Dual-mode endoscopes, handheld dual-mode endoscopes, and robotic dual-mode endoscopes

Abstract

This application relates to the field of medical device technology, specifically to a dual-mode endoscope, a handheld dual-mode endoscope, and a robotic dual-mode endoscope. The dual-mode endoscope is configured to acquire stereoscopic visual images and corresponding depth information of tissue in a target area. The dual-mode endoscope includes a lens section equipped with a depth sensor and at least two image sensors. The at least two image sensors are configured to acquire stereoscopic visual images of the tissue, including white light images, fluorescence images, or a fusion of white and fluorescence images; the depth information includes a first depth, and the depth sensor is configured to acquire the first depth of the tissue. A three-dimensional view of the surgical field can be constructed by combining the first depth and the stereoscopic visual images to display the three-dimensional spatial structure of the surgical field in a three-dimensional and accurate manner, reducing accidental contact of surgical instruments with other parts of the surgical area and improving the safety and accuracy of the surgery. Different types of stereoscopic visual images can also be selected according to different surgical needs.

Description

Technical Field

[0001] This application relates to the field of medical device technology, specifically to a dual-mode endoscope, a handheld dual-mode endoscope, and a robotic dual-mode endoscope. Background Technology

[0002] Traditional open surgery, due to its large incisions, easily leads to significant tissue trauma, a substantial risk of postoperative complications, and a prolonged recovery period for patients. With the development of clinical medicine, minimally invasive surgery (MIS) effectively reduces intraoperative tissue damage by decreasing the size of the external incision, offering advantages such as smaller scars, less postoperative pain, and shorter patient recovery periods. Modern minimally invasive techniques mainly include laparoscopy, endoscopy, arthroscopy, and thoracoscopy. Among these, laparoscopy has gradually developed into a preferred method combining diagnostic and therapeutic functions in recent years, becoming a preferred alternative to open surgery.

[0003] In laparoscopic techniques (including robot-assisted procedures), surgeons create surgical pathways to body cavities (such as the abdominal, pelvic, or thoracic cavities) by establishing tiny channels (typically 5-12 mm in diameter) on the body surface. During the procedure, optical imaging systems and surgical instruments are inserted through these pathways, and the surgical field is visualized using cold light source illumination and high-definition electronic imaging equipment. Other surgical instruments are then introduced into the surgical field via auxiliary channels, and the surgeon performs precise manipulations based on real-time image guidance.

[0004] Current technological advancements focus on the development and application of 3D visualization systems. Through stereoscopic vision and 3D reconstruction of tissues and organs, the spatial relationships of anatomical structures within the surgical field can be precisely quantified, significantly improving the accuracy and safety of surgical procedures. Therefore, there is an urgent need to develop a dual-mode endoscope to facilitate the construction of realistic, high-precision 3D views of tissues. Utility Model Content

[0005] To address the aforementioned technical problems, embodiments of this application provide a dual-mode endoscope, a handheld dual-mode endoscope, and a robotic dual-mode endoscope, which facilitate the construction and display of a three-dimensional, precise, and three-dimensional view of tissues in the target area, reducing accidental contact of surgical instruments with other parts of the surgical area and improving the safety and precision of the surgery.

[0006] In some embodiments, a dual-mode endoscope is provided, configured to acquire stereoscopic visual images of tissue in a target region and corresponding depth information, comprising: a lens portion, provided with a depth sensor and at least two image sensors; the at least two image sensors are configured to acquire stereoscopic visual images of the tissue, the stereoscopic visual images including white light images, fluorescence images, or white fluorescence fusion images; the depth information includes a first depth, the depth sensor being configured to acquire the first depth of the tissue.

[0007] The dual-mode endoscope provided in this application embodiment can construct a three-dimensional view of the surgical field by combining a first depth obtained by a depth sensor and a stereoscopic visual image obtained by an image sensor. This allows for a three-dimensional and accurate display of the three-dimensional spatial structure of the surgical field, reducing the risk of surgical instruments accidentally touching other parts of the surgical area and improving the safety and precision of the surgery. Furthermore, different types of stereoscopic visual images can be selected according to different surgical needs to enhance the ability of stereoscopic visual images to assess tissues.

[0008] In one implementation, the depth information also includes a second depth, and at least two image sensors are configured to synchronously acquire the second depth of the tissue.

[0009] In one implementation, the dual-mode endoscope further includes: an elongated output section having a proximal end and a distal end, the distal end being configured to access the target area to approach the tissue; a lens section disposed at the distal end of the output section; and when a first depth is obtained using a depth sensor, the distance between the depth sensor and the tissue is less than or equal to a preset distance, the preset distance representing the effective distance detected by the depth sensor.

[0010] In one implementation, a lens portion is rotatably disposed at the distal end of an output portion; the lens portion can rotate relative to the output portion by a first rotation angle, the first rotation angle ranging from 0° to 180°; the dual-mode endoscope has a retracted state; in the retracted state, the angle between the lens portion and the output portion is within a first angle range, such that the maximum size of the lens portion in the width direction is less than or equal to the size of the output portion; the first angle range is within the range of the first rotation angle; wherein, the dual-mode endoscope remains in the retracted state during the process of passing through the channel at the distal end to enter the target area.

[0011] In one implementation, the lens section includes: a support column; the output section includes: a transmission assembly, which is throttle-connected to the support column; and a rotation assembly, wherein the support column is rotatably disposed inside the rotation assembly; wherein the transmission assembly can controllably drive the support column to rotate within the rotation assembly, thereby driving the lens section to rotate.

[0012] In one implementation, the output section further includes: a first housing including a first top block and a second top block; the rotating assembly includes: a pressure ring configured to provide axial positioning for the bearing; the pressure ring includes a bearing flange, and the first top block and the second top block respectively abut against opposite ends of the bearing flange to fix the pressure ring.

[0013] In one implementation, the lens unit includes: a support column; the support column has a first communication hole through it; data cables for the image sensor and the depth sensor pass through the first communication hole; the output unit further includes: a first housing, including a first accommodating space, the support column being rotatably disposed in the first accommodating space, and the first communication hole being connected to the first accommodating space; when the lens unit rotates relative to the output unit, the lens unit rotates relative to the first housing; the dual-mode endoscope further includes: a sealing plug, disposed in the first communication hole, the sealing plug being configured to seal the first communication hole, and the data cable passing through the sealing plug; wherein the sealing plug is sealed to other components by dispensing adhesive.

[0014] In one implementation, at least two image sensors include a first image sensor and a second image sensor, which are symmetrically arranged on both sides of the depth sensor, and the first image sensor, the second image sensor, and the depth sensor are all located on the same straight line.

[0015] In one implementation, the depth sensor includes a TOF sensor or a structured light sensor.

[0016] In one implementation, the lens unit further includes: a second housing, including a second accommodating space; a depth sensor and at least two image sensors disposed within the second accommodating space; the second housing is made of metal; and / or, the surface of the second housing has a textured structure; and / or, the depth sensor and at least two image sensors are integrated on a PCBA, the PCBA is disposed within the second accommodating space, and thermal grease is filled between the PCBA and the second housing.

[0017] In one implementation, the dual-mode endoscope further includes: an illumination element disposed on the lens portion, the illumination element being configured to provide a light source to the target area; and a depth sensor, at least two image sensors, and the illumination element being arranged in a centrally symmetrical manner, with the depth sensor located at the center of symmetry.

[0018] In some embodiments, a handheld dual-mode endoscope is provided, comprising: a dual-mode endoscope, a control unit, an integrated cable, and a plug arranged sequentially as described in any of the above embodiments; the control unit is configured to be handheld and to control the rotation of the lens unit; the integrated cable is communicatively and electrically connected to the endoscope host via the plug; the integrated cable is communicatively and electrically connected to the control unit, the depth sensor, and the image sensor to power the control unit, the depth sensor, and the image sensor, and to transmit stereoscopic visual images of the target area tissue and corresponding depth information to the endoscope host.

[0019] The handheld dual-mode endoscope provided in this application embodiment allows the lens section to be driven by the control unit, causing it to rotate relative to the output unit. This facilitates the construction of a realistic three-dimensional visual image of the tissue based on its depth information and stereoscopic images. In this retracted state, the handheld dual-mode endoscope can be easily accessed through the channel to the target area, reducing the need for large incisions on the body surface. When in working mode, the handheld dual-mode endoscope allows for multi-angle observation of the tissue in the target area, expanding the field of view.

[0020] In some embodiments, a dual-mode endoscope for robots is provided, comprising: a dual-mode endoscope, a transmission box, an integrated cable, and a plug arranged sequentially as described in any of the above embodiments; the transmission box is configured to control the operation of the lens section; the integrated cable is communicatively and electrically connected to the endoscope host via the plug; the integrated cable is communicatively and electrically connected to the control unit, the depth sensor, and the image sensor to power the control unit, the depth sensor, and the image sensor, and to transmit stereoscopic visual images of the target area tissue and corresponding depth information to the endoscope host.

[0021] The robotic dual-mode endoscope provided in this application embodiment can drive the lens section through a transmission box, causing the lens section to rotate relative to the output section. This facilitates the construction of a realistic three-dimensional visual image of the tissue based on its depth information and stereoscopic vision. This allows the robotic dual-mode endoscope to be in a retracted state, facilitating entry into the target area through the channel and reducing the need for large incisions on the body surface. When in working mode, the robotic dual-mode endoscope allows for multi-angle observation of tissue in the target area, expanding the field of view. Attached Figure Description

[0022] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A schematic diagram of a dual-mode endoscope provided in an embodiment of this application;

[0024] Figure 2 This is a schematic diagram of the lens section provided in an embodiment of this application;

[0025] Figure 3 This is a schematic diagram illustrating the distance between the camera end face and the target tissue provided in an embodiment of this application.

