Skip to main content
. Author manuscript; available in PMC: 2021 Feb 16.
Published in final edited form as: IEEE Access. 2020 Dec 16;8:225581–225593. doi: 10.1109/access.2020.3045285

FIGURE 2.

FIGURE 2.

3D CNN architecture for detecting major calcification lesions. The network is composed of five convolutional, five maximum pooling, and two fully connected layers. Each convolutional layer has the same kernel size (3 × 5 × 5) and varying numbers (96, 128, 256, and 324) with a stride of 1 × 1 × 1 pixels. The convolutional process consists of convolutional, batch normalization, and rectified linear unit layers. The kernel size for maximum pooling is set to 2 × 2 × 1. The input is the preprocessed IVOCT volume (200 × 448 × 5), and the output is either calcification or other classes.