CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scans
Abstract Background Body composition scores allow for quantifying the volume and physical properties of specific tissues. However, their manual calculation is time-consuming and prone to human error. This study aims to develop and validate CompositIA, an automated, open-source pipeline for quantifyi...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-025-00552-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572016635412480 |
|---|---|
| author | Raffaella Fiamma Cabini Andrea Cozzi Svenja Leu Benedikt Thelen Rolf Krause Filippo Del Grande Diego Ulisse Pizzagalli Stefania Maria Rita Rizzo |
| author_facet | Raffaella Fiamma Cabini Andrea Cozzi Svenja Leu Benedikt Thelen Rolf Krause Filippo Del Grande Diego Ulisse Pizzagalli Stefania Maria Rita Rizzo |
| author_sort | Raffaella Fiamma Cabini |
| collection | DOAJ |
| description | Abstract Background Body composition scores allow for quantifying the volume and physical properties of specific tissues. However, their manual calculation is time-consuming and prone to human error. This study aims to develop and validate CompositIA, an automated, open-source pipeline for quantifying body composition scores from thoraco-abdominal computed tomography (CT) scans. Methods A retrospective dataset of 205 contrast-enhanced thoraco-abdominal CT examinations was used for training, while 54 scans from a publicly available dataset were used for independent testing. Two radiology residents performed manual segmentation, identifying the centers of the L1 and L3 vertebrae and segmenting the corresponding axial slices. MultiResUNet was used to identify CT slices intersecting the L1 and L3 vertebrae, and its performance was evaluated using the mean absolute error (MAE). Two U-nets were used to segment the axial slices, with performance evaluated through the volumetric Dice similarity coefficient (vDSC). CompositIA’s performance in quantifying body composition indices was assessed using mean percentage relative error (PRE), regression, and Bland–Altman analyses. Results On the independent dataset, CompositIA achieved a MAE of about 5 mm in detecting slices intersecting the L1 and L3 vertebrae, with a MAE < 10 mm in at least 85% of cases and a vDSC greater than 0.85 in segmenting axial slices. Regression and Bland–Altman analyses demonstrated a strong linear relationship and good agreement between automated and manual scores (p values < 0.001 for all indices), with mean PREs ranging from 5.13% to 15.18%. Conclusion CompositIA facilitated the automated quantification of body composition scores, achieving high precision in independent testing. Relevance statement CompositIA is an automated, open-source pipeline for quantifying body composition indices from CT scans, simplifying clinical assessments, and expanding their applicability. Key Points Manual body composition assessment from CTs is time-consuming and prone to errors. CompositIA was trained on 205 CT scans and tested on 54 scans. CompositIA demonstrated mean percentage relative errors under 15% compared to manual indices. CompositIA simplifies body composition assessment through an artificial intelligence-driven and open-source pipeline. Graphical Abstract |
| format | Article |
| id | doaj-art-91afa32e9124472eaadba12c07b95d4b |
| institution | Kabale University |
| issn | 2509-9280 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj-art-91afa32e9124472eaadba12c07b95d4b2025-02-02T12:07:54ZengSpringerOpenEuropean Radiology Experimental2509-92802025-01-019111210.1186/s41747-025-00552-7CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scansRaffaella Fiamma Cabini0Andrea Cozzi1Svenja Leu2Benedikt Thelen3Rolf Krause4Filippo Del Grande5Diego Ulisse Pizzagalli6Stefania Maria Rita Rizzo7Euler Institute, Università della Svizzera italianaImaging Institute of Southern Switzerland, Ente Ospedaliero CantonaleImaging Institute of Southern Switzerland, Ente Ospedaliero CantonaleEuler Institute, Università della Svizzera italianaEuler Institute, Università della Svizzera italianaImaging Institute of Southern Switzerland, Ente Ospedaliero CantonaleEuler Institute, Università della Svizzera italianaImaging Institute of Southern Switzerland, Ente Ospedaliero CantonaleAbstract Background Body composition scores allow for quantifying the volume and physical properties of specific tissues. However, their manual calculation is time-consuming and prone to human error. This study aims to develop and validate CompositIA, an automated, open-source pipeline for quantifying body composition scores from thoraco-abdominal computed tomography (CT) scans. Methods A retrospective dataset of 205 contrast-enhanced thoraco-abdominal CT examinations was used for training, while 54 scans from a publicly available dataset were used for independent testing. Two radiology residents performed manual segmentation, identifying the centers of the L1 and L3 vertebrae and segmenting the corresponding axial slices. MultiResUNet was used to identify CT slices intersecting the L1 and L3 vertebrae, and its performance was evaluated using the mean absolute error (MAE). Two U-nets were used to segment the axial slices, with performance evaluated through the volumetric Dice similarity coefficient (vDSC). CompositIA’s performance in quantifying body composition indices was assessed using mean percentage relative error (PRE), regression, and Bland–Altman analyses. Results On the independent dataset, CompositIA achieved a MAE of about 5 mm in detecting slices intersecting the L1 and L3 vertebrae, with a MAE < 10 mm in at least 85% of cases and a vDSC greater than 0.85 in segmenting axial slices. Regression and Bland–Altman analyses demonstrated a strong linear relationship and good agreement between automated and manual scores (p values < 0.001 for all indices), with mean PREs ranging from 5.13% to 15.18%. Conclusion CompositIA facilitated the automated quantification of body composition scores, achieving high precision in independent testing. Relevance statement CompositIA is an automated, open-source pipeline for quantifying body composition indices from CT scans, simplifying clinical assessments, and expanding their applicability. Key Points Manual body composition assessment from CTs is time-consuming and prone to errors. CompositIA was trained on 205 CT scans and tested on 54 scans. CompositIA demonstrated mean percentage relative errors under 15% compared to manual indices. CompositIA simplifies body composition assessment through an artificial intelligence-driven and open-source pipeline. Graphical Abstracthttps://doi.org/10.1186/s41747-025-00552-7Body compositionComputed tomographyDeep learningOpen-source softwareSegmentation |
| spellingShingle | Raffaella Fiamma Cabini Andrea Cozzi Svenja Leu Benedikt Thelen Rolf Krause Filippo Del Grande Diego Ulisse Pizzagalli Stefania Maria Rita Rizzo CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scans European Radiology Experimental Body composition Computed tomography Deep learning Open-source software Segmentation |
| title | CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scans |
| title_full | CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scans |
| title_fullStr | CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scans |
| title_full_unstemmed | CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scans |
| title_short | CompositIA: an open-source automated quantification tool for body composition scores from thoraco-abdominal CT scans |
| title_sort | compositia an open source automated quantification tool for body composition scores from thoraco abdominal ct scans |
| topic | Body composition Computed tomography Deep learning Open-source software Segmentation |
| url | https://doi.org/10.1186/s41747-025-00552-7 |
| work_keys_str_mv | AT raffaellafiammacabini compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans AT andreacozzi compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans AT svenjaleu compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans AT benediktthelen compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans AT rolfkrause compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans AT filippodelgrande compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans AT diegoulissepizzagalli compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans AT stefaniamariaritarizzo compositiaanopensourceautomatedquantificationtoolforbodycompositionscoresfromthoracoabdominalctscans |