[0026] Figure 4 A schematic diagram showing the dual-mode endoscope provided in the embodiments of this application in its working state;

[0027] Figure 5A schematic diagram showing the dual-mode endoscope provided in the embodiment of this application in a retracted state;

[0028] Figure 6 Another structural schematic diagram of the dual-mode endoscope provided in the embodiments of this application;

[0029] Figure 7 An exploded view of the lens section and output section from one perspective, provided for an embodiment of this application;

[0030] Figure 8 An exploded view of the lens section and output section from another perspective, provided for an embodiment of this application;

[0031] Figure 9 A schematic diagram of the structure of the second shell and the support column from one perspective, provided for an embodiment of this application;

[0032] Figure 10 This is a structural schematic diagram of the second shell and the support column from another perspective, provided as an embodiment of this application.

[0033] Figure 11 This is a schematic diagram of the output shaft provided in an embodiment of this application;

[0034] Figure 12 This is a schematic diagram of the structure of the first cover plate provided in an embodiment of this application;

[0035] Figure 13 for Figure 2 The illustrated embodiment is a cross-sectional view along direction AA;

[0036] Figure 14 A schematic diagram showing a first rotation angle of 0° or 180° for embodiments of this application;

[0037] Figure 15 This is a schematic diagram of the structure of the pressure ring provided in an embodiment of this application;

[0038] Figure 16 This is a structural block diagram of a surgical scene three-dimensional reconstruction system provided in an embodiment of this application;

[0039] Figure 17 A flowchart illustrating the three-dimensional reconstruction of a surgical scene provided in an embodiment of this application.

[0040] Figure label:

[0041] 1. Dual-mode endoscope;

[0042] 11. Lens unit; 111. Depth sensor; 112. Image sensor; 1121. First image sensor; 1122. Second image sensor; 113. Illumination element; 114. Support column; 1141. First groove; 1142. Second groove; 1143. Third groove; 115. Second housing; 1151. Lens mount; a. First mounting hole; b. Second mounting hole; c. Third mounting hole; d. Fourth mounting hole; e. Fifth mounting hole; 1152. Second cover plate; 1153. First communication hole; 1154. Second accommodating space; 116. PCBA; 117. Data cable; 118. Camera end face;

[0043] 12. Output section; 121. Transmission assembly; 1211. Wire end; 1212. Tungsten wire rope; 1213. Steel pipe; 122. Rotating assembly; 1221. Pressure ring; 1222. Bearing; 1223. Snap ring; 1224. Bearing retainer; 123. First housing; 1231. Output shaft; 1232. First cover plate; 1233. First top block; 1234. First accommodating space; 1235. Third accommodating space; 1236. First support bar; 1237. Second support bar; 1238. Second communication hole; 1239. Second top block; 124. Remote end;

[0044] 13. Control unit; 131. Knob;

[0045] 14. Integrated cables;

[0046] 15. Plug;

[0047] 16. Rubber stopper;

[0048] 17. Sealing plug;

[0049] 18. Transmission box;

[0050] 2. Three-dimensional reconstruction module. Detailed Implementation

[0051] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are all within the protection scope of this application.

[0052] This specification contains numerous specific technical details to enable those skilled in the art to understand the complete technical solution. However, it should be understood that embodiments of this application can be implemented without these specific technical details. Such detailed descriptions of technical details should not be considered as limitations on this application, and the scope of protection of this application is defined only by the claims. Elsewhere, well-known structures, connections / positional relationships, circuits, and / or other details may not be shown in detail to avoid misleading the public about the inventive points of this application.

[0053] This specification includes accompanying drawings illustrating several embodiments of the present application. However, the drawings are merely illustrative, and it should be understood that variations in mechanical structure, connection / positional relationships, physical composition, electrical aspects, and procedures can be made without departing from the spirit and scope of the present application. Such variations may involve substitution or combination of elements from the embodiments of the present application, or substitution or combination of known content.

[0054] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. Spatial relative terms, such as “below,” “lower,” “above,” “upper,” “middle,” “center,” “inner,” “outer,” “central,” “edge,” etc., are used for ease of description to describe the relationship between one component or feature shown in the figures and another component or feature. It should be understood that spatial relative terms are used only under the orientation of the device in use or operation (other than the orientation specifically defined in the figures) and are not necessarily unique or constant. For example, if the device in the figures is rotated 180° up and down along the plane of the paper, then an element described as “below” other components or features will become “above” other components or features. Therefore, the exemplary term “below” can encompass both above and below directions, depending on how the device is positioned. The device can also be positioned in other directions (e.g., rotated 90° or positioned in other directions), and the spatial relative descriptive terms used herein will be interpreted accordingly.

[0055] As used herein, “several,” “one,” and “the” are intended to include the plural form as well, unless the context otherwise indicates. It should be further understood that the terms “comprising” and / or “including” specify the presence of the said feature, step, operation, element, and / or component, without excluding the presence of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0056] The term "object" generally refers to a component or a group of components. Throughout the specification and claims, the terms "object," "component," "part," "part," "module," "assembly," and "element" are used interchangeably.

[0057] The terms “instrument,” “surgical instrument,” and “surgical device” are used herein to describe medical devices configured for insertion into a patient and for performing surgical or diagnostic procedures, generally including end effectors. End effectors can be surgical tools associated with one or more surgical procedures, such as forceps, needle holders, scissors, bipolar cauterizers, tissue stabilizers or retractors, clamp applicators, anastomosis devices, imaging devices (e.g., endoscopes or ultrasound probes), and the like. Some instruments used in embodiments of this application further provide articulated supports (sometimes referred to as “wrist joints” or “articular seats”) for the surgical tool, allowing flexible manipulation of the position and / or orientation of the end effector relative to the instrument axis with one or more mechanical degrees of freedom. Further, many end effectors include functional mechanical degrees of freedom, such as jaws that open or close or blades that translate along a specific path. Instruments may also contain permanent or updatable stored information (e.g., on a PCBA board within the instrument). Accordingly, the system can provide one-way or two-way communication between the instrument and one or more system components.

[0058] The term "mate" (sometimes referred to as "connection," "linkage," "installation," or "assembly") can be broadly understood as any situation in which two or more objects are connected in a manner that allows the mating objects to operate in combination with each other. It should be noted that a mating does not require a direct connection (e.g., a direct physical or electrical connection), but rather that many objects or components can be used to mate two or more objects. For example, objects A and B can be mated using object C. Furthermore, the terms "detachably connected" or "detachably mated" can be interpreted as implying a non-permanent connection or mating situation between two or more objects. This means that detachably connected objects can be unconnected and separated, allowing them to operate without being joined.

[0059] Finally, the terms “or” and “and / or” as used herein should be interpreted inclusively, meaning either one or any combination thereof. Therefore, “A, B, or C” or “A, B, and / or C” means any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C. Exceptions to this definition will only occur when the combination of elements, functions, steps, or actions is inherently mutually exclusive in some way.

[0060] To facilitate understanding of this solution, the terminology used in this application will be explained below.

[0061] Open surgery refers to a traditional surgical procedure that involves cutting open the body surface tissues to directly expose the diseased area or organ for direct visualization.

[0062] Minimally Invasive Surgery (MIS) refers to a system of techniques that involve surgical procedures through tiny incisions or natural cavities, using tools such as endoscopes, catheters, and image guidance.

[0063] Laparoscopic surgery involves inserting a laparoscope and surgical instruments through a small incision in the abdominal wall (usually 0.5-1.5 cm), and using a camera system to magnify the surgical field to complete the operation inside the body cavity.

[0064] The surgical field refers to the body area directly involved in the surgical procedure, including the incision, exposed organs or tissues, and the surrounding anatomical area that needs to be treated.

[0065] To facilitate understanding of this solution, the relevant technologies are briefly explained below.

[0066] Currently, minimally invasive surgical techniques are gradually becoming an important alternative to open surgery. These techniques mainly include laparoscopy, endoscopy, arthroscopy, and thoracoscopy. Among them, laparoscopy has increasingly become a preferred method combining diagnostic and therapeutic functions in recent years. In laparoscopy, a channel is created on the body surface to allow surgical instruments such as endoscopes to enter the body cavity for manipulation.

[0067] Specifically, after entering the surgical area with an endoscope, images of the surgical area are acquired, and anatomical structures are observed in real time using an electronic imaging system. However, because the images displayed by the electronic imaging system are two-dimensional, they cannot accurately display the surgical field. Furthermore, due to the small operating area in minimally invasive surgery, inaccurate and non-three-dimensional image display can lead to surgical instruments accidentally touching other parts of the surgical area, compromising the safety and precision of the surgery.

[0068] To address the aforementioned technical issues, this application provides a dual-mode endoscope and surgical scene 3D reconstruction system. This system combines various depth information to construct a 3D view of the surgical field, thereby providing a three-dimensional and accurate representation of the 3D spatial structure of the surgical field. This reduces the risk of surgical instruments accidentally touching other parts of the surgical area, improving the safety and precision of the surgery.

[0069] Figure 1 This is a schematic diagram of the first structure of the dual-mode endoscope provided in the embodiments of this application.

[0070] Combination Figure 1As shown, this application embodiment provides a dual-mode endoscope 1. The dual-mode endoscope 1 is configured to acquire stereoscopic visual images of tissue in a target area and corresponding depth information. The depth information includes a first depth. The dual-mode endoscope 1 includes a lens section 11 capable of entering the target area. The lens section 11 is provided with a depth sensor 111 for acquiring the first depth corresponding to the tissue and at least two image sensors 112 for acquiring stereoscopic visual images of the tissue. The target area is the area containing the tissue for which images need to be observed and acquired.

[0071] Using the dual-mode endoscope 1 provided in this application embodiment, a three-dimensional view of the surgical field can be constructed by combining the first depth obtained by the depth sensor 111 and the stereoscopic vision image obtained by the image sensor 112, so as to display the three-dimensional spatial structure of the surgical field in a three-dimensional and accurate manner, reduce the accidental contact of surgical instruments with other parts of the surgical area, and improve the safety and accuracy of the operation.

