Parameter quantification method and system based on intelligent quantification pupil pen, pupil pen and medium

Abstract

The application relates to the technical field of pupil parameter detection, and discloses a parameter quantification method and system based on an intelligent quantification pupil pen, a pupil pen and a medium.The method comprises the following steps: acquiring a resting image sequence of a target pupil in a non-stimulating measurement environment, processing the resting image sequence, and obtaining a resting pupil diameter; acquiring a dynamic image sequence of the target pupil in a visible light stimulating measurement environment, and obtaining dynamic parameters of the target according to the dynamic image sequence and the resting pupil diameter; and obtaining an analysis report according to the dynamic parameters and the resting pupil diameter.The application can directly output accurate numerical values such as the resting pupil diameter, the light reflex latency, the contraction speed, the contraction amplitude and the like, subjective estimation errors are eliminated, consistent results can be obtained by different operators using the same device, and the evaluation accuracy and reliability are improved.

Description

Technical Field

[0001] This application relates to the field of pupil parameter detection technology, and in particular to a parameter quantification method, system, pupil pen and medium based on an intelligent quantification pupil pen. Background Technology

[0002] Existing pupil pens have a single function, essentially functioning as a magnifying glass with an integrated light source. Their core deficiency lies in their inability to provide quantifiable pupil observation indicators, forcing pupil diameter measurement and light reflex assessment to rely entirely on the operator's subjective visual judgment and clinical experience. This subjectivity leads to significant intra- and inter-observer variability, affecting the accuracy, repeatability, and objectivity of neurological function assessments and medical documentation.

[0003] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0004] The main purpose of this application is to provide a parameter quantification method, system, pen and medium based on an intelligent quantification pupil pen, which aims to solve the problem that the assessment of pupil size and light reflection by traditional pupil examination tools in the prior art relies entirely on the operator's experience and visual judgment, resulting in low accuracy of pupil physiological parameter quantification.

[0005] The first aspect of this application provides a parameter quantization method based on an intelligent quantization pupil pen, the parameter quantization method based on the intelligent quantization pupil pen including the following steps: A resting image sequence of the target pupil under a non-stimulation measurement environment is acquired, and the resting image sequence is processed to obtain the resting pupil diameter; A dynamic image sequence of the target pupil under visible light stimulation measurement environment is acquired, and the dynamic parameters of the target are obtained based on the dynamic image sequence and the resting pupil diameter; An analysis report is obtained based on the dynamic parameters and the resting pupil diameter.

[0006] Optionally, in one embodiment of this application, the resting image sequence includes multiple frames of resting images; The process of processing the resting image sequence to obtain the resting pupil diameter specifically includes: For each frame of the resting image, the resting image is preprocessed to obtain a preprocessed resting image; Detect the target region of interest from the preprocessed resting image; Pupil edge detection is performed on the target region of interest to obtain the pupil boundary; Calculate the physical diameter of the pupil corresponding to each frame of the resting image based on the pupil boundary; The resting pupil diameter is determined based on the physical pupil diameter corresponding to all frames of the resting image.

[0007] Optionally, in one embodiment of this application, determining the resting pupil diameter based on the physical pupil diameter corresponding to all frames of the resting image specifically includes: Outlier values ​​are removed from the physical pupil diameters corresponding to all frames of the resting image to obtain multiple normal physical pupil diameters; Steady-state analysis was performed based on multiple normal pupil physical diameters to obtain sequence fluctuations; If the sequence fluctuation is within a preset range, the average value of the multiple normal pupil physical diameters or the mode of the multiple normal pupil physical diameters will be used as the resting pupil diameter.

[0008] Optionally, in one embodiment of this application, the dynamic image sequence includes multiple frames of dynamic images and timestamps corresponding to each frame of the dynamic images; The step of obtaining the dynamic parameters of the target based on the dynamic image sequence and the resting pupil diameter specifically includes: Based on the multiple frames of the dynamic images, calculate the instantaneous pupil diameter corresponding to each frame of the dynamic images; Based on the multiple instantaneous pupil diameters and the corresponding timestamps, a pupil diameter-time curve is obtained that reflects the change of pupil diameter over time. The dynamic parameters of the target are obtained based on the pupil diameter over time curve and the resting pupil diameter.

