Optimization of multispectral filter arrays for detection of cancers in the gastrointestinal tract (Conference Presentation)

Résumé fourni par la source

The optimal design and development of multispectral cameras could potentially improve the diagnosis of esophageal and colon cancer during routine screening and surveillance programs. We used an open-source Python toolbox Opti-MSFA and spectral data from clinical studies to determine the optimal spectral bands for inclusion in a snap-shot multispectral imaging system based on multispectral filter arrays (MSFAs) atop a CMOS image sensor. We emulated the feasibility of the proposed optimization method via synthetic datasets, which shows that the optimized MSFAs allow the accurate spectral unmixing of blood oxygen levels. The next steps are to implement the spectral imaging system with optimized MSFAs and demonstrate that the selected spectral bands are versatile in clinical trials.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.