Skip to main content
. Author manuscript; available in PMC: 2022 Nov 17.
Published in final edited form as: IEEE Trans Med Imaging. 2022 Oct 27;41(11):3003–3015. doi: 10.1109/TMI.2022.3176598

Fig. 2. Schematic of the GraphCAM.

Fig. 2.

Gradients and relevance are propagated through the network and integrated with an attention map to produce the transformer relevancy maps. Transformer relevancy maps are then mapped to graph class activation maps via reverse pooling.