3D Segmentation of Perivascular Spaces on T1-Weighted 3 Tesla MR Images With a Convolutional Autoencoder and a U-Shaped Neural Network.

Testing the Segmentation Model Against Visual Rating Results The logistic regression between the number of DWM PVS clusters ( Figure 10A ) and the visual grading rating ( Figure 10B ) in the ENCOD set was highly significant for all 3 PredMap-Thrs (R 2 0.1 = 0.38, R 2 0.5 = 0.45 see Figure 10C , R 2 0.9 = 0.47, p < 0.001, N = 1,782).

also in 132,142 other papers