[0072] In one implementation, the first depth includes a two-dimensional depth map, i.e., a two-dimensional depth matrix. It is understandable that the two-dimensional depth map can be transformed into a three-dimensional depth map (three-dimensional point cloud) during the 3D construction process.

[0073] It is worth noting that the existing 3D views are actually 2D views simulating binocular parallax, not 3D views with true depth. Their principle is to simulate binocular parallax through technical means to make the viewer perceive a stereoscopic effect. Such 3D views have the problem of large display errors, easily leading to the image showing surgical instruments touching tissue when they have not actually touched it, and also easily causing accidental instrument contact. However, based on the stereoscopic visual images of tissue and corresponding depth information acquired by the dual-mode endoscope 1 provided in this application embodiment, a stereoscopic 3D view with true depth differences can be constructed. This 3D view can display the movement depth of surgical instruments in real time as they move within the field of view of the dual-mode endoscope 1, improving the accuracy of the surgery.

[0074] In one implementation, the stereoscopic image includes a white light image, a fluorescence image, or a fused white-fluorescence image. This allows for the selection of different types of stereoscopic images based on the specific needs of the surgery, thereby enhancing the ability to assess tissue.

[0075] In one implementation, the depth information also includes a second depth, and at least two image sensors 112 are configured to synchronously acquire the second depth of the tissue. Specifically, the second depth refers to the image of the tissue acquired by each image sensor 112. Thus, during subsequent 3D construction, since the image sensors 112 are located at different positions and capture images of the same tissue at different angles, combining images of the tissue from different angles allows the depth of each point in the tissue to be determined based on the displacement of the same tissue in each image.

[0076] In one implementation, the dual-mode endoscope 1 includes two image sensors 112, which can be combined to form a binocular image sensor.

[0077] In another implementation, the dual-mode endoscope 1 includes three or more image sensors 112, which can be combined to form an array of image sensors. For example, two of them are conventional RGB image sensors, and one is a miniature multispectral image sensor. Due to the addition of the multispectral image sensor, the visible light and near-infrared range can be observed more deeply to reproduce tissue colors that are more natural and consistent with human vision, and to significantly improve white balance.

[0078] In one implementation, the depth sensor 111 includes a TOF sensor or a structured light sensor.

[0079] In one implementation, combining Figure 1 As shown, the dual-mode endoscope 1 also includes an output section 12, a control section 13, an integrated cable 14, and a plug 15. The lens section 11 and the control section 13 are respectively disposed at opposite ends of the output section 12. The control section 13, the integrated cable 14, and the plug 15 are sequentially connected for communication and electrical connection. The output section 12 is elongated. The output section 12 includes a distal end 124 and a proximal end, the distal end 124 being configured to access the target area to approach tissue. The lens section 11 is disposed at the distal end 124 of the output section 12, and the control section 13 is disposed at the proximal end of the output section. The control section 13 is configured to control the operation of the lens section 11, the depth sensor 111, and at least two image sensors 112. The integrated cable 14 is connected for communication and electrical connection to the endoscope main unit via the plug 15. The integrated cable 14 is communicatively and electrically connected to the control unit 13, the depth sensor 111 and at least two image sensors 112 to power the control unit 13, the depth sensor 111 and at least two image sensors 112 and to transmit the depth information and stereoscopic vision images collected by the depth sensor 111 and the binocular image sensor 112 to the endoscope host.

[0080] Both the proximal end and the distal end 124 are defined at the ends of the output section 12 relative to the endoscope host.

[0081] For example, when using the dual-mode endoscope 1, the distal end 124 of the output section 12 is inserted into the body cavity through the channel. After the lens section 11 reaches the target area, the control section 13 is used to control the depth sensor 111 and at least two image sensors 112 to operate in order to obtain a first depth and stereoscopic visual image of the tissue.

[0082] In this embodiment, by positioning the lens section 11 at the distal end 124 of the output section 12, the distance between the depth sensor 111 and the image sensor 112 in the lens section 11 and the tissue is reduced, thereby improving the accuracy of the depth information acquired by the depth sensor 111 and the image sensor 112. In related technologies, a time-of-flight (TOF) sensor is integrated into a conventional 2D endoscope, and an optical path assembly is added to the front end of the 2D endoscope. A portion of the light is reflected to the image sensor via a beam splitter in the optical path assembly, while the remaining light is transmitted through a lens group or optical fiber to the TOF sensor, thereby achieving 2D image acquisition and depth measurement. The optical path assembly is a coupling device containing multiple lenses.

[0083] However, due to the addition of an optical path assembly at the front of the lens and the limited detection range of the TOF sensor, both the image sensor and the TOF sensor are too far from the target tissue. Therefore, the accuracy of the image and depth information acquired by the image and TOF sensors decreases. Furthermore, the coupling of multiple lens groups within the optical path assembly increases assembly and manufacturing errors, leading to decreased light propagation accuracy and consequently, reduced TOF sensor detection accuracy. Therefore, the technology of integrating a TOF sensor onto a conventional 2D endoscope results in low accuracy and poor reliability in constructing a 3D model of the surgical field.

[0084] The dual-mode endoscope 1 provided in this application reduces the space required for setting up the optical path components, reduces the problem of decreased detection light intensity caused by the optical path components, and reduces the problem of optical signal error caused by low process precision of multi-lens coupling. Therefore, it improves the accuracy and reliability of constructing the three-dimensional model of the surgical field.

[0085] For example, when using the depth sensor 111 to acquire a first depth, the distance between the depth sensor 111 and the tissue is less than or equal to a preset distance, where the preset distance characterizes the effective detection range (maximum effective detection range) of the depth sensor 111. This allows for improved accuracy of the first depth detection within the effective detection range of the depth sensor 111 when acquiring the first depth. Specifically, when using the dual-mode endoscope 1 provided in this embodiment to acquire the first depth, there are no other devices between the depth sensor 111 and the tissue.

[0086] Furthermore, the depth sensor 111 has a minimum effective detection distance. If the distance between the tissue and the depth sensor 111 is less than the minimum effective detection distance, the detection signal will saturate, leading to increased accuracy errors. Therefore, when using the depth sensor 111 to detect the first depth, it is necessary to ensure that the distance between the tissue and the depth sensor 111 is between the minimum and maximum effective detection distances.

[0087] It should be understood that when acquiring stereoscopic visual images of an organization and the corresponding depth information, it is necessary to ensure that the distance between the organization and the depth sensor 111 is greater than or equal to the minimum effective detection distance of the depth sensor 111 and less than or equal to the maximum effective detection distance of the depth sensor 111. This can ensure the accuracy of the first depth obtained, thereby improving the accuracy of the constructed three-dimensional view.

[0088] For example, if the minimum effective detection distance of the depth sensor 111 is 0.1cm and the maximum effective detection distance is 5cm, then the detection accuracy of tissues within 0.1cm to 5cm of the depth sensor is accurate.

[0089] Figure 2 This is a schematic diagram of the lens section provided in an embodiment of this application.

[0090] In one implementation, combined with Figure 2 As shown, the depth sensor 111 and at least two image sensors 112 are arranged on the same side. In this way, the coordinate systems of the first depth and the second depth can be unified by setting a reference point, so as to facilitate the fusion of the first depth and the second depth.

[0091] For example, combined Figure 2 As shown, the lens unit 11 includes a camera end face 118, and a depth sensor 111 and an image sensor 112 are both disposed on the camera end face 118. When acquiring tissue depth information, the camera end face 118 faces the target tissue, and the distance between the camera end face 118 and the target tissue is the shortest in the dual-mode endoscope 1.

[0092] In this embodiment, by integrating a depth sensor 111 and an image sensor 112 at the front end (i.e., the camera end face 118) of the dual-mode endoscope 1, the space between the endoscope and the target tissue required for setting up the optical path components is reduced, and the distance between the depth sensor 111 and the image sensor 112 and the target tissue is within the effective detection range of the depth sensor 111 and the image sensor 112, thereby improving the detection accuracy of the depth sensor 111 and the image sensor 112 and thus improving the accuracy of the depth information.

[0093] The effective detection range refers to the distance between the tissue and the camera end face 118 when the accuracy of the detected stereoscopic vision image and depth information meets the requirements. This effective detection range can be set according to the required accuracy.

[0094] Figure 3 This is a schematic diagram showing the distance between the camera end face and the target tissue, provided in an embodiment of this application.

[0095] Combination Figure 3As shown, after the lens section 11 enters the body cavity, when the depth sensor 111 and the image sensor 112 collect tissue depth information, the distance between the camera end face 118 and the tissue is a first distance H1, and the distance between the end face of the distal end 124 of the output section 12 and the tissue is a second distance H2, where H1 is less than or equal to H2. For example, Figure 3 (a) is a schematic diagram showing that H1 equals H2. Figure 3 (b) is a schematic diagram where H1 is less than H2. This allows the depth sensor 111 and image sensor 112 to be closer to the tissue, and when H1 is less than H2, i.e., the camera end face 118 protrudes beyond the end face of the distal end 124 of the output section 12, the tissue can more easily reach the effective detection range of the depth sensor 111 and image sensor 112, thereby further improving the accuracy of stereoscopic vision images and depth information, so as to facilitate the construction of high-precision three-dimensional views.

[0096] For example, when the surface of the depth sensor 111 is flush with the camera end face 118, it is necessary to control the first distance H1 to be greater than or equal to the minimum effective detection distance of the depth sensor 111, and less than or equal to the maximum effective detection distance of the depth sensor 111.

