Construction method and application of morphological fusion classification index of neuroimaging markers

A construction method and morphological technology, which is applied in the field of neuroimaging markers-morphological fusion classification index construction, can solve problems such as increasing the human and material costs of analysis institutions, poor interpretability of prediction results, and difficulty in protecting the privacy of subjects , to achieve the effects of easy understanding, enhanced classification efficiency, and good clinical applicability

CN113222001BActive Publication Date: 2022-06-28TIANJIN MEDICAL UNIV
5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2022-06-28

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention is a construction method and application of neuroimaging marker morphological fusion classification index. The construction method includes the following contents: obtaining structural MRI data of M centers, extracting brain structural image characteristic data; performing independent training with the data of each center, respectively Establish the classification model of each center and obtain the classification model of M centers; for any sample, in the classification model of all centers, calculate the classification weight value of the sample in each feature of each model, that is, the SHAP matrix; then use each The sample size used in the training of each model is the weight, and a single morphological fusion classification index MICI value is obtained by calculating according to formula (1): where Si represents the sample size of model i, B represents the total number of features, and a i Represents the SHAP value of feature a in model i, i=1~M. The MICI value can well realize the discrimination between patients with mental illness and normal people, and has good interpretability, evolution and scalability.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of neuroimaging markers, and provides a method for constructing a neuroimaging marker based on machine learning and multi-center data-morphological fusion classification index (MICI value), which is used to assist individualized diagnosis and treatment of neuropsychiatric diseases. Background technique

[0002] Neuropsychiatric diseases characterized by diffuse brain damage, such as schizophrenia, major depression, and Alzheimer's disease, seriously affect human health and bring a huge burden to individuals and society. At present, mental illness mainly relies on the subjective diagnosis of clinical symptoms by doctors, and there are certain misdiagnoses and missed diagnoses. Magnetic resonance imaging (MRI) has attracted more and more attention due to its advantages of simplicity, non-invasiveness and comprehensiveness. Numerous studies have reported significant differences between the brain structures of patients w...

Examples

Embodiment 1

[0048] The construction method of the neuroimaging marker morphological fusion classification index in the present embodiment, the construction method includes the following contents:

[0049] 1) Obtain the structural MRI data of M centers, and extract the feature data of brain structural images:

[0050] Data acquisition: For the included three-dimensional high-resolution T1-weighted structural MRI (structural MRI, sMRI) data collected from multiple centers (multi-center data refers to data collected by multiple institutions, among which MRI data of structural images is selected), Through the Freesurfer platform (V6.0, http: / / www.freesurfer.net / ), cortical reconstruction and index calculation are performed on sMRI data [2], and further based on aparc.2009s template and aseg template, the information including cortical thickness, cortical Volume, cortical surface area, subcortical volume, and seven whole-brain indicators (total brain volume, total cortical gray matter volume, ...