Cardiac intervention operation scene low-light enhancement method and system based on diffusion model

Abstract

The invention discloses a heart interventional operation scene low-light enhancement method and system based on a diffusion model, and aims to solve the problem of unclear operation view in a low-light environment. Multi-angle low-light images are acquired through a micro camera and an external camera system, and enhancement processing is performed by using a diffusion model optimized for a cardiac interventional operation scene. The diffusion model adopts two low-light image sources with different scales and angles as a training data set so as to capture image details of different levels from microcosmic to macrocosmic. By performing the diffusion process under different resolutions, the micro structure and the overall tissue layout in the surgical field of view can be more accurately reconstructed. A noise scheduling value is dynamically adjusted by introducing prior knowledge related to a cardiac interventional operation, and illumination parameter prediction is performed to guide optimization of diffusion model parameters, so that the diffusion model can more accurately improve the image quality of an operation area in real time.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing technology, and more specifically, to a low-light enhancement method and system for cardiac interventional surgery scenes based on a diffusion model. Background Art

[0002] Heart valve replacement surgery is a key treatment in the field of modern cardiac surgery, which aims to replace damaged or diseased heart valves to restore normal heart function. Traditional heart valve replacement surgery is usually performed through a median sternotomy incision. Although this method provides surgeons with a wider field of view, it also increases the patient's trauma and postoperative recovery time. In recent years, the development of minimally invasive cardiac surgery techniques, such as transcatheter aortic valve replacement (TAVR) and minimally invasive mitral valve repair, has reduced patient trauma, but has also brought new challenges, especially in terms of surgical field of view.

[0003] Accurate visual perception is crucial in heart valve replacement surgery. Surgeons need to clearly observe the structure of the heart valve, the state of the surrounding tissues, and the placement of the artificial valve. However, due to the complex anatomical structure of the heart and the limited operating space required for surgery, low-light areas often occur, which seriously affects the smooth progress of the operation.

[0004] The low light conditions in cardiac interventional surgery are mainly due to the following aspects:

[0005] 1. Complexity of cardiac anatomy: The heart has a complex internal structure with multiple chambers and septa, which block light and cause insufficient light in certain areas.

[0006] 2. Limitation of surgical incision: To reduce trauma to patients, surgical incisions are often smaller, which limits the placement and number of light sources.

[0007] 3. Blockage of surgical instruments: During the operation, the use of various surgical instruments will block part of the light and cause local shadows.

[0008] 4. Interference from blood and tissue fluid: Bleeding and tissue fluid during surgery will absorb and scatter light, reducing the lighting effect.

[0009] These low light conditions bring many adverse effects to surgery:

[0010] 1. Increased difficulty of surgery: In low light conditions, it is difficult for doctors to accurately identify subtle anatomical structures, which increases the difficulty of surgical operations.

[0011] 2. Prolonged operation time: Due to unclear vision, doctors need to spend more time to confirm each step of the operation, which significantly prolongs the time of the entire operation.

[0012] 3. Increased surgical risk: Poor vision may lead to operational errors and increase the risk of complications such as bleeding, paravalvular leak, conduction block, etc.

[0013] 4. Increase the doctor's fatigue: Working for a long time under low-light conditions will increase the doctor's visual fatigue and may affect the quality and safety of the operation.

[0014] 5. Impact on surgical teaching: For young surgeons in training, the effect of surgical observation and learning under low light conditions will be greatly reduced.

[0015] At present, in order to improve the surgical field of view, the medical community has taken some measures:

[0016] 1. Improved surgical light design: Brighter, better-focused surgical lights have been developed, but this approach still has difficulty addressing the illumination of deep tissue.

[0017] 2. Use head-mounted lighting equipment: This type of equipment can change the lighting direction as the doctor's head moves, but it often increases the doctor's burden and the light intensity is limited.

[0018] 3. Endoscopic technology: The use of endoscopes in some minimally invasive surgeries can provide a better field of view, but its application is limited and the image quality is limited by the performance of the equipment.

[0019] 4. Fluorescence imaging: By injecting fluorescent dyes and using special light sources, certain tissue structures can be highlighted, but this method cannot comprehensively improve the overall lighting conditions.

[0020] Although these methods have improved the surgical field of view to a certain extent, they still cannot completely solve the low light problem in heart valve replacement surgery. Especially in deep tissues and narrow spaces, existing technologies still have difficulty in providing ideal lighting effects.