[0009] Optionally, in one embodiment of this application, the dynamic parameters include latency, contraction rate, and contraction amplitude; The process of obtaining the dynamic parameters of the target based on the pupil diameter-time curve and the resting pupil diameter specifically includes: The initial and minimum contraction data are determined from the pupil diameter-time curve. The latency, contraction rate, and contraction amplitude of the target are obtained based on the contraction initiation data, the contraction minimum value data, and the resting pupil diameter.

[0010] Optionally, in one embodiment of this application, the contraction initiation data includes the stimulation initiation point and the contraction initiation point, the contraction minimum value data includes the time minimum value and the diameter minimum value, and the contraction speed includes the average contraction speed; The process of obtaining the latency, contraction rate, and contraction amplitude of the target based on the contraction initiation data, the contraction minimum data, and the resting pupil diameter specifically includes: The latency of the target is obtained by calculating the difference between the contraction initiation point and the stimulation initiation point; The difference between the resting pupil diameter and the minimum diameter is calculated to obtain the contraction amplitude of the target. Calculate the first difference between the stimulation initiation point and the minimum diameter, calculate the second difference between the minimum time and the contraction initiation point, and calculate the quotient of the first difference and the second difference to obtain the average contraction speed.

[0011] Optionally, in one embodiment of this application, the analysis report includes a verified package of quantitative parameters, interpretive text, and visualization charts; The analysis report obtained based on the dynamic parameters and the resting pupil diameter specifically includes: The validity of the resting pupil diameter, the pupil diameter-time curve, the latency, the contraction velocity, and the contraction amplitude is tested to obtain a package of quantitative parameters after testing. The verified quantization parameter package is compared with the preset threshold of each parameter to generate interpretation text, and a visualization chart is generated based on the verified quantization parameter package.

[0012] A second aspect of this application also provides a parameter quantization system based on an intelligent quantization pupil pen, wherein the parameter quantization system based on the intelligent quantization pupil pen is used to implement the parameter quantization method based on the intelligent quantization pupil pen described in any of the above solutions; the parameter quantization system based on the intelligent quantization pupil pen includes: An optical imaging and data processing module is used to acquire a resting image sequence of the target pupil under a non-stimulation measurement environment, and to process the resting image sequence to obtain the resting pupil diameter; A controllable light source stimulation and data processing module is used to acquire a dynamic image sequence of the target pupil under a visible light stimulation measurement environment, and to obtain the dynamic parameters of the target based on the dynamic image sequence and the resting pupil diameter; The report analysis module is used to generate an analysis report based on the dynamic parameters and the resting pupil diameter.

[0013] A third aspect of this application also provides an intelligent quantization pupil pen, wherein the intelligent quantization pupil pen includes: a memory, a processor, and a parameter quantization program based on the intelligent quantization pupil pen stored in the memory and executable on the processor. When the parameter quantization program based on the intelligent quantization pupil pen is executed by the processor, it implements the steps of the parameter quantization method based on the intelligent quantization pupil pen as described above.

[0014] A fourth aspect of this application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a parameter quantization program based on an intelligent quantization pupil pen, and when the parameter quantization program based on the intelligent quantization pupil pen is executed by a processor, it implements the steps of the parameter quantization method based on the intelligent quantization pupil pen as described above.

[0015] Beneficial effects: This application provides a parameter quantification method, system, pupil pen and medium based on an intelligent quantification pupil pen. This application can directly output accurate values ​​such as resting pupil diameter, light reflex latency, contraction speed and contraction amplitude, eliminating subjective estimation errors. Different operators can obtain consistent results using the same device, improving the reliability of the assessment, and can quickly provide key and objective neurological function indicators. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a preferred embodiment of the parameter quantization method based on the intelligent quantization pupil pen of this application; Figure 2 This is a structural diagram of a preferred embodiment of the parameter quantization system based on the intelligent quantization pupil pen of this application; Figure 3 This is a structural diagram of a preferred embodiment of the intelligent quantitative pupil pen of this application.

[0018] Explanation of reference numerals in the attached figures: 100. Optical Imaging and Data Processing Module; 200. Controllable Light Source Stimulation and Data Processing Module; 300. Report Analysis Module. Detailed Implementation

[0019] To make the objectives, technical solutions, and effects of this application clearer and more explicit, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are only possible technical implementations of this application and not all possible implementations. Based on the embodiments in this application, those skilled in the art can obtain other embodiments without creative effort, and these embodiments are also within the protection scope of this application.

