Anti-collision method and device, image processing equipment and endoscope system

Abstract

The invention is suitable for the technical field of medical equipment, and provides an anti-collision method and device, image processing equipment and an endoscope system.The method is applied to an endoscope, an insertion part of the endoscope is provided with scales, and in the process that the digestive tract of a to-be-detected object is examined through the endoscope, the digestive tract of the to-be-detected object is examined through the scales. The method comprises the steps of determining a target position in a digestive tract part according to the digestive tract part recognized by the endoscope in the endoscope entering process, determining an early warning scale according to a first scale, corresponding to the target position, of the insertion part, and determining an early warning scale according to a second scale, corresponding to the target position, of the insertion part in the endoscope withdrawing process. And when it is identified that the insertion part reaches the early warning scale, early warning is carried out. According to the invention, accurate anti-collision early warning can be carried out on the endoscope.

Description

Technical Field

[0001] The present application belongs to the field of medical equipment technology, and in particular, relates to an anti-collision method, device, image processing equipment, endoscope system and computer-readable storage medium. Background Art

[0002] An endoscope is a medical instrument used to examine the human digestive tract, such as the bronchi, stomach, and intestines. Depending on the specific part of the digestive tract to be examined, endoscopes mainly include colonoscopes, enteroscopes, capsule endoscopes, and pharyngoscopes. During an endoscopic examination, an endoscope is used to enter the human digestive tract and examine the digestive tract. For example, a colonoscope is used to examine the patient's intestines.

[0003] The endoscope includes a connection part, an operation part, and an insertion part, wherein a lens is installed in the head end of the insertion part. In practical applications, the endoscope generally uses the lens at the head end to identify the digestive tract. Therefore, when the endoscope is withdrawn, the parts that cannot be photographed by the lens are prone to collision, thereby injuring the patient, for example, causing complications after the collision. Summary of the invention

[0004] The embodiments of the present application provide a collision avoidance method, system, device, and electronic device that can provide accurate collision avoidance warning for an endoscope.

[0005] In a first aspect, an embodiment of the present application provides an anti-collision method, which is applied to an endoscope, wherein the insertion portion of the endoscope has a scale;

[0006] In the process of using the endoscope to examine the digestive tract of the object to be examined, the method includes:

[0007] During the endoscope insertion process, a target position in the digestive tract is determined according to the digestive tract position identified by the endoscope; and a warning scale is determined according to the first scale of the insertion portion corresponding to the target position;

[0008] During the endoscope retraction process, when it is recognized that the insertion portion has reached the warning scale, a warning is issued.

[0009] Optionally, when the digestive tract site is a first type of site, the method further comprises:

[0010] During the endoscope advancement process, when the endoscope recognizes the target position for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale;

[0011] When the endoscope reaches the target position, the insertion portion is exposed outside the body of the object to be measured and the scale closest to the object to be measured is determined as the first scale;

[0012] The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position comprises:

[0013] The warning scale is determined based on the first scale and the second scale.

[0014] Optionally, when the digestive tract site is the second type of site, the method further comprises:

[0015] During the endoscope advancement process, when the endoscope recognizes the digestive tract site for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale; when the endoscope recognizes the digestive tract site for the last time, the target position is determined based on the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured and the second scale, and the first scale corresponding to the target position is determined;

[0016] The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position comprises:

[0017] The warning scale is determined based on the first scale and the second scale.

[0018] Optionally, the difference between the warning scale and the third scale is smaller than a preset length difference, and the third scale is a scale value based on the first scale and symmetrical to the second scale.

[0019] Optionally, after determining the warning scale based on the first scale and the second scale, the method further includes:

[0020] When a bending operation on the insertion portion is detected, updating the warning scale to obtain the updated warning scale;

[0021] When it is identified that the insertion portion reaches the warning scale, issuing a warning comprises:

[0022] When it is recognized that the insertion portion has reached the updated warning scale, a warning is issued.

[0023] Optionally, updating the warning scale includes:

[0024] The bending degree of the insertion portion caused by the bending operation is obtained, and the warning scale is increased according to the bending degree; wherein the increase in the warning scale is positively correlated with the bending degree.

[0025] Optionally, the method further comprises:

[0026] During the process of withdrawing the endoscope, the position of the tip of the insertion portion is identified according to the digestive tract site identified by the endoscope;

[0027] When the position of the head end does not meet the preset requirement, navigation is performed on the position of the head end based on the digestive tract site until the head end is separated from the digestive tract site.

[0028] Optionally, the navigating the position of the head end based on the digestive tract site includes:

[0029] In the case where the endoscope cannot identify the complete edge of the digestive tract, navigating the tip portion away from the digestive tract;

[0030] In the case where the endoscope can identify the complete edge of the digestive tract part, the center position of the complete edge is determined based on the complete edge of the digestive tract part; when the distance between the center position and the center of the image identified by the endoscope does not satisfy a preset distance difference, the head end is navigated until the distance between the center position and the center of the image satisfies the distance difference.

