Machine learning preoperative positioning method based on generalized linear model

Abstract

The invention discloses a machine learning preoperative positioning method based on a generalized linear model. The machine learning preoperative positioning method comprises the following steps thatobtaining a structure image and a functional magnetic resonance image; preprocessing the structure image and the functional magnetic resonance image; segmenting and registering the structure image andthe functional magnetic resonance image, and extracting a motion network by using a double regression method; constructing a generalized linear prediction model, and performing generalized linear prediction model fitting on brain partitions; according to the method, the motion activation graph of the motion area prediction individual can be more accurately identified on the basis of resting statefunctional magnetic resonance, and passive task activation can be effectively predicted by using a generalized linear prediction model trained by active task activation with actual task functional magnetic resonance image activation as a reference; the generalized linear prediction model has important clinical application value for patients who cannot achieve satisfactory task performance, including old people, children and tumor patients.

Description

technical field [0001] The invention relates to the field of medical assistance technology, in particular to a preoperative positioning method based on generalized linear model machine learning. Background technique [0002] Accurate positioning of brain functional areas is crucial for preoperative planning and surgical path planning. Preoperative positioning not only helps to maximize tumor resection, but also minimizes postoperative neurological deficits, thereby improving the quality of life of patients after surgery. Intraoperative electrical cortical stimulation (ECS), as the gold standard for clinical localization of important functional brain regions, provides an important aid during surgery. But ECS is an invasive technique that requires the expertise of the surgical team and the active cooperation of the patient. Furthermore, this approach often results in prolonged operative time and increases the incidence of intraoperative seizures. In the past two decades, bl...

AI Technical Summary

Problems solved by technology

However, the ICA method requires manual selection of important brain function components based on visual inspection

Therefore, interpretation of ICA is time-consuming and subjective, and can be affected by physiological signal noise

Images