“…In the field of ET, segmentation of the target particle within the imaging area is a significant challenge due to complex cellular structures and the impact of incorporated ice. For DL architectures, common models, like CNN 106 and encoder-decoder, 107 , 108 , 109 , 110 , 111 , 112 , 113 are often used. To segment a single particle, some researchers 106 , 108 combined prior knowledge with these DL models to get more easily trained networks.…”