Cerebral blood flow abnormal signal judgment method, device and equipment and medium

Abstract

The invention discloses a cerebral blood flow abnormal signal judgment method and device, equipment and a medium. The method comprises the steps that near-infrared VFT normal form data of a testee are obtained; generating an analysis waveform according to the acquired VFT normal form data, and performing multi-condition judgment on the waveform; and when at least one judgment condition is met, outputting a cerebral blood flow abnormity result. According to the method, abnormal features are found through near-infrared waveform analysis under VFT normal form data, and whether the cerebral blood flow change trend of the waveform is normal or not is accurately judged.

Description

Technical Field

[0001] The present invention relates to a method, device, equipment and medium for judging abnormal cerebral blood flow signals. Background Art

[0002] Psychiatric and psychological diseases are one of the brain function diseases. With the rapid development of brain science and the brain science industry, many researchers in universities, hospitals, enterprises, etc. have carried out a large number of studies on objectively and quantitatively assisting the diagnosis and identification of mental diseases. These studies mainly focus on exploring the differences between normal people and disease patients, and finding possible objective and quantitative clinical evaluation methods through the research on neurobiological markers and imaging features of the neural activity patterns of normal people and disease patients. In the research on the differences between normal and abnormal populations of near-infrared brain imaging technology for mental diseases in the past 20 years, there have been more than a hundred SCI articles in clinical research. A large number of scientific research papers have clearly revealed that there are significant differences in the cerebral blood flow activity characteristics between mental disease patients and normal people. However, these research results and findings have not yet solved the problem of image recognition algorithms, that is, automatically identifying and distinguishing whether the tested cerebral blood flow data is normal or abnormal through algorithms. Summary of the Invention

[0003] To solve the problem of positive and abnormal recognition of near-infrared cerebral blood flow activity patterns in psychiatric and psychological diseases, the present invention provides a method for judging abnormal cerebral blood flow signals. By analyzing the near-infrared waveforms under the VFT paradigm data, abnormal features are found to accurately judge whether the cerebral blood flow change trend of the waveforms is normal.

[0004] According to one aspect of the specification of the present invention, a method for judging abnormal cerebral blood flow signals is provided, including: Obtaining near-infrared VFT paradigm data of a subject; Generating an analysis waveform according to the obtained VFT paradigm data, and making the following judgments on the waveform: The β value in the GLM analysis is less than or equal to Th1; the integral during the task period is less than or equal to Th2; the integral of the full waveform length / the maximum value of the waveform is less than or equal to Th3; the integral of the waveform within a preset time period is less than 0; the number of times the waveform crosses the X-axis during the task period is greater than or equal to a preset number; the T centroid is less than or equal to Th4-low or greater than or equal to Th4-upper; the recovery period is active; the number of negative points during the task period is greater than or equal to Th5; wherein, Th1, Th2, Th3, Th4-low, Th4-upper and Th5 respectively represent numerical thresholds or time thresholds in the waveforms generated by the VFT data; When at least one judgment condition is met, outputting an abnormal cerebral blood flow result.

[0005] As a further technical solution, the method further includes: Taking the concentration of each channel as the explained variable and the task period in the VFT paradigm as the explanatory variable, a GLM model is constructed; According to the constructed GLM model, calculate the β value of each channel; Delete the bad leads in the channel and calculate the average of the β values of the remaining channels.

[0006] As a further technical solution, if the average result of the β values of the remaining channels is less than or equal to Th1, it is considered that there is an abnormal cerebral blood flow in the current analyzed waveform.

[0007] As a further technical solution, the method further includes: determining that the range of the preset time period is 11 - 125 seconds.

[0008] As a further technical solution, the method further includes: determining that the preset number of times is 4.

[0009] As a further technical solution, the judgment of recovery period activity includes: Determine the true peaks on the waveform diagram; When the time of the positive T center of gravity of any one of the true peaks is greater than or equal to the first threshold and the peak time of the current true peak is greater than the second threshold, it is determined that the current waveform has the characteristics of recovery period activity, where the range of the first threshold is 80 - 85 seconds and the second threshold is 70 seconds.

[0010] As a further technical solution, after determining that the waveform has the characteristics of recovery period activity, the following judgment is also made: The peak value is the maximum value of the waveform, and the peak time is greater than or equal to 73 seconds.

