Endoscopic image processing method and system

Abstract

The present invention provides an endoscopic image processing method and system. The method obtains an endoscopic image of a liver with a tumor, determines target pixel points in the endoscopic image according to a pixel range value of fluorescence detection of ICG; combines all target pixel points in the endoscopic image to obtain a first area; determines whether there is a reflective area within a preset range of the first area; if it is determined that there is a reflective area within the preset range of the first area, generates a second area according to the position of the reflective area; determines the boundary of the second area, and generates a first target boundary at the periphery of the second area according to a first preset distance and a boundary of the second area; processes the first target boundary to obtain a smooth second target boundary, and a user can clearly define the tumor boundary according to the second target boundary to provide a reference for subsequent surgery.

Description

Technical Field

[0001] The present invention belongs to the technical field of endoscopic image processing, and in particular relates to an endoscopic image processing method and system. Background Art

[0002] Endoscopic images are of great significance in clinical medicine. Through endoscopic images, doctors can intuitively observe the conditions of internal tissues and organs of the human body, thereby accurately diagnosing diseases and formulating appropriate treatment plans.

[0003] Currently, in the diagnosis of liver tumors, indocyanine green molecular fluorescence imaging technology is used to determine the tumor boundary. Indocyanine green (ICG) is a near-infrared fluorescent dye. Protein-bound ICG can be excited by external light in the wavelength range of 750nm to 810nm, and emits near-infrared light with a wavelength of about 840nm.

[0004] Specifically, after preoperative injection of ICG, the tumor boundary can be observed under ICG molecular fluorescence detection during surgery, and then liver resection is performed. However, due to imaging accuracy and light influence, the tumor boundary is unclear. In addition, different doctors have different tumor boundaries based on their own experience. For the same liver, the range of liver resection may be different. Summary of the invention

[0005] Based on this, an embodiment of the present invention provides an endoscopic image processing method and system, which aims to assist doctors in determining tumor boundaries and achieving the best treatment effect.

[0006] A first aspect of an embodiment of the present invention provides an endoscopic image processing method, which is applied to a liver injected with ICG and performing fluorescence detection, and the method comprises:

[0007] Acquire an endoscopic image of a liver having a tumor, and determine a target pixel point in the endoscopic image according to a pixel range value of fluorescence detection of ICG;

[0008] Combining all target pixel points in the endoscope image to obtain a first area;

[0009] Determine whether there is a reflective area within a preset range of the first area;

[0010] If it is determined that there is a reflective area within the preset range of the first area, generating a second area according to the position of the reflective area;

[0011] Determine a boundary of the second area, and generate a first target boundary at the periphery of the second area according to the first preset distance and the boundary of the second area;

[0012] The first target boundary is processed to obtain a smooth second target boundary.

[0013] Furthermore, if it is determined that there is a reflective area within the preset range of the first area, the step of generating the second area according to the position of the reflective area includes:

[0014] Determining whether the reflective area is located in the first area;

[0015] If it is determined that the reflective area is located within the first area, the corresponding reflective area is subjected to a first assimilation process to generate the second area;

[0016] If it is determined that the reflective area is not located in the first area, determining whether the reflective area is adjacent to the first area;

[0017] If it is determined that the reflective area is adjacent to the first area, a second assimilation process is performed on the corresponding reflective area to generate the second area.

[0018] Furthermore, if it is determined that the reflective area is located in the first area, the corresponding reflective area is subjected to a first assimilation process to generate the second area, the step includes:

[0019] Obtain pixel values ​​of pixel points in a preset area outside the reflective area, and calculate the difference between the maximum pixel value and the minimum pixel value;

[0020] Determining whether the difference is within a preset difference range;

[0021] If it is determined that the difference is within the preset difference range, then calculating the first pixel value average of the pixel points in the preset area outside the reflective area, and assigning values ​​to the pixel points in the reflective area according to the first pixel value average to generate the second area;

[0022] If it is determined that the difference is not within the preset difference range, a plurality of first sub-regions are determined in a preset area outside the reflective area according to a clustering algorithm, and the average of the second pixel values ​​of the pixel points in each first sub-region is calculated;

[0023] Calculating the pixel area of ​​each first sub-region respectively, and determining the pixel area ratio of each first sub-region;

[0024] Determine the common boundaries between each first sub-region and the reflective region respectively, and divide the reflective region into corresponding second sub-regions according to the common boundaries and the corresponding pixel area ratios;

[0025] The second pixel value mean is assigned to the pixel points of the corresponding second sub-region to generate the second region.