[0097] In one implementation, continue to refer to Figure 2 As shown, the dual-mode endoscope 1 includes a first image sensor 1121 and a second image sensor 1122. The first image sensor 1121 and the second image sensor 1122 are symmetrically arranged on both sides of the depth sensor 111, and the first image sensor 1121, the second image sensor 1122, and the depth sensor 111 are all located on the same straight line. This allows for the formation of a binocular image sensor based on the combination of the first image sensor 1121 and the second image sensor 1122, reducing the complexity of subsequent algorithms constructing a 3D model based on depth information, and also reducing the space occupied by the image sensor 112 and the depth sensor 111. Furthermore, the alignment of the three sensors in a single line facilitates the integration of the stereo vision image, the first depth sensor, and the second depth sensor into the same coordinate system, enabling the fusion of the stereo vision image and depth information.

[0098] In one implementation, the distance (baseline length) between the first image sensor 1121 and the second image sensor 1122 ranges from 5 cm to 15 cm. This increases the visible measurement distance of the binocular image sensors by extending the baseline length, thereby improving the accuracy of the stereo vision image and the second depth.

[0099] In one implementation, the lens portion 11 is rotatable relative to the distal end 124 of the output portion 12, such that the first image sensor 1121 and the second image sensor 1122 are arranged along the length direction of the output portion 12, i.e., along the distal end 124 to the proximal end or along the proximal end to the distal end 124, so as to reduce the maximum radial dimension of the dual-mode endoscope 1 on one side of the distal end 124 of the output portion 12, thereby reducing the required channel radial dimension.

[0100] It is worth noting that current technologies using binocular image sensors to acquire tissue images in endoscopes suffer from a short binocular baseline, resulting in a short viewing distance. Forcibly increasing the baseline length would increase the size of the lens end, requiring a larger channel when the lens enters the passage, thus increasing the required size of the surface opening. However, the dual-mode endoscope provided in this application, by increasing the baseline length and employing a rotatable lens section 11, allows the lens section 11 to rotate when the distal end 124 enters the channel. This allows the first image sensor 1121 and the second image sensor 1122 to be positioned along the distal end 124 to the proximal end, thereby reducing the size of the lens end, decreasing the radial length of the required channel, and reducing the required size of the surface opening.

[0101] Figure 4 This is a schematic diagram showing the dual-mode endoscope provided in the embodiments of this application in its working state. Figure 5 This is a schematic diagram of the dual-mode endoscope provided in the embodiment of this application in its retracted state.

[0102] Combination Figure 4 As shown, the length direction is defined as the direction between the proximal end and the distal end 124 of the output section 12 or the direction between the distal end 124 and the proximal end, and the width direction is defined as the direction perpendicular to the length direction.

[0103] In one embodiment, the lens portion 11 can rotate at multiple angles relative to the distal end 124 of the output portion 12.

[0104] For example, the lens section 11 is rotatably connected to the distal end 124 via a shaft structure, that is, the lens section 11 rotates along the axis of the shaft structure, which can be parallel to or perpendicular to the length direction of the output section 12. Alternatively, the lens section 11 is rotatably connected to the distal end 124 via a universal joint, that is, the lens section 11 can rotate at any angle relative to the distal end 124.

[0105] For example, the dual-mode endoscope has a retracted state (such as...) Figure 5 (as shown) and working status (such as) Figure 4 (As shown). Taking the lens section 11 rotatably connected to the distal end 124 via a shaft structure as an example, the rotation method of the lens section is explained: When using the dual-mode endoscope 1, adjust the dual-mode endoscope 1 to the retracted state (e.g., Figure 5After (as shown), the distal end 124 of the output section 12 enters the body cavity through the channel. After the lens section 11 reaches the target area, the lens section 11 is adjusted to rotate relative to the output section 12 to the working state (as shown). Figure 4 As shown, at this time, compared to the retracted state, the lens section 11 rotates 90° relative to the output section 12, controlling the depth sensor 111 and image sensor 112 to operate, thereby obtaining depth information and stereoscopic vision images. When it is necessary to withdraw the lens section 11 from the body cavity, first adjust the dual-mode endoscope 1 to the retracted state (e.g., Figure 5 As shown), the lens section 11 is then driven out of the body cavity by the moving output section 12.

[0106] It should be understood that the rotation of the lens section 11 can be performed after the lens section 11 has fully entered the body cavity, or after the lens section 11 has reached the camera position, and this application does not limit this.

[0107] It should be understood that Figure 5 The retracted state shown is a schematic diagram with the camera end face 118 of the lens section 11 facing the first direction. The retracted state can also be with the camera end face 118 of the lens section 11 facing the second direction, which is opposite to the first direction. This application does not limit this.

[0108] Understandable Figure 4 The diagram is only schematically shown to illustrate one working state; it does not mean that the lens unit 11 can only work after rotating to this angle.

[0109] In related technologies, TOF sensors are placed at the ends of surgical instruments or cannulas to measure the depth of the surgical area, thereby acquiring and constructing information about the shape of the surgical space. However, there is no space at the ends of surgical instruments and cannulas to install TOF sensors. Even if TOF sensors are forcibly installed on surgical instruments or cannulas, the size of the ends of the surgical instruments or cannulas will increase, resulting in a larger incision on the body surface, which does not meet the requirements of small incisions in minimally invasive surgery.

[0110] The dual-mode endoscope 1 provided in this application embodiment reduces the space required for setting the depth sensor 111 and image sensor 112 at the end of the endoscope when entering the surgical area through the channel by setting the lens part 11 which can rotate relative to the output part 12, thereby reducing the size of the incision required on the body surface and meeting the small incision requirement of laparoscopic technology.

[0111] The dual-mode endoscope 1 provided in this embodiment has multiple states because the lens section 11 rotates relative to the output section 12. Figure 4 The dual-mode endoscope 1 shown defines the width and length directions of each component (the width direction is perpendicular to the length direction). The following description uses the working state (e.g.) Figure 4 (as shown) and collapsed state (as shown) Figure 5 (As shown) This explains how to reduce the required incision size:

[0112] Combination Figure 4 As shown, the depth sensor 111 and the image sensor 112 are arranged along the width direction of the lens portion 11. That is, the width of the lens portion 11 includes the width of the depth sensor 111, the width of the image sensor 112, and the width of other devices inside the lens portion 11 (such as the illumination element 113), resulting in the width of the lens portion 11 being greater than the width of the output portion 12. Furthermore, the length of the lens portion 11 includes the maximum length among the length of the depth sensor 111, the length of the image sensor 112, and the length of other devices inside the lens portion 11, as well as the length of other devices arranged along the length direction of the lens portion 11. It is known that the lengths of the aforementioned devices are all less than the width of the lens portion 11. Therefore, the length of the lens portion 11 is less than the width of the lens portion 11.

[0113] Combination Figure 4 As shown, in the working state, if the lens part 11 is directly allowed to enter or exit the channel, the width of the inner wall of the channel in a certain direction needs to be slightly larger than the width of the lens part 11 in order for the lens part 11 to enter or exit the channel. This will result in a larger required cut to arrange the channel.

[0114] Combination Figure 5 As shown, in the retracted state, the width direction of the lens section 11 is aligned with the length direction of the output section 12, reducing the width of the dual-mode endoscope 1 at the distal end 124 of the output section 12. This allows the dual-mode endoscope 1 with a smaller width to enter the body cavity through the channel, reducing the required width of the inner wall of the channel and thus reducing the required cut size for arranging the channel.

[0115] In this embodiment, the size required for setting up the depth sensor 111 and image sensor 112 can be reduced by using the rotatable lens section 11. The lens section 11, which integrates the depth sensor 111 and at least two image sensors 112, has a strip-shaped structure. The width of the lens section 11 is greater than its length. By rotating, the depth sensor 111 and image sensor 112, which are arranged in the width direction of the lens end, can be arranged in the length direction of the output shaft 1231 (i.e., the width direction of the lens section 11 coincides with the length direction of the output section 12), thereby reducing the space required when the distal end 124 of the output section 12 enters the surgical area through the channel, and reducing the required incision size.

[0116] In one implementation, the lens section 11 can rotate relative to the output section 12 by a first rotation angle, which can be any angle.

[0117] For example, the first rotation angle can be set as needed.

[0118] For example, the angle at which the lens section 11 can rotate relative to the output section 12 is a first rotation angle; the range of the first rotation angle is 0° to 180°.

[0119] In this embodiment, the range of motion of the lens 11 and the adjustable range of the field of view of the lens 11 within the body cavity are increased, overcoming the shortcomings of traditional rigid endoscopes and making it easier for surgeons to use.

[0120] Understandably, in combination Figure 4 It can be seen that if the lens section 11 can continue to rotate to 270° or 360°, the orientation of the imaging end face 118 of the lens section 11 can be rotated to be in harmony with the image. Figure 4 When the camera end face 118 is oriented in the opposite direction, the output unit 12 will obstruct the detection range of the depth sensor 111 and the image sensor 112, thus affecting the field of view of the dual-mode endoscope 1. For example, during the rotation of the lens unit 11 from 181° to 360° relative to the output unit 12, the output unit 12 obstructs the field of view and places higher demands on the transmission component 121 (the device used to drive the lens unit 11 to rotate). By limiting the first rotation angle, the requirements on the transmission component 121 can be reduced while ensuring that the field of view of the dual-mode endoscope 1 is unobstructed, and a wider variety of transmission components 121 can be used to drive the lens end to rotate.

[0121] In one implementation, combining Figure 5 As shown, in the retracted state, the angle between the lens section 11 and the output section 12 is within a first angle range, such that the maximum size of the lens section 11 in the width direction is less than or equal to the size of the output section 12; the first angle range is within the range of the first rotation angle. The dual-mode endoscope 1 remains in the retracted state as the distal end 124 passes through the channel to enter the target area.

