Skip to main content
. 2023 Jan 16;13:791. doi: 10.1038/s41598-023-27815-w

Figure 1.

Figure 1

(a) The overall architecture of the proposed anatomical structures segmentation in the X-ray images, and (b) illustrates the attention-gating module in the red dotted lines. The attention coefficients computed in the AGM are used to scale the input features. The gating signal in the AGMs uses both the activations and the contextual information to identify the spatial regions. (c) The Squeeze-and-Excite (SE) block.