Real-time three-dimensional imaging system in thoracic surgery

Abstract

The invention provides a real-time three-dimensional imaging system in a thoracic surgery, and relates to the field of thoracic surgery auxiliary equipment, and the system comprises a multi-modal image collection module which is used for collecting multi-source data of tissues and organs in a thoracic cavity; the data core processor is used for processing and fusing the multi-source data collected by the multi-mode image acquisition module; the three-dimensional reconstruction module is used for generating a dynamically updated submillimeter-level precision three-dimensional model according to the processed and fused multi-source data and marking a dangerous structure and a safety boundary; and the augmented reality navigation module is used for superposing the three-dimensional model on an operation visual field through a holographic head-mounted display, and realizing real-time three-dimensional visual navigation in combination with instrument tracking and a multi-stage early warning mechanism. According to the invention, radiation-free and high-precision real-time three-dimensional visual navigation can be provided, and the precision and safety in the thoracic surgery can be ensured.

Description

Technical Field

[0001] The present invention relates to the field of thoracic surgery auxiliary equipment, and particularly to a real-time three-dimensional imaging system in thoracic surgery. Background Art

[0002] Thoracic surgery involves complex anatomical structures such as the heart, lung lobes, esophagus, and mediastinum. Conventionally, it relies on preoperative two-dimensional CT / MRI images and intraoperative two-dimensional X-rays or ultrasound guidance. Preoperative images cannot reflect the dynamic changes of tissues during surgery (such as lung collapse, blood vessel displacement, etc.), and thus cannot accurately guide the surgery. X-ray fluoroscopy requires multiple shots, increasing the radiation risk for patients and medical staff. Two-dimensional images cannot effectively present the complex structures in the thoracic cavity, and doctors need to infer the three-dimensional spatial relationship based on experience, which is prone to misjudgment.

[0003] Among existing solutions, although intraoperative CT systems provide real-time three-dimensional imaging, they are expensive and have a low refresh rate, making it difficult to handle complex dynamic scenarios. Electromagnetic navigation bronchoscopes are limited to local applications and have limited navigation capabilities for multiple sites and various structures. Therefore, there is an urgent need for a real-time three-dimensional imaging system in thoracic surgery to provide dynamic, real-time, and radiation-free three-dimensional images and break through the bottleneck of existing technologies. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to propose a real-time three-dimensional imaging system in thoracic surgery, which adopts a variety of sensor integrations and advanced data processing technologies to provide radiation-free and high-precision real-time three-dimensional visualization navigation, ensuring the accuracy and safety in thoracic surgery.

[0005] To achieve the above purpose, the present invention provides the following technical solutions: Based on the above purpose, in the first aspect, the present invention provides a real-time three-dimensional imaging system in thoracic surgery, including the following components: A multimodal image acquisition module for collecting multi-source data of tissues and organs in the thoracic cavity; A data core processor for processing and fusing the multi-source data collected by the multimodal image acquisition module; A three-dimensional reconstruction module for generating a dynamically updated three-dimensional model with sub-millimeter accuracy based on the processed and fused multi-source data, and marking dangerous structures and safety boundaries; An augmented reality navigation module for superimposing the three-dimensional model on the surgical field through a holographic headset and realizing real-time three-dimensional visualization navigation in combination with instrument tracking and a multi-level warning mechanism.

[0006] As a further solution of the present invention, the multimodal image acquisition module includes: An optical coherence tomography (OCT) probe, integrated at the front end of a thoracoscope, is used for real-time scanning of the tissue surface and superficial blood vessels, with a resolution of 10 μm; A high-frequency ultrasound array probe, integrated at the front end of a thoracoscope operating instrument, is used to obtain data on deep tumors, blood vessels, and lung structures; An electromagnetic positioning module is used to track the position of the tip of a surgical instrument and synchronously map the position of the tip of the surgical instrument to a three-dimensional model; A bioimpedance sensor is used to detect the density difference between a tumor and normal tissue and distinguish the safe boundary between the tumor and normal tissue.

[0007] As a further solution of the present invention, the high-frequency ultrasound array probe is composed of broadband piezoelectric ceramic array elements with a frequency range of 5 - 20 MHz to form a frequency-tunable probe, with an axial resolution of 0.1 mm and a penetration depth of 2 - 8 cm.