[0020] In related technologies, the widely used traditional pupillary pens are merely magnifying glasses with integrated light sources. Physicians manually assess two key indicators through visual observation: pupil size, which relies on personal experience and can vary by 1-2 millimeters between different physicians (e.g., judging the same pupil as 2mm or 3mm); and light reflex, which uses subjective descriptive terms such as "sensitive," "sluggish," or "absent," lacking a unified and objective measurement standard. The core problem is that this subjectivity leads to significant inter-observer variability, introducing uncertainty into neurological function assessment, especially in critical scenarios such as stroke, traumatic brain injury, increased intracranial pressure, and anesthesia monitoring, potentially affecting the timeliness and accuracy of diagnostic and treatment decisions. Furthermore, the lack of objective data hinders the standardization of medical documentation, continuous tracking of patient condition changes, and remote consultations. Alternatives include traditional pupillary pens (inexpensive but with limited functionality) and pupil monitoring modules from large monitors (similar in function but extremely expensive and not portable). Compared to alternatives, the parameter quantification method based on the intelligent quantification pupil pen in this application enables quantitative assessment of the pupil on a portable device; it focuses on pupil examination, achieving "portability, specialization, and high cost-effectiveness"; and it can provide storable and traceable objective data, facilitating the generation of trend charts and dynamic assessment of the condition.

[0021] First, the architecture of the pupil pen in this application will be described. This application uses a pupil pen to automatically, objectively, and quantitatively detect and output pupil physiological parameters. Its innovation lies in the integration of an optical imaging module, a controllable stimulus light source, and a data processing unit. Through automatic analysis of image sequences using algorithms, it can directly output one or more quantitative data, including but not limited to: resting pupil diameter, pupillary light reflex latency, constriction speed, and constriction amplitude, thereby achieving objectivity and standardization of pupil examination.

[0022] Specifically, the pupil pen includes: a dual-light source system, including an infrared light source (for non-intrusive, continuous measurement of the resting pupil) and a programmable visible light stimulation light source (for inducing light reflection); a miniature image sensor for acquiring high-definition eye images and video streams; and an embedded processor and display unit, which has a built-in computing chip, runs the core algorithm, and outputs the results through a small OLED screen or wireless transmission.

[0023] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0024] The parameter quantization method based on the intelligent quantization pupil pen described in the preferred embodiment of this application, such as Figure 1 As shown, the parameter quantization method based on the intelligent quantization pupil pen includes the following steps: In step S101, a resting image sequence of the target pupil under a non-stimulation measurement environment is obtained, and the resting image sequence is processed to obtain the resting pupil diameter.

[0025] Understandably, this application uses image recognition algorithms to accurately locate the edges of the iris and pupil, overcoming interference from different races and lighting conditions. Through dynamic parameter analysis algorithms, it calculates the resting pupil diameter and, by analyzing the light reflection process, outputs quantitative parameters such as latency, contraction speed, and contraction amplitude. Based on clinical big data, it sets thresholds and automatically outputs "normal / abnormal" prompts.

[0026] In one possible implementation, the resting image sequence comprises multiple frames of resting images.

[0027] Step S101 specifically includes: for each frame of the resting image, preprocessing the resting image to obtain a preprocessed resting image; detecting a target region of interest from the preprocessed resting image; performing pupil edge detection on the target region of interest to obtain the pupil boundary; calculating the physical diameter of the pupil corresponding to each frame of the resting image based on the pupil boundary; and determining the resting pupil diameter based on the physical diameter of the pupil corresponding to all frames of the resting image.

[0028] The specific implementation of the step of determining the resting pupil diameter is as follows: outlier removal is performed on the physical pupil diameter corresponding to all frames of the resting image to obtain multiple normal pupil physical diameters; steady-state analysis is performed on the multiple normal pupil physical diameters to obtain sequence fluctuations; if the sequence fluctuations are within a preset range, the average value of the multiple normal pupil physical diameters or the mode of the multiple normal pupil physical diameters is taken as the resting pupil diameter.

[0029] Specifically, the user (doctor) presses the "Measure" button, and the embedded processor receives a start command. The processor activates only the infrared light source while ensuring that the visible light stimulation source is off. It then controls the miniature image sensor to begin acquiring images at a specific frame rate (e.g., 30 frames per second). This creates a measurement environment that does not stimulate the pupil. Infrared light is invisible to the human eye and does not trigger pupillary light reflection, thus ensuring that the measurement is performed in a "resting" state.

