AB088. SOH25_AB_106. AI-based fat mapping: an exploration of fat distribution across body regions with 3D slicer, MONAI label and TotalSegmentator
Plenary Session

AB088. SOH25_AB_106. AI-based fat mapping: an exploration of fat distribution across body regions with 3D slicer, MONAI label and TotalSegmentator

Emelia Deane1, Dara Walsh2,3, Esther Man Yu Lim4, John Calvin Coffey2,4

1Department of Surgery, University of Galway, Galway, Ireland; 2Department of Surgery, University of Limerick, Limerick, Ireland; 3Faculty of Education & Health Services, School of Medicine, University of Limerick, Limerick, Ireland; 4Department of Colorectal Surgery, University Hospital Limerick, Limerick, Ireland

Background: The distribution of body fat, particularly somatic and mesenteric fat, is a critical factor in understanding its relationship with outcomes such as cardiovascular disease and metabolic disorders. Advances in artificial intelligence (AI) and medical imaging software have opened new avenues for efficiently mapping and quantifying fat regions from computed tomography (CT) scans. This project explores the use of AI-powered tools, including 3D-Slicer, MONAI label, and TotalSegmentator, for fat segmentation and analysis.

Methods: 3D-Slicer, an open-source medical image analysis platform, used for importing and processing CT data. Utilising its built-in modules and AI-powered extensions, we employed thresholding and region-specific segmentation to distinguish and quantify fat volumes in different areas. MONAI label was integrated within three-dimensional (3D)-Slicer to facilitate semi-automated annotation and refinement of fat regions. TotalSegmentator, was used for fully automated identification of multiple tissue types, streamlining the process of isolating fat tissues for further analysis.

Results: Provisional findings indicate notable gender and age-related differences in fat distribution. Males consistently exhibit higher volumes of mesenteric fat compared to females. However, this difference diminishes with age, as females maintain lower mesenteric fat volumes from their mid-60s to 80s. Women have higher subcutaneous fat volumes than men across most age groups. Between approximately 65 and 75 years, subcutaneous fat volumes become similar in both genders. After this age range, males tend to have lower subcutaneous fat volumes, while females show a continued increase.

Conclusions: This methodology highlights the potential of combining open-source platforms with AI-driven algorithms to automate and standardise fat mapping, enabling researchers to efficiently analyse fat distributions across diverse populations.

Keywords: Artificial intelligence (AI); fat distribution; machine learning; medical imaging; mesenteric fat

Acknowledgments

None.

Footnote

Funding: None.

Conflicts of Interest: The authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

doi: 10.21037/map-25-ab088
Cite this abstract as: Deane E, Walsh D, Lim EMY, Coffey JC. AB088. SOH25_AB_106. AI-based fat mapping: an exploration of fat distribution across body regions with 3D slicer, MONAI label and TotalSegmentator. Mesentery Peritoneum 2025;9:AB088.

Article Options

Download Citation

Share