[0008] As a further solution of the present invention, the high-frequency ultrasound array probe is also provided with a built-in shear wave elastography module for real-time measurement of tissue hardness (unit: kPa) to distinguish tumors from normal tissues, and data is transmitted through optical fibers to avoid electromagnetic interference.

[0009] As a further solution of the present invention, the tracking accuracy of the electromagnetic positioning module is 0.1 mm (static) and 0.3 mm (dynamic), which is used to ensure the precise navigation of the position of the surgical instrument.

[0010] As a further solution of the present invention, the multimodal image acquisition module further includes: An intraoperative cone beam CT scanner, integrated on the surgical shadowless lamp bracket, uses a silicon carbide photon counting detector, with a scanning time ≤ 30 seconds and a radiation dose ≤ 1 mSv / time. It is automatically positioned by the robotic arm of the surgical shadowless lamp bracket, adjusts the scanning angle according to the surgical area (adjustable from 0° to 120°), and supports respiratory gating-triggered scanning.

[0011] As a further solution of the present invention, the multimodal image acquisition module further includes: An optical body surface scanner, using 940 nm VCSEL structured light projection, with an accuracy of ±0.2 mm, generates a three-dimensional model of the patient's chest wall within 30 seconds, and combines infrared thermal imaging (resolution 0.1 °C) to mark the incision position to avoid damaging the intercostal nerves.

[0012] As a further solution of the present invention, the data core processor includes: A multi-source data fusion module is used to perform spatio-temporal alignment on the multi-source data of the multimodal image acquisition module and construct a three-dimensional point cloud model with sub-millimeter accuracy; A dynamic deformation prediction model is used to predict the movement trajectory of the lung lobe in real time based on the ventilator signal and the biomechanical characteristics of the tissue, and compensate for the tissue deformation and imaging delay caused by breathing. A deep learning enhancement module is used to train with thoracoscopic surgery data, automatically label high-risk areas, and perform intelligent risk warnings.

[0013] As a further solution of the present invention, the dynamic deformation prediction model can compensate for the image delay of the lung lobe caused by respiratory movement based on intraoperative real-time respiratory data, and can automatically set the resection margin according to the tumor pathological type, calculate the safety margin, and ensure the accuracy of three-dimensional imaging.

[0014] As a further solution of the present invention, the deep learning enhancement module can automatically identify and mark the possible high-risk areas during the operation, and trigger multi-level alarms when the distance between the tip of the instrument and the dangerous structure is ≤ 1 mm. The multi-level alarms include but are not limited to visual flashing, tactile feedback, and beeping. The high-risk areas include but are not limited to the thoracic aorta, phrenic nerve, pulmonary artery, etc.

[0015] As a further solution of the present invention, the augmented reality navigation module includes: A holographic projector is used to project the real-time generated three-dimensional model above the surgical field of view, supporting the doctor to perform operations such as zooming and rotating through gestures. A force feedback surgical instrument, when approaching a dangerous area, reminds the doctor by increasing the resistance or triggering an audible and visual alarm to ensure the safety of the doctor's operation.

[0016] As a further solution of the present invention, the holographic projector is a holographic waveguide head-mounted display with a refresh rate of not less than 30 frames per second, a field of view angle of 60°, a brightness of 5000 nit, supporting dynamic adjustment of the focal plane (0.5 m - ∞), avoiding visual convergence conflict. The multi-modal interaction of the holographic waveguide head-mounted display includes gesture recognition, voice control, and foot switch to ensure the real-time synchronization of the three-dimensional model and tissue movement and perform multi-modal interaction.

[0017] As a further solution of the present invention, when the force feedback surgical instrument approaches a high-risk area, it can remind the doctor by increasing the resistance or vibration feedback to avoid damaging important structures. An active RFID tag is embedded in the surgical instrument handle of the force feedback surgical instrument, with a transmission frequency of 2.4 GHz and a spatial positioning accuracy of ±0.3 mm.

[0018] The real-time three-dimensional imaging system in thoracic surgery of the present invention supports a battery backup mode to ensure the continuous operation of the device during the operation, and can be widely applied to various thoracic surgery scenarios, including but not limited to lung cancer resection, mediastinal tumor resection, chest wall reconstruction, tracheal anastomosis, etc. The present invention also effectively reduces the intraoperative blood loss and shortens the operation time through multi-source data fusion and real-time prediction models, and can provide accurate navigation and risk warning for doctors by real-time displaying the tumor boundary and the position of the instrument, ensuring the safety and success rate of the operation.