[0021] In addition, existing lighting solutions often only consider the intensity of light, while ignoring the importance of light quality. In cardiac surgery, different tissue structures have different reflection and absorption characteristics of light. Simply increasing the light intensity may cause some areas to be overexposed while other areas are still underlit. This uneven lighting not only fails to effectively improve the field of vision, but may also cause visual interference and affect the doctor's judgment.

[0022] Another issue worth noting is that most existing lighting solutions are static and cannot dynamically adjust the light according to the different stages and needs of the surgical process. Heart valve replacement surgery is a dynamic process, and the lighting requirements at different stages are also different. For example, more concentrated and bright light may be required during the suturing stage, while softer and more uniform light may be required during the observation stage. Lighting systems that lack flexibility have difficulty meeting such dynamic needs.

[0023] The diffusion model was first proposed by Sohl-Dickstein et al. in 2015, and has achieved remarkable results in image generation, super-resolution reconstruction, and image restoration in recent years. The core idea of ​​this model is to generate or reconstruct images by simulating a process that gradually approaches the data distribution. In the field of image enhancement, the diffusion model has demonstrated superior performance to traditional methods, especially when dealing with problems such as low light, noise, and blur. However, when the standard diffusion model is directly applied to low-light image enhancement in cardiac interventional surgery scenes, it still faces the problems of difficult noise control, insufficient local detail recovery, and poor adaptability. Therefore, the development of a low-light enhancement method and system based on a diffusion model suitable for cardiac interventional surgery scenes is still a technical problem that has not yet been broken through. Summary of the invention

[0024] Due to the problems existing in the prior art, the present invention proposes a low-light enhancement method and system for cardiac interventional surgery scenes based on a diffusion model, aiming to solve the problem of unclear surgical field of view in low-light environments, which affects the accuracy and safety of surgical operations. The present invention collects multi-angle low-light images through a micro camera and an external camera system, and uses a diffusion model optimized for cardiac interventional surgery scenes for enhancement processing.

[0025] To achieve the above objectives, in a first aspect, the present invention provides a low-light enhancement method for cardiac interventional surgery scenes based on a diffusion model, which is characterized by comprising:

[0026] Step S1, constructing and pre-training a diffusion model for cardiac interventional surgery: collecting image pairs under different lighting conditions during cardiac interventional surgery for pre-training of the diffusion model; the diffusion model designs a diffusion process with multiple time steps, each step corresponding to a gradual improvement in image quality; the diffusion process is performed at high resolution and low resolution for the fine structure inside the heart and the global structure of the surrounding tissue under the heart motion state;

[0027] Step S2, obtaining a low-light image of the cardiac interventional surgery scene: using a miniature camera, inserted into the heart through a surgical incision or catheter, to obtain a real-time image of the heart, and using an external camera system to capture a global image of the entire surgical area;

[0028] Step S3, using the pre-trained diffusion model to process the low-light image in step S2 in real time to obtain an enhanced high-quality image, and using the image data continuously collected during the operation to perform online learning and parameter adjustment of the model: the diffusion model dynamically adjusts the value of noise scheduling according to different stages of the operation process; predicts illumination parameters according to cardiac anatomical structure information, characteristic information of surgical instruments and characteristic information of different types of valves, and adjusts the parameters in a certain time step in the diffusion model;

[0029] Step S4: Feedback the enhanced high-quality image to the lighting system of the operating area to dynamically adjust the lighting system.

[0030] The diffusion model uses two low-light image sources with different scales and angles as training data sets to capture image details at different levels from microscopic to macroscopic. By performing the diffusion process at different resolutions, the microstructures and overall tissue layout in the surgical field can be reconstructed more accurately. By introducing prior knowledge related to cardiac interventional surgery to dynamically adjust the value of noise scheduling, and predicting illumination parameters to guide the optimization of diffusion model parameters, the diffusion model can improve the image quality of the surgical area more accurately in real time.

[0031] Furthermore, in the step S1, when pre-training the diffusion model, the parameters including the noise level and the step size in the diffusion process are optimized.

[0032] Furthermore, in step S3, a small noise scheduling parameter is used in the operation preparation stage; the noise scheduling parameter is increased during the valve replacement process; and the noise scheduling parameter is reduced again in the suturing stage.

