Skip to main content
. Author manuscript; available in PMC: 2024 Jun 1.
Published in final edited form as: Magn Reson Med. 2023 Jan 24;89(6):2419–2431. doi: 10.1002/mrm.29593

Figure 1. The architecture of the proposed weakly supervised learning segmentation method (WPSS).

Figure 1.

WPSS is composed of mainly two parts: a Frangi filter as convolution neural network (CNN) with fixed Gaussian kernels, and a simple convolutional neural network Unet. The results from these two parts are used as inputs of a conditional random field (CRF) as the recurrent neural network (RNN) to perform segmentation post-processing. The three parallel backpropagations (denoted by green lines) are conducted during each training step to effectively train all the weights and parameters of WPSS.