[0019] Compared with the prior art, a real-time three-dimensional imaging system in thoracic surgery proposed by the present invention has the following beneficial effects: 1. The multi-modal image acquisition module of the present invention integrates intraoperative cone beam CT, high-frequency ultrasound and optical scanning technologies to obtain high-quality images of the thoracic anatomical structure in real time. After being processed by deep learning algorithms, it can generate a high-precision three-dimensional reconstruction model and update it in real time, with precise three-dimensional visualization ability, which can help surgeons better understand the internal structure of the patient's chest cavity, especially in complex anatomical regions, significantly reducing the blind spots and errors that cannot be presented by traditional two-dimensional images, thus effectively improving the accuracy of the operation.

[0020] 2. The present invention also has the ability of dynamic respiration compensation. The dynamic changes of the thoracic anatomical structure, such as the respiratory movement of the lungs, often pose challenges to the navigation accuracy during the operation. By compensating for the lung movement, the present invention can predict the position changes of the lung lobes in real time and adjust the dynamic update of the three-dimensional model accordingly, ensuring that the model is always synchronized with the actual anatomical structure during the operation, and surgeons can obtain accurate anatomical information during the operation, thus reducing the surgical risks caused by movement errors.

[0021] 3. The present invention also uses an augmented reality navigation module to directly superimpose the three-dimensional reconstruction model on the patient's anatomical area by using a holographic waveguide head-mounted display, providing an immersive navigation experience. Surgeons can see the real-time anatomical structure and the surgical path within the field of view, and at the same time interact through functions such as gesture, voice control and instrument tracking, which not only greatly enhances the visualization effect during the operation, but also improves the operation efficiency of doctors. Especially in complex and invisible areas, it can effectively avoid misoperations.

[0022] In summary, the real-time three-dimensional imaging system in thoracic surgery of the present invention significantly improves the accuracy, safety, efficiency and operability of thoracic surgery through the comprehensive application of multi-modal imaging, intelligent three-dimensional reconstruction, augmented reality navigation and dynamic compensation technologies. By enhancing the understanding of the anatomical structure and the adaptability to intraoperative dynamic changes, the system effectively reduces the risks during the operation, improves the treatment effect of patients, and has broad clinical application value and promotion prospects.

[0023] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the related art, the following will briefly introduce the drawings required for use in the description of the exemplary embodiments or the related art. The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings: Figure 1 is a structural block diagram of a real-time three-dimensional imaging system in thoracic surgery according to an embodiment of the present invention.

[0025] Figure 2 is a structural block diagram of a multi-modal image acquisition module in a real-time three-dimensional imaging system in thoracic surgery according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] Next, in combination with the drawings and the specific embodiments, the present application will be further described. It should be noted that, on the premise of no conflict, the following described embodiments or technical features can be combined arbitrarily to form new embodiments.

[0027] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following will further elaborate on the embodiments of the present invention in detail in combination with specific embodiments and with reference to the drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] It should be noted that all the expressions using "first" and "second" in the embodiments of the present invention are used to distinguish two non-identical entities or non-identical parameters with the same name. It can be seen that "first" and "second" are only for the convenience of expression and should not be construed as a limitation to the embodiments of the present invention. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units inherently includes other steps or units.

[0029] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0030] The flowcharts shown in the accompanying drawings are only illustrative examples, and do not necessarily include all content and operations / steps, nor are they necessarily executed in the described order. For example, some operations / steps can be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0031] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0032] Regarding the problems in the existing solutions, although the intraoperative CT system provides real-time three-dimensional imaging, it is expensive and has a low refresh rate, making it difficult to handle complex dynamic scenarios. The electromagnetic navigation bronchoscope is limited to local applications and has limited navigation capabilities for multiple sites and various structures. The present invention proposes a real-time three-dimensional imaging system for thoracic surgery, which uses a variety of sensor integrations and advanced data processing technologies to provide radiation-free and high-precision real-time three-dimensional visualization navigation, ensuring accuracy and safety in thoracic surgery.

