Skip to main content
Fig. 5 | BMC Medical Imaging

Fig. 5

From: Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules

Fig. 5

Diagram of attention mechanism module 2(ATM2). The white block is the feature obtained by convolution which height is H, width is W, channel dimension is C), and the green block’s size is 1 × 1 × C. In this block, ATM2 carries out fast 1D convolution with size k (k is adaptive selected with the channel dimension C), and the result is the yellow block. Then it is calculated with the features before the ATM2 calculation, gaining the finally result which is the blue block

Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us