[0033] Furthermore, in step S3, when predicting the lighting parameters, the shadow areas in the surgical area caused by the surgical instruments and the doctor's operation are identified, and the shadows are eliminated by enhancing the image brightness and contrast; the changes in the color of the internal tissue of the heart due to factors including blood flow and lighting angle are identified, and the image is corrected according to a preset standard color model.

[0034] Furthermore, in step S3, a user interaction interface is introduced to allow doctors to provide real-time feedback on the enhanced image according to their needs; based on the doctor's feedback, the enhanced image is fine-tuned by quickly fine-tuning the parameters of the diffusion model.

[0035] Furthermore, in step S4, the intensity and direction of the surgical light are dynamically adjusted according to the brightness distribution in the enhanced image; for the internal area of ​​the heart, a controllable micro LED light source is used to adjust the internal lighting according to the needs of the enhanced image.

[0036] In a second aspect, the present invention provides a low-light enhancement system for cardiac interventional surgery scenes based on a diffusion model, characterized in that the system is used to implement the low-light enhancement method for cardiac interventional surgery scenes as described above, comprising:

[0037] Image acquisition module, which acquires low-light images of the heart and the entire surgical area in real time from the micro camera and global camera;

[0038] The diffusion model processing module based on the GPU acceleration server introduces multi-scale processing strategy and illumination parameter prediction module to execute dynamic image enhancement algorithm;

[0039] Intelligent lighting module that adjusts the parameters of surgical lighting equipment based on the enhanced image.

[0040] Furthermore, it also includes a user interaction module that provides an interactive interface for the surgical team; doctors can provide real-time feedback on the enhanced images according to their own needs.

[0041] Furthermore, the diffusion model processing module includes a data set, a pre-training module, a model real-time operation module, an illumination parameter prediction module, and an image quality assessment module; the model real-time operation module obtains high-quality images through low-light image enhancement, and dynamically adjusts the model parameters according to the prediction results of the illumination parameter prediction module and the evaluation results of the image quality assessment module.

[0042] Furthermore, the user interaction module allows the doctor to mark areas or details that require special attention. The image quality assessment module can receive feedback from the user interaction interface and assess whether the image quality meets the requirements.

[0043] Compared with the prior art, the present invention has the following technical effects:

[0044] 1. Effectively improve image quality: enhance the visibility of valves and surrounding tissues, improve the contrast between surgical instruments and tissues, reduce image noise, and provide more stable visual feedback.

[0045] 2. Customized optimization: Integrate prior knowledge of cardiac anatomy and surgical instruments to perform precise enhancements for different types of valve surgeries and adapt to dynamic scenarios such as heart beating and respiratory movement.

[0046] 3. Real-time interaction: Real-time interaction with the surgical lighting system, dynamically adjusting lighting parameters according to enhanced images, and achieving coordinated optimization of the lighting system and image enhancement.

[0047] 4. Improve surgical safety and efficiency: reduce the risk of surgical errors and complications, shorten operation time, and improve the response speed of the surgical team.

[0048] 5. Enhance surgical teaching and training effects: It helps doctors observe and learn complex surgical steps, and can be used for postoperative analysis and teaching discussions.

[0049] 6. Support remote surgery: High-quality enhanced images are suitable for remote transmission, which is conducive to remote experts to provide real-time guidance and improve the accuracy and safety of robot-assisted surgery.

[0050] 7. Data accumulation and AI-assisted diagnosis: Establish an image database of heart valve disease to develop automated valvular lesion identification and surgical planning assistance tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 The figure is a flowchart of the execution of a low-light enhancement method for a cardiac interventional surgery scene in one embodiment of the present invention.

[0052] Figure 2 FIG. 4 is a flow chart of a diffusion model algorithm in one embodiment of the present invention.

[0053] Figure 3 This is an example diagram of a low-light image of a cardiac surgery area according to an embodiment of the present invention.

[0054] Figure 4 for Figure 3 An example of the effect after low-light enhancement.

[0055] Figure 5 This is a framework diagram of a low-light enhancement system for cardiac interventional surgery scenarios in one embodiment of the present invention.

[0056] Figure 6 It is a framework diagram of a diffusion model processing module in one embodiment of the present invention.

