator>O, Joo Hyun</creator><creator>Yoo, Ie Ryung</creator><general>Springer Singapore</general><general>Springer Nature</general><general>Springer Nature B.V</general><scope>BLEPL</scope><scope>DTL</scope><scope>HGBXW</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><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/0000-0003-2016-1373</orcidid></search><sort><creationdate>20210301</creationdate><title>Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC</title><author>Yoon, Hyukjin ; Ha, Seunggyun ; Kwon, Soo Jin ; Park, Sonya Youngju ; Kim, Jihyun ; O, Joo Hyun ; Yoo, Ie Ryung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c465t-f79097c93676f3c64d3dd80228ebdeef5fa3718ad06a50cc55bc713b8f71f6573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Aged, 80 and over</topic><topic>Cancer</topic><topic>Computed tomography</topic><topic>Confidence intervals</topic><topic>Emission analysis</topic><topic>Female</topic><topic>Fluorine isotopes</topic><topic>Fluorodeoxyglucose F18</topic><topic>Glucose</topic><topic>Head & neck cancer</topic><topic>Head and Neck Neoplasms - diagnostic imaging</topic><topic>Head and Neck Neoplasms - metabolism</topic><topic>Heterogeneity</topic><topic>Humans</topic><topic>Image processing</topic><topic>Image Processing, Computer-Assisted</topic><topic>Imaging</topic><topic>Life Sciences & Biomedicine</topic><topic>Male</topic><topic>Medical imaging</topic><topic>Medical prognosis</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Metabolism</topic><topic>Middle Aged</topic><topic>Multivariate analysis</topic><topic>Nonuniformity</topic><topic>Nuclear Medicine</topic><topic>Original Article</topic><topic>Parameters</topic><topic>Patients</topic><topic>Pattern analysis</topic><topic>Phenotype</topic><topic>Phenotypes</topic><topic>Positron emission</topic><topic>Positron emission tomography</topic><topic>Positron Emission Tomography Computed Tomography</topic><topic>Prognosis</topic><topic>Radiology</topic><topic>Radiology, Nuclear Medicine & Medical Imaging</topic><topic>Radiomics</topic><topic>Rank tests</topic><topic>Regression analysis</topic><topic>Resampling</topic><topic>Retrospective Studies</topic><topic>Risk assessment</topic><topic>Science & Technology</topic><topic>Squamous cell carcinoma</topic><topic>Squamous Cell Carcinoma of Head and Neck - diagnostic imaging</topic><topic>Squamous Cell Carcinoma of Head and Neck - metabolism</topic><topic>Statistical analysis</topic><topic>Survival</topic><topic>Tomography</topic><topic>Training</topic><topic>Tumors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yoon, Hyukjin</creatorcontrib><creatorcontrib>Ha, Seunggyun</creatorcontrib><creatorcontrib>Kwon, Soo Jin</creatorcontrib><creatorcontrib>Park, Sonya Youngju</creatorcontrib><creatorcontrib>Kim, Jihyun</creatorcontrib><creatorcontrib>O, Joo Hyun</creatorcontrib><creatorcontrib>Yoo, Ie Ryung</creatorcontrib><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>Web of Science - Science Citation Index Expanded - 2021</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><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>Yoon, Hyukjin</au><au>Ha, Seunggyun</au><au>Kwon, Soo Jin</au><au>Park, Sonya Youngju</au><au>Kim, Jihyun</au><au>O, Joo Hyun</au><au>Yoo, Ie Ryung</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC</atitle><jtitle>Annals of nuclear medicine</jtitle><stitle>Ann Nucl Med</stitle><stitle>ANN NUCL MED</stitle><addtitle>Ann Nucl Med</addtitle><date>2021-03-01</date><risdate>2021</risdate><volume>35</volume><issue>3</issue><spage>370</spage><epage>377</epage><pages>370-377</pages><issn>0914-7187</issn><issn>1864-6433</issn><eissn>1864-6433</eissn><abstract>Objective
Tumor metabolic phenotype can be assessed with integrated image pattern analysis of
18
F-fluoro-deoxy-glucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT), called radiomics. This study was performed to assess the prognostic value of radiomics PET parameters in head and neck squamous cell carcinoma (HNSCC) patients.
