Image segmentation model training method, image processing method and related device

Abstract

The invention discloses an image segmentation model training method, an image processing method and a related device. The training method comprises the following steps: acquiring a training image and a corresponding training label; wherein the training image is a levator ani muscle section image, the training label comprises a first label and a second label, the first label is used for representing the range of levator ani muscle fissure holes in the training image, and the second label is used for representing the range of a urethra area in the training image; segmenting the training image by using the initial segmentation model to obtain a first training result and a second training result; generating a loss value based on the training label, the first training result and the second training result, and performing parameter adjustment on the initial segmentation model based on the loss value; if it is detected that a training completion condition is satisfied, determining the initial segmentation model after parameter adjustment as an image segmentation model; according to the method, the levator ani muscle fissure hole area and the urethra area are associated for training, so that the levator ani muscle fissure hole position and the urethra area position can be identified more accurately by the image segmentation model.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to an image segmentation model training method, an image processing method and related devices. Background technique [0002] Ultrasonography of the pelvic floor has been widely used in the diagnosis of pelvic floor dysfunction and the evaluation of the efficacy after treatment due to its non-invasiveness, reproducibility, non-radiation and low cost. Three-dimensional pelvic floor can be used to assess the status of levator hiatus and assist in the diagnosis of pelvic floor dysfunction. Usually, pelvic floor measurement identifies and measures the levator ani muscle based on the levator ani cross-section image. However, the recognition accuracy of the levator ani muscle is low, which makes the measurement results inaccurate. SUMMARY OF THE INVENTION [0003] In view of this, the purpose of the present application is to provide an image segmentation model t...

Images