Machine learning-based end-to-end operation puncture path automatic planning method and system

Abstract

The invention discloses an end-to-end operation puncture path automatic planning method and system based on machine learning, and the method comprises the steps: 1, collecting and preprocessing the sample image data of an existing case, and obtaining a sagittal plane heat map and a coronal plane heat map; 2, designing an end-to-end deep neural network model, and training the end-to-end deep neural network model to obtain a puncture path automatic planning model; 3, predicting the sample image data of the patient by using the puncture path automatic planning model to obtain coordinates of a target spot and a needle insertion puncture point under an image coordinate system; 4, calculating a registration matrix from the magnetic resonance image coordinate system to the physical world coordinate system; and 5, registering the coordinates of the target spot and the needle insertion puncture point in the image coordinate system to a physical world coordinate system, thereby completing surgical puncture path planning. According to the invention, the surgical puncture path and the needle entry point position can be quickly determined, and the puncture path can be intelligently planned, so that the planning efficiency and the positioning precision can be improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and medical automation, and relates to an automatic planning method for a surgical puncture path and an automatic planning system for a surgical puncture path based on machine learning, and can be used for a medical surgical puncture robot or a non-invasive surgical 3D automatic positioning and navigation platform. Background technique [0002] In surgical puncture operations (needle biopsy, directional hematoma aspiration, directional implantation, etc.), doctors need to repeatedly review computed tomography (CT) images or magnetic resonance imaging (MRI) images on the surgical navigation software when planning the puncture path. Surgical planning is accomplished by continuously adjusting the puncture needle trajectory in transverse, sagittal, and coronal views of the patient's head or abdomen and thoracic cavity. In this process, the doctor needs to spend a lot of time to ensure ...

AI Technical Summary

Problems solved by technology

However, this planning method still belongs to the image feature recognition method in the traditional field. It does not have artificial intelligence factors, and the recognition accuracy and operation intelligence are limited.

Images