[0031] Exemplarily, during the endoscope advancement process, the method further includes:

[0032] Calculating the actual distance between the tip of the endoscope and the digestive tract site;

[0033] When the actual distance is less than a preset threshold, an early warning is issued.

[0034] In a second aspect, an embodiment of the present application provides an anti-collision device, including an endoscope, a target recognition module, a warning calculation module and a reminder module, including:

[0035] The endoscope includes an insertion portion with a scale;

[0036] The target recognition module is used to determine the target position in the digestive tract according to the digestive tract part recognized by the endoscope during the endoscope advancement process; and to recognize that the insertion portion reaches the warning scale during the endoscope withdrawal process;

[0037] The warning calculation module is used to determine the warning scale according to the first scale of the insertion part corresponding to the target position during the endoscope advancement process;

[0038] The reminder module is used to issue an early warning when the insertion portion reaches the early warning position.

[0039] In a third aspect, an embodiment of the present application provides an image processing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the anti-collision method described in the first aspect when executing the computer program.

[0040] In a fourth aspect, an embodiment of the present application provides an endoscope system, which includes: an image processing device, an endoscope, a light source host, and a display device.

[0041] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the anti-collision method described in the first aspect are implemented.

[0042] In a sixth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on an image processing device, the image processing device executes the anti-collision method described in any one of the first aspects above.

[0043] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0044] When the endoscope is used to examine the digestive tract of the object to be tested, the present application determines the warning scale through the process of the endoscope advancing, and uses the above-mentioned warning scale to perform anti-collision warning when the endoscope is withdrawn. Specifically, during the above-mentioned process of the endoscope advancing, the target position in the digestive tract is determined according to the digestive tract part identified by the endoscope, and the warning scale is determined according to the first scale of the insertion part corresponding to the above-mentioned target position, which means that the warning scale can be locked in advance during the process of the endoscope advancing, and a corresponding warning reminder can be given during the process of the endoscope withdrawing, which can improve the standardization of manual operation during the endoscope withdrawal inspection and reduce endoscope collisions through warnings. At the same time, the warning scale is determined by the target position identified by the endoscope in the digestive tract of the object to be tested, and the real scale of the insertion part corresponding to the target position, indicating that the warning scale is measured by the real physical distance, so the warning scale can be used to more accurately perform anti-collision warnings during the process of the endoscope withdrawing. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1is a schematic diagram of the structure of the intestine provided in one embodiment of the present application;

[0047] Figure 2 is a flowchart of an anti-collision method provided by an embodiment of the present application;

[0048] Figure 3 This is a schematic diagram of identifying the splenic flexure during the endoscope advancement process provided by an embodiment of the present application;

[0049] Figure 4 This is a schematic diagram of identifying the transverse colon during the endoscope insertion process provided by an embodiment of the present application;

[0050] Figure 5 is a schematic diagram of determining a warning scale provided by an embodiment of the present application;

[0051] Figure 6 is a schematic diagram of navigating the position of the head end of an endoscope provided by an embodiment of the present application;

[0052] Figure 7 is a schematic structural diagram of an anti-collision device provided in an embodiment of the present application;

[0053] Figure 8 is a structural schematic diagram of an image processing device provided in an embodiment of the present application;

[0054] Fig. 9 It is a functional architecture diagram of the endoscope system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0056] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0057] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0058] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0059] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0060] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0061] When using an endoscope to examine the digestive tract, the specific part of the digestive tract will be identified by the lens at the end of the endoscope head, and the doctor's operating behavior will be standardized to avoid collision between the endoscope and the digestive tract. Figure 1The figure shows a schematic diagram of the structure of the intestine, in which the ascending colon (101), the right flexure of the colon (102), the transverse colon (103), the left flexure of the colon (104) and the descending colon-sigmoid colon (105) are different parts of the intestine. In addition, the intestine also includes the appendix, cecum, rectum, ileocecal valve and anal canal (not shown in the figure). When performing a transverse colon entry inspection, the left flexure of the colon (splenic flexure) will cause the intestinal cavity to expand due to air retention, and it will be impossible to enter the transverse colon smoothly. At this time, the transverse colon will be entered through a sliding endoscope. For example, the endoscope body is rotated counterclockwise to place the next intestinal cavity at the 12 o'clock position, and then the knob is turned upward, and the endoscope is advanced inward by <10cm to achieve sliding entry; when performing a right flexure of the colon (hepatic flexure) entry inspection, it is necessary to follow the rule of rightward, leftward and then rightward for inspection, including: first place the hepatic flexure on the right side of the endoscope recognition screen, and pass through the hepatic flexure by rotating the endoscope body clockwise and turning the knob upward appropriately. When withdrawing the endoscope for observation, the hepatic flexure and splenic flexure are relatively curved and prone to slippage, so it is necessary to determine in advance how to operate at the turning points of the splenic flexure and hepatic flexure to avoid collision between the endoscope and the intestinal cavity. That is, in actual examinations, due to structural differences in different parts of the digestive tract (such as the large curvature of the splenic flexure and hepatic flexure of the intestine, and the high degree of freedom of the transverse colon, etc.), the different complexities of endoscopic operations in different parts of the digestive tract, and the limitations of the endoscope itself (only the lens is installed in the head of the endoscope, and the rear cannot be identified when the endoscope is withdrawn), etc., the endoscope may collide with the digestive tract, which may injure the patient.

