Diagnosis and Treatment Effect of Convolutional Neural Network-Based Magnetic Resonance Image Features on Severe Stroke and Mental State

<div>Comparison of the segmentation effects of the three algorithms. (a) Magnetic resonance images of patients with severe stroke were input; (b) FCN algorithm segmentation effect; (c) segmentation effect of U-Net algorithm; (d) segmentation effect of the proposed algorithm.</div>

Contrast Media & Molecular Imaging

fig4

Figure 4

Figure 4: Diagnosis and Treatment Effect of Convolutional Neural Network-Based Magnetic Resonance Image Features on Severe Stroke and Mental State 