A method of dynamic soft tissue motion prediction for HIFU treatment system

Abstract

The invention discloses a method of dynamic soft tissue motion prediction for an HIFU treatment system. The method comprises the following steps: firstly, preprocessing an HIFU image sequence; constructing a prediction mapping relationship between the image sequence and a label sequence; constructing a data set and carrying out online data enhancement on a training set; building and training a dynamic soft tissue motion prediction model of the HIFU treatment system and acquiring an optimal model through an evaluation index optimization network; and after the optimal model is obtained, inputting the test set into the network, and carrying out dynamic soft tissue motion prediction and performance evaluation of a medical image sequence. A combination mode of combining the stacked convolutionlong-short-term memory network with a time wrapper is adopted to provide basic data conditions for a network model to process a medical image sequence, space-time information of an HIFU image sequencecan be fully utilized, and motion prediction with an accurate contour can be carried out on dynamic soft tissue of an HIFU treatment system.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and relates to a method for motion prediction, in particular to a method for dynamic soft tissue motion prediction in a HIFU treatment system. Background technique [0002] The HIFU treatment system is a treatment device that "can focus the ultrasonic beam on the target tissue to generate heat to ablate without damaging the surrounding healthy body". Its most prominent and competitive feature is non-invasive or minimally invasive. Its core technology is to accurately locate the lesion under the premise of considering the inhomogeneity of the human body structure, the nonlinearity at high sound intensity, and the tissue as a time-varying system, so as to achieve accurate sound output of the HIFU treatment system. Time and space control. In the surgical navigation of HIFU treatment, with factors such as the patient's respiratory movement and body position changes, the target tissu...

AI Technical Summary

Problems solved by technology

However, most of the above-mentioned traditional medical image processing methods regard the target tissue as a rigid whole or a point, and cannot accurately locate the region and boundary of the target tissue, so it is impossible to accurately predict soft tissue motion

In addition, the traditional methods have the following disadvantages in the target tracking and motion prediction of ultrasound sequences: the sharp change of the tracking target contour may lead to poor motion prediction; if the inter-frame target displacement is too large or the traditional method incorrectly estimates the target direction, the tracking target may be lost

Images