[0062] In order to improve the accuracy of anti-collision warning, the present application provides an anti-collision method for warning based on the scale of the insertion part of the endoscope.

[0063] Figure 2 A schematic flow chart of an anti-collision method provided in an embodiment of the present application is shown. The method is applied to an endoscope, and a scale is provided on the insertion portion of the endoscope. In the process of using the endoscope to examine the digestive tract of the object to be tested, the method includes:

[0064] S20. During the endoscope advancement process, a target position in the digestive tract portion is determined based on the digestive tract portion identified by the endoscope; and a warning scale is determined based on the first scale of the insertion portion corresponding to the target position.

[0065] In an embodiment of the present application, when the endoscope is advanced, the digestive tract site will be identified through the lens at the head end of the endoscope, and the distance between the head end of the endoscope and the identified digestive tract site will be calculated in real time. The above-mentioned target position refers to a position point in the digestive tract that has specific pipeline structural characteristics, such as a bending position, a center position, etc. The above-mentioned first scale corresponds to the above-mentioned target position, and indicates the scale on the insertion part recorded when the endoscope reaches the above-mentioned target position or near the target position during the endoscope advancement process. The above-mentioned warning scale is determined by the first scale, and is used to warn the current position of the endoscope. Since the warning scale is a real scale on the insertion part, it means that the current position of the endoscope can be measured by the real physical distance outside the body, thereby improving the accuracy of the endoscope position reminder.

[0066] In some embodiments, assuming that the above-mentioned digestive tract part is the splenic flexure or the transverse colon, the above-mentioned target position can be the bending position of the splenic flexure or the center position of the transverse colon, and the bending position of the splenic flexure or the center position of the transverse colon is determined according to the splenic flexure or the transverse colon recognized by the lens of the head end of the endoscope, and the real-time distance between the head end of the endoscope and the splenic flexure or the transverse colon. For example, when the endoscope cannot recognize the splenic flexure, and the real-time distance between the head end of the endoscope and the splenic flexure is less than the preset distance threshold, it means that the endoscope has reached the bending position (or the vicinity of the bending position) of the splenic flexure, and the scale on the insertion part corresponding to the bending position at this time is determined to be the first scale, and the warning scale corresponding to the bending position is determined according to the scale after the first scale on the insertion part; at the same time, although the center position of the transverse colon cannot be directly identified, the center position can be determined according to the scale corresponding to the insertion part when the endoscope enters the transverse colon and the scale corresponding to the insertion part when the endoscope leaves the transverse colon, and then the corresponding first scale and warning scale are determined.

[0067] S21. During the process of retracting the endoscope, when it is recognized that the insertion portion has reached the warning mark, a warning is issued.

[0068] In the embodiment of the present application, during the process of retracting the endoscope, since the lens at the head end of the endoscope cannot recognize the rear part, when the above-mentioned insertion part reaches the above-mentioned warning scale, it indicates that the position of the endoscope is close to the above-mentioned target position. Therefore, an early warning can be given according to the early warning scale to remind the doctor that the endoscope is about to reach the above-mentioned target position, thereby reducing endoscope collision.

[0069] In some embodiments, assuming that the above-mentioned digestive tract part is the splenic flexure or the transverse colon, when it is identified that the insertion part reaches the warning scale, it means that the endoscope is close to the bending position of the splenic flexure or the center position of the transverse colon. Since these positions are prone to collision, early warning is given through the above-mentioned warning scale to avoid the endoscope from colliding at the target position. The above-mentioned warning includes one or more of a turning arrow appearing on the display device, voice reminders, text reminders, etc. Of course, warning prompts can also be given through other devices, such as warnings through sound and light alarms, etc., which are not limited here.

[0070] When the endoscope is used to examine the digestive tract of the object to be tested, the present application determines the warning scale through the process of the endoscope advancing, and uses the above-mentioned warning scale to perform anti-collision warning when the endoscope is withdrawn. Specifically, during the above-mentioned process of the endoscope advancing, the target position in the digestive tract is determined according to the digestive tract part identified by the endoscope, and the warning scale is determined according to the first scale of the insertion part corresponding to the above-mentioned target position, which means that the warning scale can be locked in advance during the process of the endoscope advancing, and a corresponding warning reminder can be given during the process of the endoscope withdrawing, which can improve the standardization of manual operation during the endoscope withdrawal inspection and reduce endoscope collisions through warnings. At the same time, the warning scale is determined by the target position identified by the endoscope in the digestive tract of the object to be tested, and the real scale of the insertion part corresponding to the target position, indicating that the warning scale is measured by the real physical distance, so the warning scale can be used to more accurately perform anti-collision warnings during the process of the endoscope withdrawing.

[0071] In the embodiment of the present application, during the endoscope advancement process, the method further includes:

[0072] Calculating the actual distance between the tip of the endoscope and the digestive tract site;

[0073] When the above actual distance is less than the preset threshold, an early warning is issued.