Methods
18
F-fluoro-deoxy-glucose (FDG) PET/CT data of 215 patients from HNSCC collection free database in The Cancer Imaging Archive (TCIA), and 122 patients in Seoul St. Mary’s Hospital with baseline FDG PET/CT for locally advanced HNSCC were reviewed. Data from TCIA database were used as a training cohort, and data from Seoul St. Mary’s Hospital as a validation cohort. With the training cohort, primary tumors were segmented by Nestles’ adaptive thresholding method. Segmental tumors in PET images were preprocessed using relative resampling of 64 bins. Forty-two PET parameters, including conventional parameters and texture parameters, were measured. Binary groups of homogeneous imaging phenotypes, clustered by K-means method, were compared for overall survival (OS) and disease-free survival (DFS) by log-rank test. Selected individual radiomics parameters were tested along with clinical factors, including age and sex, by Cox-regression test for OS and DFS, and the significant parameters were tested with multivariate analysis. Significant parameters on multivariate analysis were again tested with multivariate analysis in the validation cohort.
Results
A total of 119 patients, 70 from training, and 49 from validation cohort, were included in the study. The median follow-up period was 62 and 52 months for the training and the validation cohort, respectively. In the training cohort. binary groups with different metabolic radiomics phenotypes showed significant difference in OS (
p
= 0.036), and borderline difference in DFS (
p
= 0.086). Gray-Level Non-Uniformity for zone (GLNU
GLZLM
) was the most significant prognostic factor for both OS (hazard ratio [HR] 3.1, 95% confidence interval [CI] 1.4–7.3,
p
= 0.008) and DFS (HR 4.5, CI 1.3–16,
p
= 0.020). Multivariate analysis revealed GLNU
GLZLM
as an independent prognostic factor for OS (HR 3.7, 95% CI 1.1–7.5,
p
= 0.032). GLNU
GLZLM
remained as an independent prognostic factor in the validation cohort (HR 14.8. 95% CI 3.3–66,
p
< 0.001).
Conclusions
Baseline FDG PET radiomics contain risk information for survival prognosis in HNSCC patients. The metabolic heterogeneity parameter, GLNU
GLZLM,
may assist clinicians in patient risk assessment as a feasible prognostic factor.</abstract><cop>Singapore</cop><pub>Springer Singapore</pub><pmid>33554314</pmid><doi>10.1007/s12149-021-01586-8</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0003-2016-1373</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0914-7187 |
| ispartof | Annals of nuclear medicine, 2021-03, Vol.35 (3), p.370-377 |
| issn | 0914-7187 1864-6433 1864-6433 |
| language | eng |
| recordid | cdi_pubmed_primary_33554314 |
| source | MEDLINE; SpringerNature Journals; Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /> |
| subjects | Adult Aged Aged, 80 and over Cancer Computed tomography Confidence intervals Emission analysis Female Fluorine isotopes Fluorodeoxyglucose F18 Glucose Head & neck cancer Head and Neck Neoplasms - diagnostic imaging Head and Neck Neoplasms - metabolism Heterogeneity Humans Image processing Image Processing, Computer-Assisted Imaging Life Sciences & Biomedicine Male Medical imaging Medical prognosis Medicine Medicine & Public Health Metabolism Middle Aged Multivariate analysis Nonuniformity Nuclear Medicine Original Article Parameters Patients Pattern analysis Phenotype Phenotypes Positron emission Positron emission tomography Positron Emission Tomography Computed Tomography Prognosis Radiology Radiology, Nuclear Medicine & Medical Imaging Radiomics Rank tests Regression analysis Resampling Retrospective Studies Risk assessment Science & Technology Squamous cell carcinoma Squamous Cell Carcinoma of Head and Neck - diagnostic imaging Squamous Cell Carcinoma of Head and Neck - metabolism Statistical analysis Survival Tomography Training Tumors |
| title | Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-12T10%3A00%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prognostic%20value%20of%20tumor%20metabolic%20imaging%20phenotype%20by%20FDG%20PET%20radiomics%20in%20HNSCC&rft.jtitle=Annals%20of%20nuclear%20medicine&rft.au=Yoon,%20Hyukjin&rft.date=2021-03-01&rft.volume=35&rft.issue=3&rft.spage=370&rft.epage=377&rft.pages=370-377&rft.issn=0914-7187&rft.eissn=1864-6433&rft_id=info:doi/10.1007/s12149-021-01586-8&rft_dat=%3Cproquest_pubme%3E2492678206%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2492678206&rft_id=info:pmid/33554314&rfr_iscdi=true |