[0057] Figure 7 This is a framework diagram of a low-light enhancement system for cardiac interventional surgery scenarios in another embodiment of the present invention. DETAILED DESCRIPTION

[0058] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0059] In the following detailed description, many specific details are set forth to provide a more thorough understanding of the present invention. However, it is obvious to those skilled in the art that well-known algorithms are not shown in detail to avoid obscuring the subject matter of the present invention.

[0060] In addition, the order of execution of actions, steps, etc. in the devices and methods shown in the claims, specifications and drawings can be implemented in any order as long as there is no special explicit limitation on the order and the output of the previous processing is not used in the subsequent processing.

[0061] Example 1

[0062] This embodiment takes heart valve replacement as an example, see Figure 1 , a low-light enhancement method for cardiac interventional surgery scenes based on a diffusion model is provided. The hardware required for the low-light enhancement method is:

[0063] - A tiny camera is inserted into the heart through a surgical incision or catheter.

[0064] - GPU-accelerated server: for running diffusion models in real time.

[0065] - Intelligent lighting system: including adjustable surgical light and micro LED light source.

[0066] - High-resolution displays: for displaying enhanced images.

[0067] The low light enhancement method comprises the following steps:

[0068] Step S1: Construct and pre-train a diffusion model for cardiac interventional surgery: collect image pairs (low-light images and ideal images) under different lighting conditions during cardiac interventional surgery for pre-training of the diffusion model. Figure 2 The diffusion model designs a diffusion process with multiple time steps, each step corresponding to a gradual improvement in image quality; the diffusion process is performed at high resolution and low resolution for the fine structure inside the heart and the global structure of the surrounding tissue under the state of cardiac motion.

[0069] More specifically, a dedicated diffusion model for heart valve replacement surgery is constructed: When initializing the diffusion model, the acquired low-light image is used as the starting point. The diffusion process is designed with multiple time steps, and each step corresponds to a gradual improvement in image quality. The final output is an enhanced high-quality image that can clearly show the valve structure, surrounding tissues, and surgical instruments.

[0070] Optimize the learnable parameters of the diffusion model (train the model):

[0071] Collect a large amount of image data from heart valve replacement surgery, including valve images under different lighting conditions.

[0072] Use this data to train a diffusion model and optimize the parameters of the diffusion process, such as noise level, step size, etc.

[0073] The core idea of ​​the Diffusion model is to generate or reconstruct images by simulating a process that gradually approaches the data distribution. In image enhancement tasks, this principle is used to reconstruct high-quality images from low-quality images.

[0074] 1. Forward Diffusion Process

[0075] The forward diffusion process is defined as gradually adding Gaussian noise to the image:

[0076]

[0077] in, is the image at step t, is a predefined noise schedule.

[0078] 2. Reverse diffusion process

[0079] The back diffusion process aims to recover the original image from a noisy image:

[0080]

[0081] in, and are the mean and variance parameterized by the neural network.

[0082] 3. Training objectives

[0083] The training objective of the model is to minimize the following loss function:

[0084]

[0085] in, is the added noise, is the noise in the model prediction.

[0086] In order to meet the special needs of heart valve replacement surgery, we introduced a multi-scale processing strategy based on the standard diffusion model to capture image details at different levels from micro to macro. By performing the diffusion process at different resolutions, the tiny structures and overall tissue layout in the surgical field can be reconstructed more accurately. At the microscale: In heart valve replacement surgery, clear imaging of the fine structures of the valve (such as leaflets and chordae tendineae) is crucial. The multiscale model can process images at high resolution and accurately reconstruct these tiny structures to help doctors assess the degree of valve lesions, select appropriate artificial valves, and perform precise suturing operations. At the macroscale: At the same time, doctors also need to observe the movement of the entire heart and the surrounding tissues (such as atria, ventricles, and aorta). The multiscale model can capture this global information at low resolution, helping doctors to comprehensively evaluate the surgical effect and detect potential problems (such as bleeding and arrhythmias) early.

[0087] Step S2, obtaining low-light images of cardiac interventional surgery scenes: using a micro camera inserted into the heart through a surgical incision or catheter to obtain real-time images of the heart, while using an external camera system to capture a global image of the entire surgical area. These two image sources can provide low-light images of different scales and angles, providing rich information for subsequent processing.