[0074] In an optional embodiment of the present application, the image frames taken by the head of the endoscope can be continuously identified by a pre-trained convolutional neural network (such as a VGG network pre-trained with images of different digestive tract parts, etc.), so as to identify different digestive tract parts. Assuming that the digestive tract part is the splenic flexure, when the endoscope recognizes the splenic flexure for the first time, the actual distance from the head of the endoscope to the splenic flexure will be calculated in real time, for example, 3 cm. During the continuous advancement of the endoscope, the calculation of the actual distance is still in progress, for example, 2.9 cm, 2.5 cm…0.1 cm, until the last recognition of the splenic flexure. The above actual distance can be calculated by a pre-trained convolutional neural network (such as adding distance labels to images of different digestive tract parts during training, so that the convolutional neural network outputs the corresponding actual distance while identifying the digestive tract part), or according to the monocular distance measurement principle (i.e., pinhole imaging), that is, the actual size (known) of the digestive tract part (such as the splenic flexure, the hepatic flexure, the ileocecal valve, etc.) and the size of the digestive tract part in the image frame are used to calculate the actual distance. At the same time, since the digestive tract (splenic flexure, hepatic flexure, ileocecal valve, etc.) may not be located in the center of the image frame, for example, it may be located above, below, left, or right of the intestinal wall, before calculating the actual distance, the image frame can be corrected for image distortion to improve the accuracy of the actual distance calculation. The actual distance between the endoscope and the digestive tract can be used to warn the endoscope during the endoscope insertion process to avoid collision between the endoscope and the digestive tract.

[0075] It should be noted that the parts of the digestive tract (such as the splenic flexure, the hepatic flexure, the ileocecal valve, etc.) photographed by the head of the above-mentioned endoscope can be displayed on the display device in the form of image frames, and the actual distance between the current head of the endoscope and the part of the digestive tract can be displayed in real time. When the actual distance between the head of the endoscope and the part of the digestive tract is less than a preset threshold, an early warning is issued. The form and content of the above-mentioned early warning include: one or more of a turning arrow appearing on the display device, a voice reminder, a text reminder, etc.

[0076] In an optional embodiment of the present application, since the structures of different digestive tract parts in the digestive tract are quite different, when the digestive tract part is a first type of part, the method further includes:

[0077] During the endoscope advancement process, when the endoscope recognizes the target position for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale;

[0078] When the endoscope reaches the target position, the insertion portion is exposed outside the body of the object to be measured and the scale closest to the object to be measured is determined as the first scale;

[0079] The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position includes:

[0080] The warning scale is determined based on the first scale and the second scale.

[0081] In some embodiments, the first type of part refers to a part of the digestive tract with a high degree of curvature, such as the splenic flexure or hepatic flexure in the intestine. The second scale and the first scale are the scales on the insertion portion that are exposed outside the body of the object to be measured and closest to the object to be measured when the endoscope first identifies the target position and when the endoscope reaches the target position, respectively. Since the moving distance of the same part of the digestive tract in the digestive tract when the endoscope is advanced and retracted is basically the same, it means that during the process of advancing the endoscope, the endoscope position corresponding to the warning scale determined by the second scale and the first scale is basically the same as the endoscope position corresponding to the insertion portion reaching the warning scale during the process of retracting the endoscope. Therefore, the warning scale determined when the endoscope is advanced can accurately warn the position of the endoscope when the endoscope is retracted. At the same time, since the rear position of the endoscope cannot be determined based on visual information when the endoscope is retracted, that is, the target position identified when the endoscope is advanced cannot be identified when the endoscope is retracted, the real physical scale on the insertion part can simulate the visual information at the rear when the endoscope is retracted, thereby reducing the possibility of collision when the endoscope is retracted.

[0082] In an optional embodiment of the present application, since the first type of part in the digestive tract is a part with a high degree of curvature, it can be identified based on the curvature characteristics of the curved position in the intestinal cavity, and the target position of the first type of part is the curved position, which means that identifying the first type of part is identifying the target position of the first type of part. Assuming that the first type of part is the splenic flexure, and the scale on the insertion part is identified by an external camera, refer to Figure 3 As shown, it is a schematic diagram of identifying the splenic flexure during the endoscope advancement process. When the endoscope is advanced, the lens at the head end of the endoscope first identifies the splenic flexure (304) at position 1, which means that the endoscope first identifies the bending position of the splenic flexure, and the insertion portion identified by the external camera is exposed outside the body of the object to be measured and is closest to the object to be measured. The scale is determined as the second scale; when the endoscope reaches the target position (i.e., reaches the splenic flexure (304)), the insertion portion identified by the external camera is exposed outside the body of the object to be measured and is closest to the object to be measured as the second scale, and at the same time, a warning scale is selected from the scales of the insertion portion exposed outside the body of the object to be measured to remind when the endoscope is withdrawn.

[0083] In another optional embodiment of the present application, when the digestive tract part is the second type of part, the method further includes:

[0084] During the endoscope advancement process, when the endoscope recognizes the digestive tract site for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale; when the endoscope recognizes the digestive tract site for the last time, the target position is determined based on the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured and the second scale, and the first scale corresponding to the target position is determined;

[0085] The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position includes:

[0086] The warning scale is determined based on the first scale and the second scale.

[0087] In some embodiments, the second type of part refers to a part of the digestive tract with a high degree of freedom, such as the transverse colon in the intestine. Since the pipe structure characteristics of the target position of this type of digestive tract (such as the center of the transverse colon) are not obvious enough, it cannot be directly identified based on the image frame. Assuming that the second type of part is the transverse colon in the intestine, and identifying the scale on the insertion part through the external camera, refer to Figure 4 As shown, it is a schematic diagram of the endoscope identifying the transverse colon (403) during the endoscope advancement process. When the endoscope enters the transverse colon (403), it means that the endoscope identifies the transverse colon for the first time, and the scale at which the insertion portion identified by the external camera is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale (i.e., the entry scale); when the endoscope leaves the transverse colon (403), it means that the endoscope identifies the transverse colon for the last time, and the scale at which the insertion portion identified by the external camera is exposed outside the body of the object to be measured and is closest to the object to be measured (i.e., the exit scale) is recorded. degrees); during the advancement of the endoscope, the movement distance of the endoscope in the transverse colon can be measured according to the scale on the insertion portion when entering and leaving the transverse colon, which means that the center position of the transverse colon (i.e., the target position) can be accurately determined by the scale on the insertion portion. For example, the middle scale between the entry scale and the exit scale on the insertion portion is calculated, and the middle scale corresponds to the center position of the transverse colon. The middle scale is determined as the first scale corresponding to the center position. Similarly, the warning scale is determined according to the first scale and the second scale to remind when the endoscope is withdrawn.

[0088] In an optional embodiment of the present application, due to the differences in pipeline structural characteristics in different parts of the digestive tract, in order to improve the accuracy of the determined warning scale, it also includes: the difference between the above-mentioned warning scale and the third scale is less than a preset length difference, and the above-mentioned third scale is a scale value based on the above-mentioned first scale and symmetrical to the above-mentioned second scale.

[0089] Among them, refer to Figure 5As shown in the figure, after obtaining the first and second scales during the endoscope insertion process, the third scale corresponding to the second scale can be calculated with the first scale as the symmetry center. For example, if the second scale is 20cm and the first scale is 22cm, then the third scale is 24cm. The third scale can be used directly as a warning scale; or, in order to adapt to different parts of the digestive tract, a warning scale can be set based on the third scale, and the difference between the warning scale and the third scale is less than the preset length difference, such as Figure 5 Warning scale 1 or warning scale 2 in.

[0090] In another optional embodiment of the present application, after determining the warning scale based on the first scale and the second scale, the method further includes:

[0091] When a bending operation on the insertion portion is detected, the warning scale is updated to obtain an updated warning scale.

[0092] In some embodiments, during actual operation, the doctor will control the bending portion of the endoscope to bend according to needs to rotate the direction of the head end to achieve directional observation. At this time, the insertion portion will increase in bending degree as the doctor manually operates, which means that the insertion portion will continue to enter the human body, but the position of the endoscope has not changed, resulting in the position of the endoscope corresponding to the warning scale being inconsistent with the target position. For example, when the endoscope is retracted, if the doctor bends the insertion portion, the actual distance between the head end and the target position will be reduced, making it impossible for the warning scale to accurately warn the position of the endoscope. Therefore, when the bending operation of the insertion portion is detected, a more accurate warning scale is obtained by updating the above-mentioned warning scale.

[0093] Correspondingly, when it is identified that the insertion portion reaches the warning scale, issuing a warning includes:

[0094] When it is recognized that the insertion portion has reached the updated warning scale, a warning is issued.

[0095] In some embodiments, it is assumed that an external camera is used to identify the scale of the insertion portion exposed outside the body of the object to be tested. When it is identified that the insertion portion reaches the updated warning scale, a warning is issued, thereby improving the accuracy of the anti-collision warning.

[0096] In the embodiment of the present application, the updating of the warning scale includes:

[0097] The bending degree of the insertion portion caused by the bending operation is obtained, and the warning scale is increased according to the bending degree; wherein the increase in the warning scale is positively correlated with the bending degree.

[0098] In some embodiments, different degrees of bending operations on the insertion part will cause different degrees of bending of the insertion part, and the warning scale can be bent and compensated according to the bending deformation amount corresponding to the bending degree. For example, different Xs can be set according to the bending deformation amounts corresponding to different bending degrees, where X is positively correlated with the above-mentioned bending degree, so that the warning scale is updated to the warning scale + X to compensate for the impact of the bending operation on the warning scale on the insertion part and improve the effectiveness of the anti-collision warning.

[0099] In another optional embodiment of the present application, a sensor can also be used to identify the scale of the insertion part that is exposed outside the body of the object to be measured and is closest to the object to be measured. Since foreign matter in the digestive tract may adhere to the insertion part, the external camera cannot accurately identify the scale on the insertion part. By using a sensor, such as an optical sensor, the scale of the insertion part entering the human body can be identified according to changes in light and darkness, thereby more accurately identifying the scale on the insertion part, thereby improving the applicability of identifying the scale on the insertion part.

[0100] In an optional embodiment of the present application, the above method further includes:

[0101] During the process of withdrawing the endoscope, the position of the tip of the insertion portion is identified according to the digestive tract site identified by the endoscope;

[0102] When the position of the head end does not meet the preset requirement, navigation is performed on the position of the head end based on the digestive tract portion until the head end is separated from the digestive tract portion.

[0103] In some embodiments, the position of the endoscope tip may not be standardized. For example, if the tip is too close to the intestinal cavity on one side, it will increase the difficulty of turning and retreating during the endoscope withdrawal process, which may easily cause the endoscope to collide with the intestinal cavity. Therefore, the position of the tip of the insertion portion is identified according to the digestive tract site identified by the endoscope. When the position of the tip does not meet the preset requirements, the position of the tip is navigated based on the specific digestive tract site (such as the intestinal cavity), thereby standardizing the position of the endoscope tip and reducing collisions. The preset requirements include: the position of the tip is far away from the intestinal cavity or the position of the tip is in the middle of the intestinal cavity, etc.

[0104] Optionally, the navigation for the position of the head end portion based on the digestive tract position includes:

[0105] In the case where the endoscope cannot identify the complete edge of the digestive tract, navigating the tip portion away from the digestive tract;

[0106] In the case where the endoscope can identify the complete edge of the digestive tract part, the center position of the complete edge is determined based on the complete edge of the digestive tract part. When the distance between the center position and the center of the image identified by the endoscope does not satisfy a preset distance difference, the head end is navigated until the distance between the center position and the center of the image satisfies the distance difference.

[0107] In some embodiments, assuming that the digestive tract is the intestine, since the endoscope is inspected in the intestine, the position of the endoscope head can be determined by the integrity of the inner edge of the intestinal cavity for any digestive tract part. When the endoscope cannot identify the complete edge of the digestive tract part, it means that the endoscope is too close to the intestinal cavity on one side, and the endoscope needs to be navigated to keep the endoscope away from the intestinal cavity of the digestive tract part. For example, if an obvious depression is found in the elliptical edge of the intestinal cavity in the digestive tract, it means that the head end of the endoscope is too close to the depressed side, and the endoscope is navigated away from the depressed side, that is, the endoscope is moved in the direction away from the depressed side; when the endoscope can recognize the complete edge of the digestive tract, if the intestinal cavity recognized by the endoscope is not in the center of the picture recognized by the endoscope, it will also affect the doctor's operation, and thus easily cause a collision. Therefore, the center position of the complete edge is calculated according to the image frame containing the complete edge recognized by the head end, and when the distance between the above center position and the center of the picture recognized by the endoscope does not meet the preset distance difference, the head end is navigated close to the center of the picture until the distance between the center position and the center of the picture meets the distance difference. For example, when the endoscope recognizes the complete elliptical edge in the intestinal cavity, the center position of the ellipse is calculated. If the distance between the center position and the center of the picture recognized by the endoscope is greater than the preset distance difference, the endoscope is navigated so that the center position moves in the direction close to the center of the picture until the distance between the center position and the center of the picture is less than or equal to the preset distance difference.

[0108] It should be noted that the above-mentioned navigation for the endoscope can also be set to navigate the endoscope to a preset area, which is a target area preset in the image recognized by the endoscope. The navigation method is similar to the above-mentioned navigation to the center of the image, and will not be repeated here. The above-mentioned navigation for the position of the head end is similar to the above-mentioned warning, and can include the appearance of a directional navigation arrow on the display device, and voice reminders and / or text reminders at the same time. Figure 6 As shown, it is a schematic diagram of navigating the position of the head end, in which the endoscope is prompted to move toward a preset area in the picture in the form of arrow navigation.

[0109] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0110] Corresponding to the anti-collision method described in the above embodiment, Figure 7 A schematic structural diagram of an anti-collision device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0111] Reference Figure 7 The device may be an anti-collision device 71 , and the anti-collision device 71 may include an endoscope 711 , a target recognition module 712 , an early warning calculation module 713 and a reminder module 714 .

[0112] Reference Figure 7 , the anti-collision device 71 comprises:

[0113] The endoscope 711 includes an insertion portion with a scale;

[0114] The target recognition module 712 is used to determine the target position in the digestive tract according to the digestive tract part recognized by the endoscope during the endoscope advancement process; and to recognize that the insertion portion reaches the warning scale during the endoscope withdrawal process;

[0115] The warning calculation module 713 is used to determine the warning scale according to the first scale of the insertion portion corresponding to the target position during the endoscope advancement process;

[0116] The reminder module 714 is used to issue an early warning when the insertion portion reaches the early warning position.

[0117] In some other embodiments, the anti-collision device 71 further includes a scope entry warning module, which is used in the process of endoscope entry and includes:

[0118] Calculating the actual distance between the tip of the endoscope and the digestive tract site;

[0119] When the actual distance is less than a preset threshold, an early warning is issued.

[0120] In some other embodiments, the anti-collision device 71 further includes a first warning scale calculation module, and the first warning scale calculation module is used when the digestive tract part is a first type of part, including:

[0121] During the endoscope advancement process, when the endoscope recognizes the target position for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale;

[0122] When the endoscope reaches the target position, the insertion portion is exposed outside the body of the object to be measured and the scale closest to the object to be measured is determined as the first scale;

[0123] The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position comprises:

[0124] The warning scale is determined based on the first scale and the second scale.

[0125] In some other embodiments, the anti-collision device 71 further includes a second warning scale calculation module, and the second warning scale calculation module is used when the digestive tract part is the second type of part, including:

[0126] During the endoscope advancement process, when the endoscope recognizes the digestive tract site for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale; when the endoscope recognizes the digestive tract site for the last time, the target position is determined based on the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured and the second scale, and the first scale corresponding to the target position is determined;

[0127] The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position comprises:

[0128] The warning scale is determined based on the first scale and the second scale.

[0129] In some other embodiments, the anti-collision device 71 further includes a warning scale updating module, and the warning scale updating module is used for determining the warning scale based on the first scale and the second scale, and includes:

[0130] When a bending operation on the insertion portion is detected, the warning scale is updated to obtain the updated warning scale.

[0131] Correspondingly, the reminder module 714 performs an early warning through the following steps, including:

[0132] When it is recognized that the insertion portion has reached the updated warning scale, a warning is issued.

[0133] In some embodiments, the early warning scale updating module updates the early warning scale through the following steps, including:

[0134] The bending degree of the insertion portion caused by the bending operation is obtained, and the warning scale is increased according to the bending degree; wherein the increase in the warning scale is positively correlated with the bending degree.

[0135] In some other embodiments, the anti-collision device 71 further includes a navigation module, and the navigation module includes:

[0136] During the process of withdrawing the endoscope, the position of the tip of the insertion portion is identified according to the digestive tract site identified by the endoscope;

[0137] When the position of the head end does not meet the preset requirement, navigation is performed on the position of the head end based on the digestive tract site until the head end is separated from the digestive tract site.

[0138] Optionally, the navigation module performs navigation for the position of the head end based on the digestive tract site through the following steps, including:

[0139] In the case where the endoscope cannot identify the complete edge of the digestive tract, navigating the tip portion away from the digestive tract;

[0140] In the case where the endoscope can identify the complete edge of the digestive tract part, the center position of the complete edge is determined based on the complete edge of the digestive tract part; when the distance between the center position and the center of the image identified by the endoscope does not satisfy a preset distance difference, the head end is navigated until the distance between the center position and the center of the image satisfies the distance difference.

[0141] It should be noted that the information interaction, execution process, etc. between the devices / units are based on the same concept as the method embodiments of the present application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0142] Figure 8 This is a schematic diagram of the structure of an image processing device provided by an embodiment of the present application. Figure 8 As shown, the image processing device 8 of this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown in the figure), a memory 81, and a computer program 82 stored in the memory 81 and executable on the at least one processor 80. When the processor 80 executes the computer program 82, the steps in any of the method embodiments are implemented.

[0143] The image processing device 8 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The image processing device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of the image processing device 8 and does not constitute a limitation of the image processing device 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the image processing device may also include an input sending device, a network access device, a bus, etc.

[0144] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0145] In some embodiments, the memory 81 may be an internal storage unit of the image processing device 8, such as a hard disk or memory of the image processing device 8. The memory 81 may also be an external storage device of the image processing device 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the image processing device 8. Further, the memory 81 may also include both an internal storage unit and an external storage device of the image processing device 8. The memory 81 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 81 may also be used to temporarily store data that has been sent or is to be sent.

[0146] The present application also provides an endoscope system for executing the anti-collision method described in the embodiment. The endoscope system provided by the present application is described below. The endoscope system described below and the anti-collision method described above can be referenced to each other.

[0147] Reference Fig. 9FIG. 1 is a functional architecture diagram of an endoscope system provided by an embodiment of the present invention. In this embodiment, the endoscope system 9 includes an image processing device 90 , an endoscope 91 , a light source host 92 and a display device 93 .

[0148] The image processing device 90 is used to identify the digestive tract part according to the endoscope 91 and determine the target position in the digestive tract part during the process of the endoscope 91 being advanced; determine the warning scale according to the first scale of the insertion part of the endoscope 91 corresponding to the target position; and issue a warning when it is identified that the insertion part of the endoscope 91 reaches the warning scale during the process of the endoscope 91 being withdrawn;

[0149] The endoscope 91 includes an insertion portion with a scale, and is used to examine the digestive tract of the subject to be examined;

[0150] The light source host 92 is used to connect to the endoscope 91 and provide light to the head end of the endoscope 91;

[0151] The display device 93 is used to display the digestive tract part identified by the endoscope 91, and to issue an early warning when the image processing device 90 identifies that the insertion portion has reached the early warning scale.

[0152] Among them, it is assumed that the scale of the insertion part exposed in the object to be tested is identified by using an external camera. During the process of the endoscope 91 inspecting the digestive tract of the object to be tested, the light source host 92 provides light to the head end of the endoscope 91, and the image processing device 90 determines the digestive tract part through the image frame taken by the lens of the head end of the endoscope, and at the same time determines the scale on the insertion part according to the image frame of the insertion part exposed in the object to be tested taken by the external camera. During the process of the endoscope 91 advancing, the image processing device 90 determines the target position in the digestive tract part according to the digestive tract part identified by the endoscope 91, the image processing device 90 determines the first scale of the insertion part corresponding to the target position, and determines the warning scale according to the first scale; during the process of the endoscope 91 retracting, when the image processing device 90 identifies that the insertion part has reached the warning scale, a warning is issued through the display device 93.

[0153] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the functional units and modules is used as an example. In practical applications, the function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0154] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the method embodiments when executing the computer program.

[0155] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the various method embodiments can be implemented.

[0156] An embodiment of the present application provides a computer program product. When the computer program product is run on an image processing device, the image processing device can implement the steps in the various method embodiments when the computer program product is executed.

[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each method embodiment when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / image processing device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, RandomAccess Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0158] In the embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0159] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0160] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A collision prevention method, characterized in that: Applied to an endoscope, the insertion portion of the endoscope is provided with a scale; In the process of using the endoscope to examine the digestive tract of the object to be examined, the method includes: During the endoscope insertion process, a target position in the digestive tract is determined according to the digestive tract position identified by the endoscope; and a warning scale is determined according to the first scale of the insertion portion corresponding to the target position; During the endoscope retraction process, when it is recognized that the insertion portion has reached the warning scale, a warning is issued.

2. The anti-collision method according to claim 1, characterized in that: When the digestive tract part is a first type of part, the method further comprises: During the endoscope advancement process, when the endoscope recognizes the target position for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale; When the endoscope reaches the target position, the insertion portion is exposed outside the body of the object to be measured and the scale closest to the object to be measured is determined as the first scale; The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position comprises: The warning scale is determined based on the first scale and the second scale.

3. The anti-collision method according to claim 1, characterized in that: When the digestive tract part is the second type of part, the method further comprises: During the endoscope advancement process, when the endoscope recognizes the digestive tract site for the first time, the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured is determined as the second scale; when the endoscope recognizes the digestive tract site for the last time, the target position is determined based on the scale at which the insertion portion is exposed outside the body of the object to be measured and is closest to the object to be measured and the second scale, and the first scale corresponding to the target position is determined; The step of determining the warning scale according to the first scale of the insertion portion corresponding to the target position comprises: The warning scale is determined based on the first scale and the second scale.

4. The anti-collision method according to claim 2 or 3, characterized in that: The difference between the warning scale and the third scale is smaller than a preset length difference, and the third scale is a scale value based on the first scale and symmetrical to the second scale.

5. The anti-collision method according to claim 2 or 3, characterized in that: After determining the warning scale based on the first scale and the second scale, the method further includes: When a bending operation on the insertion portion is detected, updating the warning scale to obtain the updated warning scale; When it is identified that the insertion portion reaches the warning scale, issuing a warning comprises: When it is recognized that the insertion portion has reached the updated warning scale, a warning is issued.

6. The anti-collision method according to claim 5, characterized in that: The updating of the warning scale includes: The bending degree of the insertion portion caused by the bending operation is obtained, and the warning scale is increased according to the bending degree; wherein the increase in the warning scale is positively correlated with the bending degree.

7. The anti-collision method according to claim 2, characterized in that: The method further comprises: During the process of withdrawing the endoscope, the position of the tip of the insertion portion is identified according to the digestive tract site identified by the endoscope; When the position of the head end does not meet the preset requirement, navigation is performed on the position of the head end based on the digestive tract site until the head end is separated from the digestive tract site.

8. The anti-collision method according to claim 7, characterized in that: The navigating the position of the head end based on the digestive tract position includes: In the case where the endoscope cannot identify the complete edge of the digestive tract, navigating the tip portion away from the digestive tract; In the case where the endoscope can identify the complete edge of the digestive tract part, the center position of the complete edge is determined based on the complete edge of the digestive tract part; when the distance between the center position and the center of the image identified by the endoscope does not satisfy a preset distance difference, the head end is navigated until the distance between the center position and the center of the image satisfies the distance difference.

9. An anti-collision device, characterized in that: The anti-collision device includes an endoscope, a target recognition module, an early warning calculation module and a reminder module, including: The endoscope includes an insertion portion with a scale; The target recognition module is used to determine the target position in the digestive tract according to the digestive tract part recognized by the endoscope during the endoscope advancement process; and to recognize that the insertion portion reaches the warning scale during the endoscope withdrawal process; The warning calculation module is used to determine the warning scale according to the first scale of the insertion part corresponding to the target position during the endoscope advancement process; The reminder module is used to issue an early warning when the insertion portion reaches the early warning position.

10. An image processing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. An endoscope system, characterized in that: include: An image processing device as claimed in claim 10, an endoscope as claimed in any one of claims 1 to 8, a light source host and a display device.

Images