[0033] See Figure 1 and Figure 2 As shown, the embodiments of the present invention provide a real-time three-dimensional imaging system for thoracic surgery, which includes the following components: A multimodal image acquisition module 100 for collecting multi-source data of tissues and organs in the thoracic cavity; A data core processor 200 for processing and fusing the multi-source data collected by the multimodal image acquisition module 100; A three-dimensional reconstruction module 300 for generating a dynamically updated three-dimensional model with sub-millimeter accuracy based on the processed and fused multi-source data, and marking dangerous structures and safety boundaries; An augmented reality navigation module 400 for superimposing the three-dimensional model on the surgical field through a holographic headset, and realizing real-time three-dimensional visualization navigation in combination with instrument tracking and a multi-level warning mechanism.

[0034] In this embodiment, see Figure 1 and Figure 2 As shown, the multimodal image acquisition module 100 includes: An optical coherence tomography probe 101 integrated at the front end of the thoracoscope, which uses a broadband piezoelectric ceramic array element with a frequency range of 5 - 20 MHz to form an adjustable frequency probe, with an axial resolution of 0.1 mm and a penetration depth of 2 - 8 cm, for real-time scanning of the tissue surface and superficial blood vessels, and has a resolution of 10 μm; A high-frequency ultrasound array probe 102 integrated at the front end of the thoracoscope operating instrument for obtaining data of deep tumors, blood vessels, and lung structures; The electromagnetic positioning module 103 is used to track the position of the tip of the surgical instrument, with a tracking accuracy of 0.1 mm (static) and 0.3 mm (dynamic), and synchronously map the position of the tip of the surgical instrument to the three-dimensional model; The bioimpedance sensor 104 is used to detect the density difference between the tumor and normal tissues and distinguish the safe boundary between the tumor and normal tissues.

[0035] Among them, the high-frequency ultrasound array probe 102 is also provided with a built-in shear wave elastography module for real-time measurement of tissue hardness (unit: kPa), distinguishing tumors from normal tissues, and transmitting data through optical fibers to avoid electromagnetic interference.

[0036] In this embodiment, the multimodal image acquisition module 100 further includes: The intraoperative cone beam CT scanner 105 is integrated into the surgical shadowless lamp bracket, uses a silicon carbide photon counting detector, has a scanning time ≤ 30 seconds and a radiation dose ≤ 1 mSv / time, is automatically positioned by the robotic arm of the surgical shadowless lamp bracket, adjusts the scanning angle according to the surgical area (adjustable from 0° to 120°), and supports respiratory gating-triggered scanning; The optical body surface scanner 106 uses a 940 nm VCSEL structured light projection, with an accuracy of ±0.2 mm, generates a three-dimensional model of the patient's chest wall within 30 seconds, and combines infrared thermal imaging (resolution 0.1 °C) to mark the incision position to avoid damaging the intercostal nerves.

[0037] The present invention integrates intraoperative cone beam CT, high-frequency ultrasound, and optical scanning technologies through the multimodal image acquisition module 100, obtains high-quality images of the thoracic anatomical structure in real time, and after being processed by a deep learning algorithm, can generate a three-dimensional reconstruction model with high precision and update it in real time, having precise three-dimensional visualization ability, which can help surgeons more clearly understand the internal structure of the patient's chest cavity, especially in complex anatomical regions, significantly reducing the blind spots and errors that cannot be presented by traditional two-dimensional images, thereby effectively improving the accuracy of the surgery.

[0038] In this embodiment, the data core processor 200 includes: The multi-source data fusion module 201 is used to perform spatio-temporal alignment on the multi-source data of the multimodal image acquisition module 100 and construct a three-dimensional point cloud model with sub-millimeter accuracy; The dynamic deformation prediction model 202 is used to predict the movement trajectory of the lung lobe in real time based on the ventilator signal and the biomechanical characteristics of the tissue, and compensate for tissue deformation and imaging delay caused by breathing; The deep learning enhancement module 203 is used to train with thoracic surgery data, automatically label high-risk areas, and perform intelligent risk warning.

[0039] Among them, the dynamic deformation prediction model 202 can compensate for the image delay caused by respiratory movement of the lung lobe based on real-time intraoperative respiratory data, and can automatically set the resection margin according to the tumor pathological type, calculate the safety margin, and ensure the accuracy of three-dimensional imaging. The deep learning enhancement module 203 can automatically identify and mark the high-risk areas that may exist during the operation, and trigger multi-level alarms when the distance between the instrument tip and the dangerous structure is ≤ 1 mm. The multi-level alarms include but are not limited to visual flashing, tactile feedback, and beeping. The high-risk areas include but are not limited to the thoracic aorta, phrenic nerve, pulmonary artery, etc.