[0088] Step S3, using the pre-trained diffusion model to process the low-light image in step S2 in real time to obtain an enhanced high-quality image, and using the image data continuously collected during the operation to perform online learning and parameter adjustment of the model: the diffusion model dynamically adjusts the value of noise scheduling according to different stages of the operation process; predicts illumination parameters according to cardiac anatomical structure information, characteristic information of surgical instruments and characteristic information of different types of valves, and adjusts the parameters in a certain time step in the diffusion model.

[0089] More specifically, the real-time processing flow includes:

[0090] - Input: Low-light image acquired from camera system .

[0091] - Diffusion process: Applies a diffusion process with T time steps.

[0092] - Output: Enhanced high quality image .

[0093] In order to meet the special needs of heart valve replacement surgery, we introduced prior knowledge related to heart valve replacement surgery: integrating cardiac anatomical structure information, such as the typical morphology of the valve, the distribution of surrounding blood vessels, etc. Adding feature information of commonly used surgical instruments, such as artificial valves, suture needles, etc., so as to better preserve these key elements during the enhancement process. Considering the characteristics of different types of valves (such as mitral valves and aortic valves), we specifically optimize the image quality of the corresponding areas.

[0094] a. Adjustment for specific lighting conditions:

[0095] The model adds an illumination parameter prediction module to adjust the brightness and contrast of the image so that the reconstructed image is more consistent with the lighting conditions in the operating room. This is achieved by adjusting the parameters in a certain time step in the diffusion model, so that the output of the model is more adapted to the actual needs of the surgery.

[0096] Shadow elimination: Surgical instruments and the doctor’s operation will cause shadows in the surgical area. The lighting parameter prediction module can identify these shadow areas and eliminate them by enhancing image brightness and contrast, thereby improving the clarity of the surgical field of view.

[0097] Color correction: The color of the heart's internal tissues will change due to factors such as blood flow and lighting angle, which will affect the doctor's judgment of tissue health. The lighting parameter prediction module can correct the image according to the preset standard color model to present a more realistic surgical scene.

[0098] b. Dynamically adjust noise scheduling:

[0099] Dynamically adjust according to different stages of the surgical process (such as preparation stage, replacement process, suturing stage). This is because different stages have different requirements for image clarity, and dynamic adjustment can reduce the introduction of noise in the stage where high clarity is required.

[0100] Preparation stage: During the preparation stage of surgery, it is necessary to clearly observe the anatomical structure and lesions of the valve. At this time, the model can use smaller noise scheduling parameters to obtain high-definition images.

[0101] Replacement process: During the valve replacement process, it is necessary to pay attention to the placement and suturing of the artificial valve. At this time, the model can appropriately increase the noise scheduling parameters to speed up image processing and ensure real-time performance.

[0102] Suturing stage: During the suturing stage, the direction and tension of the suture line need to be clearly observed. At this time, the model can reduce the noise scheduling parameters again to obtain high-definition images and ensure the quality of the surgery.

[0103] c. Real-time optimization and adaptation:

[0104] The model is learned and adjusted online using new image data collected during surgery. This ensures that the model can adapt to the changing environment and specific surgical characteristics, such as anatomical differences between different patients.

[0105] Figure 3 and Figure 4 The effect of low-light enhancement of the valve region and the entire surgical area during cardiac surgery is shown. As can be seen from the figure, the low-light image processed by the diffusion model of this embodiment is enhanced to a high-quality image.

[0106] Step S4: Feedback the enhanced high-quality image to the lighting system of the operating area to dynamically adjust the lighting system.

[0107] More specifically, an intelligent lighting control system is designed to receive and interpret enhanced image information. The intensity and direction of the surgical light are dynamically adjusted based on the brightness distribution in the enhanced image. For the internal area of ​​the heart, a controllable micro-LED light source can be used to adjust the internal lighting based on the needs of the enhanced image.

[0108] Based on enhanced images, real-time valve recognition and analysis functions can also be developed to help doctors assess valve status.

[0109] From the above method steps, it can be seen that this embodiment uses a micro camera and an external camera system to collect multi-angle low-light images, and uses a diffusion model optimized for cardiac interventional surgery scenarios for enhancement processing, which can solve the problem of unclear surgical field of view in low-light environments.

