Near-infrared brain imaging spectrum classifying method based on cognition task testing

Abstract

The invention discloses a near-infrared brain imaging spectrum classifying method based on cognition task testing. A near-infrared brain imaging spectrum at least comprises a first curve corresponding to the oxyhemoglobin concentration and a second curve corresponding to the deoxygenated hemoglobin concentration. The classifying method comprises the following specific steps: 1, reading the near-infrared brain imaging spectrum obtained by a near-infrared brain imager, and extracting the waveform characteristics of the first curve and the second curve of the near-infrared brain imaging spectrum; and 2, comparing the waveform characteristics obtained in the step 1 with a preset value, and classifying the near-infrared brain imaging spectrum according to the comparison result. The near-infrared brain imaging spectrum classifying method based on the cognition task testing provided by the invention can be applied to the fundamental research in the field of psychology or applied to the clinic for automatically classifying the near-infrared brain imaging spectrum.

Description

technical field [0001] The invention relates to an image processing method, in particular to a near-infrared brain imaging atlas classification method based on a cognitive task test. This method can be applied to automatic classification of near-infrared brain imaging atlases in basic research or clinical applications in the field of psychology. Background technique [0002] At present, the process of identification, analysis, and identification of psychological symptoms of mental disorders mainly follows the "symptom-syndrome-medical history" model, mainly relying on empirical diagnosis of symptom identification, and there is still a lack of convenient technology to assist symptom identification in clinical practice. With the gradual application of non-invasive detection methods such as functional near-infrared spectroscopy brain imaging (fNIRS), functional magnetic resonance imaging (fMRI), positron emission tomography (PET) and single electron emission tomography (SPECT),...

AI Technical Summary

Problems solved by technology

However, the maps obtained by functional near-infrared spectroscopy brain imaging are generally difficult to identify, the work is cumbersome, and it is difficult for users to effectively understand and use

Specifically, taking the cognitive task-based test in clinical research on mental disorders as an example, in the existing traditional map classification analysis methods, most of the methods are to compare the average oxy-Hb concentration difference between the task period and the rest period or Using topographic map to indirectly reflect the activation of regional cortex (Noda et al, 2012; Liu et al, 2014), although some findings were obtained, but some information was covered up after averaging, failing to reflect oxy-Hb, Changes in deoxy-Hb over time (ecological effects)

Furthermore, due to the high time resolution of NIRS, if the traditional method of fMRI data interpretation is used, it cannot fully utilize its characteristics of real-time measurement of changes in cerebral cortex oxygenation and deoxygenated hemoglobin when subjects complete mental tasks. And the conversion relationship of hemoglobin in the task state

Images