Multitask Deep Neural Network for the Fully Automatic Measurement of the Angle of Progression

Figure 6

Our MT-Unet is compared to Zhou et al. [33]. (a) Compared to the predicted results of Zhou et al. (b) Endpoints obtained from ours and Zhou et al. are compared to the corresponding labels, respectively. (c) Calculations of AoP between Zhou et al. and ours. Note: Dist_L/Dist_R denotes the Euclidean distances between the predicted left/right endpoints and the true left/right endpoints. APT denotes the angle between the true line and the predicted line of two endpoints. AoP denotes the absolute value of the AoP difference between the true AoP and the predicted one (complete and detailed results are provided in Appendix S4).

(a) Image segmentation (Task2)

(b) Endpoint detection (Task3)

(c) AoP calculations