[0122] In this embodiment, by keeping the dual-mode endoscope 1 in a retracted state, the radial dimension of the end of the dual-mode endoscope 1 that needs to enter through the channel (i.e., the end where the distal end 124 and the lens portion 11 are located) is smaller than the radial dimension of the channel. This allows the dual-mode endoscope 1 to smoothly enter the target area through the channel, reducing the problem of increased channel and body surface incision caused by the increased size of the lens portion 11 due to the installation of the depth sensor 111 and at least two image sensors 112. For example, when the lens portion 11 and the output portion 12 are parallel, the angle between the lens portion 11 and the output portion 12 is defined as 0° (e.g., ...). Figure 5 As shown), the first angle range can be the angle between the lens section 11 and the output section 12 from 0° to 0.5°.

[0123] It is worth noting that the first angle range can be set according to actual needs. As long as the maximum size of the lens part 11 in the width direction is less than or equal to the size of the output part 12 in the retracted state, that is, as long as the lens part 11 in the width direction can be housed in the output part 12, this application does not impose specific restrictions on the first angle range.

[0124] For example, the lens section also includes a top surface and a back surface, with the back surface facing the camera end face 118. The connection between the top surface and the camera end face 118 and the back surface are both rounded or chamfered. Thus, when the dual-mode endoscope 1 is in the retracted state, the top corner of the lens section 11 near the channel is rounded or chamfered, which facilitates the entry of the lens section 11 into the channel.

[0125] For example, the joints between the outer peripheral surfaces of the lens portion 11 are all rounded or chamfered. In this way, since the apex corners of the lens portion 11 are all rounded or chamfered, the problem of tissue damage caused by the lens portion 11 touching the tissue during rotation can be reduced.

[0126] Figure 6 This is another structural schematic diagram of the dual-mode endoscope provided in the embodiments of this application.

[0127] In one implementation, combining Figure 6 As shown, the control unit 13 is provided with a knob 131, which is configured to receive rotation commands. When a rotation command is received, the drive transmission assembly 121 is operated to drive the lens unit 11 to rotate.

[0128] For example, the knob 131 is connected to the transmission assembly 121. When the knob 131 is rotated, it receives a rotation command, and the rotation of the knob 131 drives the transmission assembly 121 to work.

[0129] For example, the knob 131 is communicatively connected to the transmission assembly 121. When the knob 131 is rotated, it receives a rotation command, and the knob 131 drives the motor to work, thereby driving the transmission assembly 121 to work.

[0130] For example, taking the longest side of the lens section 11 rotated to coincide with the length direction of the output section 12 to form a fully folded state (a case of the retracted state), when the lens section 11 enters the body cavity and needs to acquire images of the target tissue, the lens section 11 can be rotated at any angle relative to the output section 12 by the knob 131 to obtain depth information at various different angles, thereby adjusting the angle of the surgical field.

[0131] For example, refer again Figure 4 and Figure 5 ,by Figure 5The dual-mode endoscope 1 shown is in the state where the lens section 11 is in the channel, taking this as an example. After the lens section 11 enters the surgical area, by operating the knob 131, the lens section 11 is driven to rotate relative to the output section 12, so as to move from a fully folded state (a case of the retracted state, such as...) Figure 5 (As shown) to the fully deployed state (one of the working states, such as...) Figure 4 As shown), and then to another fully folded state (another case of the folded state, where the camera end face 118 of the lens section 11 and... Figure 4 (The orientation is opposite in the image sensor 111), so that the lens unit 11 rotates 180° relative to the output unit 12. In this way, during the rotation of the lens unit 11, the depth sensor 111 and the image sensor 112 acquire a wider surgical field, which is convenient for the surgeon to use.

[0132] In one implementation, the lens section 11 includes a support column 114. The support column 114 is rotatably disposed on the output section 12. In this way, a rotation axis is provided for the rotation of the lens section 11, realizing a rotatable connection between the lens section 11 and the output section 12.

[0133] In one implementation, the output unit 12 includes a first housing 123. The first housing 123 includes a first accommodating space 1234, and the support column 114 is rotatably disposed in the first accommodating space 1234. When the lens unit 11 rotates relative to the output unit 12, the lens unit 11 rotates relative to the first housing 123.

[0134] In this embodiment, the first housing 123 is the outer housing of the output section 12, and the distal end 124 of the output section 12 enters the body cavity, which is the distal end 124 of the first housing 123 entering the body cavity. Furthermore, the first accommodating space 1234 provides rotation space for the support column 114 to realize the rotational connection between the lens section 11 and the output section 12.

[0135] In one implementation, the output unit 12 includes a transmission assembly 121 and a rotation assembly 122. The transmission assembly 121 is drively connected to the support column 114; the support column 114 is rotatably disposed inside the rotation assembly 122. The transmission assembly 121 can controllably drive the support column 114 to rotate within the rotation assembly 122, thereby driving the lens unit 11 to rotate.

[0136] Figure 7 This is an exploded view of the lens section and output section from one perspective, provided in an embodiment of this application. Figure 8 An exploded view of the lens section and output section from another perspective, provided for an embodiment of this application.

[0137] In one implementation, combining Figure 7 and Figure 8As shown, the lens unit 11 also includes a second housing 115. The second housing 115 includes a second accommodating space 1154. The depth sensor 111 and the binocular image sensor 112 are disposed within the second accommodating space 1154.

[0138] In this embodiment, the depth sensor 111 and the image sensor 112 are housed in the second accommodating space 1154 to protect the depth sensor 111 and the image sensor 112 and reduce the risk of damage to the depth sensor 111 and the image sensor 112.

[0139] In one implementation, combining Figure 7 As shown, the dual-mode endoscope 1 also includes an illumination element 113. The illumination element 113 is disposed on the lens portion 11 and is configured to provide a light source to the surgical area.

[0140] For example, the illumination element 113 is also disposed on the camera end face 118 of the lens portion 11, reducing the distance between the illumination element 113 and the target tissue, increasing the brightness of the target tissue, thereby improving the accuracy of the depth information collected by the depth sensor 111 and the binocular image sensor 112.

[0141] For example, the lighting element 113 is an LED light.

[0142] It is worth noting that, since the dual-mode endoscope 1 provided in this application embodiment illuminates the tissue by using LED lighting, it reduces the problem of light intensity reduction caused by existing fiber optic lighting, thereby improving the detection accuracy of the image sensor 112.

[0143] In one implementation, combining Figure 8 As shown, a first communication hole 1153 is provided along the axis of the support column 114; the data lines 117 of the image sensor 112 and the depth sensor 111 pass through the first communication hole 1153. The first communication hole 1153 is connected to the first accommodating space 1234.

[0144] In this embodiment, the data line 117 passes through the first communication hole 1153 and reaches the first accommodating space 1234 in the output section 12, and then connects with the integrated cable 14 to realize the transmission of signals and power.

[0145] For example, the first communication hole 1153 is connected to the second accommodating space 1154.

[0146] In one implementation, combining Figure 7 and Figure 8As shown, the dual-mode endoscope 1 also includes a sealing plug 17. The sealing plug 17 is disposed in the first communication hole 1153 and is configured to seal the first communication hole 1153. The data cable 117 passes through the sealing plug 17. In this way, the lens section 11 is sealed, reducing the problem of foreign objects entering the lens section 11 and causing damage to devices such as the depth sensor 111 and the image sensor 112.

[0147] Specifically, data cable 117 includes power lines and signal lines to provide power and transmit signals, respectively.

[0148] For example, the sealing plug 17 is sealed to other components by dispensing adhesive. This further improves the sealing of the lens section 11 and reduces the risk of damage to components such as the depth sensor 111 and the image sensor 112 caused by external foreign objects.

[0149] Figure 9 This is a schematic diagram of the structure of the second shell and the support column from one perspective, provided as an embodiment of this application. Figure 10 This is a schematic diagram of the second shell and the support column from another perspective, provided for an embodiment of this application.

[0150] In one implementation, combining Figures 7 to 10 As shown, the second housing 115 includes a lens mount 1151 and a second cover plate 1152. The lens mount 1151 includes a camera end face 118, which has multiple mounting holes. A depth sensor 111 and a binocular image sensor 112 are disposed within the mounting holes. The second cover plate 1152 and the lens mount 1151 together form a second accommodating space 1154.

[0151] For example, when the lens section 11 enters the body cavity to collect depth information of the target tissue, the camera end face 118 of the lens section 11 faces the target tissue.

[0152] For example, the first image sensor 1121 and the second image sensor 1122 are symmetrically arranged on both sides of the axis of the support column 114, and the axis of the depth sensor 111 is parallel to the axis of the support column 114.

[0153] For example, the lighting element 113 includes a first LED light and a second LED light.

[0154] For example, combined Figure 9 and Figure 10As shown, the camera end face 118 of the lens mount 1151 has a first mounting hole a, a second mounting hole b, a third mounting hole c, a fourth mounting hole d, and a fifth mounting hole e. The first mounting hole a is used to mount the first image sensor 1121, the second mounting hole b is used to mount the first LED light, the third mounting hole c is used to mount the depth sensor 111, the fourth mounting hole d is used to mount the second LED light, and the fifth mounting hole e is used to mount the second image sensor 1122.

[0155] In one implementation, the second cover plate 1152 is made of metal.

[0156] In one implementation, the surface of the second cover plate 1152 has a textured structure.

[0157] In one implementation, the depth sensor 111 and the image sensor 112 are integrated on a PCBA 116. The PCBA 116 is disposed within a second accommodating space 1154, and thermal grease is filled between the PCBA 116 and the second cover plate 1152.

[0158] The depth sensor 111, image sensor 112, and illumination element 113 generate heat during operation. To improve heat dissipation efficiency, the heat dissipation capacity and efficiency of the lens section 11 are improved through the above embodiments. Specifically, by making the second cover plate 1152 a metal part, the thermal conductivity and heat dissipation capacity of the second cover plate 1152 are improved. By providing a textured structure on the surface of the second cover plate 1152, the heat dissipation area of ​​the second cover plate 1152 is increased, thereby improving the heat dissipation capacity of the second cover plate 1152. By filling the space between the second cover plate 1152 and the PCBA 116 with thermally conductive silicone grease, the thermal conductivity from the PCBA 116 to the second cover plate 1152 is improved, thereby improving the heat dissipation capacity of the second cover plate 1152.

