Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscle
Abstract This retrospective study developed an automated algorithm for 3D segmentation of adipose tissue and paravertebral muscle on chest CT using artificial intelligence (AI) and assessed its feasibility. The study included patients from the Boston Lung Cancer Study (2000–2011). For adipose tissue...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83897-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559521580810240 |
|---|---|
| author | Akinori Hata Yohei Muraguchi Minoru Nakatsugawa Xinan Wang Jiyeon Song Noriaki Wada Takuya Hino Kota Aoyagi Masami Kawagishi Takuo Negishi Vladimir I. Valtchinov Mizuki Nishino Akihiro Koga Naoki Sugihara Masahiro Ozaki Gary M. Hunninghake Noriyuki Tomiyama Mark L. Schiebler Yi Li David C. Christiani Hiroto Hatabu |
| author_facet | Akinori Hata Yohei Muraguchi Minoru Nakatsugawa Xinan Wang Jiyeon Song Noriaki Wada Takuya Hino Kota Aoyagi Masami Kawagishi Takuo Negishi Vladimir I. Valtchinov Mizuki Nishino Akihiro Koga Naoki Sugihara Masahiro Ozaki Gary M. Hunninghake Noriyuki Tomiyama Mark L. Schiebler Yi Li David C. Christiani Hiroto Hatabu |
| author_sort | Akinori Hata |
| collection | DOAJ |
| description | Abstract This retrospective study developed an automated algorithm for 3D segmentation of adipose tissue and paravertebral muscle on chest CT using artificial intelligence (AI) and assessed its feasibility. The study included patients from the Boston Lung Cancer Study (2000–2011). For adipose tissue quantification, 77 patients were included, while 245 were used for muscle quantification. The data were split into training and test sets, with manual segmentation as the ground truth. Subcutaneous and visceral adipose tissues (SAT and VAT) were segmented separately. Muscle area, mean attenuation value, and intermuscular adipose tissue percentage (IMAT%) were calculated in the paravertebral muscle segmentation. The AI algorithm was trained on the training sets, and its performance was evaluated on the test sets. The AI achieved Dice scores above 0.87 and showed excellent correlations for VAT/SAT ratios, muscle attenuation value, and IMAT% (correlation coefficients > 0.98, p < 0.001). The mean differences between the AI and ground truth were minimal (VAT/SAT ratio: 0.7%; muscle attenuation value: 1 HU; IMAT%: <1%). In conclusion, we developed a feasible AI algorithm for automated 3D segmentation of adipose tissue and paravertebral muscle on chest CT. |
| format | Article |
| id | doaj-art-d71cd7d182134b1c9cd52ec0b46a12f2 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-d71cd7d182134b1c9cd52ec0b46a12f22025-01-05T12:26:00ZengNature PortfolioScientific Reports2045-23222024-12-011411910.1038/s41598-024-83897-0Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscleAkinori Hata0Yohei Muraguchi1Minoru Nakatsugawa2Xinan Wang3Jiyeon Song4Noriaki Wada5Takuya Hino6Kota Aoyagi7Masami Kawagishi8Takuo Negishi9Vladimir I. Valtchinov10Mizuki Nishino11Akihiro Koga12Naoki Sugihara13Masahiro Ozaki14Gary M. Hunninghake15Noriyuki Tomiyama16Mark L. Schiebler17Yi Li18David C. Christiani19Hiroto Hatabu20Department of Radiology, Center for Pulmonary Functional Imaging, Brigham and Women’s Hospital and Harvard Medical SchoolCanon Medical Systems CorporationCanon Medical Systems CorporationDepartment of Biostatistics, Harvard TH Chan School of Public HealthDepartment of Biostatistics, University of MichiganDepartment of Radiology, Center for Pulmonary Functional Imaging, Brigham and Women’s Hospital and Harvard Medical SchoolDepartment of Radiology, Center for Pulmonary Functional Imaging, Brigham and Women’s Hospital and Harvard Medical SchoolCanon Medical Systems CorporationR&D Headquarters, Canon Inc.Canon Medical Systems CorporationDepartment of Radiology, Center for Pulmonary Functional Imaging, Brigham and Women’s Hospital and Harvard Medical SchoolDepartment of Radiology, Center for Pulmonary Functional Imaging, Brigham and Women’s Hospital and Harvard Medical SchoolCanon Medical Systems CorporationCanon Medical Systems CorporationCanon Medical Systems CorporationPulmonary and Critical Care Division, Brigham and Women’s Hospital and Harvard Medical SchoolDiagnostic and Interventional Radiology, Osaka University Graduate School of MedicineDepartment of Radiology, UW Madison School of Medicine and Public HealthDepartment of Biostatistics, University