[0011] According to one aspect of the specification of the present invention, a device for judging abnormal cerebral blood flow signals is provided, including: An input module for acquiring near-infrared VFT paradigm data of a subject; A judgment module for generating an analysis waveform according to the acquired VFT paradigm data and making the following judgments on the waveform: In the GLM analysis, the β value is less than or equal to Th1; the integral of the task period is less than or equal to Th2; the integral of the full waveform length / the maximum value of the waveform is less than or equal to Th3; the integral of the waveform within the preset time period is less than 0; the number of times the task period crosses the X-axis is greater than or equal to the preset number of times; the T center of gravity is less than or equal to Th4-low or greater than or equal to Th4-upper; recovery period activity; the number of negative points in the task period is greater than or equal to Th5; where Th1, Th2, Th3, Th4-low, Th4-upper, and Th5 respectively represent numerical thresholds or time thresholds in the waveform generated from the VFT data; An output module for outputting the abnormal cerebral blood flow result when at least one judgment condition is met.

[0012] According to one aspect of the specification of the present invention, there is provided a cerebral blood flow abnormal signal judgment device, including a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the steps of the cerebral blood flow abnormal signal judgment method.

[0013] According to one aspect of the specification of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the cerebral blood flow abnormal signal judgment method are implemented.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: By extracting the near-infrared VFT data of the subject, the present invention can predict the change trend of cerebral blood flow, accurately judge whether it is normal, further judge what the abnormality is, and perform relevant interventions as early as possible. The present invention can be used for large-scale and extensive preliminary screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic flow chart of the cerebral blood flow abnormal signal judgment method provided by an embodiment of the present invention.

[0016] Figure 2 It is a schematic diagram of the integral during the task period provided by an embodiment of the present invention.

[0017] Figure 3 It is a schematic diagram of passing the X-axis during the task period provided by an embodiment of the present invention.

[0018] Figure 4 It is a schematic diagram of the number of negative points during the task period provided by an embodiment of the present invention.

[0019] Figure 5 It is a schematic diagram of the cerebral blood flow abnormal signal judgment device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0021] In the description of the present invention, "a plurality" and "several" mean two or more, unless otherwise specifically defined.

[0022] An embodiment of the present invention provides a cerebral blood flow abnormal signal judgment method, as Figure 1As shown, first, obtain the near-infrared VFT paradigm data of the subject; then, generate an analysis waveform based on the obtained VFT paradigm data, and perform multi-condition judgment on the waveform: finally, if at least one judgment condition is met, output the result of abnormal cerebral blood flow.

[0023] The embodiment of the present invention aims to adopt a reverse screening criterion, that is, if any one of the reverse conditions is met, it is determined that the trend of cerebral blood flow change is abnormal, so as to realize the judgment of cerebral blood flow signals.

[0024] In the embodiment of the present invention, the reverse conditions are specifically as follows: Condition 1: The β value in the GLM analysis is less than or equal to Th1.

[0025] The general linear model (GLM) is a widely used method for modeling fNIRS brain imaging data. The mathematical formula of GLM data is as follows:

[0026] Among them, y is the explained variable, is the explanatory variable, is the residual. In the embodiment of the present invention, y is the concentration of each channel, and the explanatory variable is the task period in the VFT paradigm. By constructing a model, the value of each channel can be calculated, and finally the bad leads are deleted and averaged according to the ROI.

[0027] ROI is a set of partial channels. For example, if ROI = [1, 3, 5, 7], it means that ROI contains channels 1, 3, 5, and 7. The average of the β values of these 4 channels is the result of this ROI. If channel 3 is a bad lead, delete channel 3, and the average of channels 1, 5, and 7 is the β value of the ROI.

[0028] In the embodiment of the present invention, the range of Th1 is 0.032 - 0.047. That is, when the β value in the GLM analysis is less than or equal to Th1, it is considered that the cerebral blood flow of the current analysis waveform is abnormal.

[0029] Condition 2: The integral of the task period is less than or equal to Th2.

[0030] After the preprocessing of the VFT paradigm, it includes a 10-second preparation stage, a 60-second task stage, and a 55-second recovery stage. The integral of the task period is to calculate the waveform area of the 60-second task stage. As Figure 2 shown, the blue area is the integral area of the task period.

