Abstract: A method of training neural network for obtaining medical sagittal image includes: using a first neural network on a 3-D medical image to generate a prediction sagittal mask; generating a prediction result according to the 3-D medical image and the prediction sagittal mask; generating a ground truth result according to the 3-D medical image and a ground truth sagittal mask; using a second neural network on the prediction result and the ground truth result; generating a loss function data according to an output of the second neural network; and adjusting parameters of the first neural network or the second neural network according to the loss function data.

Abstract: A method of training neural network for obtaining medical sagittal image includes: using a first neural network on a 3-D medical image to generate a prediction sagittal mask; generating a prediction result according to the 3-D medical image and the prediction sagittal mask; generating a ground truth result according to the 3-D medical image and a ground truth sagittal mask; using a second neural network on the prediction result and the ground truth result; generating a loss function data according to an output of the second neural network; and adjusting parameters of the first neural network or the second neural network according to the loss function data.

Abstract: In a ball movement state measuring system with a ball, a sensing module, a wireless communication module, a power supply and an induction coil, the speed, rotation speed, rotation axis and trace of the ball at first movement state are calculated based on first accelerated speed and first angular velocity of the ball at first movement state and first movement result is obtained by the processor. The speed, rotation speed, rotation axis and trace of the ball at second movement state are calculated based on speed and rotation axis of the ball at first movement state, second accelerated speed and environment parameter of the ball at second movement state and second movement result is obtained by the processor. The ball is forced by gravity, applied force and air resistance at first movement state, and the ball is forced by gravity, air resistance and centripetal force at second movement state.

Abstract: In a ball movement state measuring system with a ball, a sensing module, a wireless communication module, a power supply and an induction coil, the speed, rotation speed, rotation axis and trace of the ball at first movement state are calculated based on first accelerated speed and first angular velocity of the ball at first movement state and first movement result is obtained by the processor. The speed, rotation speed, rotation axis and trace of the ball at second movement state are calculated based on speed and rotation axis of the ball at first movement state, second accelerated speed and environment parameter of the ball at second movement state and second movement result is obtained by the processor. The ball is forced by gravity, applied force and air resistance at first movement state, and the ball is forced by gravity, air resistance and centripetal force at second movement state.

Abstract: In a ball movement state measuring system with a ball, a sensing module, a wireless communication module, a power supply and an induction coil, the speed, rotation speed, rotation axis and trace of the ball at first movement state are calculated based on first accelerated speed and first angular velocity of the ball at first movement state and first movement result is obtained by the processor. The speed, rotation speed, rotation axis and trace of the ball at second movement state are calculated based on speed and rotation axis of the ball at first movement state, second accelerated speed and environment parameter of the ball at second movement state and second movement result is obtained by the processor. The ball is forced by gravity, applied force and air resistance at first movement state, and the ball is forced by gravity, air resistance and centripetal force at second movement state.