Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning
Abstract In this retrospective study, we aimed to predict the body height and weight of pediatric patients using CT localizers, which are overview scans performed before the acquisition of the CT. We trained three commonly used networks (EfficientNetV2-S, ResNet-18, and ResNet-34) on a cohort of 100...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-46080-5 |
| _version_ | 1797636894733893632 |
|---|---|
| author | Aydin Demircioğlu Anton S. Quinsten Lale Umutlu Michael Forsting Kai Nassenstein Denise Bos |
| author_facet | Aydin Demircioğlu Anton S. Quinsten Lale Umutlu Michael Forsting Kai Nassenstein Denise Bos |
| author_sort | Aydin Demircioğlu |
| collection | DOAJ |
| description | Abstract In this retrospective study, we aimed to predict the body height and weight of pediatric patients using CT localizers, which are overview scans performed before the acquisition of the CT. We trained three commonly used networks (EfficientNetV2-S, ResNet-18, and ResNet-34) on a cohort of 1009 and 1111 CT localizers of pediatric patients with recorded body height and weight (between January 2013 and December 2019) and validated them in an additional cohort of 116 and 127 localizers (acquired in 2020). The best-performing model was then tested in an independent cohort of 203 and 225 CT localizers (acquired between January 2021 and March 2023). In addition, a cohort of 1401 and 1590 localizers from younger adults (acquired between January 2013 and December 2013) was added to the training set to determine if it could improve the overall accuracy. The EfficientNetV2-S using the additional adult cohort performed best with a mean absolute error of 5.58 ± 4.26 cm for height and 4.25 ± 4.28 kg for weight. The relative error was 4.12 ± 4.05% for height and 11.28 ± 12.05% for weight. Our study demonstrated that automated estimation of height and weight in pediatric patients from CT localizers can be performed. |
| first_indexed | 2024-03-11T12:40:38Z |
| format | Article |
| id | doaj.art-61087b62a0ca4cd2a44939578ad1b3e7 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-11T12:40:38Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-61087b62a0ca4cd2a44939578ad1b3e72023-11-05T12:17:51ZengNature PortfolioScientific Reports2045-23222023-11-011311910.1038/s41598-023-46080-5Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learningAydin Demircioğlu0Anton S. Quinsten1Lale Umutlu2Michael Forsting3Kai Nassenstein4Denise Bos5Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenAbstract In this retrospective study, we aimed to predict the body height and weight of pediatric patients using CT localizers, which are overview scans performed before the acquisition of the CT. We trained three commonly used networks (EfficientNetV2-S, ResNet-18, and ResNet-34) on a cohort of 1009 and 1111 CT localizers of pediatric patients with recorded body height and weight (between January 2013 and December 2019) and validated them in an additional cohort of 116 and 127 localizers (acquired in 2020). The best-performing model was then tested in an independent cohort of 203 and 225 CT localizers (acquired between January 2021 and March 2023). In addition, a cohort of 1401 and 1590 localizers from younger adults (acquired between January 2013 and December 2013) was added to the training set to determine if it could improve the overall accuracy. The EfficientNetV2-S using the additional adult cohort performed best with a mean absolute error of 5.58 ± 4.26 cm for height and 4.25 ± 4.28 kg for weight. The relative error was 4.12 ± 4.05% for height and 11.28 ± 12.05% for weight. Our study demonstrated that automated estimation of height and weight in pediatric patients from CT localizers can be performed.https://doi.org/10.1038/s41598-023-46080-5 |
| spellingShingle | Aydin Demircioğlu Anton S. Quinsten Lale Umutlu Michael Forsting Kai Nassenstein Denise Bos Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning Scientific Reports |
| title | Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning |
| title_full | Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning |
| title_fullStr | Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning |
| title_full_unstemmed | Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning |
| title_short | Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning |
| title_sort | determining body height and weight from thoracic and abdominal ct localizers in pediatric and young adult patients using deep learning |
| url | https://doi.org/10.1038/s41598-023-46080-5 |
| work_keys_str_mv | AT aydindemircioglu determiningbodyheightandweightfromthoracicandabdominalctlocalizersinpediatricandyoungadultpatientsusingdeeplearning AT antonsquinsten determiningbodyheightandweightfromthoracicandabdominalctlocalizersinpediatricandyoungadultpatientsusingdeeplearning AT laleumutlu determiningbodyheightandweightfromthoracicandabdominalctlocalizersinpediatricandyoungadultpatientsusingdeeplearning AT michaelforsting determiningbodyheightandweightfromthoracicandabdominalctlocalizersinpediatricandyoungadultpatientsusingdeeplearning AT kainassenstein determiningbodyheightandweightfromthoracicandabdominalctlocalizersinpediatricandyoungadultpatientsusingdeeplearning AT denisebos determiningbodyheightandweightfromthoracicandabdominalctlocalizersinpediatricandyoungadultpatientsusingdeeplearning |