Let it shine: Autofluorescence of Papanicolaou-stain improves AI-based cytological oral cancer detection

Wenyi Lian, Joakim Lindblad, Christina Runow Stark, Jan-Michael Hirsch, Natasa Sladoje

Abstract: Highlights•AI-supported cytological analysis may facilitate cost-effective oral cancer detection.•Complementing brightfield with fluorescence microscopy reveals additional information.•Deep learning-based multimodal information fusion improves cancer detection accuracy.•CAFNet reaches the overall best performance among the evaluated fusion approaches.•Accurate alignment is found crucial for maximal benefit of the multimodal analysis.