Visual image reconstruction system based on brain-computer interface
By monitoring and adjusting the response voltage of the flexible electrode, and combining multi-contact collaboration and electric field superposition technology, accurate simulation of visual features was achieved, solving the problem of low resolution in existing technologies and optimizing the visual experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-31
- Publication Date
- 2026-04-14
AI Technical Summary
Existing image reconstruction systems have few channels, few stimulus points, and low resolution, making it difficult to meet the visual reconstruction needs of patients with severely impaired visual function.
By monitoring the response voltage of the flexible electrodes through a feedback adjustment module to ensure constant current stimulation, and combining the precise positioning of the flexible electrodes in the visual cortex of the brain, the precise simulation of visual features is achieved by using a multi-contact collaborative approach and electric field superposition technology.
It improves the resolution and accuracy of the visual reconstruction system, reduces damage to other brain neurons, and optimizes the visual experience.
Smart Images
Figure CN121846524A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of brain-computer interface technology, and in particular to a visual image reconstruction system based on a brain-computer interface. Background Technology
[0002] Among the many causes of visual impairment, cataracts, glaucoma, age-related macular degeneration (AMD), retinitis pigmentosa (RP), and diabetic retinopathy are considered the leading causes of blindness. Although these diseases have different causes, they all involve damage and death of retinal neurons, ultimately leading to severe impairment of visual function. Traditional treatments mainly focus on addressing the underlying cause and alleviating symptoms, such as surgical treatment for cataracts, intraocular pressure-lowering treatment for glaucoma, and anti-VEGF therapy for AMD. However, when the disease progresses to advanced stages, especially when there is extensive death of retinal ganglion cells or severe visual impairment, traditional treatments often fail to achieve satisfactory results.
[0004] The rise of brain-computer interface (BCI) technology has brought revolutionary hope to visual reconstruction. When humans first used BCI technology to allow blind people to "see" light spots, animal images, and even virtual objects, a revolution that would overturn traditional visual cognition quietly began. This cutting-edge technology, which integrates neuroscience, artificial intelligence, and materials engineering, is moving from the laboratory to the clinic, opening a "third eye" for the blind and providing infinite possibilities for expanding the boundaries of human perception.
[0005] Existing image reconstruction systems have few channels and few stimulus points, resulting in very low resolution.
[0006] Therefore, existing technologies still need to be improved and developed. Summary of the Invention
[0007] Based on this, this application provides a visual image reconstruction system based on a brain-computer interface, which monitors the response voltage of the flexible electrodes in each channel through a feedback adjustment module to ensure constant current stimulation, enabling the system to learn collaboratively with the brain and optimize the visual experience.
[0008] To achieve the above objectives, embodiments of this application provide a visual image reconstruction system based on a brain-computer interface, comprising:
[0009] An image acquisition and processing module is used to acquire external visual images and perform noise reduction, filtering and normalization processing on the visual images, and then extract the visual features of the visual images.
[0010] An electrical stimulation control module is used to convert visual features into electrical stimulation commands that include electrode channel selection, current intensity, stimulation timing, and polarity matching.
[0011] A flexible electrode module, which is implanted in the visual cortex of a patient's or animal's brain, is used to receive electrical stimulation commands and control the corresponding flexible electrodes to stimulate neurons to induce visual perception.
[0012] The feedback adjustment module is used to monitor the response voltage of the flexible electrode in each channel. If the impedance of any flexible electrode in any channel increases, the information of the flexible electrode in the corresponding channel is sent to the electrical stimulation control module. The electrical stimulation control module automatically adjusts the voltage of the corresponding flexible electrode to ensure constant current stimulation.
[0013] Preferably, the electrical stimulation control module includes a PCB board, on which a biocompatible ceramic substrate is connected via solder pads. The ceramic substrate has metal-filled through holes, and the other side of the ceramic substrate is soldered to a flexible electrode module with several channels via the through holes. The stimulation point at the other end of the flexible electrode module is attached to the visual cortex of the brain.
[0014] A coil for wireless charging and signal transmission is provided on one side of the PCB board.
[0015] Preferably, the flexible electrode of each channel is electrically connected to an independent current source or voltage source.
[0016] Preferably, the current source is a Howland current source.
[0017] Preferably, the flexible electrodes of each channel are positioned on both sides of the neurons to be stimulated in the visual cortex of the brain, so that the flexible electrodes provide the strongest stimulation to the neurons.
