Presentation
9 March 2022 Investigating sources of FLIm data variability in head & neck cancer
Author Affiliations +
Abstract
The primary standard of care for Head and Neck (H&N) cancer patients is the complete surgical removal of cancer. Tissue classifiers based of autofluorescence lifetime imaging (FLIm) parameters have shown potential to differentiate healthy from cancer tissue in H&N patients and thus enhance the accuracy of this procedure. Here we report how collective autofluorescence trends (100-patient cohort, oral/oropharyngeal cancer) driving healthy vs. tumor contrast depend on anatomical location, patient medical history (e.g. tobacco use) and surgical context (in vivo vs. ex vivo). Accounting for such biological variables may further improve the accuracy of FLIm-guided H&N cancer surgery.
Conference Presentation
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Brent W. Weyers, Julien Bec, Athena K. Tam, Mohamed Hassan, Sukhkaran S. Aulakh, Dorina Gui, Andrew C. Birkeland, Arnaud F. Bewley, Marianne Abouyared, D. Gregory Farwell, and Laura Marcu "Investigating sources of FLIm data variability in head & neck cancer", Proc. SPIE PC11949, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XX, PC1194902 (9 March 2022); https://doi.org/10.1117/12.2609864
Advertisement
Advertisement
KEYWORDS
Tissues

Cancer

Medical imaging

In vivo imaging

Machine learning

Statistical analysis

Neck

Back to Top