[0110] Example 2

[0111] See also Figure 5 This embodiment provides a low-light enhancement system for cardiac interventional surgery scenes based on a diffusion model, which is used to implement the low-light enhancement method for cardiac interventional surgery scenes as described in Example 1, including:

[0112] An image acquisition module 100 acquires low-light images of the interior of the heart and the entire surgical area in real time from a micro camera and a global camera;

[0113] The diffusion model processing module 200 based on the GPU acceleration server introduces a multi-scale processing strategy and an illumination parameter prediction module to execute a dynamic image enhancement algorithm;

[0114] The intelligent lighting module 300 adjusts parameters of the surgical lighting equipment according to the enhanced image.

[0115] See also Figure 6 The diffusion model processing module 200 includes a data set 201, a pre-training module 202, a model real-time operation module 203, an illumination parameter prediction module 204, and an image quality assessment module 205; the model real-time operation module 203 obtains a high-quality image through low-light image enhancement, and dynamically adjusts the model parameters according to the prediction results of the illumination parameter prediction module 204 and the evaluation results of the image quality assessment module 205.

[0116] This diffusion model-based low-light enhancement system for cardiac interventional surgery scenes can effectively improve the quality of images collected during surgery and provide more stable visual feedback.

[0117] Example 3

[0118] This embodiment provides a method and system for low-light enhancement of cardiac interventional surgery scenes based on a diffusion model. The steps of the low-light enhancement method are similar to those of Embodiment 1, except that a user interaction interface is introduced to allow doctors to provide real-time feedback on the enhanced image according to their needs; based on the doctor's feedback, the enhanced image is fine-tuned by quickly fine-tuning the parameters of the diffusion model. Figure 7, the corresponding low-light enhancement system is similar to Example 2, but also includes a user interaction module 400 to provide an interactive interface for the surgical team. Different doctors have different preferences for image clarity, contrast, color, etc. The interactive user feedback mechanism allows doctors to provide feedback on the enhanced image according to their needs through simple operations (such as sliders, buttons), so as to obtain a visual effect that is more in line with personal habits. The system obtains real-time feedback and outputs the image by quickly fine-tuning the model parameters to ensure that the enhanced image always meets the requirements of surgical accuracy. For example, the image quality assessment module receives feedback from the user interaction interface and evaluates whether the image quality meets the requirements. Furthermore, the user interaction module can also allow doctors to mark areas or details that require special attention, such as circling, highlighting, etc., to facilitate subsequent observation and processing.

[0119] The above-mentioned low-light enhancement method for cardiac intervention surgery can be embodied in the form of a computer program product or a software functional unit. If the above-mentioned low-light enhancement method for cardiac intervention surgery is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Therefore, the essence of this technical solution or the part that contributes to the prior art or the part of this technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for an electronic system (which can be a personal computer, a server, or a network system, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0120] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or in 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 to be beyond the scope of this application.

[0121] In summary, the present invention provides a low-light enhancement method and system for cardiac interventional surgery scenes based on a diffusion model, aiming to solve the problem of unclear surgical field of view in low-light environments. The present invention collects multi-angle low-light images through a micro camera and an external camera system, and uses a diffusion model optimized for cardiac interventional surgery scenes for enhancement processing. The diffusion model uses two low-light image sources of different scales and angles as training data sets to capture image details at different levels from micro to macro. By performing the diffusion process at different resolutions, the tiny structures and overall tissue layout in the surgical field of view can be more accurately reconstructed. By introducing prior knowledge related to cardiac interventional surgery to dynamically adjust the value of noise scheduling, and performing illumination parameter prediction to guide the optimization of diffusion model parameters, the diffusion model can improve the image quality of the surgical area more accurately in real time.

[0122] Those skilled in the art should understand that those skilled in the art can implement variations by combining the prior art and the above embodiments, which will not be described in detail here. Such variations do not affect the essential content of the present invention, and will not be described in detail here.

[0123] The above describes the preferred embodiments of the present invention. It should be understood that the present invention is not limited to the above-mentioned specific embodiments, and the systems and structures that are not described in detail should be understood to be implemented in a common manner in the art; any technician familiar with the art can use the above-disclosed methods and technical contents to make many possible changes and modifications to the technical solutions of the present invention without departing from the scope of the technical solutions of the present invention, or modify them into equivalent embodiments of equivalent changes, which does not affect the essential content of the present invention. Therefore, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solutions of the present invention are still within the scope of protection of the technical solutions of the present invention.