[0031] In the embodiment of the present invention, the value of Th2 is 34. That is, when the integral of the task period is less than or equal to 34, it is considered that the cerebral blood flow of the current analysis waveform is abnormal.

[0032] Condition 3: The integral of the full waveform / the maximum value of the waveform ≤ Th3.

[0033] In the embodiments of the present invention, Th3 takes a value of 210 - 300. That is, when the ratio of the integral of the full waveform / the maximum value of the waveform is less than or equal to Th3, it is considered that the cerebral blood flow of the currently analyzed waveform is abnormal.

[0034] Condition 4: The integral of the waveform from 11 - 125 seconds is less than 0.

[0035] Condition 5: The number of times the waveform crosses the x-axis during the task period is greater than or equal to 4.

[0036] As Figure 3 shown, if the waveform crosses the X-axis 4 times during the task period from 10 - 70 seconds, then the cerebral blood flow of the waveform is abnormal.

[0037] Condition 6: The T centroid is less than or equal to Th4-low or greater than or equal to Th4-upper. The T centroid index refers to the moment at which half of the area of the HbO positive concentration is located within 125 seconds, that is, the T centroid value.

[0038] In the embodiments of the present invention, the range of Th4_low is 25 - 30 seconds, and the range of Th4_upper is 68 - 70 seconds.

[0039] Condition 7: The recovery period active algorithm determines that it is active during the recovery period.

[0040] The recovery period active algorithm includes: determining the peaks on each waveform diagram according to the hill climbing method; judging one by one whether each peak on each waveform diagram is a true peak; when the time of the positive T centroid of any one of the true peaks is greater than or equal to the first threshold and the peak time of the current true peak is greater than the second threshold, it is determined that the current waveform has the characteristics of being active during the recovery period, where the range of the first threshold is 80 - 85 seconds and the second threshold is 70 seconds. It should be noted that the recovery period active algorithm in the embodiments of the present invention can be implemented by using the method described in the Chinese patent application CN119444753A published on February 14, 2025.

[0041] As a preferred embodiment, after determining that it is active during the recovery period, the embodiments of the present invention further make the following judgments: The peak value is the maximum value of the waveform, and the peak time is greater than or equal to 73.

[0042] Condition 8: The number of negative points during the task period is greater than or equal to Th5.

[0043] The range of Th5 is 25 - 30. The number of negative points during the task period refers to the points below the X-axis. As Figure 4 shown, the area between the two Y-direction dotted lines is the task period. If the number of points falling below the X-axis within this task period is greater than or equal to 30, it is considered that Condition 8 is satisfied and there is abnormal cerebral blood flow.

[0044] The above are the reverse screening conditions for the cerebral blood flow algorithm. If any one of them is satisfied, it is determined that the cerebral blood flow is abnormal.

[0045] The implementation basis of each embodiment of the present invention is achieved through programmed processing by a device with processor functions. Therefore, in engineering practice, the technical solutions and functions of each embodiment of the present invention are encapsulated into various modules. Based on this actual situation, on the basis of the above embodiments, an embodiment of the present invention provides a device for judging abnormal cerebral blood flow signals, and this device is used to execute a method for judging abnormal cerebral blood flow signals in the above method embodiments.

[0046] See Figure 5 , the device includes: an input module, which is used to obtain the near-infrared VFT paradigm data of the subject; a judgment module, which is used to generate an analysis waveform according to the obtained VFT paradigm data, and make the following judgments on the waveform: the β value in the GLM analysis is less than or equal to Th1; the integral during the task period is less than or equal to Th2; the integral of the full length of the waveform / the maximum value of the waveform is less than or equal to Th3; the integral of the waveform within a preset time period is less than 0; the number of times the waveform crosses the X-axis during the task period is greater than or equal to the preset number of times; the T centroid is less than or equal to Th4-low or greater than or equal to Th4-upper; the recovery period is active; the number of negative points during the task period is greater than or equal to Th5; wherein, Th1, Th2, Th3, Th4-low, Th4-upper and Th5 respectively represent numerical thresholds or time thresholds in the waveform generated by the VFT data; an output module, which is used to output the result of abnormal cerebral blood flow when at least one judgment condition is satisfied.

