Automatic deep learning method for third lumbar selection and body composition evaluation on CT scans of cancer patients

Lidia Delrieu, Damien Blanc, Amine Bouhamama, Fabien Reyal, Frank Pilleul, Victor Racine, Anne Sophie Hamy, Hugo Crochet, Timothée Marchal, Pierre Etienne Heudel · 2024

Read Automatic deep learning method for third lumbar selection and body composition evaluation on CT scans of cancer patients by Lidia Delrieu, Damien Blanc, Amine Bouhamama, Fabien Reyal, Frank Pilleul, Victor Racine, Anne Sophie Hamy, Hugo Crochet, Timothée Marchal, Pierre Etienne Heudel (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-11440831.txt.

Description

Lidia Delrieu and co-authors built, in a 2023 study, a deep learning tool that finds the right CT slice and measures body makeup for cancer patients on its own. Muscle and fat patterns predict how patients weather treatment, yet hand measuring is too slow for routine care. Their algorithm picks the third lumbar slice, then outlines muscle, deep belly fat, and under-skin fat.

Trained on 352 scans from two cancer centers, the tool missed the target slice by about four millimeters on home data and five and a half on outside scans. Tissue outlines matched human tracing closely, with overlap scores above 0.93 for muscle and belly fat. Its wasting scores also tracked hand-derived ones tightly. Automation could make body composition a standard vital sign in oncology.

Catalog record

CREATORLidia Delrieu, Damien Blanc, Amine Bouhamama, Fabien Reyal, Frank Pilleul, Victor Racine, Anne Sophie Hamy, Hugo Crochet, Timothée Marchal, Pierre Etienne Heudel
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE31 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11440831

Browse the full library · About the Tower of Babel