of MichiganDepartment of Biostatistics, Harvard TH Chan School of Public HealthDepartment of Radiology, Center for Pulmonary Functional Imaging, Brigham and Women’s Hospital and Harvard Medical SchoolAbstract This retrospective study developed an automated algorithm for 3D segmentation of adipose tissue and paravertebral muscle on chest CT using artificial intelligence (AI) and assessed its feasibility. The study included patients from the Boston Lung Cancer Study (2000–2011). For adipose tissue quantification, 77 patients were included, while 245 were used for muscle quantification. The data were split into training and test sets, with manual segmentation as the ground truth. Subcutaneous and visceral adipose tissues (SAT and VAT) were segmented separately. Muscle area, mean attenuation value, and intermuscular adipose tissue percentage (IMAT%) were calculated in the paravertebral muscle segmentation. The AI algorithm was trained on the training sets, and its performance was evaluated on the test sets. The AI achieved Dice scores above 0.87 and showed excellent correlations for VAT/SAT ratios, muscle attenuation value, and IMAT% (correlation coefficients > 0.98, p < 0.001). The mean differences between the AI and ground truth were minimal (VAT/SAT ratio: 0.7%; muscle attenuation value: 1 HU; IMAT%: <1%). In conclusion, we developed a feasible AI algorithm for automated 3D segmentation of adipose tissue and paravertebral muscle on chest CT.https://doi.org/10.1038/s41598-024-83897-0ThoraxAdipose tissueSarcopeniaTomographyX-ray computedArtificial intelligence |
| spellingShingle | Akinori Hata Yohei Muraguchi Minoru Nakatsugawa Xinan Wang Jiyeon Song Noriaki Wada Takuya Hino Kota Aoyagi Masami Kawagishi Takuo Negishi Vladimir I. Valtchinov Mizuki Nishino Akihiro Koga Naoki Sugihara Masahiro Ozaki Gary M. Hunninghake Noriyuki Tomiyama Mark L. Schiebler Yi Li David C. Christiani Hiroto Hatabu Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscle Scientific Reports Thorax Adipose tissue Sarcopenia Tomography X-ray computed Artificial intelligence |
| title | Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscle |
| title_full | Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscle |
| title_fullStr | Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscle |
| title_full_unstemmed | Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscle |
| title_short | Automated chest CT three-dimensional quantification of body composition: adipose tissue and paravertebral muscle |
| title_sort | automated chest ct three dimensional quantification of body composition adipose tissue and paravertebral muscle |
| topic | Thorax Adipose tissue Sarcopenia Tomography X-ray computed Artificial intelligence |
| url | https://doi.org/10.1038/s41598-024-83897-0 |
| work_keys_str_mv | AT akinorihata automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT yoheimuraguchi automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT minorunakatsugawa automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT xinanwang automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT jiyeonsong automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT noriakiwada automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT takuyahino automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT kotaaoyagi automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT masamikawagishi automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT takuonegishi automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT vladimirivaltchinov automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT mizukinishino automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT akihirokoga automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT naokisugihara automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT masahiroozaki automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT garymhunninghake automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT noriyukitomiyama automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT marklschiebler automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT yili automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT davidcchristiani automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle AT hirotohatabu automatedchestctthreedimensionalquantificationofbodycompositionadiposetissueandparavertebralmuscle |