[0047] A device for judging abnormal cerebral blood flow signals provided by an embodiment of the present invention, aiming at the problem of positive and abnormal recognition of the near-infrared cerebral blood flow activity pattern in mental and psychological diseases, adopts Figure 5 several modules among them, and through the analysis of the near-infrared waveform under the VFT paradigm data, discovers the abnormal features therein, and accurately judges whether the changing trend of the cerebral blood flow of the waveform is normal.

[0048] It should be noted that the device embodiment provided by the present invention, in addition to being used to implement the method in the above method embodiment, is also used to implement the methods in other method embodiments provided by the present invention. The difference is only in setting the corresponding functional modules, and its principle is basically the same as the principle of the above device embodiment provided by the present invention. As long as those skilled in the art, on the basis of the above device embodiment, refer to the specific technical solutions in other method embodiments, obtain the corresponding technical means by combining technical features, and the technical solutions constituted by these technical means, and on the premise of ensuring the practicability of the technical solutions, improve the modules in the above device embodiment to obtain the corresponding device-type embodiments for implementing the methods in other method-type embodiments. For example: Based on the content of the above device embodiments, as a preferred embodiment, a cerebral blood flow abnormal signal judgment device provided in the embodiments of the present invention, the judgment module is further configured to execute the following instructions: Taking the concentration of each channel as the explained variable and the task period in the VFT paradigm as the explanatory variable, construct a GLM model; According to the constructed GLM model, calculate the β value of each channel; Delete the bad leads in the channel and calculate the average of the β values of the remaining channels.

[0049] Based on the content of the above device embodiments, as a preferred embodiment, a cerebral blood flow abnormal signal judgment device provided in the embodiments of the present invention, the judgment module is further configured to execute the following instructions: If the average result of the β values of the remaining channels is less than or equal to Th1, it is considered that there is an abnormal cerebral blood flow in the current analyzed waveform.

[0050] Based on the content of the above device embodiments, as a preferred embodiment, a cerebral blood flow abnormal signal judgment device provided in the embodiments of the present invention, the judgment module is further configured to execute the following instructions: Determine that the range of the preset time period is 11 - 125 seconds.

[0051] Based on the content of the above device embodiments, as a preferred embodiment, a cerebral blood flow abnormal signal judgment device provided in the embodiments of the present invention, the judgment module is further configured to execute the following instructions: Determine that the preset number of times is 4.

[0052] Based on the content of the above device embodiments, as a preferred embodiment, a cerebral blood flow abnormal signal judgment device provided in the embodiments of the present invention, the judgment module is further configured to execute the following instructions: Determine the true peaks on the waveform diagram; When the time of the positive T centroid of any one of the true peaks is greater than or equal to the first threshold and the peak time of the current true peak is greater than the second threshold, it is determined that the current waveform has the active feature during the recovery period, where the range of the first threshold is 80 - 85 seconds and the second threshold is 70 seconds.

[0053] Based on the content of the above device embodiments, as a preferred embodiment, a cerebral blood flow abnormal signal judgment device provided in the embodiments of the present invention, the judgment module is further configured to execute the following instructions: The peak value is the maximum value of the waveform, and the peak time is greater than or equal to 73 seconds.

[0054] Based on the same inventive concept as the above embodiments, an embodiment of the present invention further provides a cerebral blood flow abnormal signal judgment device, including a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the steps of the cerebral blood flow abnormal signal judgment method described above.

[0055] In an embodiment of the present invention, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., or may also be a volatile memory, such as a random-access memory (RAM). The memory is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiment of the present invention may also be a circuit or any other device capable of implementing a storage function, for storing program instructions and / or data.

[0056] In an embodiment of the present invention, the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0057] Based on the same inventive concept as the above embodiments, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the cerebral blood flow abnormal signal judgment method described above are implemented as follows: Obtain the near-infrared VFT paradigm data of the subject; Generate an analysis waveform according to the obtained VFT paradigm data, and perform the following judgments on the waveform: In the GLM analysis, the β value is less than or equal to Th1; the integral during the task period is less than or equal to Th2; the full-length integral of the waveform / the maximum value of the waveform is less than or equal to Th3; the integral of the waveform within a preset time period is less than 0; the number of times the waveform crosses the X-axis during the task period is greater than or equal to a preset number; the T centroid is less than or equal to Th4-low or greater than or equal to Th4-upper; the recovery period is active; the number of negative points during the task period is greater than or equal to Th5; where Th1, Th2, Th3, Th4-low, Th4-upper, and Th5 respectively represent numerical thresholds or time thresholds in the waveform generated from the VFT data; When at least one judgment condition is satisfied, an abnormal cerebral blood flow result is output.