[0040] The present invention also has the ability of dynamic respiratory compensation. The dynamic changes of the thoracic anatomical structure, such as the respiratory movement of the lungs, often pose challenges to the navigation accuracy during the operation. By compensating for the lung movement, the present invention can predict the position change of the lung lobe in real time and correspondingly adjust the dynamic update of the three-dimensional model to ensure that the model is always synchronized with the actual anatomical structure during the operation, so that the doctor can obtain accurate anatomical information during the operation, thereby reducing the surgical risk caused by movement errors.

[0041] In this embodiment, the augmented reality navigation module 400 includes: A holographic projector 401 for projecting the real-time generated three-dimensional model above the surgical field of view, supporting the doctor to perform operations such as zooming and rotating through gestures; A force feedback surgical instrument 402, when approaching a dangerous area, the surgical instrument reminds by increasing resistance or triggering an audible and visual alarm to ensure the safety of the doctor's operation.

[0042] Among them, the holographic projector 401 is a holographic waveguide head-mounted display with a refresh rate of not less than 30 frames per second, a field of view angle of 60°, a brightness of 5000 nit, supporting dynamic focal plane adjustment (0.5 m - ∞), avoiding visual convergence conflict. The multi-modal interaction of the holographic waveguide head-mounted display includes gesture recognition, voice control, and foot switch to ensure the real-time synchronization of the three-dimensional model and tissue movement and perform multi-modal interaction.

[0043] Among them, when the force feedback surgical instrument 402 approaches a high-risk area, it can remind the doctor by increasing resistance or vibration feedback to avoid damaging important structures; an active RFID tag is embedded in the surgical instrument handle of the force feedback surgical instrument 402, with a transmission frequency of 2.4 GHz and a spatial positioning accuracy of ±0.3 mm.

[0044] The present invention also utilizes the augmented reality navigation module 400 to directly superimpose the three-dimensional reconstruction model on the patient's anatomical area through a holographic waveguide head-mounted display, providing an immersive navigation experience. The surgeon can see the real-time anatomical structure and surgical path within the field of view and interact through functions such as gesture control, voice control, and instrument tracking. This not only greatly enhances the visualization effect during the operation but also improves the doctor's operation efficiency. Especially in complex and invisible areas, it can effectively avoid misoperations.

[0045] The real-time three-dimensional imaging system for thoracic surgery of the present invention supports a battery backup mode to ensure the continuous operation of the device during the operation and can be widely applied to various thoracic surgery scenarios, including but not limited to lung cancer resection, mediastinal tumor resection, chest wall reconstruction, tracheal anastomosis, etc. The present invention also effectively reduces the intraoperative blood loss and shortens the operation time through multi-source data fusion and real-time prediction models, and can provide accurate navigation and risk warning for doctors by real-time displaying the tumor boundary and instrument position, ensuring the safety and success rate of the operation.

[0046] In the operation of thoracic tumor resection, the working process of this system is as follows: Step 1: Multi-modal image acquisition.

[0047] Before the operation starts, an optical coherence tomography (OCT) probe is used to perform real-time scanning on the surface and superficial blood vessels of the patient's chest cavity. Due to the high axial resolution of 0.1 mm of the OCT probe, it can detail the fine structures in the chest cavity, including the distribution of superficial tumors and blood vessels.

[0048] The high-frequency ultrasound array probe 102 is integrated at the front end of the thoracoscope operating instrument to obtain real-time image data of deep tumors, blood vessels, and lung tissues. This probe can perform high-precision scanning on the position and shape of the tumor and, combined with the built-in shear wave elastography module, measure tissue hardness to help distinguish the boundary between the tumor and normal tissues.

[0049] During the operation, the intraoperative cone-beam CT scanner 105 and the optical body surface scanner 106 work together to provide three-dimensional structure data on deep tumors and surrounding tissues in the chest cavity. At the same time, an accurate three-dimensional model of the chest wall is generated through optical body surface scanning, and the incision position is marked by infrared thermal imaging to avoid damaging the intercostal nerves during the operation.

