Near-infrared brain imaging spectrum recognition method

Abstract

The invention discloses a near-infrared brain imaging spectrum analysis method, which comprises the following steps of: extracting single-channel full-time-sequence spectrum data of relative concentrations of deoxyhemoglobin and oxyhemoglobin of a plurality of channels in a forehead calibration brain region of a patient under the stimulation of a cognitive task, constructing a detection curve of deoxyhemoglobin and oxyhemoglobin according to the spectrum data; sampling the detection curve, conducting zoning sampling with the total detection time T as the horizontal axis, and conducting normalization processing on the longitudinal axis, so as to obtain a final data set; and constructing a neural network algorithm model according to the standard map curve, respectively inputting the final data sets of the plurality of channels into the neural network algorithm model, judging the proportion of the standard map in the detection curve corresponding to the plurality of channels, and obtaining a judgment result according to a preset corresponding relationship between the preset proportion and the plurality of standard maps. The near-infrared brain imaging spectrum analysis method provided by the invention can provide reference for clinical diagnosis.

Description

technical field [0001] The invention relates to an image recognition method, in particular to a near-infrared brain imaging atlas recognition method. Background technique [0002] Near-infrared spectroscopy (NIRS) utilizes two kinds of near-infrared light and the distance between deoxygenate hemoglobin (a.k.a. Deoxy-Hb) and oxygenated hemoglobin (Oxygenate hemoglobin, Oxy-Hb) in brain tissue. The relationship between absorption and scattering allows researchers to quantitatively observe the relative concentration changes of Oxy-Hb and Deoxy-Hb in cerebral cortex tissue in a non-invasive way, and then indirectly reflect brain activity. After entering the 1980s, due to the development of optical fiber technology, NIRS gradually entered the medical field. In 1985, Farrari and his colleagues reported the first quantitative measurement of blood oxygen in the human brain using a near-infrared spectrometer. Later, researchers began to use functional near-infrared spectroscopy (fN...

AI Technical Summary

Problems solved by technology

But in fact, the current research results can only help relevant medical workers to establish awareness of the typical maps of various mental diseases, and cannot effectively improve the efficiency of diagnosis or effectively reduce the probability of misdiagnosis

In the actual diagnosis process, it is still difficult for patients and doctors to avoid the influence of subjective factors

In other words, when doctors currently make diagnoses based on near-infrared brain imaging maps of actual patients, they still make subjective judgments based on experience

In addition, in the existing diagnosis and treatment process, when diagnosing the infrared brain imaging atlas of the patient, another defect of manual identification, except for the influence of subjective consciousness, is that the diagnostic efficiency is also relatively low. For large-scale hospitals, diagnosis Results may show a large degree of lag

Images