[0018] Preferably, the flexible electrode has a corresponding cathode and an anode, and the cathode and anode cooperate to form a complete current loop.
[0019] Preferably, when charge accumulates, the flexible electrode switches between different channels at a high speed at the microsecond level, working in turn.
[0020] Preferably, the visual features are object edge features, contour features, and shape features.
[0021] Preferably, the image acquisition and processing module includes wearable glasses and a graphics processor;
[0022] The graphics processor can automatically select the corresponding visual feature extraction strategy according to the user's actual environmental needs.
[0023] Preferably, the environmental requirements include indoor walking, object recognition, and obstacle avoidance.
[0024] The visual image reconstruction system based on a brain-computer interface provided by this invention has the following advantages and beneficial effects:
[0025] The feedback adjustment module monitors the response voltage of the flexible electrode in each channel. If the impedance of any flexible electrode in any channel increases, the information of the flexible electrode in the corresponding channel is sent to the electrical stimulation control module. The electrical stimulation control module automatically adjusts the voltage of the corresponding flexible electrode to ensure constant current stimulation, enabling the system to learn collaboratively with the brain and optimize the visual experience.
[0026] The flexible electrodes in each channel are positioned on both sides of the neuron to be stimulated in the visual cortex of the brain. This allows the focus of the electric field to be concentrated on the neuron to be stimulated, enabling precise control of the stimulation location and effectively avoiding damage to other brain neurons. Attached Figure Description
[0027] Figure 1 This is a schematic diagram of the modules of the visual image reconstruction system based on brain-computer interface of this application.
[0028] Figure 2 This is a schematic diagram of the flexible electrode module in the visual image reconstruction system based on a brain-computer interface according to this application.
[0029] Figure 3 This is a partial schematic diagram of the flexible electrode module in the visual image reconstruction system based on a brain-computer interface of this application.
[0030] Figure 4 This is a schematic diagram of the image acquisition and processing module in the visual image reconstruction system based on brain-computer interface of this application. Detailed Implementation
[0031] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate preferred embodiments of the application. However, this application may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.
[0032] It should be noted that when a component is considered to be "connected" to another component, it can be directly connected to and integrated with the other component, or there may be an intervening component present. The term "mounted" and similar expressions used in this document are for illustrative purposes only.
[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.
[0034] like Figure 1 As shown, a visual image reconstruction system based on a brain-computer interface is provided, which includes:
[0035] An image acquisition and processing module is used to acquire external visual images and perform noise reduction, filtering and normalization processing on the visual images, and then extract the visual features of the visual images.
[0036] An electrical stimulation control module is used to convert visual features into electrical stimulation commands that include electrode channel selection, current intensity, stimulation timing, and polarity matching.
[0037] A flexible electrode module, which is implanted in the visual cortex of a patient's or animal's brain, is used to receive electrical stimulation commands and control the corresponding flexible electrodes to stimulate neurons to induce visual perception.
[0038] The feedback adjustment module is used to monitor the response voltage of the flexible electrode in each channel. If the impedance of any flexible electrode in any channel increases, the information of the flexible electrode in the corresponding channel is sent to the electrical stimulation control module. The electrical stimulation control module automatically adjusts the voltage of the corresponding flexible electrode to ensure constant current stimulation.
[0039] This application encodes visual images acquired by an image acquisition and processing module into neural electrical signals after processing. These neural electrical signals are then converted into electrical stimulation commands, which are transmitted to the brain via flexible electrical stimulation electrodes. The brain interprets these neural electrical signals into the perceived image. Visual impairment is primarily caused by damage to the retina or optic nerve. This application utilizes brain-computer interface visual reconstruction technology to bypass the damaged visual pathway through "direct signal transmission," sending information directly to the brain. This "bionic vision" does not reproduce real images but simulates light spots, lines, or simple shapes through electrical pulse patterns, enabling patients or animals to perceive the presence and location of light. The electrical stimulation control module is also implanted in the visual cortex of the patient's or animal's brain.
[0040] Since pixel data alone is meaningless to the brain, it is necessary to extract key visual features, such as object edges (e.g., table edges), door frame positions, and specific shapes (squares, circles). The image acquisition and processing module intelligently selects the optimal stimulus strategy based on environmental needs (e.g., indoor walking, object recognition, or obstacle avoidance). This step is equivalent to simplifying complex images into "line drawings" or "outlines" that the brain can understand.
