Ultrasonic image video classification prediction method and system

[0037] Embodiment 1 of the present invention provides a method for classifying and predicting ultrasound images and videos, which can be widely used in frame-level classification of video data. This embodiment uses prenatal ultrasound data as an example to illustrate the detailed prediction process of the method for classifying and predicting ultrasound images and videos in this embodiment. However, it does not mean that this embodiment is limited to ultrasound video data.

[0038] Prenatal ultrasound is mainly used for newborn screening. In many areas, the lack of methods and equipment for automatic analysis of ultrasound images greatly limits the efficiency of prenatal ultrasound examinations. Especially in some underdeveloped areas, the situation is particularly serious because of the lack of experienced doctors.

[0039] Such as Figure 1 ~ Figure 3 As shown, it is a schematic diagram of prenatal ultrasound video images, which are: figure 1 Indicates the section of the abdo

[0078] This embodiment provides a system for classifying and predicting ultrasound images and videos, which is used to implement the method described in the embodiment, such as Figure 8 As shown, it is a structural block diagram of the ultrasonic image video classification and prediction system of this embodiment, including:

[0079] Obtaining module 100: used to obtain the original video image;

[0080] Feature extraction module 200: for utilizing the feature extraction network to extract the features of the original video image;

[0081] Output module 300: used for outputting classification prediction results by using temporal upsampling on features.

[0082] The specific details of the modules of the ultrasonic image video classification and prediction system described above have been described in detail in the method for ultrasonic image video classification and prediction corresponding to Embodiment 1, so details will not be repeated here.

[0083] In addition, the presen