Claims

1. A low-light enhancement method for cardiac interventional surgery scenes based on a diffusion model, characterized in that: include: Step S1, constructing and pre-training a diffusion model for cardiac interventional surgery: collecting image pairs under different lighting conditions during cardiac interventional surgery for pre-training of the diffusion model; the diffusion model designs a diffusion process with multiple time steps, each step corresponding to a gradual improvement in image quality; the diffusion process is performed at high resolution and low resolution for the fine structure inside the heart and the global structure of the surrounding tissue under the heart motion state; Step S2, obtaining a low-light image of the cardiac interventional surgery scene: using a miniature camera, inserted into the heart through a surgical incision or catheter, to obtain a real-time image of the heart, and using an external camera system to capture a global image of the entire surgical area; Step S3, using the pre-trained diffusion model to process the low-light image in step S2 in real time to obtain an enhanced high-quality image, and using the image data continuously collected during the operation to perform online learning and parameter adjustment of the model: the diffusion model dynamically adjusts the value of noise scheduling according to different stages of the operation process; predicts illumination parameters according to cardiac anatomical structure information, characteristic information of surgical instruments and characteristic information of different types of valves, and adjusts the parameters in a certain time step in the diffusion model; Step S4: Feedback the enhanced high-quality image to the lighting system of the operating area to dynamically adjust the lighting system.

2. The low-light enhancement method for cardiac interventional surgery scene based on diffusion model according to claim 1, characterized in that: In the step S1, when pre-training the diffusion model, the parameters including the noise level and the step size in the diffusion process are optimized.

3. The low-light enhancement method for cardiac interventional surgery scene based on diffusion model according to claim 1, characterized in that: In step S3, a small noise scheduling parameter is used during the operation preparation stage; the noise scheduling parameter is increased during the valve replacement process; and the noise scheduling parameter is reduced again during the suturing stage.

4. The low-light enhancement method for cardiac interventional surgery scene based on diffusion model according to claim 1, characterized in that: In step S3, when predicting the lighting parameters, the shadow areas in the surgical area caused by the surgical instruments and the doctor's operation are identified, and the shadows are eliminated by enhancing the image brightness and contrast; the changes in the color of the internal tissue of the heart due to factors including blood flow and lighting angle are identified, and the image is corrected according to a preset standard color model.

5. The low-light enhancement method for cardiac interventional surgery scene based on diffusion model according to claim 1, characterized in that: In step S3, a user interaction interface is introduced to allow doctors to provide real-time feedback on the enhanced image according to their needs; Based on physician feedback, the enhanced image is fine-tuned by quickly fine-tuning the parameters of the diffusion model.

6. The low-light enhancement method for cardiac interventional surgery scene based on diffusion model according to claim 1, characterized in that: In step S4, the intensity and direction of the surgical light are dynamically adjusted according to the brightness distribution in the enhanced image; for the internal area of ​​the heart, a controllable micro LED light source is used to adjust the internal lighting according to the needs of the enhanced image.

7. A low-light enhancement system for cardiac interventional surgery scenes based on a diffusion model, characterized in that: The method for implementing the low-light enhancement method for cardiac interventional surgery scene according to any one of claims 1 to 6 comprises: Image acquisition module, which acquires low-light images of the heart and the entire surgical area in real time from the micro camera and global camera; The diffusion model processing module based on the GPU acceleration server introduces multi-scale processing strategy and illumination parameter prediction module to execute dynamic image enhancement algorithm; Intelligent lighting module that adjusts the parameters of surgical lighting equipment based on the enhanced image.

8. The low-light enhancement system for cardiac interventional surgery scenes based on a diffusion model according to claim 7, characterized in that: It also includes a user interaction module that provides an interactive interface for the surgical team; doctors can provide real-time feedback on the enhanced images according to their needs.

9. The low-light enhancement system for cardiac interventional surgery scenes based on a diffusion model according to claim 7 or 8, characterized in that: The diffusion model processing module includes a data set, a pre-training module, a model real-time operation module, an illumination parameter prediction module, and an image quality assessment module; the model real-time operation module obtains high-quality images through low-light image enhancement, and dynamically adjusts model parameters according to the prediction results of the illumination parameter prediction module and the evaluation results of the image quality assessment module.

10. The low-light enhancement system for cardiac interventional surgery scenes based on a diffusion model according to claim 8, characterized in that: The user interaction module allows the physician to mark areas or details that require special attention.

Images