AI-extracted volumetric body composition from staging CT predicts oesophageal cancer survival, with sex-specific impact

In 563 patients with oesophageal cancer, AI-derived 3D CT sarcopenia index independently predicted survival: high-index males 33.3 vs 21.8 months (p<0.001), females 68.8 vs 16.8 months (p<0.001), with a significant sex interaction (p=0.026).

• Fully automated nnU-Net pipeline quantified three volumetric body composition indices from staging CT: sarcopenia index (SI), myosteatotic fat index (MFI), and abdominal fat index (AFI).
• Only the sarcopenia index (muscle-to-bone volume ratio) independently predicted overall survival; MFI and AFI did not retain significance after adjustment.
• The study was retrospective, single-center, and included only 19.7% females, but the survival separation was larger in women and confirmed by a significant sex-sarcopenia index interaction.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.