Ruiqi Yu1, Ying Hou2, Yang Song1, Yu-dong Zhang2, and Guang Yang1
1Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China, 2Department of Radiology, the First Affiliated Hospital with Nanjing Medical University, Jiangsu, China
1Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China, 2Department of Radiology, the First Affiliated Hospital with Nanjing Medical University, Jiangsu, China
For PI-RADS v2 assessment, the
proposed CNN model with UDM achieved an F1 score of 0.640 and achieved an
accuracy of 64.4% on an independent validation cohort.
Figure 1. The overview of the ResNet-UDM.
The output of ResNet50 was continuous and would
be discretized with three self-learnt .
The discrete output was than compared with the ground truth. In the Inference
stage, were
also used to discretize the output of ResNet50 and produce the final PI-RADS
category.
Table 1. The comparison of ResNet-UDM and S. Thomas’s work.