[0050] Step 2: Data processing and fusion.

[0051] Transfer the collected multi-source image data to the data core processor 200. The data core processor 200 will process and fuse the data from different image acquisition modules (OCT, high-frequency ultrasound, cone beam CT, etc.) to generate a high-precision three-dimensional model. This three-dimensional model not only has a sub-millimeter resolution but also can be dynamically updated to reflect the changes in the patient's anatomical structure during the operation in real time.

[0052] In the three-dimensional model, the system automatically marks the positions of the tumor and important blood vessels and nerve structures, and uses a safety margin algorithm to generate a warning area to help the doctor determine the optimal resection path.

[0053] Step 3: Real-time three-dimensional navigation and surgical operation.

[0054] The surgeon wears a holographic headset, and through the augmented reality navigation module 400, the processed three-dimensional model is superimposed on the surgical field of view, visually displaying important anatomical structures such as tumors, blood vessels, and nerves.

[0055] At the same time, the electromagnetic positioning module 103 real-time tracks the position of the surgical instrument and accurately maps the instrument trajectory to the three-dimensional model. In this way, when the doctor operates, he can adjust the surgical path in real time to avoid colliding with important structures.

[0056] The navigation system of the present invention also combines a multi-level warning mechanism. According to the real-time image information, it can intelligently identify potential risks during the operation (such as when approaching important blood vessels or nerves), and prompt the doctor through visual and audio means.

[0057] Step 4: Tumor resection and postoperative monitoring During the tumor resection process, the system provides real-time references for the tumor boundary and safe resection area to help the doctor accurately resect the tumor and reduce damage to healthy tissues.

[0058] After the operation, the doctor can accurately evaluate the resection site through the complete three-dimensional data generated by the system and provide guidance for postoperative recovery.

[0059] The present invention has high precision. By combining multi-modal technologies such as OCT, ultrasonic imaging, cone beam CT, and optical surface scanning, the system provides high-resolution images to help the doctor clearly view the complex anatomical structures in the chest cavity during the operation, especially the deep tumors and their relationships with surrounding tissues. The system can update the three-dimensional model in real time according to the intraoperative dynamic changes. Especially when the patient's breathing causes lung movement, the three-dimensional model will also automatically adapt to ensure that the model is synchronized with the actual anatomical situation. The augmented reality navigation and multi-level warning mechanism enhance the safety of the operation. Through real-time feedback and precise navigation, the doctor can avoid accidentally injuring important structures and reduce the occurrence of bleeding and other complications.

[0060] In summary, the real-time three-dimensional imaging system in thoracic surgery of the present invention significantly improves the accuracy, safety, efficiency, and operability of thoracic surgery through the comprehensive application of multi-modal imaging, intelligent three-dimensional reconstruction, augmented reality navigation, and dynamic compensation technologies. By enhancing the understanding of anatomical structures and the ability to adapt to intraoperative dynamic changes, the system effectively reduces the risks during surgery, improves the treatment effect of patients, and has broad clinical application value and promotion prospects.

[0061] The above are exemplary embodiments disclosed by the present invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments disclosed by the present invention as defined by the claims. The functions, steps, and / or actions of the method claims according to the disclosed embodiments herein do not need to be performed in any specific order. In addition, although the elements disclosed by the embodiments of the present invention can be described or claimed in individual form, they can also be understood as plural unless explicitly limited to the singular.

[0062] It should be understood that, as used herein, unless the context clearly supports the exception, the singular form "a" is also intended to include the plural form. It should also be understood that the "and / or" used herein refers to any and all possible combinations of one or more of the related listed items. The serial numbers of the disclosed embodiments of the present invention above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0063] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the embodiments disclosed by the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features between the above embodiments or different embodiments can also be combined, and there are many other variations in different aspects of the embodiments of the present invention as above, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included in the protection scope of the embodiments of the present invention.

Claims

1. A real-time three-dimensional imaging system for thoracic surgery, characterized in that: The system consists of the following components: Multimodal image acquisition module, used to collect multi-source data of tissues and organs in the chest cavity; A data core processor, used for processing and fusing multi-source data collected by the multi-modal image acquisition module; 3D reconstruction module, which is used to generate dynamically updated sub-millimeter precision 3D models based on processed and fused multi-source data, and mark dangerous structures and safety boundaries; The augmented reality navigation module is used to superimpose the three-dimensional model on the surgical field of view through a holographic head display, and combine instrument tracking with a multi-level warning mechanism to achieve real-time three-dimensional visual navigation.

