B1 - μPEN: Multi-class PseudoEdgeNet for PD-L1 assessment
Jeroen Vermazeren, Leander van Eekelen, Luca Dulce Meesters, Monika Looijen-Salamon, Shoko Vos, Enrico Munari, Caner Mercan, Francesco Ciompi
In this paper, we take the recently presented PseudoEdgeNet model to the level of multi-class cell segmentation in histopathology images solely trained with point annotations. We tailor its loss function to the challenges of multi-class segmentation and equip it with an additional false positive loss term. We evaluate it on the assessment of tumor and immune cells in PD-L1 stained lung cancer histopathology images, and compare it with YOLOv5.
Wednesday 7th July
B1-9 (short): Application: Histopathology - 13:45 - 14:30 (UTC+2)