[0159] Figure 11 This is a schematic diagram of the output shaft provided in an embodiment of this application. Figure 12 This is a schematic diagram of the structure of the first cover plate provided in an embodiment of this application.

[0160] In one implementation, combining Figure 11 and Figure 12 As shown, the first housing 123 further includes an output shaft 1231 and a first cover plate 1232. The first cover plate 1232 is fixedly connected to the output shaft 1231, and the first cover plate 1232 and the output shaft 1231 together form a first accommodating space 1234. The first accommodating space 1234 has a rotating hole communicating with the outside, and the support column 114 is inserted into the rotating hole so that the support column 114 is rotatably disposed within the first accommodating space 1234.

[0161] In one implementation, combining Figure 11As shown, the first cover plate 1232 and the output shaft 1231 can also be closed to form a third accommodating space 1235. The third accommodating space 1235 is configured to accommodate the data line 117.

[0162] Optionally, combined Figure 11 and Figure 12 As shown, the output shaft 1231 includes a first support bar 1236, and the first cover plate 1232 includes a second support bar 1237. When the first cover plate 1232 covers the output shaft 1231, the end of the first support bar 1236 abuts against the end of the second support bar 1237 along the length of the output shaft 1231. This achieves a mating installation between the output shaft 1231 and the first cover plate 1232.

[0163] In one implementation, combining Figure 12 As shown, the output shaft 1231 further includes a second communication port 1238. The second communication port 1238 is formed in the sidewall between the first accommodating space 1234 and the third accommodating space 1235 to connect the first accommodating space 1234 and the third accommodating space 1235. The second communication port 1238 is configured to allow the data cable 117 to pass through.

[0164] In one implementation, the output shaft 1231 further includes a sealing through-hole. The dual-mode endoscope 1 also includes a rubber plug 16. The sealing through-hole and the rotating hole are respectively disposed at opposite ends of the first accommodating space 1234. The rubber plug 16 is plugged in the sealing through-hole, and the rubber plug 16 is configured to close the first accommodating space 1234.

[0165] Specifically, after the support column 114, bearing 1222, data cable 117 and other components are installed, multiple glue storage grooves are formed between the support column 114 and other components (i.e., grooves formed between components). After sealing each glue storage groove with glue, the through hole is sealed by rubber plug 16 to close the first accommodating space 1234, thereby achieving secondary sealing of the internal components and reducing the problem of foreign objects entering the interior of the dual-mode endoscope 1 and causing damage.

[0166] In one implementation, the transmission component 121 is a wire transmission system.

[0167] Figure 13 for Figure 2 The illustrated embodiment is a cross-sectional view along direction AA.

[0168] For example, combined Figure 7 and Figure 8 As shown, a first groove 1141 and a second groove 1142 are formed on the side wall of the support column 114. The first groove 1141 and the second groove 1142 communicate to form a transmission groove, which is circumferentially disposed on the side wall of the support column 114. Figure 7 , Figure 8 and Figure 13 As shown, the transmission assembly 121 includes: a wire head 1211, a tungsten wire rope 1212, and a steel pipe 1213. The wire head 1211 is engaged with the first groove 1141 and has an interference fit with the groove wall of the first groove 1141. The tungsten wire rope 1212 passes through the wire head 1211 and is fixedly connected to the wire head 1211, and the tungsten wire rope 1212 is located in the second groove 1142. The thin steel pipe 1213 is sleeved on the tungsten wire rope 1212. The controlled movement of the tungsten wire rope 1212 drives the wire head 1211 to move, thereby driving the lens section 11 to rotate.

[0169] For example, steel pipe 1213 is a thin steel pipe.

[0170] For example, the third accommodating space 1235 accommodates a portion of the components of the transmission assembly 121 (the portion of the components connecting the drive section and the lead screw 1211).

[0171] Figure 14 This is a schematic diagram showing a first rotation angle of 0° or 180° for an embodiment of this application.

[0172] Combination Figure 14 As shown, when the first rotation angle is 0° or 180°, the wire end 1211 is in the maximum non-slip position, that is, in this state, the wire end 1211 is still engaged with the second groove 1142. It is understandable that when the lens part 11 continues to rotate, although the wire end 1211 is engaged with the second groove 1142 and has an interference fit with the second groove 1142, it may still be pulled away from the second groove 1142 by the tungsten wire rope 1212 when the rotation angle is further adjusted.

[0173] Optionally, combined Figure 7 , Figure 8 and Figure 13 As shown, the rotating assembly 122 includes a bearing 1222. The support column 114 is rotatably connected to the output section 12 via the bearing 1222.

[0174] Specifically, the outer ring of the bearing 1222 is fixedly disposed on the side wall of the first accommodating space 1234, and the inner ring of the bearing 1222 is sleeved on the side wall of the support column 114.

[0175] For example, the data line 117 in the second accommodating space 1154 passes through the first communication hole 1153 and reaches the first accommodating space 1234 in the output section 12, then passes through the second communication hole 1238 and reaches the third accommodating space 1235, and then connects with the integrated cable 14 to realize the transmission of signals and power.

[0176] In one implementation, refer to Figure 9 and Figure 10 As shown, the outer wall of the support column 114 is provided with a third groove 1143. (This is in conjunction with...) Figure 7, Figure 8 and Figure 13 As shown, the rotating assembly 122 further includes a pressure ring 1221 and a retaining ring 1223. The pressure ring 1221 is fixedly disposed in the first housing 123, and the retaining ring 1223 is fixedly disposed in the second groove 1142, and is interference-fitted with the groove wall of the second groove 1142. The pressure ring 1221 and the retaining ring 1223 are configured to be positioned in the axial limiting bearing 1222. The pressure ring 1221, bearing 1222, and retaining ring 1223 are all coaxial with the support column 114 and arranged sequentially along the axis of the support column 114.

[0177] Figure 15 This is a schematic diagram of the pressure ring provided in an embodiment of this application.

[0178] Optionally, the output shaft 1231 includes a receiving groove corresponding to the first receiving space 1234, the groove wall of which forms a second top block 1239. When the first cover plate 1232 and the output shaft 1231 are closed, the groove wall of the receiving groove and the side wall of the first cover plate 1232 form the first receiving space 1234. Figure 13 As shown, the sidewall of the first cover plate 1232 includes a first top block 1233. (Combined with...) Figure 15 As shown, the pressure ring 1221 includes a bearing flange 1224.

[0179] For example, combined Figure 13 and Figure 15 As shown, the first top block 1233, the bearing retaining edge 1224, and the groove wall of the receiving groove (i.e., the second top block 1239) are arranged sequentially from top to bottom to limit and fix the pressure ring 1221. The first top block 1233 and the second top block 1239 respectively abut against the opposite ends of the bearing retaining edge 1224 to fix the pressure ring 1221.

[0180] For example, combined Figure 13 and Figure 15 As shown, a first cover plate 1232, a pressure ring 1221, a bearing 1222, and a retaining ring 1223 are sequentially arranged along the axial direction of the support column 114. This achieves the limiting of each component in the axial direction and improves the structural stability.

[0181] For example, the sidewall of the first accommodating space 1234 is provided with a notch, which is located on the sidewall of the second top block 1239. The upper end face of the bearing 1222 is pressed with a bearing retainer 1224, and the lower end face of the bearing 1222 abuts against the sidewall of the notch. In this way, the outer ring of the bearing is fixed to the sidewall of the first accommodating space 1234.

[0182] Combination Figure 6As shown, this application provides a handheld dual-mode endoscope, including: a dual-mode endoscope 1 as described in any of the above embodiments, a control unit 13, an integrated cable 14, and a plug 15 arranged sequentially; the control unit 13 is configured to be handheld and to control the operation of the lens unit 11; the integrated cable 14 is communicatively and electrically connected to the endoscope host via the plug 15; the integrated cable 14 is communicatively and electrically connected to the control unit 13, the depth sensor 111, and the image sensor 112 to supply power to the control unit 13, the depth sensor 111, and the image sensor 112, and to transmit stereoscopic visual images of the target area tissue and corresponding depth information to the endoscope host.

[0183] The handheld dual-mode endoscope provided in this application embodiment allows the lens section 11 to be driven by the control unit 13, causing the lens section 11 to rotate relative to the output unit 12. This facilitates the construction of a realistic three-dimensional visual image of the tissue based on its depth information and stereoscopic visual image. This allows the handheld dual-mode endoscope to be in a retracted state, facilitating entry into the target area through the channel and reducing the need for large incisions on the body surface. When the handheld dual-mode endoscope is in working state, it allows for multi-angle observation of the tissue in the target area, expanding the field of view.

[0184] In one implementation, such as Figure 6 As shown, the control unit 13 also includes a knob 131, which is connected to the lens unit 11 via a transmission assembly 121 so that rotating the knob 131 can drive the lens unit 11 to rotate.

[0185] Combination Figure 1 As shown, this application provides a dual-mode endoscope for robots, comprising: a dual-mode endoscope 1 as described in any of the above embodiments, a transmission box 18, an integrated cable 14, and a plug 15 arranged sequentially; the transmission box 18 is configured to control the operation of the lens section 11; the integrated cable 14 is communicatively and electrically connected to the endoscope host via the plug 15; the integrated cable 14 is communicatively and electrically connected to the control unit 13, the depth sensor 111, and the image sensor 112 to supply power to the control unit 13, the depth sensor 111, and the image sensor 112, and to transmit stereoscopic visual images of the target area tissue and corresponding depth information to the endoscope host.

[0186] The robotic dual-mode endoscope provided in this application embodiment can drive the lens section 11 to work via the transmission box 18, causing the lens section 11 to rotate relative to the output section 12. This facilitates the construction of a realistic three-dimensional visual image of the tissue based on tissue depth information and stereoscopic visual images. This allows the robotic dual-mode endoscope to be in a retracted state, facilitating entry into the target area through the channel and reducing the need for large incisions on the body surface. When the robotic dual-mode endoscope is in working state, it allows for multi-angle observation of tissue in the target area, expanding the field of view. It should be understood that... Figure 1 The control unit 13 shown is the transmission box 18 in the embodiment of this application, which is used to drive the lens part to rotate.

[0187] In one implementation, the transmission box 18 can control the rotation of the lens section 11 and the overall rotation of the dual-mode endoscope 1.

[0188] In one implementation, the transmission box 18 is provided with one or more buttons, which can control functions such as taking pictures and turning on the lighting.

[0189] In one implementation, the transmission box 18 and the lens section 11 are connected by a wire transmission system, so that the transmission box 18 drives the wire transmission system to rotate the lens section 11.

[0190] Figure 16 This is a structural block diagram of a surgical scene three-dimensional reconstruction system provided in an embodiment of this application.

[0191] Figure 17 A flowchart illustrating the three-dimensional reconstruction of a surgical scene provided in an embodiment of this application.

[0192] Combination Figure 16 and Figure 17 As shown, this application embodiment also provides a surgical scene three-dimensional reconstruction system, including: a dual-mode endoscope 1 and a three-dimensional reconstruction module 2. The dual-mode endoscope 1 includes a lens section, which is equipped with a depth sensor and at least two image sensors; the dual-mode endoscope 1 is configured to acquire stereoscopic visual images of tissue in a target area and corresponding depth information; the depth information includes a first depth and a second depth; the depth sensor is configured to acquire the first depth of the tissue, and the at least two image sensors are configured to acquire the stereoscopic visual image and the second depth of the tissue; the three-dimensional reconstruction module 2 is communicatively connected to the dual-mode endoscope 1, and the three-dimensional reconstruction module 2 is configured to: Step S1, acquire the stereoscopic visual image and depth information acquired by the dual-mode endoscope. Step S2, convert the first depth and the second depth to the target coordinate system. Step S3, fuse the first depth and the second depth in the target coordinate system to determine the target depth. Step S4, generate three-dimensional point cloud data corresponding to the target depth based on the target depth. Step S5, generate a three-dimensional surface mesh model of the surgical area based on the three-dimensional point cloud data through surface reconstruction technology. Step S6, render the three-dimensional surface mesh model to generate a three-dimensional view.

[0193] The surgical scene 3D reconstruction system provided in this application can generate a 3D view of the surgical area based on depth information and stereoscopic vision images obtained by a depth sensor and at least two image sensors. This enables stereoscopic presentation of tissues and organs, reduces the risk of spatial positioning deviation caused by lack of stereoscopic sense in images, facilitates precise control of the movement trajectory of surgical instruments, and can accurately quantify the spatial relationship of anatomical structures within the surgical field, thereby significantly improving the accuracy and safety of surgical operations.

[0194] The surgeon can view a real-time 3D view on the monitor of the endoscope. As the perspective changes during the surgery, the system updates the reconstructed 3D view in real time, providing a dynamic 3D perspective.

[0195] Specifically, the 3D reconstruction module fuses the first depth obtained by at least two image sensors with the second depth obtained by a depth sensor to construct a high-precision 3D point cloud, and then reconstructs a realistic 3D model based on the 3D point cloud.

[0196] It is understood that the 3D reconstruction module can be directly installed in the endoscope host to facilitate the direct generation and display of 3D views, or it can be connected to an external electronic device to generate 3D views and then transmit them back to the endoscope host for display. This application does not impose any restrictions on this.

[0197] Depth sensors directly calculate depth information by emitting light signals and measuring the return time of those signals, generating a first depth image at DTOF (Depth-to-Flight). Unlike the "calculation" method of binocular vision, depth sensors directly obtain the accurate distance to each point through time measurement.

[0198] In one implementation, the process of the depth sensor acquiring the first depth includes steps S111 to S113, as follows:

[0199] Step S111: Record the first time of light pulse emission and the second time of receiving the reflected light pulse.

[0200] Step S112: Calculate the difference between the second time and the first time to determine the round-trip time δt of the optical pulse.

[0201] Step S113: Calculate the distance based on the speed of light and the round-trip time. The formula is Z = c × δt / 2, where c is the speed of light.

[0202] Based on the above steps S111 to S113, a first depth DTOF is generated. The first depth is a two-dimensional depth matrix, where the value of each pixel represents the distance from the pixel to the depth sensor.

[0203] In one implementation, the process of the depth sensor acquiring the first depth further includes step S114, as follows:

[0204] Step S114: Convert the first depth of the two-dimensional depth matrix into the first depth in the form of a three-dimensional point cloud.

[0205] An image sensor (including a first image sensor and a second image sensor) uses the parallax between the first image sensor and the second image sensor to estimate the distance to each point in the scene.

[0206] In one implementation, the process of acquiring the second depth using at least two image sensors includes steps S121 to S123, as follows:

[0207] Step S121: Take a first image and a second image of the same target tissue using a first image sensor and a second image sensor, respectively.

[0208] Step S122: Calculate the disparity corresponding to each pixel in the first image and the second image. The disparity is the displacement of the same pixel in the first image and the second image.

[0209] In this step, the pixel displacement can be calculated using a stereo matching algorithm, such as the Sum of Absolute Differences (SAD) algorithm or the Semi-Global Matching (SGM) algorithm.

[0210] Step S123: Calculate the depth of each pixel based on parallax. The calculation formula is Z = f × B / d, where f is the focal length of the camera (the focal lengths of the first image sensor and the second image sensor are the same), B is the distance between the first image sensor and the second image sensor (i.e., the baseline length), and d is the parallax.

[0211] Based on the above steps S121 to S123, a set of calculation results Z can be obtained, which is the second depth DStereo. The second depth is a two-dimensional depth matrix, where the value of each pixel represents the distance of that pixel.

[0212] It is understandable that after step S122, the two-dimensional second depth can also be transformed into a three-dimensional second depth.

[0213] In one implementation, in step S2, the 3D reconstruction module is specifically configured as follows: steps S21 and S22:

[0214] Step S21: Calibrate the depth sensor and the image sensor to determine the first calibration data corresponding to the depth sensor and the second calibration data corresponding to the binocular image sensor.

[0215] In one implementation, the dual-mode endoscope includes a binocular image sensor. First calibration data for the binocular image sensor can be acquired using tools such as a checkerboard pattern. This first calibration data includes intrinsic and extrinsic parameters. Intrinsic parameters include focal length and principal point position, while extrinsic parameters include the relative positions and angles between the cameras. Second calibration data for the depth sensor includes the position and orientation of the depth sensor in space.

[0216] Step S22: Based on the first calibration data and the second calibration data, transform the first depth and the second depth to the target coordinate system.

[0217] In one implementation, a coordinate system displacement method can be used to shift the second depth to the coordinate system of the first image or the coordinate system of the second image.

[0218] In this embodiment, since the image sensor and depth sensor are mounted in different locations, and their coordinate systems (i.e., the reference points upon which the first and second depths are based) are different, coordinate alignment is required first in order to correctly combine the first and second depths.

[0219] Specifically, since the structures of image sensors and depth sensors are fixed and their coordinate alignment is stable, the coordinate alignment is calibrated before leaving the factory and preset in the 3D reconstruction module.

[0220] Optionally, in step S3, the 3D reconstruction module is specifically configured as follows: steps S31 to S33:

[0221] Step S31: Determine the first weight corresponding to the first depth and the second weight corresponding to the second depth.

[0222] In one implementation, the first and second weights are determined based on the quality of their respective depths (e.g., noise, viewing distance, etc.). For example, data from the first depth is given a higher weight if the viewing distance is within the first 50% of the endoscope's working distance (e.g., 5-15cm), and vice versa (e.g., 15-30cm) if the viewing distance is within the first 50% of the endoscope's working distance.

[0223] Step S32: Calculate the weighted average value of each point in the two-dimensional coordinate system based on the first weight, the second weight, the first depth, and the second depth.

[0224] For example, the calculation formula is as follows:

[0225] ZFinal(x,y) = wStereo(x,y) × ZStereo(x,y) + wTOF(x,y) × ZTOF(x,y) / (wStereo(x,y) + wTOF(x,y)), where wTOF(x,y) is the first weight and wStereo(x,y) is the second weight.

[0226] Step S33: Construct the target depth based on the weighted average value.

[0227] In this embodiment, the first depth and the second depth are fused to achieve mutual complementarity. For example, the second depth is more accurate at long distances, while the first depth is more accurate at short distances. Therefore, fusing the data from both can yield a more accurate and stable target depth.

[0228] In one implementation, prior to step S31 in step S3, the 3D reconstruction module is further configured as follows: steps S34 and S35:

[0229] Step S34: Determine the missing depth data in the first depth and / or the second depth at the target resolution; the target resolution is the first resolution of the first depth or the second resolution of the second depth.

[0230] In one implementation, when the resolutions of the first depth and the second depth are different, the resolutions of the first depth and the second depth need to be unified. The larger of the two resolutions is used as the target resolution, and the missing parts (i.e., missing depth data) in the depth corresponding to the smaller resolution are filled in according to the target resolution. This facilitates the fusion of the first depth and the second depth.

[0231] In the event of missing depth data in the first depth and / or the second depth, the missing depth data is filled in to facilitate the fusion of the first depth and the second depth.

[0232] Step S35: Use an interpolation algorithm to fill in the missing depth data.

[0233] In one implementation, the interpolation algorithm includes, but is not limited to, nearest neighbor interpolation, bilinear interpolation, or stereo interpolation.