[0030] Then, a resting image sequence is acquired. Under stable infrared illumination, the image sensor continuously acquires images of the eye, forming an image sequence lasting approximately 1-2 seconds (e.g., obtaining 60 frames). The acquired image sequence is transmitted in real time and cached in the processor's memory. Understandably, a single image may contain errors due to blinking, momentary focus deviation, or minute movements. Acquiring a time series provides a data foundation for subsequent multi-frame analysis to filter out random errors and improve measurement robustness.

[0031] Then, image recognition and pupil localization (frame-by-frame processing) are performed. The following sub-steps are executed for each frame in the sequence: image preprocessing, including noise reduction and contrast enhancement to optimize image quality; region of interest detection to quickly locate the eye region in the image; pupil edge detection using image recognition algorithms (such as edge detection, Hough circle transform, or machine learning models) to accurately identify the boundary between the pupil and iris. The algorithm can adapt to different iris colors and partial eyelid occlusion in different ethnicities; and single-frame diameter calculation, based on the identified pupil boundary and known image sensor optical parameters (the actual physical size corresponding to each pixel, obtained through pre-calibration), to calculate the physical diameter of the pupil in that frame (unit: millimeters). An image sequence is thus transformed into a "pupil diameter numerical sequence."

[0032] Finally, data cleaning and resting diameter calculation are performed. The pupil diameter numerical sequence is analyzed to remove obviously unreliable outliers, such as frames where the pupil is completely or partially obscured due to blinking, frames where rapid head movements cause image blurring and algorithm failure, and frames where the diameter value deviates excessively from the sequence median. The stability of the cleaned sequence is analyzed (e.g., standard deviation is calculated). If the sequence fluctuation is within an acceptable range, the pupil is considered to be in a stable resting state. The average value of the cleaned and stable diameter numerical sequence is taken, or the diameter value with the highest frequency (mode) is used as the final resting pupil diameter D0.

[0033] It should be noted that D0 serves as the absolute benchmark for calculating the contraction amplitude: the diameter D_min of the pupil when it contracts to its minimum size is found from the dynamic image sequence, and the formula for calculating the contraction amplitude is directly: amplitude = D0 - D_min.

[0034] In step S102, a dynamic image sequence of the target pupil under visible light stimulation measurement environment is acquired, and the dynamic parameters of the target are obtained based on the dynamic image sequence and the resting pupil diameter.

[0035] In one possible implementation, the dynamic image sequence includes multiple frames of dynamic images and timestamps corresponding to each frame of the dynamic images.

[0036] Step S102 specifically includes: calculating the instantaneous pupil diameter corresponding to each frame of the dynamic image based on multiple frames of the dynamic image; obtaining a pupil diameter time curve showing the change of pupil diameter over time based on multiple instantaneous pupil diameters and the corresponding timestamps; and obtaining the dynamic parameters of the target based on the pupil diameter time curve and the resting pupil diameter.

[0037] In one possible implementation, the dynamic parameters include latency, contraction rate, and contraction amplitude.

[0038] Specifically, the step of determining the dynamic parameters of the target is implemented as follows: determining the contraction initiation data and contraction minimum data from the pupil diameter time curve; and obtaining the latency, contraction speed, and contraction amplitude of the target based on the contraction initiation data, the contraction minimum data, and the resting pupil diameter.

[0039] In one possible implementation, the contraction initiation data includes a stimulation initiation point and a contraction initiation point, the contraction minimum data includes a time minimum and a diameter minimum, and the contraction velocity includes an average contraction velocity.

[0040] Specifically, the steps for determining the latency, contraction speed, and contraction amplitude of the target are as follows: calculate the difference between the contraction initiation point and the stimulation initiation point to obtain the latency of the target; calculate the difference between the resting pupil diameter and the minimum diameter to obtain the contraction amplitude of the target; calculate the first difference between the stimulation initiation point and the minimum diameter; calculate the second difference between the minimum time and the contraction initiation point; and calculate the quotient of the first difference and the second difference to obtain the average contraction speed.

[0041] Specifically, the time-synchronized dynamic image sequence contains a precise time stamp of the start of the light stimulus; each frame in the sequence is preprocessed, such as noise reduction, contrast adjustment, and distortion correction, to ensure consistent image quality.

