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

Figure 4

Examples of MT-Unet on the PS-FH. (a) Prediction examples (i.e., #1, #2, and #3) of the MT-Unet segmentation task. (b) Prediction examples of the MT-Unet endpoint detection task. (c) Prediction examples of AoP calculation. 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 AoP difference between the true AoP and the predicted one.

(a) Image segmentation (Task2)

(b) Endpoint detection (Task3)

(c) AoP calculations