2. The real-time three-dimensional imaging system for thoracic surgery according to claim 1, characterized in that: The multimodal image acquisition module comprises: Optical coherence tomography probe, integrated into the front end of the thoracoscope, for real-time scanning of tissue surfaces and superficial blood vessels; High-frequency ultrasound array probe, integrated into the front end of the thoracoscopic instrument, is used to obtain data on deep tumors, blood vessels, and lung structures; An electromagnetic positioning module, used to track the position of the surgical instrument tip and synchronously map the position of the surgical instrument tip to the three-dimensional model; Bioimpedance sensors are used to detect the density difference between tumors and normal tissues and distinguish the safe boundary between tumors and normal tissues.

3. The real-time three-dimensional imaging system for thoracic surgery according to claim 2, characterized in that: The high-frequency ultrasonic array probe uses 5-20MHz wide-band piezoelectric ceramic array elements to form an adjustable frequency probe with an axial resolution of 0.1mm and a penetration depth of 2-8cm. The high-frequency ultrasonic array probe also has a built-in shear wave elastic imaging module for real-time measurement of tissue hardness, distinguishing tumors from normal tissues, and transmitting data via optical fiber.

4. The real-time three-dimensional imaging system for thoracic surgery according to claim 2, characterized in that: The electromagnetic positioning module has a static tracking accuracy of 0.1mm and a dynamic tracking accuracy of 0.3mm, which are used to ensure accurate navigation of the surgical instrument position.

5. The real-time three-dimensional imaging system during thoracic surgery according to claim 2, characterized in that: The multimodal image acquisition module also includes: The intraoperative cone beam CT scanner is integrated into the surgical shadowless lamp bracket, uses a silicon carbide photon counting detector, is automatically positioned by the mechanical arm of the surgical shadowless lamp bracket, adjusts the scanning angle according to the surgical area, and supports respiratory gating trigger scanning; The optical body surface scanner uses structured light projection to generate a three-dimensional model of the patient's chest wall and combines it with infrared thermal imaging to mark the incision location.

6. The real-time three-dimensional imaging system for thoracic surgery according to claim 1, characterized in that: The data core processor comprises: The multi-source data fusion module is used to align the multi-source data of the multi-modal image acquisition module in time and space to construct a three-dimensional point cloud model with sub-millimeter accuracy; Dynamic deformation prediction model, which is used to predict the motion trajectory of the lung lobes in real time based on ventilator signals and biomechanical properties of tissues, and compensate for tissue deformation and imaging delay caused by breathing; The deep learning enhancement module is used to train thoracic surgery data, automatically mark high-risk areas, and provide intelligent risk warnings.

7. The real-time three-dimensional imaging system during thoracic surgery according to claim 6, characterized in that: The dynamic deformation prediction model can compensate for the image delay of the lung lobe caused by respiratory movement based on real-time respiratory data during surgery, and can automatically set the resection margin and calculate the safety margin according to the tumor pathology type.

8. The real-time three-dimensional imaging system during thoracic surgery according to claim 1, characterized in that: The augmented reality navigation module includes: Holographic projector, used to project the real-time generated 3D model onto the surgical field, allowing doctors to zoom in and out and rotate the model through gestures; Force feedback surgical instruments, when approaching a dangerous area, the surgical instrument will give a warning by increasing resistance or triggering an audible or visual alarm.

9. The real-time three-dimensional imaging system during thoracic surgery according to claim 8, characterized in that: The holographic projector is a holographic waveguide head display with a refresh rate of not less than 30 frames per second, a field of view of 60°, a brightness of 5000nit, and supports dynamic adjustment of the focal plane; the multimodal interaction of the holographic waveguide head display includes gesture recognition, voice control and foot switch.

10. The real-time three-dimensional imaging system during thoracic surgery according to claim 8, characterized in that: When the force feedback surgical instrument approaches a high-risk area, it alerts the doctor by increasing resistance or vibration feedback; an active RFID tag is embedded in the handle of the force feedback surgical instrument, with a transmission frequency of 2.4 GHz and a spatial positioning accuracy of ±0.3 mm.

Images