[0042] The preprocessed dynamic images are then processed to generate a pupil diameter-time curve. This is divided into two parallel and collaborative sub-tasks: Task A: Continuous pupil tracking and measurement. For each frame in the sequence, a pupil recognition algorithm similar to step S101 is run to calculate the physical diameter (instantaneous diameter) of the pupil in real time for each frame; each diameter value is associated with its precise acquisition time point. Task B: Data cleaning and interpolation. Invalid data points caused by blinking, violent shaking, or recognition failure are automatically identified and removed; filtering algorithms (such as moving average and low-pass filtering) are applied to eliminate minor jitter caused by physiological tremors or measurement noise, resulting in a smooth curve. Thus, after the above processing, an original image sequence is transformed into a clean and smooth function curve of pupil diameter changing over time, i.e., the pupil diameter-time curve.

[0043] Then, key event point detection and feature extraction are performed. Key point detection is carried out on this curve: Locating the stimulus start point (t0): Using the hardware synchronization signal, the precise moment when the light stimulus begins is marked on the curve (usually set as the zero point of time); Detecting the contraction start point (t_start): Starting from t0, the curve is scanned to find the inflection point where the diameter begins to decrease continuously and trendily. The real-time derivative (rate of change) of the curve is calculated to determine the start of contraction. When the rate of change continuously exceeds a negative threshold, it is determined that contraction has started, and the latency period = t_start - t0; Locating the contraction minimum point (t_min, D_min): The curve is scanned to find the minimum diameter value and its corresponding time in the entire contraction process.

[0044] Then, quantitative parameters are calculated and generated: contraction amplitude: amplitude = resting pupil diameter (D0) - D_min; contraction speed: the maximum contraction speed is the maximum value of the derivative of the contraction segment curve (the slope at the steepest point), and the average contraction speed is (D0-D_min) / (t_min-t_start).

[0045] Finally, all the calculated parameters (latency, amplitude, velocity, etc.) are packaged together with the original resting diameter (D0) to form a complete quantization report, ready to be sent to the display unit or storage system.

[0046] It should be noted that for each frame of the dynamic sequence, an image recognition algorithm similar to that in the second stage is used to calculate the instantaneous pupil diameter of that frame. The calculated result (diameter) of each frame is correlated with its corresponding timestamp (determined by the acquisition frequency) to draw a continuous diameter-time curve. Key event points are located on the curve (dependent on time synchronization). Because a time stamp is synchronously entered when light stimulation is turned on, the algorithm can accurately know the position of the zero point (t0) on the curve. Key location: Latency start point: t0 (light stimulation begins); Latency end point / contraction start point: after t0, the time point t_start where the curve begins its first and sustained decline from the plateau phase, latency = t_start - t0; Contraction amplitude end point: the diameter value D_min and the corresponding time when the curve reaches its lowest point. Based on the curve and key points, dynamic parameters are calculated. The contraction speed is calculated in the rapid decline segment after the contraction start point t_start. A segment of the curve (e.g., 20 milliseconds) is taken, and the slope of this segment (diameter change / time change) is calculated to obtain the contraction speed (mm / s).

[0047] In step S103, an analysis report is obtained based on the dynamic parameters and the resting pupil diameter.

[0048] In one possible implementation, the analysis report includes a verified package of quantitative parameters, interpretive text, and visualization charts.

[0049] Step S103 specifically includes: performing validity checks on the resting pupil diameter, the pupil diameter-time curve, the latency, the contraction velocity, and the contraction amplitude to obtain a set of quantitative parameters after verification; comparing the set of quantitative parameters after verification with the preset thresholds of each parameter to generate interpretation text; and generating a visualization chart based on the set of quantitative parameters after verification.

[0050] Specifically, all quantitative parameter packages include: static parameters: resting pupil diameter (D0); dynamic parameters: latency, contraction velocity, and contraction amplitude; intermediate data: processed pupil diameter-time curve data points. Data validity is automatically checked for completeness and reasonableness (e.g., whether the latency is negative, whether the contraction amplitude is greater than the resting diameter, etc.). If the data is invalid, a measurement failure message is displayed, requesting a retry.

[0051] The validated parameters are then organized into a clearly structured digital report according to clinical reading habits. A pupil diameter-time curve is simultaneously plotted on the device's display screen, with key points (stimulus onset, contraction onset, minimum diameter point) clearly marked to make the dynamic process readily apparent.

[0052] This application compares the measurement results with a built-in medical knowledge base. Threshold comparison: Each parameter is compared with a pre-set normal range threshold (based on clinical references using large datasets such as age and gender). Clinically-based judgment logic is executed, for example: bilateral comparison judgment (if contralateral eye data is available): if |left eye D0 - right eye D0| > 0.5 mm, a "pupil unequal size" warning is issued; unilateral abnormality judgment: if the latency is > 0.3 s and the constriction amplitude is < 1.0 mm, a "significantly sluggish pupillary light reflex" warning is issued; critical value judgment: if unilateral pupil D0 > 5.0 mm and the constriction amplitude is < 0.5 mm, a "high-risk acute mydriasis" warning is triggered (e.g., visual or audible cues). Then, an interpretation text is generated: based on the judgment results, a clear concluding statement is automatically added to the end of the report, such as a normal or abnormal result warning: "Prolonged pupillary light reflex latency in the left pupil; clinical evaluation recommended."

[0053] Next, referring to the accompanying drawings, a parameter quantization system based on an intelligent quantization pupil pen, according to an embodiment of this application, is described to implement the parameter quantization method based on an intelligent quantization pupil pen as described in any of the above schemes.

[0054] Figure 2 This is a structural diagram of the parameter quantization system based on the intelligent quantization pupil pen according to an embodiment of this application.

[0055] like Figure 2As shown, the parameter quantification system based on the intelligent quantification pupil pen includes: an optical imaging and data processing module 100, a controllable light source stimulation and data processing module 200, and a report analysis module 300.

[0056] Specifically, the optical imaging and data processing module 100 is used to acquire a resting image sequence of the target pupil under a non-stimulation measurement environment, and to process the resting image sequence to obtain the resting pupil diameter; The controllable light source stimulation and data processing module 200 is used to acquire a dynamic image sequence of the target pupil under a visible light stimulation measurement environment, and to obtain the dynamic parameters of the target based on the dynamic image sequence and the resting pupil diameter; The report analysis module 300 is used to generate an analysis report based on the dynamic parameters and the resting pupil diameter.

[0057] Figure 3 A structural diagram of the intelligent quantitative pupil pen provided in an embodiment of this application. The intelligent quantitative pupil pen may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0058] When the processor 502 executes the program, it implements the parameter quantization method based on the intelligent quantization pupil pen provided in the above embodiments.

[0059] Furthermore, the intelligent quantitative pupil pen also includes: Communication interface 503 is used for communication between memory 501 and processor 502.

[0060] The memory 501 is used to store computer programs that can run on the processor 502.

[0061] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0062] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EIS) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0063] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0064] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0065] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the parameter quantization method based on the intelligent quantization pupil pen described above.

[0066] One embodiment of this application provides a computer program product, including a computer program that, when executed by a processor, implements the features described in this application. Figure 1 The corresponding embodiments provide a parameter quantization method based on an intelligent quantization pupil pen.

[0067] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0068] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0069] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable storage medium could be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0071] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0072] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0073] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0074] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

[0075] It should be understood that the application of this application is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A parameter quantization method based on an intelligent quantization pupil pen, characterized in that, The parameter quantization method based on the intelligent quantization pupil pen includes: A resting image sequence of the target pupil under a non-stimulation measurement environment is acquired, and the resting image sequence is processed to obtain the resting pupil diameter; A dynamic image sequence of the target pupil under visible light stimulation measurement environment is acquired, and the dynamic parameters of the target are obtained based on the dynamic image sequence and the resting pupil diameter; An analysis report is obtained based on the dynamic parameters and the resting pupil diameter.

2. The parameter quantization method based on the intelligent quantization pupil pen according to claim 1, characterized in that, The resting image sequence includes multiple resting images; The process of processing the resting image sequence to obtain the resting pupil diameter specifically includes: For each frame of the resting image, the resting image is preprocessed to obtain a preprocessed resting image; Detect the target region of interest from the preprocessed resting image; Pupil edge detection is performed on the target region of interest to obtain the pupil boundary; Calculate the physical diameter of the pupil corresponding to each frame of the resting image based on the pupil boundary; The resting pupil diameter is determined based on the physical pupil diameter corresponding to all frames of the resting image.

3. The parameter quantization method based on the intelligent quantization pupil pen according to claim 2, characterized in that, The step of determining the resting pupil diameter based on the physical pupil diameter corresponding to all frames of the resting image specifically includes: Outlier values ​​are removed from the physical pupil diameters corresponding to all frames of the resting image to obtain multiple normal physical pupil diameters; Steady-state analysis was performed based on multiple normal pupil physical diameters to obtain sequence fluctuations; If the sequence fluctuation is within a preset range, the average value of the multiple normal pupil physical diameters or the mode of the multiple normal pupil physical diameters will be used as the resting pupil diameter.

4. The parameter quantization method based on the intelligent quantization pupil pen according to claim 2, characterized in that, The dynamic image sequence includes multiple frames of dynamic images and timestamps corresponding to each frame of the dynamic images; The step of obtaining the dynamic parameters of the target based on the dynamic image sequence and the resting pupil diameter specifically includes: Based on the multiple frames of the dynamic images, calculate the instantaneous pupil diameter corresponding to each frame of the dynamic images; Based on the multiple instantaneous pupil diameters and the corresponding timestamps, a pupil diameter-time curve is obtained that reflects the change of pupil diameter over time. The dynamic parameters of the target are obtained based on the pupil diameter over time curve and the resting pupil diameter.

5. The parameter quantization method based on the intelligent quantization pupil pen according to claim 4, characterized in that, The dynamic parameters include latency, contraction rate, and contraction amplitude; The process of obtaining the dynamic parameters of the target based on the pupil diameter-time curve and the resting pupil diameter specifically includes: The initial and minimum contraction data are determined from the pupil diameter-time curve. The latency, contraction rate, and contraction amplitude of the target are obtained based on the contraction initiation data, the contraction minimum value data, and the resting pupil diameter.

6. The parameter quantization method based on the intelligent quantization pupil pen according to claim 5, characterized in that, The contraction initiation data includes the stimulation initiation point and the contraction initiation point; the contraction minimum data includes the minimum time and the minimum diameter; and the contraction speed includes the average contraction speed. The process of obtaining the latency, contraction rate, and contraction amplitude of the target based on the contraction initiation data, the contraction minimum data, and the resting pupil diameter specifically includes: The latency of the target is obtained by calculating the difference between the contraction initiation point and the stimulation initiation point; The difference between the resting pupil diameter and the minimum diameter is calculated to obtain the contraction amplitude of the target. Calculate the first difference between the stimulation initiation point and the minimum diameter, calculate the second difference between the minimum time and the contraction initiation point, and calculate the quotient of the first difference and the second difference to obtain the average contraction speed.

7. The parameter quantization method based on the intelligent quantization pupil pen according to claim 5, characterized in that, The analysis report includes a package of verified quantitative parameters, interpretive text, and visualization charts; The analysis report obtained based on the dynamic parameters and the resting pupil diameter specifically includes: The effectiveness of the resting pupil diameter, the pupil diameter-time curve, the latency, the contraction velocity, and the contraction amplitude is verified to obtain a package of quantitative parameters after verification. The verified quantization parameter package is compared with the preset threshold of each parameter to generate interpretation text, and a visualization chart is generated based on the verified quantization parameter package.

8. A parameter quantization system based on an intelligent quantization pupil pen, characterized in that, The parameter quantization system based on the intelligent quantization pupil pen is used to implement the parameter quantization method based on the intelligent quantization pupil pen according to any one of claims 1-7, wherein the parameter quantization system based on the intelligent quantization pupil pen includes: An optical imaging and data processing module is used to acquire a resting image sequence of the target pupil under a non-stimulation measurement environment, and to process the resting image sequence to obtain the resting pupil diameter; A controllable light source stimulation and data processing module is used to acquire a dynamic image sequence of the target pupil under a visible light stimulation measurement environment, and to obtain the dynamic parameters of the target based on the dynamic image sequence and the resting pupil diameter; The report analysis module is used to generate an analysis report based on the dynamic parameters and the resting pupil diameter.

9. A smart quantitative pupil pen, characterized in that, The intelligent quantization pupil pen includes: a memory, a processor, and a parameter quantization program based on the intelligent quantization pupil pen stored in the memory and executable on the processor. When the parameter quantization program based on the intelligent quantization pupil pen is executed by the processor, it implements the steps of the parameter quantization method based on the intelligent quantization pupil pen as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a parameter quantization program based on an intelligent quantization pupil pen, which, when executed by a processor, implements the steps of the parameter quantization method based on an intelligent quantization pupil pen as described in any one of claims 1-7.

Images