[0041] Converting graphic signals into specific electrical stimulation commands—which can include electrode channel selection, constant current intensity, stimulation timing, and polarity matching—is essentially a process of "encoding visual information into neural stimulation signals." The encoded electrical signals are transmitted through an electrode array implanted in the visual cortex, stimulating neurons to induce visual perception. By incorporating a feedback regulation module, the brain's response to stimulation can be monitored, and stimulation parameters can be dynamically adjusted, enabling the system to learn collaboratively with the brain and optimize the visual experience.
[0042] The electrode array collects the response intensity signals of brain neurons and the impedance change signals of each electrode channel. If an increase in brain tissue impedance is detected in a certain channel (possibly due to glial cell encapsulation) or insufficient neuronal response intensity, the feedback adjustment module sends a signal to the electrical stimulation control module. The electrical stimulation control module automatically fine-tunes the constant current stimulation voltage compensation parameters of the corresponding channel to ensure the stability of the constant current output and the consistency of the electrical stimulation effect.
[0043] like Figure 2 and Figure 3 As shown, the electrical stimulation control module includes a PCB board 100, which is connected to a biocompatible ceramic substrate 300 via pads 200. The ceramic substrate 300 has metal-filled through holes, and a flexible electrode 400 with several channels is soldered to the other side of the ceramic substrate 300 through the through holes. The stimulation point at the other end of the flexible electrode 400 is attached to the visual cortex of the brain. A coil 500 for wireless charging and signal transmission is provided on one side of the PCB board 100.
[0044] In practice, each flexible electrode in each channel is electrically connected to an independent current or voltage source, specifically a Howland current source. This allows for the simultaneous stimulation of multiple independent electrode points. Alternatively, other precision modules similar to the Howland current source can be used. The Howland current source ensures that even if the body's impedance fluctuates due to physiological changes, the current flowing through each electrode remains at a pre-set value (e.g., 200 μA), thus guaranteeing the precision of stimulation and ensuring consistent brightness of the optic hallucination each time it is "activated."
[0045] For example, in visual reconstruction, if you want to see a "cross", the system will activate two sets of electrodes representing "horizontal" and "vertical" at the same time, so that the brain can perceive the two lines at the same time, instead of drawing the horizontal line first and then the vertical line.
[0046] In practice, the flexible electrodes of each channel are positioned on both sides of the neurons to be stimulated in the visual cortex of the brain, so that the flexible electrodes provide the strongest stimulation to the neurons.
[0047] To precisely control the stimulation location and avoid "accidentally damaging" surrounding neurons (reducing side effects), the system employs a "multi-touch synergy" approach, utilizing the principle of "electric field superposition." By adjusting the magnitude and polarity (positive or negative) of the current on different electrodes, the "focus" of the electric field can be concentrated at a specific location between two electrodes. For example, if electrode A outputs +1 unit current and electrode B outputs -1 unit current, the strongest stimulation point will be at the midpoint between A and B. This method can achieve a higher resolution of "virtual electrodes" than physical electrode density. Therefore, placing a pair of electrodes on either side of the neuron to be stimulated provides the strongest stimulation.
[0048] In specific implementation, the flexible electrode has corresponding cathodes and anodes. The cathodes and anodes work together to form a complete current loop. When charge accumulates, the flexible electrode switches between different channels at a high speed at a microsecond level. Of course, under certain hardware resource constraints, the channels will also work at an extremely high speed.
[0049] The essence of electrode stimulation of neurons is to use an electric field to change the "potential difference" of the neuronal cell membrane, thereby inducing an electric signal. After the electrode comes into contact with brain tissue, when a current (usually in the microampere (mA) or milliampere (mA) range) flows out of the electrode, it generates a tiny electric field around it. This electric field interferes with the ion channels on the neuronal cell membrane. If the electric field is strong enough, it will increase the positive charge inside the neuron (i.e., "depolarization"). Once it exceeds a certain threshold, the neuron will generate an action potential (i.e., a nerve impulse), as if it has been "ignited". Therefore, in multi-channel stimulation, one electrode is usually designated as the "cathode" (current flows in, usually the main site that causes neuronal excitation), and the other electrode is designated as the "anode" (current flows out, acting as a circuit).
[0050] While the human eye has visual persistence, neurons also have a refractory period. For example, the system switches rapidly between channels 1, 2, and 3 at a speed on the order of microseconds. Because the switching speed is extremely fast, the brain does not perceive flickering, but rather a continuous series of stimuli covering a large area. This is common in flexible electrode arrays that cover a large area of the cortex.
