Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors
Previous studies suggest an impact of body composition on outcome in melanoma patients. We aimed to determine the prognostic value of CT-based body composition assessment in patients receiving immune checkpoint inhibitor therapy for treatment of metastatic disease using a deep learning approach. One...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/12/2314 |
| _version_ | 1797505442584199168 |
|---|---|
| author | Anton Faron Nikola S. Opheys Sebastian Nowak Alois M. Sprinkart Alexander Isaak Maike Theis Narine Mesropyan Christoph Endler Judith Sirokay Claus C. Pieper Daniel Kuetting Ulrike Attenberger Jennifer Landsberg Julian A. Luetkens |
| author_facet | Anton Faron Nikola S. Opheys Sebastian Nowak Alois M. Sprinkart Alexander Isaak Maike Theis Narine Mesropyan Christoph Endler Judith Sirokay Claus C. Pieper Daniel Kuetting Ulrike Attenberger Jennifer Landsberg Julian A. Luetkens |
| author_sort | Anton Faron |
| collection | DOAJ |
| description | Previous studies suggest an impact of body composition on outcome in melanoma patients. We aimed to determine the prognostic value of CT-based body composition assessment in patients receiving immune checkpoint inhibitor therapy for treatment of metastatic disease using a deep learning approach. One hundred seven patients with staging CT examinations prior to initiation of checkpoint inhibition between January 2013 and August 2019 were retrospectively evaluated. Using an automated deep learning-based body composition analysis pipeline, parameters for estimation of skeletal muscle mass (skeletal muscle index, SMI) and adipose tissue compartments (visceral adipose tissue index, VAI; subcutaneous adipose tissue index, SAI) were derived from staging CT. The cohort was binarized according to gender-specific median cut-off values. Patients below the median were defined as having low SMI, VAI, or SAI, respectively. The impact on outcome was assessed using the Kaplan–Meier method with log-rank tests. A multivariable logistic regression model was built to test the impact of body composition parameters on 3-year mortality. Patients with low SMI displayed significantly increased 1-year (25% versus 9%, <i>p</i> = 0.035), 2-year (32% versus 13%, <i>p</i> = 0.017), and 3-year mortality (38% versus 19%, <i>p</i> = 0.016). No significant differences with regard to adipose tissue compartments were observed (3-year mortality: VAI, <i>p</i> = 0.448; SAI, <i>p</i> = 0.731). On multivariable analysis, low SMI (hazard ratio (HR), 2.245; 95% confidence interval (CI), 1.005–5.017; <i>p</i> = 0.049), neutrophil-to-lymphocyte ratio (HR, 1.170; 95% CI, 1.076–1.273; <i>p</i> < 0.001), and Karnofsky index (HR, 0.965; 95% CI, 0.945–0.985; <i>p</i> = 0.001) remained as significant predictors of 3-year mortality. Lowered skeletal muscle index as an indicator of sarcopenia was associated with worse outcome in patients with metastatic melanoma receiving immune checkpoint inhibitor therapy. |
| first_indexed | 2024-03-10T04:18:38Z |
| format | Article |
| id | doaj.art-17eb8392ae27462193ac446d3e14242b |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T04:18:38Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-17eb8392ae27462193ac446d3e14242b2023-11-23T07:54:22ZengMDPI AGDiagnostics2075-44182021-12-011112231410.3390/diagnostics11122314Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint InhibitorsAnton Faron0Nikola S. Opheys1Sebastian Nowak2Alois M. Sprinkart3Alexander Isaak4Maike Theis5Narine Mesropyan6Christoph Endler7Judith Sirokay8Claus C. Pieper9Daniel Kuetting10Ulrike Attenberger11Jennifer Landsberg12Julian A. Luetkens13Department of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyCenter of Integrated Oncology (CIO) Bonn, Department of Dermatology and Allergy, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyCenter of Integrated Oncology (CIO) Bonn, Department of Dermatology and Allergy, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyDepartment of Diagnostics and Interventional Radiology, Venusberg Campus 1, University Hospital Bonn, 53127 Bonn, GermanyPrevious studies suggest an impact of body composition on outcome in melanoma patients. We aimed to determine the prognostic value of CT-based body composition assessment in patients receiving immune checkpoint inhibitor therapy for treatment of metastatic disease using a deep learning approach. One hundred seven patients with staging CT examinations prior to initiation of checkpoint inhibition between January 2013 and August 2019 were retrospectively evaluated. Using an automated deep learning-based body composition analysis pipeline, parameters for estimation of skeletal muscle mass (skeletal muscle index, SMI) and adipose tissue compartments (visceral adipose tissue index, VAI; subcutaneous adipose tissue index, SAI) were derived from staging CT. The cohort was binarized according to gender-specific median cut-off values. Patients below the median were defined as having low SMI, VAI, or SAI, respectively. The impact on outcome was assessed using the Kaplan–Meier method with log-rank tests. A multivariable logistic regression model was built to test the impact of body composition parameters on 3-year mortality. Patients with low SMI displayed significantly increased 1-year (25% versus 9%, <i>p</i> = 0.035), 2-year (32% versus 13%, <i>p</i> = 0.017), and 3-year mortality (38% versus 19%, <i>p</i> = 0.016). No significant differences with regard to adipose tissue compartments were observed (3-year mortality: VAI, <i>p</i> = 0.448; SAI, <i>p</i> = 0.731). On multivariable analysis, low SMI (hazard ratio (HR), 2.245; 95% confidence interval (CI), 1.005–5.017; <i>p</i> = 0.049), neutrophil-to-lymphocyte ratio (HR, 1.170; 95% CI, 1.076–1.273; <i>p</i> < 0.001), and Karnofsky index (HR, 0.965; 95% CI, 0.945–0.985; <i>p</i> = 0.001) remained as significant predictors of 3-year mortality. Lowered skeletal muscle index as an indicator of sarcopenia was associated with worse outcome in patients with metastatic melanoma receiving immune checkpoint inhibitor therapy.https://www.mdpi.com/2075-4418/11/12/2314oncologic imagingCTimaging biomarkerssarcopeniaartificial intelligence |
| spellingShingle | Anton Faron Nikola S. Opheys Sebastian Nowak Alois M. Sprinkart Alexander Isaak Maike Theis Narine Mesropyan Christoph Endler Judith Sirokay Claus C. Pieper Daniel Kuetting Ulrike Attenberger Jennifer Landsberg Julian A. Luetkens Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors Diagnostics oncologic imaging CT imaging biomarkers sarcopenia artificial intelligence |
| title | Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors |
| title_full | Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors |
| title_fullStr | Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors |
| title_full_unstemmed | Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors |
| title_short | Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors |
| title_sort | deep learning based body composition analysis predicts outcome in melanoma patients treated with immune checkpoint inhibitors |
| topic | oncologic imaging CT imaging biomarkers sarcopenia artificial intelligence |
| url | https://www.mdpi.com/2075-4418/11/12/2314 |
| work_keys_str_mv | AT antonfaron deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT nikolasopheys deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT sebastiannowak deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT aloismsprinkart deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT alexanderisaak deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT maiketheis deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT narinemesropyan deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT christophendler deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT judithsirokay deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT clauscpieper deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT danielkuetting deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT ulrikeattenberger deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT jenniferlandsberg deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors AT julianaluetkens deeplearningbasedbodycompositionanalysispredictsoutcomeinmelanomapatientstreatedwithimmunecheckpointinhibitors |