Automated Supraclavicular Brown Adipose Tissue Segmentation in Computed Tomography Using nnU-Net: Integration with TotalSegmentator
Kasper Jørgensen, Frederikke Engel Høi-Hansen, Ruth J F Loos, Christian Hinge, Flemming Littrup Andersen, Zhuhuang Zhou · 2024
Read Automated Supraclavicular Brown Adipose Tissue Segmentation in Computed Tomography Using nnU-Net: Integration with TotalSegmentator by Kasper Jørgensen, Frederikke Engel Høi-Hansen, Ruth J F Loos, Christian Hinge, Flemming Littrup Andersen, Zhuhuang Zhou (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11727111.txt.
Description
Kasper Jørgensen and co-authors teach a neural network to outline brown fat in CT scans, in a 2024 study. Brown fat burns energy to make heat, so it draws interest in metabolism research. Tracing it by hand in scans is slow and varies between readers.
The team trained a 3D nnU-Net on hand-drawn outlines from 159 lymphoma patients and merged it into a public body-mapping tool. On 30 fresh patients the model scored a DICE overlap of 0.780, a solid match with human tracings. The team also mined over 7,000 PET/CT studies for brown fat activity patterns, finding gaps between the sexes. Fast auto-tracing opens large scan archives to brown fat research.
Catalog record
| CREATOR | Kasper Jørgensen, Frederikke Engel Høi-Hansen, Ruth J F Loos, Christian Hinge, Flemming Littrup Andersen, Zhuhuang Zhou |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |