Multi-mode feedback control method and system for femtosecond laser stone crusher

Abstract

The invention discloses a multi-mode feedback control method and system for a femtosecond laser stone crusher, and relates to the technical field of medical instruments. The method comprises the following steps: constructing spectral component analysis, collecting spectral signals, and executing target chemical component identification; ultrasonic position detection: acquiring an ultrasonic echo signal through a transducer, and calculating a spatial distance; performing vision-assisted positioning, acquiring image data through an endoscope, and generating space image information; according to the spectrum identification result, the distance parameter and the space image information, multi-source data synchronization processing is completed; generating a laser parameter control instruction according to the fusion result; and executing a real-time feedback regulation and control process, obtaining feedback information, and completing control parameter updating and closed-loop response. Through fusion of multi-modal information such as spectrum identification, ultrasonic distance measurement and visual navigation, real-time identification of stone types, intelligent matching of laser parameters and accurate control of spatial positioning are realized, and the accuracy, safety and intuition of lithotripsy operation are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a multimodal feedback control method and system for a femtosecond laser lithotripsy. Background Art

[0002] In the field of minimally invasive treatment of urinary stones, laser lithotripsy has become a common clinical treatment due to its efficient and precise lithotripsy capabilities. Femtosecond lasers, leveraging the nonlinear optical effects of their ultrashort pulse width, can achieve a "cold ablation" lithotripsy process within an extremely short timescale, significantly reducing the risk of thermal damage to surrounding tissues and possessing high clinical development potential. Compared to traditional nanosecond laser devices, femtosecond lasers can achieve high energy density focusing without significant thermal diffusion, thus achieving a better balance between lithotripsy efficiency and tissue protection.

[0003] However, the current device systems used for femtosecond laser lithotripsy still have key bottlenecks in terms of intraoperative accuracy and real-time response capabilities. On the one hand, most existing systems rely solely on a single visual imaging method for spatial positioning of stones, lack the ability to obtain real-time information on the target depth dimension, and are easily affected by complex physiological factors such as intracavitary tissue overlap, gas interference, and intraoperative respiratory displacement, resulting in fiber positioning errors and affecting the targeting accuracy of the laser. On the other hand, existing equipment generally relies on the operator's experience to distinguish between stones and tissues, and lacks a real-time stone composition identification mechanism during surgery. As a result, the laser energy parameter setting cannot adapt to the physical properties of the target, increasing the risk of tissue accidental injury and inefficient lithotripsy.

[0004] Furthermore, in narrow anatomical structures (such as stenotic ureters or edematous tissue), traditional systems lack effective monitoring mechanisms for the safe operating distance between the fiber tip and the stone, further increasing the possibility of misdirected energy delivery during surgery. While some existing systems attempt to incorporate ultrasound assistance and preoperative image registration mechanisms, they still lack real-time performance, integration, and intelligent decision-making capabilities.

[0005] Therefore, it is urgent to propose a multimodal fusion control method for the femtosecond laser lithotripsy process. By integrating multidimensional perception methods such as spectral component recognition, ultrasonic position detection and vision-assisted navigation, a multi-source information-driven feedback control mechanism is constructed to achieve dynamic adaptive adjustment and closed-loop control of laser parameters, thereby improving the accuracy, safety and intraoperative response efficiency of lithotripsy. Summary of the Invention

[0006] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a multi-modal feedback control method and system for a femtosecond laser lithotripsy to solve the above-mentioned technical problems.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a multimodal feedback control method for a femtosecond laser lithotripsy, comprising:

[0008] Establish a spectral component analysis process, collect the plasma spectral signal generated by the target area under laser irradiation through a fiber optic spectrum acquisition device, and perform target chemical composition identification based on the plasma spectral signal;

[0009] Establish an ultrasonic position detection process, obtain the ultrasonic echo signal of the target area by setting the ultrasonic transmitting transducer and the ultrasonic receiving transducer, and calculate the spatial distance between the laser end and the target by combining the time difference parameter;

[0010] Set up a visually assisted positioning process to obtain real-time image data through a micro-endoscope and generate spatial image information between the fiber end and the target area;

[0011] Construct a multimodal information fusion process to fuse spectral recognition results, distance parameters, and spatial image information to complete the synchronous processing of multi-source data;

[0012] Set up the laser control scheduling process, generate laser parameter control instructions based on the fusion results, and adjust the energy parameters, frequency parameters and emission timing of the femtosecond laser;

[0013] Execute real-time feedback control process, obtain feedback information during surgery, and complete control parameter updates and closed-loop response.

[0014] The present invention is further configured such that the spectral component analysis process includes:

[0015] A high-sensitivity fiber optic spectrum acquisition device is coaxially integrated with the femtosecond laser transmission fiber to collect the spectral signal generated by the laser in the target area in real time through the plasma excitation area;

[0016] Extract characteristic spectral lines from the collected spectrum based on the spectral feature extraction algorithm, call the built-in spectral standard data set for spectral line matching, and complete the identification process of the target chemical component;

[0017] The results are analyzed to determine the type of information needed for laser parameter adjustment.

[0018] The present invention is further configured such that the spectrum recognition process uses a feature recognition algorithm to perform spectral line analysis, including:

[0019] The original spectral data is degraded based on the principal component analysis method, and the main spectral line factors are screened to construct the feature vector;

[0020] A classifier is constructed by combining supervised machine learning algorithms, and the feature vectors are compared with the spectral templates in the standard database to achieve stone type identification and output.

[0021] The present invention is further configured such that the ultrasonic position detection process includes:

[0022] The ultrasonic transmitting transducer is set to generate a pulsed excitation signal at a fixed frequency, which is emitted along the axial direction of the laser fiber and penetrates the tissue to the target area;

[0023] An ultrasonic receiving transducer is arranged coaxially with a transmitting transducer to receive an echo signal reflected from a target surface;

[0024] The received echo signal is denoised and feature extracted through signal processing, and the distance information of the target position is extracted by combining time parameters, and the spatial distance is output in real time.

[0025] The present invention is further configured such that the visually assisted positioning process includes:

[0026] A micro high-definition image sensor is embedded in a flexible and controllable sheath structure, and the front end is integrated with the laser transmission fiber;

[0027] Set up high color rendering index cold light source lighting to provide continuous and uniform illumination of the surgical area to enhance image quality;

[0028] Through high-speed image acquisition, the real-time video signal collected by the endoscope is transmitted, and the boundary features of the target area and the optical fiber space image information are extracted by combining image enhancement and edge recognition algorithms.

[0029] The present invention is further configured such that the multimodal information fusion process includes:

[0030] Receive multi-source perception data including spectrum recognition results, distance parameters and spatial image information;

[0031] Call multi-channel synchronous sampling and timestamp alignment to calibrate the time consistency between different modal data;

[0032] By constructing a fusion discriminant model to extract cross-modal feature information, a linkage mapping structure of target category-spatial position-tissue image is established to generate fusion decision parameters.

[0033] The present invention is further configured such that a fuzzy logic reasoning mechanism is adopted in the multimodal information fusion process, including:

[0034] Define component intensity, spatial proximity, and image recognition confidence as fuzzy input variables;

[0035] Set the control weight coefficients under different input variable combinations based on the rule base;

[0036] Fusion output results are generated through fuzzy membership functions and inference engines to support nonlinear scheduling decisions of control parameters.

[0037] The present invention is further configured such that the laser control scheduling process includes:

[0038] According to the component judgment label, spatial distance parameter and image auxiliary information output by the fusion model, the preset laser parameter configuration rule library is matched;

[0039] Dynamically generate a laser firing instruction set containing energy parameters, pulse width, and repetition rate control fields;

[0040] According to the laser emission instruction set, the real-time parameter loading and state scheduling of the laser drive are completed.

[0041] The present invention is further configured such that the real-time feedback control process includes:

[0042] A monitoring mechanism is set up to periodically collect status feedback information on intraoperative spectral changes, position offsets, and image displacements;

[0043] Perform deviation calculation and change trend judgment on the feedback information, and update the current laser parameter configuration in combination with the real-time control strategy model;

[0044] A closed-loop control mechanism is implemented to achieve continuous optimization and adaptive adjustment of laser control parameters through multiple adjustment iterations.

[0045] The present invention also provides a multimodal feedback control system for a femtosecond laser lithotripsy, the system comprising:

[0046] Laser emission module: equipped with a femtosecond laser module and a nanosecond laser, each used to provide laser signals with different pulse width characteristics. The laser signals are transmitted to the target area through optical fiber to achieve lithotripsy;

[0047] Fiber control module: connected to the femtosecond laser module and nanosecond laser, it manages the output channel selection, power path switching, and signal stable transmission control of the laser signal, and applies control instructions to the laser emission process at the end of the optical fiber in real time;

[0048] Spectral component analysis module: Builds a spectral component analysis process, collects the plasma spectral signal generated in the target area under laser irradiation through a fiber optic spectrum acquisition device, and performs target chemical composition identification based on the plasma spectral signal;

[0049] Ultrasonic position detection module: establishes an ultrasonic position detection process, acquires the ultrasonic echo signal of the target area by setting the ultrasonic transmitting transducer and the ultrasonic receiving transducer, and calculates the spatial distance between the laser end and the target by combining the time difference parameter;

[0050] Vision-assisted positioning module: Set up a vision-assisted positioning process, obtain real-time image data through a micro-endoscope, and generate spatial image information between the fiber end and the target area;

[0051] Endoscope module: Located at the distal end of the optical fiber, it includes an integrated image acquisition head, piezoelectric transducer, and optical fiber transmission path, enabling multifunctional collaboration in visualizing the surgical area, transmitting and receiving ultrasound signals, and focusing laser irradiation.

[0052] Fusion control module: Builds a multimodal information fusion process to fuse spectral recognition results, distance parameters, and spatial image information to complete multi-source data synchronization processing;

[0053] Laser control module: sets the laser control scheduling process, generates laser parameter control instructions based on the fusion results, and adjusts the energy parameters, frequency parameters, and emission timing of the femtosecond laser;

[0054] Human-computer interaction system: executes real-time feedback control process, obtains feedback information during the operation, and completes control parameter updates and closed-loop response.

[0055] The present invention provides a multimodal feedback control method and system for a femtosecond laser lithotripsy. The method constructs a spectral component analysis process, collects plasma spectral signals generated in a target area under laser irradiation through an optical fiber spectral acquisition device, and performs target chemical composition identification based on the plasma spectral signals; establishes an ultrasonic position detection process, obtains ultrasonic echo signals in the target area by setting an ultrasonic transmitting transducer and an ultrasonic receiving transducer, and calculates the spatial distance between the laser end and the target in combination with a time difference parameter; sets a visually assisted positioning process, obtains real-time image data through a micro-endoscope, and generates spatial image information of the optical fiber end and the target area; constructs a multimodal information fusion process, fuses spectral identification results, distance parameters, and spatial image information, and completes multi-source data synchronization processing; sets a laser control scheduling process, generates laser parameter control instructions based on the fusion results, and adjusts the energy parameters, frequency parameters, and emission timing of the femtosecond laser; executes a real-time feedback control process, obtains feedback information during the operation, and completes control parameter update and closed-loop response. The beneficial effects produced include:

[0056] 1. Real-time identification of stone composition and personalized parameter matching: The spectral component analysis module collects the plasma spectral signal generated by the laser, and combines it with the spectral line feature recognition algorithm to establish a stone composition recognition mechanism, enabling the system to dynamically identify the stone type during the lithotripsy process. Based on the recognition results, the system can adaptively control key parameters such as the energy, frequency, and pulse width of the femtosecond laser to improve the physical compatibility between the laser and the target, enhance lithotripsy efficiency, and reduce energy waste;

[0057] 2. Enhanced intraoperative spatial positioning accuracy and safety: By setting up an ultrasonic position detection module and using transmitting and receiving transducers to build a real-time ranging mechanism, the spatial distance between the end of the optical fiber and the target area can be measured. Combined with echo signal processing and time difference analysis technology, the system can monitor the depth of laser action in real time, helping to avoid the risk of accidental injury to surrounding tissues. It is particularly suitable for surgical scenarios with narrow anatomical structures or restricted fields of view.

[0058] 3. Improve intraoperative visual navigation and intuitive operation: The system acquires real-time images of the cavity by integrating a micro high-definition endoscope and a cold light source illumination device. Combined with image enhancement and edge extraction algorithms, it assists the surgeon in accurately identifying the location, morphology, and fiber optic direction of the stone, providing intuitive image support for surgical navigation and positioning control, and effectively improving the problem of insufficient visual information dimension of traditional lithotripsy equipment.

[0059] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. In the drawings:

[0061] Figure 1 This is a schematic diagram of module control logic flow of a multi-modal feedback control method for a femtosecond laser lithotripsy according to an exemplary embodiment of the present invention;

[0062] Figure 2 A system architecture diagram of a multimodal feedback control system for a femtosecond laser lithotripsy is shown as an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0064] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0065] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0066] Example 1:

[0067] A multimodal feedback control method for femtosecond laser lithotripsy, such as Figure 1 Shown, including:

[0068] Establish a spectral component analysis process, collect the plasma spectral signal generated by the target area under laser irradiation through a fiber optic spectrum acquisition device, and perform target chemical composition identification based on the plasma spectral signal;

[0069] Establish an ultrasonic position detection process, obtain the ultrasonic echo signal of the target area by setting the ultrasonic transmitting transducer and the ultrasonic receiving transducer, and calculate the spatial distance between the laser end and the target by combining the time difference parameter;

[0070] Set up a visually assisted positioning process to obtain real-time image data through a micro-endoscope and generate spatial image information between the fiber end and the target area;

[0071] Construct a multimodal information fusion process to fuse spectral recognition results, distance parameters, and spatial image information to complete the synchronous processing of multi-source data;

[0072] Set up the laser control scheduling process, generate laser parameter control instructions based on the fusion results, and adjust the energy parameters, frequency parameters and emission timing of the femtosecond laser;

[0073] Execute real-time feedback control process, obtain feedback information during surgery, and complete control parameter updates and closed-loop response.

[0074] The present invention is further configured such that the spectral component analysis process includes:

[0075] A high-sensitivity fiber optic spectrum acquisition device is coaxially integrated with the femtosecond laser transmission fiber to collect the spectral signal generated by the laser in the target area in real time through the plasma excitation area;

[0076] Extract characteristic spectral lines from the collected spectrum based on the spectral feature extraction algorithm, call the built-in spectral standard data set for spectral line matching, and complete the identification process of the target chemical component;

[0077] The type of information required for laser parameter adjustment is determined by analyzing the results. Specifically, based on the principles of plasma spectroscopy, the plasma spectra generated by stones of different chemical compositions under femtosecond laser induction have characteristic fingerprint spectral lines. For example, uric acid stones have specific absorption peaks in the 300nm-350nm band, while calcium oxalate stones have characteristic emission spectra in the 400nm-450nm band.

[0078] The present invention is further configured such that the spectrum recognition process uses a feature recognition algorithm to perform spectral line analysis, including:

[0079] The original spectral data is degraded based on the principal component analysis method, and the main spectral line factors are screened to construct the feature vector;

[0080] A classifier is constructed by combining a supervised machine learning algorithm, and the feature vector is compared with the spectral template in the standard database to realize the stone type identification output. Specifically, the spectral analysis uses the stone composition identification model to perform fast spectral matching and feature comparison with the pre-built stone spectral standard database. It can accurately identify the chemical composition of stones within sub-second time, and adaptively adjust key parameters such as the femtosecond laser pulse energy and repetition frequency in real time to achieve personalized and precise lithotripsy.

[0081] The present invention is further configured such that the ultrasonic position detection process includes:

[0082] The ultrasonic transmitting transducer is set to generate a pulsed excitation signal under fixed frequency conditions, which is emitted along the axial direction of the laser fiber and penetrates the tissue to the target area; specifically, the ultrasonic transmitting transducer uses high-frequency broadband piezoelectric ceramic materials to transmit ultrasonic signals in the direction of the stone in the form of pulse waves, and its center frequency is set to 5-10MHz to ensure good penetration and resolution in human tissue. The ultrasonic receiving transducer is used to capture the echo signal reflected by the stone interface. The distance calculation unit is based on the principle of transit time, combined with the ultrasonic sound velocity parameters of human tissue calibrated before surgery, and the formula d=c×Δt / 2, where d is the distance from the end of the optical fiber to the stone, c is the ultrasonic sound velocity, and Δt is the time difference between emission and reception, accurately calculates the spatial distance between the optical fiber and the stone. When it is detected that the distance exceeds the safety threshold, the system will trigger the sound and light warning mechanism to assist the operator to adjust the optical fiber position in time to ensure that the laser energy effectively acts on the stone target area;

[0083] An ultrasonic receiving transducer is arranged coaxially with a transmitting transducer to receive an echo signal reflected from a target surface;

[0084] Through signal processing, the received echo signal is denoised and feature extraction is performed, and the distance information of the target position is extracted in combination with time parameters, and the spatial distance is output in real time. Specifically, the distance between the optical fiber and the stone is calculated based on the principle of transit time measurement and the ultrasonic sound velocity compensation algorithm of human tissue.

[0085] The present invention is further configured such that the visually assisted positioning process includes:

[0086] A micro high-definition image sensor is embedded in a flexible and controllable sheath structure, and the front end is integrated with the laser transmission fiber;

[0087] Set up a cold light source with a high color rendering index to provide continuous and uniform illumination of the surgical area to enhance image quality;

[0088] The system uses high-speed image acquisition to transmit real-time video signals captured by the endoscope. Image enhancement and edge recognition algorithms are then combined to extract target region boundary features and fiber-optic spatial image information. Specifically, the visual assistance module consists of a micro-HD endoscope imaging unit, an LED cold light source illumination unit, and an image display terminal. The micro-endoscope is integrated into a flexible sheath and features high-definition macro imaging. The LED cold light source utilizes a high-color rendering index (CRI) white LED array. The micro-endoscope utilizes a CMOS image sensor, enabling high-definition resolution and macro imaging. Its front end and laser fiber are integrated into the flexible sheath, enabling deep penetration into human cavities to obtain real-time images of stones and surrounding tissues. The LED cold light source utilizes a high-color rendering index (CRI>90) white LED array, which is uniformly illuminated through a light-guiding fiber, avoiding the thermal damage to tissues caused by traditional thermal light sources. The captured real-time images are transmitted to the surgical display terminal via a high-speed data transmission interface. The surgeon can visually observe stone morphology, location, and the relative spatial relationship between the fiber and the stone through a high-definition visualization interface, enabling precise, vision-guided surgery and real-time surgical navigation.

[0089] The present invention is further configured such that the multimodal information fusion process includes:

[0090] Receive multi-source perception data including spectrum recognition results, distance parameters and spatial image information;

[0091] Call multi-channel synchronous sampling and timestamp alignment to calibrate the time consistency between different modal data;

[0092] By constructing a fusion discriminant model to extract cross-modal feature information, a linkage mapping structure of target category-spatial position-tissue image is established to generate fusion decision parameters.

[0093] The present invention is further configured such that a fuzzy logic reasoning mechanism is adopted in the multimodal information fusion process, including:

[0094] Define component intensity, spatial proximity, and image recognition confidence as fuzzy input variables;

[0095] Set the control weight coefficients under different input variable combinations based on the rule base;

[0096] Fusion output results are generated through fuzzy membership functions and inference engines to support nonlinear scheduling decisions of control parameters. Specifically, based on the FPGA and DSP heterogeneous computing architecture, multimodal information fusion processing is achieved through fuzzy logic decision-making algorithms, and closed-loop control of parameters such as the pulse energy, frequency, and pulse width of the femtosecond laser lithotripsy is performed through the control bus.

[0097] The present invention is further configured such that the laser control scheduling process includes:

[0098] According to the component judgment label, spatial distance parameter and image auxiliary information output by the fusion model, the preset laser parameter configuration rule library is matched;

[0099] Dynamically generate a laser firing instruction set containing energy parameters, pulse width, and repetition rate control fields;

[0100] According to the laser emission instruction set, the real-time parameter loading and state scheduling of the laser drive are completed.

[0101] The present invention is further configured such that the real-time feedback control process includes:

[0102] A monitoring mechanism is set up to periodically collect status feedback information on intraoperative spectral changes, position offsets, and image displacements;

[0103] Perform deviation calculation and change trend judgment on the feedback information, and update the current laser parameter configuration in combination with the real-time control strategy model;

[0104] A closed-loop control mechanism is implemented to achieve continuous optimization and adaptive adjustment of laser control parameters through multiple adjustment iterations.

[0105] Example 2:

[0106] See also Figure 2 , the exemplary multimodal feedback control system for a femtosecond laser lithotripsy comprises:

[0107] Laser emission module: equipped with a femtosecond laser module and a nanosecond laser, each used to provide laser signals with different pulse width characteristics. The laser signals are transmitted to the target area through optical fiber to achieve lithotripsy;

[0108] Fiber control module: connected to the femtosecond laser module and nanosecond laser, it manages the output channel selection, power path switching, and signal stable transmission control of the laser signal, and applies control instructions to the laser emission process at the end of the optical fiber in real time;

[0109] Spectral component analysis module: Builds a spectral component analysis process, collects the plasma spectral signal generated in the target area under laser irradiation through a fiber optic spectrum acquisition device, and performs target chemical composition identification based on the plasma spectral signal;

[0110] Ultrasonic position detection module: establishes an ultrasonic position detection process, acquires the ultrasonic echo signal of the target area by setting the ultrasonic transmitting transducer and the ultrasonic receiving transducer, and calculates the spatial distance between the laser end and the target by combining the time difference parameter;

[0111] Vision-assisted positioning module: Set up a vision-assisted positioning process, obtain real-time image data through a micro-endoscope, and generate spatial image information between the fiber end and the target area;

[0112] Endoscope module: Located at the distal end of the optical fiber, it includes an integrated image acquisition head, piezoelectric transducer, and optical fiber transmission path, enabling multifunctional collaboration in visualizing the surgical area, transmitting and receiving ultrasound signals, and focusing laser irradiation.

[0113] Fusion control module: Builds a multimodal information fusion process to fuse spectral recognition results, distance parameters, and spatial image information to complete multi-source data synchronization processing;

[0114] Laser control module: sets the laser control scheduling process, generates laser parameter control instructions based on the fusion results, and adjusts the energy parameters, frequency parameters, and emission timing of the femtosecond laser;

[0115] Human-computer interaction system: executes real-time feedback control process, obtains feedback information during the operation, and completes control parameter updates and closed-loop response.

[0116] It should be noted that the multimodal feedback control system for a femtosecond laser lithotripsy provided in the above-mentioned embodiment and the multimodal feedback control method for a femtosecond laser lithotripsy provided in the above-mentioned embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiments and will not be repeated here. In actual applications, the multimodal feedback control system for a femtosecond laser lithotripsy provided in the above-mentioned embodiment can, as needed, allocate the aforementioned functions to different functional modules, i.e., divide the internal structure of the system into different functional modules to perform all or part of the functions described above. This is not a limitation herein.

[0117] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0118] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0119] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0120] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0121] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0122] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0124] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0126] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0127] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A multimodal feedback control method for a femtosecond laser lithotripsy, characterized in that: include: Establish a spectral component analysis process, collect the plasma spectral signal generated by the target area under laser irradiation through a fiber optic spectrum acquisition device, and perform target chemical composition identification based on the plasma spectral signal; Establish an ultrasonic position detection process, obtain the ultrasonic echo signal of the target area by setting the ultrasonic transmitting transducer and the ultrasonic receiving transducer, and calculate the spatial distance between the laser end and the target by combining the time difference parameter; Set up a visually assisted positioning process to obtain real-time image data through a micro-endoscope and generate spatial image information between the fiber end and the target area; Construct a multimodal information fusion process to fuse spectral recognition results, distance parameters, and spatial image information to complete the synchronous processing of multi-source data; Set up the laser control scheduling process, generate laser parameter control instructions based on the fusion results, and adjust the energy parameters, frequency parameters and emission timing of the femtosecond laser; Execute real-time feedback control process, obtain feedback information during surgery, and complete control parameter updates and closed-loop response.

2. A multimodal feedback control method for a femtosecond laser lithotripsy according to claim 1, characterized in that: The spectral component analysis process includes: A high-sensitivity fiber optic spectrum acquisition device is coaxially integrated with the femtosecond laser transmission fiber to collect the spectral signal generated by the laser in the target area in real time through the plasma excitation area; Extract characteristic spectral lines from the collected spectrum based on the spectral feature extraction algorithm, call the built-in spectral standard data set for spectral line matching, and complete the identification process of the target chemical component; The results are analyzed to determine the type of information needed for laser parameter adjustment.

3. The multimodal feedback control method for a femtosecond laser lithotripsy according to claim 2, characterized in that: The spectrum recognition process uses feature recognition algorithms to analyze spectral lines, including: The original spectral data is degraded based on the principal component analysis method, and the main spectral line factors are screened to construct the feature vector; A classifier is constructed by combining supervised machine learning algorithms, and the feature vectors are compared with the spectral templates in the standard database to achieve stone type identification and output.

4. The multimodal feedback control method for a femtosecond laser lithotripsy according to claim 1, characterized in that: The ultrasonic position detection process includes: The ultrasonic transmitting transducer is set to generate a pulsed excitation signal at a fixed frequency, which is emitted along the axial direction of the laser fiber and penetrates the tissue to the target area; An ultrasonic receiving transducer is arranged coaxially with a transmitting transducer to receive an echo signal reflected from a target surface; The received echo signal is denoised and feature extracted through signal processing, and the distance information of the target position is extracted by combining time parameters, and the spatial distance is output in real time.

5. The multimodal feedback control method for a femtosecond laser lithotripsy according to claim 1, characterized in that: The vision-assisted positioning process includes: A micro high-definition image sensor is embedded in a flexible and controllable sheath structure, and the front end is integrated with the laser transmission fiber; Set up high color rendering index cold light source lighting to provide continuous and uniform illumination of the surgical area to enhance image quality; Through high-speed image acquisition, the real-time video signal collected by the endoscope is transmitted, and the boundary features of the target area and the optical fiber space image information are extracted by combining image enhancement and edge recognition algorithms.

6. The multimodal feedback control method for a femtosecond laser lithotripsy according to claim 1, characterized in that: The multimodal information fusion process includes: Receive multi-source perception data including spectrum recognition results, distance parameters and spatial image information; Call multi-channel synchronous sampling and timestamp alignment to calibrate the time consistency between different modal data; By constructing a fusion discriminant model to extract cross-modal feature information, a linkage mapping structure of target category-spatial position-tissue image is established to generate fusion decision parameters.

7. The multimodal feedback control method for a femtosecond laser lithotripsy according to claim 6, characterized in that: The fuzzy logic reasoning mechanism is used in the multimodal information fusion process, including: Define component intensity, spatial proximity, and image recognition confidence as fuzzy input variables; Set the control weight coefficients under different input variable combinations based on the rule base; Fusion output results are generated through fuzzy membership functions and inference engines to support nonlinear scheduling decisions of control parameters.

8. The multimodal feedback control method for a femtosecond laser lithotripsy according to claim 6, characterized in that: The laser control scheduling process includes: According to the component judgment label, spatial distance parameter and image auxiliary information output by the fusion model, the preset laser parameter configuration rule library is matched; Dynamically generate a laser firing instruction set containing energy parameters, pulse width, and repetition rate control fields; According to the laser emission instruction set, the real-time parameter loading and state scheduling of the laser drive are completed.

9. The multimodal feedback control method for a femtosecond laser lithotripsy according to claim 1, characterized in that: The real-time feedback control process includes: A monitoring mechanism is set up to periodically collect status feedback information on intraoperative spectral changes, position offsets, and image displacements; Perform deviation calculation and change trend judgment on the feedback information, and update the current laser parameter configuration in combination with the real-time control strategy model; A closed-loop control mechanism is implemented to achieve continuous optimization and adaptive adjustment of laser control parameters through multiple adjustment iterations.

10. A multimodal feedback control system for a femtosecond laser lithotripsy, used to implement the multimodal feedback control method for a femtosecond laser lithotripsy according to any one of claims 1 to 9, characterized in that: include: Laser emission module: equipped with a femtosecond laser module and a nanosecond laser, each used to provide laser signals with different pulse width characteristics. The laser signals are transmitted to the target area through optical fiber to achieve lithotripsy; Fiber control module: connected to the femtosecond laser module and nanosecond laser, it manages the output channel selection, power path switching, and signal stable transmission control of the laser signal, and applies control instructions to the laser emission process at the end of the optical fiber in real time; Spectral component analysis module: Builds a spectral component analysis process, collects the plasma spectral signal generated in the target area under laser irradiation through a fiber optic spectrum acquisition device, and performs target chemical composition identification based on the plasma spectral signal; Ultrasonic position detection module: establishes an ultrasonic position detection process, acquires the ultrasonic echo signal of the target area by setting the ultrasonic transmitting transducer and the ultrasonic receiving transducer, and calculates the spatial distance between the laser end and the target by combining the time difference parameter; Vision-assisted positioning module: Set up a vision-assisted positioning process, obtain real-time image data through a micro-endoscope, and generate spatial image information between the fiber end and the target area; Endoscope module: Located at the distal end of the optical fiber, it includes an integrated image acquisition head, piezoelectric transducer, and optical fiber transmission path, enabling multifunctional collaboration in visualizing the surgical area, transmitting and receiving ultrasound signals, and focusing laser irradiation. Fusion control module: Builds a multimodal information fusion process to fuse spectral recognition results, distance parameters, and spatial image information to complete multi-source data synchronization processing; Laser control module: sets the laser control scheduling process, generates laser parameter control instructions based on the fusion results, and adjusts the energy parameters, frequency parameters, and emission timing of the femtosecond laser; Human-computer interaction system: executes real-time feedback control process, obtains feedback information during the operation, and completes control parameter updates and closed-loop response.

Images