[0051] In practice, the image acquisition and processing module includes wearable glasses and a graphics processor (GPU). The GPU can automatically select the corresponding visual feature extraction strategy based on the user's actual environmental needs. The wearable glasses are equipped with a miniature camera that captures external image information in real time (e.g., a red table in front of you). This image data is transmitted to the GPU in real time for processing, extracting the visual features of the image.
[0052] like Figure 4 As shown, the glasses are equipped with an external coil that communicates with and supplies power to the electrostimulation control module via a coil 500 within the module. Wireless communication and power supply are achieved through this external coil and the coil 500 within the electrostimulation control module.
[0053] In summary, the encoded neural electrical signals are "pushed" by electrodes in the form of microcurrents to make neurons fire, while the multichannel uses "parallel lighting" and "current guidance" to draw specific images or movement commands on the cerebral cortex like pixels, so that you can "see" or "move".
[0054] In summary, this application provides a brain-computer interface-based visual image reconstruction system. A feedback adjustment module monitors the response voltage of the flexible electrodes in each channel. If an increase in the impedance of any flexible electrode is detected, the corresponding information is sent to the electrical stimulation control module. The module automatically adjusts the voltage of the corresponding flexible electrode to ensure constant current stimulation, enabling the system to learn collaboratively with the brain and optimize the visual experience. The flexible electrodes in each channel are positioned on either side of the neuron to be stimulated within the visual cortex of the brain. This concentrates the electric field on the neuron, allowing for precise control of the stimulation location and effectively avoiding damage to other brain neurons.
[0055] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0056] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A visual image reconstruction system based on a brain-computer interface, characterized in that, include: An image acquisition and processing module is used to acquire external visual images and perform noise reduction, filtering and normalization processing on the visual images, and then extract the visual features of the visual images. An electrical stimulation control module is used to convert visual features into electrical stimulation commands that include electrode channel selection, current intensity, stimulation timing, and polarity matching. A flexible electrode module, which is implanted in the visual cortex of a patient's or animal's brain, is used to receive electrical stimulation commands and control the corresponding flexible electrodes to stimulate neurons to induce visual perception. The feedback adjustment module is used to monitor the response voltage of the flexible electrode in each channel. If the impedance of any flexible electrode in any channel increases, the information of the flexible electrode in the corresponding channel is sent to the electrical stimulation control module. The electrical stimulation control module automatically adjusts the voltage of the corresponding flexible electrode to ensure constant current stimulation.
2. The visual image reconstruction system based on a brain-computer interface according to claim 1, characterized in that, The electrical stimulation control module includes a PCB board, which is connected to a biocompatible ceramic substrate via solder pads. The ceramic substrate has metal-filled through holes. The other side of the ceramic substrate is soldered to a flexible electrode module with several channels via the through holes. The stimulation point at the other end of the flexible electrode module is attached to the visual cortex of the brain. A coil for wireless charging and signal transmission is provided on one side of the PCB board.
3. The visual image reconstruction system based on a brain-computer interface according to claim 2, characterized in that, Each channel's flexible electrode is electrically connected to an independent current or voltage source.
4. The visual image reconstruction system based on a brain-computer interface according to claim 3, characterized in that, The current source is a Howland current source.
5. The visual image reconstruction system based on a brain-computer interface according to claim 2, characterized in that, The flexible electrodes in each channel are positioned on either side of the neurons to be stimulated in the visual cortex of the brain, so that the flexible electrodes provide the strongest stimulation to the neurons.
6. The visual image reconstruction system based on a brain-computer interface according to claim 2, characterized in that, The flexible electrode has a corresponding cathode and an anode, and the cathode and anode cooperate to form a complete current loop.
7. The visual image reconstruction system based on a brain-computer interface according to claim 1, characterized in that, When charge accumulates, the flexible electrode switches between different channels at a high speed at the microsecond level, working in turn.
8. The visual image reconstruction system based on a brain-computer interface according to claim 1, characterized in that, The visual features are object edge features, contour features, and shape features.
9. The visual image reconstruction system based on a brain-computer interface according to claim 8, characterized in that, The image acquisition and processing module includes wearable glasses and a graphics processor; The graphics processor can automatically select the corresponding visual feature extraction strategy according to the user's actual environmental needs.
10. The visual image reconstruction system based on a brain-computer interface according to claim 9, characterized in that, The environmental requirements include indoor walking, object recognition, and obstacle avoidance.