Multiloss Function Based Deep Convolutional Neural Network for Segmentation of Retinal Vasculature into Arterioles and Venules

Figure 10

AV classification on DRIVE dataset: (a) original images [31]; (b) original labels [35]; (c) semantic labels; (d) pixel-wise deep learning results; (e) multiloss function deep learning results.

(a)

(b)

(c)

(d)

(e)