[0058] In summary of the above embodiments, based on the clinical academic research results of near-infrared imaging, the present invention collects large-sample norm data, and based on the large-sample data, overcomes the positive and abnormal recognition algorithm for the near-infrared cerebral blood flow activity pattern of mental and psychological diseases. By analyzing the waveform changes, the present invention discovers the abnormal features therein and accurately determines whether the cerebral blood flow change trend of the waveform is normal, providing certain help for large-scale preliminary screening.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining abnormal cerebral blood flow signals, characterized in that: include: Obtain the near-infrared VFT paradigm data of the subjects; Generate an analysis waveform based on the acquired VFT paradigm data, and make the following judgments on the waveform: In the GLM analysis, the β value is less than or equal to Th1; the integral during the task period is less than or equal to Th2; the integral of the entire waveform length / maximum waveform value is less than or equal to Th3; The waveform integral within the preset time period is less than 0; the number of times the task period passes through the X axis is greater than or equal to the preset number; The center of gravity of T is less than or equal to Th4-low or greater than or equal to Th4-upper; the recovery period is active; the number of negative points in the task period is greater than or equal to Th5; where Th1, Th2, Th3, Th4-low, Th4-upper and Th5 represent the numerical threshold or time threshold in the waveform generated by the VFT data respectively; When at least one judgment condition is met, the abnormal cerebral blood flow result is output.

2. The method for determining abnormal cerebral blood flow signals according to claim 1, characterized in that: The method further comprises: A GLM model was constructed with the concentration of each channel as the explained variable and the task period in the VFT paradigm as the explanatory variable; According to the constructed GLM model, the β value of each channel was calculated; Delete the bad guides in the channel and calculate the average β value of the remaining channels.

3. The method for determining abnormal cerebral blood flow signals according to claim 2, characterized in that: If the average result of the β values ​​of the remaining channels is less than or equal to Th1, it is considered that the current analyzed waveform has cerebral blood flow abnormality.

4. The method for determining abnormal cerebral blood flow signals according to claim 1, characterized in that: The method further includes: determining that the range of the preset time period is 11-125 seconds.

5. The method for determining abnormal cerebral blood flow signals according to claim 1, characterized in that: The method further includes: determining that the preset number of times is 4.

6. The method for determining abnormal cerebral blood flow signals according to claim 1, characterized in that: The judgment of active recovery period includes: Determine true peaks on the waveform graph; When the time of the positive T center of gravity of any true peak is greater than or equal to the first threshold and the peak occurrence time of the current true peak is greater than the second threshold, it is determined that the current waveform has active characteristics in the recovery period, wherein the first threshold ranges from 80 to 85 seconds and the second threshold is 70 seconds.

7. A method for determining abnormal cerebral blood flow signals according to claim 6, characterized in that: After determining that the waveform has the active characteristics of the recovery period, the following judgment is also made: The peak value is the maximum value of the waveform, and the peak time is greater than or equal to 73 seconds.

8. A device for determining abnormal cerebral blood flow signals, characterized in that: include: An input module is used to obtain the near-infrared VFT paradigm data of the subjects; The judgment module is used to generate an analysis waveform based on the acquired VFT paradigm data and make the following judgments on the waveform: In the GLM analysis, the β value is less than or equal to Th1; the integral during the task period is less than or equal to Th2; the integral of the entire waveform length / maximum waveform value is less than or equal to Th3; The waveform integral within the preset time period is less than 0; the number of times the task period passes through the X axis is greater than or equal to the preset number; The center of gravity of T is less than or equal to Th4-low or greater than or equal to Th4-upper; the recovery period is active; the number of negative points in the task period is greater than or equal to Th5; where Th1, Th2, Th3, Th4-low, Th4-upper and Th5 represent the numerical threshold or time threshold in the waveform generated by the VFT data respectively; The output module is used to output the abnormal cerebral blood flow result when at least one judgment condition is met.

9. A device for judging abnormal cerebral blood flow signals, characterized in that: It comprises a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the steps of the method for determining abnormal cerebral blood flow signals as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for determining abnormal cerebral blood flow signals according to any one of claims 1 to 7 are implemented.

Images