[0234] For example, in step S3, after step S33, the 3D reconstruction module is further configured as follows in step S36:

[0235] Step S36: Use Kalman filtering to optimize the target depth.

[0236] In one implementation, a Kalman filter can be used to optimize depth data fusion by predicting and updating data from depth sensors and image sensors to reduce noise, thereby obtaining a more stable depth estimate, making the target depth smoother and more stable, and correcting errors in measurement.

[0237] In one implementation, in step S4, the 3D reconstruction module is specifically configured as follows: step S41:

[0238] Step S41: Based on the intrinsic parameter matrix of the image sensor, the points in the target depth are transformed from a two-dimensional coordinate system to a three-dimensional coordinate system to generate three-dimensional point cloud data.

[0239] In this embodiment, each pixel in the target depth corresponds to a point in three-dimensional space, and the three-dimensional coordinates of each point are determined by the intrinsic parameters of the image sensor and the depth information. The point cloud generated in step S41 includes the three-dimensional coordinates of each point in the scene.

[0240] In one implementation, the intrinsic parameter matrix includes focal length, principal point position, etc. The transformation of points in the target depth from a two-dimensional coordinate system to a three-dimensional coordinate system is mainly achieved through back projection. The specific formula for back projection is as follows:

[0241] ;

[0242] in, It is the inverse of the camera intrinsic parameter matrix. It is the position of a pixel within the target depth. It is the pixel value (i.e., the depth value) of a pixel.

[0243] In one implementation, in step S5, an algorithm is used to repair and smooth the surface of the 3D point cloud data, making the generated 3D model smoother and more realistic.

[0244] In one implementation, the algorithm used can be the Delaunay Triangulation Algorithm, the Poisson Surface Reconstruction Algorithm, or the Marching Cubes Algorithm.

[0245] In one implementation, prior to step S5, the 3D reconstruction module is further configured as follows in step S7:

[0246] Step S7: Optimize the 3D point cloud data to remove redundant data and / or noise from the 3D point cloud data.

[0247] In this embodiment, the three-dimensional point cloud data generated in step S4 may contain noise and / or redundant data. Therefore, it is necessary to optimize the three-dimensional point cloud data to remove redundant data and / or noise and improve the accuracy and quality of the three-dimensional point cloud data.

[0248] In one implementation, methods for optimizing 3D point cloud data include using a voxel grid filter to reduce redundant points, compressing the point cloud size, and removing unwanted noise points to eliminate redundant data and / or noise.

[0249] In one implementation, in step S6, a three-dimensional surface mesh model is rendered in real time using graphics technology (such as OpenGL) to generate a three-dimensional view of the surgical scene.

[0250] In one implementation, after step S6, the following step S8 is also included:

[0251] Step S8: Identify and label the tissues in the 3D view.

[0252] The dual-mode endoscope 1, handheld dual-mode endoscope, robotic dual-mode endoscope, and surgical scene 3D reconstruction system provided in this application's embodiments, combining laparoscopic surgical robots with intracavitary 3D reconstruction technology, can improve the accuracy, safety, efficiency, and personalization of laparoscopic minimally invasive surgery. By providing clear and accurate 3D views, surgeons can better understand the patient's intracavitary structures, thereby making more precise decisions in complex surgeries, avoiding surgical risks, and improving treatment outcomes.

[0253] Specifically, laparoscopic surgical robots, combined with intracavitary 3D reconstruction technology, overcome the limitations of traditional planar vision by precisely constructing three-dimensional images of tissues in the target area. Especially in areas with complex anatomical structures such as the gastrointestinal tract and urinary system, the 3D images clearly present the spatial location and morphology of organs, tumors, or lesions, allowing surgeons to intuitively grasp the three-dimensional relationships of intracavitary structures. Simultaneously, 3D depth perception effectively compensates for the lack of depth perception caused by the limited operating channel in laparoscopic surgery, helping surgeons accurately determine the depth and angle of the target area, reducing the risk of accidentally damaging healthy tissue during puncture or resection procedures. This enhanced stereoscopic vision and depth judgment significantly improves the precision of surgical instrument manipulation; for example, during tumor resection, it allows for complete removal of lesions while avoiding the removal of normal tissue.

[0254] Three-dimensional reconstruction technology updates navigation images in real time during surgery. When a surgical robot is equipped with a real-time three-dimensional reconstruction system, the surgeon can not only predict the optimal operating path through the three-dimensional view, but also obtain instant positional feedback during instrument movement. This ensures that the spatial relationship between surgical instruments and tissues remains controllable in high-precision surgeries such as biliary tract and vascular anastomosis, greatly reducing surgical risks.

[0255] It should be noted that those skilled in the art, upon considering the specification and practicing the application disclosed herein, will readily conceive of other embodiments of this application. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope of this application is indicated by the claims.

[0256] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A dual-mode endoscope configured to acquire stereoscopic visual images of tissue in a target region and corresponding depth information, characterized in that, include: The lens section is equipped with a depth sensor and at least two image sensors; At least two of the image sensors are configured to acquire stereoscopic images of the tissue, the stereoscopic images including white light images, fluorescence images, or white-fluorescence fusion images; The depth information includes a first depth, and the depth sensor is configured to acquire the first depth of the tissue.

2. The dual-mode endoscope according to claim 1, characterized in that, The depth information also includes a second depth, and at least two of the image sensors are configured to simultaneously acquire the second depth of the tissue.

3. The dual-mode endoscope according to claim 1, characterized in that, Also includes: An elongated output portion having a proximal end and a distal end, the distal end being configured to enter the target region to approach the tissue; The lens section is located at the far end of the output section; When the first depth is obtained using the depth sensor, the distance between the depth sensor and the tissue is less than or equal to a preset distance, whereby the preset distance characterizes the effective detection distance of the depth sensor.

4. The dual-mode endoscope according to claim 3, characterized in that, The lens portion is rotatably disposed at the far end of the output portion; The angle at which the lens can rotate relative to the output section is a first rotation angle, and the range of the first rotation angle is 0° to 180°. The dual-mode endoscope has a retracted state; In the retracted state, the angle between the lens section and the output section is within a first angle range, such that the maximum size of the lens section along the width direction is less than or equal to the size of the output section; the first angle range is within the range of the first rotation angle. During the process of entering the target area through the channel at the distal end, the dual-mode endoscope remains in the retracted state.

5. The dual-mode endoscope according to claim 3, characterized in that, The lens section includes: a support pillar; The output section includes: The transmission assembly is connected to the support column in a transmission manner; A rotating assembly, wherein the support column is rotatably disposed inside the rotating assembly; The transmission component can controllably drive the support column to rotate within the rotating component, thereby driving the lens section to rotate.

6. The dual-mode endoscope according to claim 5, characterized in that, The output section also includes: The first housing includes a first top block and a second top block; The rotating assembly includes: The pressure ring is configured to provide axial restraint for the bearing; The pressure ring includes a bearing flange, and the first top block and the second top block respectively abut against the opposite ends of the bearing flange to fix the pressure ring.

7. The dual-mode endoscope according to claim 3, characterized in that, The lens section includes: a support pillar; The support column has a first communication hole; the data lines of the image sensor and the depth sensor pass through the first communication hole. The output section also includes: The first housing includes a first accommodating space, the support column is rotatably disposed in the first accommodating space, and the first communication hole is connected to the first accommodating space; when the lens part rotates relative to the output part, the lens part rotates relative to the first housing. The dual-mode endoscope also includes: A sealing plug is disposed at the first communication hole, the sealing plug being configured to seal the first communication hole, and the data cable passing through the sealing plug; The sealing plug is sealed to other components by dispensing adhesive.

8. The dual-mode endoscope according to any one of claims 1 to 7, characterized in that, The at least two image sensors include a first image sensor and a second image sensor, which are symmetrically arranged on both sides of the depth sensor, and the first image sensor, the second image sensor and the depth sensor are located on the same straight line.

9. The dual-mode endoscope according to any one of claims 1 to 7, characterized in that, The depth sensor includes a TOF sensor or a structured light sensor.

10. The dual-mode endoscope according to any one of claims 1 to 7, characterized in that, The lens section also includes: The second housing includes a second accommodating space; the depth sensor and at least two of the image sensors are disposed within the second accommodating space; The second casing is made of metal; And / or, the surface of the second housing has a textured structure; And / or, the depth sensor and at least two of the image sensors are integrated on a PCBA, the PCBA is disposed within the second accommodating space, and thermally conductive silicone grease is filled between the PCBA and the second housing.

11. The dual-mode endoscope according to any one of claims 1 to 7, characterized in that, Also includes: An illumination element is disposed on the lens portion, and the illumination element is configured to provide a light source to the target area; The depth sensor, at least two of the image sensors, and the illumination element are arranged in a centrally symmetrical manner, with the depth sensor located at the center of symmetry.

12. A handheld dual-mode endoscope, characterized in that, include: The dual-mode endoscope, control unit, integrated cable, and plug as described in any one of claims 1 to 11 are arranged sequentially. The control unit is configured to be handheld and to control the rotation of the lens unit; The integrated cable is connected to the endoscope host via a plug for communication and electrical connection. The integrated cable is communicatively and electrically connected to the control unit, the depth sensor, and the image sensor to power the control unit, the depth sensor, and the image sensor, and to transmit stereoscopic visual images of the target area tissue and corresponding depth information to the endoscope host.

13. A dual-mode endoscope for robots, characterized in that, include: The dual-mode endoscope, transmission box, integrated cable, and plug as described in any one of claims 1 to 11 are arranged sequentially. The transmission box is configured to control the operation of the lens section; The integrated cable is connected to the endoscope host via a plug for communication and electrical connection. The integrated cable is communicatively and electrically connected to the transmission box, the depth sensor, and the image sensor to power the transmission box, the depth sensor, and the image sensor, and to transmit stereoscopic visual images of the target area tissue and corresponding depth information to the endoscope host.

Images