[0026] Furthermore, the step of obtaining pixel values ​​of pixel points in a preset area outside the reflective area and calculating the difference between the maximum pixel value and the minimum pixel value includes:

[0027] Determine the geometric center of the reflective area boundary according to the reflective area boundary, and determine a circular area including the reflective area according to the geometric center and a preset radius;

[0028] Determining whether the circular area interferes with the non-tumor area;

[0029] If it is determined that the circular area interferes with the non-tumor area, the circular area is controlled to move in a direction away from the interference until the circular area does not interfere with the non-tumor area, and the target circular area is determined to obtain a preset area outside the reflective area.

[0030] Furthermore, in the step of respectively determining the common boundary between each first sub-region and the reflective region, and dividing the reflective region into corresponding second sub-regions according to the common boundary and the corresponding pixel area ratio, a first boundary adjacent to the common boundary in each first sub-region is determined, and the reflective region is divided into corresponding second sub-regions according to the common boundary, the corresponding pixel area ratio and the trend of the first boundary.

[0031] Furthermore, if it is determined that the reflective area is adjacent to the first area, the corresponding reflective area is subjected to a second assimilation process to generate the second area, the step includes:

[0032] Obtain line segments on the first area on both sides of the reflective area, analyze the trends of the two line segments respectively, and control the two line segments to extend toward the reflective area according to the trends. During the extension process, periodically copy the corresponding line segments until they intersect, and finally divide the reflective area into two parts;

[0033] The pixel points of the portion of the reflective area close to the first area are assigned values, wherein the assigned pixel values ​​are the third pixel value averages of the pixel points in the first area that are separated from the reflective area by a second preset distance.

[0034] Furthermore, the step of processing the first target boundary to obtain a smooth second target boundary includes:

[0035] Segmenting the first target boundary to obtain a plurality of sub-boundaries;

[0036] Perform linear fitting on the pixel points on each sub-boundary to obtain each target line segment;

[0037] The target line segments are combined to obtain the second target boundary.

[0038] A second aspect of an embodiment of the present invention provides an endoscopic image processing system, which is used to implement the endoscopic image processing method provided in the first aspect, and the system includes:

[0039] An acquisition module, used to acquire an endoscopic image of a liver having a tumor, and determine a target pixel point in the endoscopic image according to a pixel range value of fluorescence detection of ICG;

[0040] A combining module, used for combining all target pixel points in the endoscopic image to obtain a first area;

[0041] A judging module, used for judging whether there is a reflective area within a preset range of the first area;

[0042] A first generating module, configured to generate a second area according to a position of the reflective area if it is determined that there is a reflective area within a preset range of the first area;

[0043] a second generating module, configured to determine a boundary of the second area, and generate a first target boundary at the periphery of the second area according to the first preset distance and the boundary of the second area;

[0044] The smoothing processing module is used to process the first target boundary to obtain a smooth second target boundary.

[0045] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the endoscopic image processing method provided in the first aspect.

[0046] A fourth aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the endoscopic image processing method provided in the first aspect is implemented.

[0047] An endoscopic image processing method and system are provided in an embodiment of the present invention. The method obtains an endoscopic image of a liver with a tumor, determines the target pixel points in the endoscopic image according to the pixel range value of ICG fluorescence detection; combines all the target pixel points in the endoscopic image to obtain a first area; determines whether there is a reflective area within a preset range of the first area; if it is determined that there is a reflective area within the preset range of the first area, generates a second area according to the position of the reflective area; determines the boundary of the second area, and generates a first target boundary around the second area according to the first preset distance and the boundary of the second area; processes the first target boundary to obtain a smooth second target boundary, and the user can clearly define the tumor boundary based on the second target boundary to provide a reference for subsequent surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flowchart of an endoscope image processing method according to the first embodiment of the present invention;

[0049] Figure 2 A structural block diagram of an endoscope image processing system provided in Embodiment 2 of the present invention;

[0050] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0051] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0052] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0054] Embodiment 1

[0055] According to an embodiment of the present invention, an endoscopic image processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0056] In the first embodiment, an endoscopic image processing method is provided, which can be used in an electronic device, such as a computer. It should be noted that the method is applied to a liver injected with ICG and a scenario of fluorescence detection.

[0057] See also Figure 1 , Figure 1The flowchart of an implementation of an endoscopic image processing method provided in the first embodiment of the present invention is shown, which specifically includes steps S01 to S06.

[0058] Step S01, acquiring an endoscopic image of a liver with a tumor, and determining a target pixel point in the endoscopic image according to a pixel range value of fluorescence detection of ICG.

[0059] Specifically, the target pixel point in the endoscopic image is determined by the pixel range value of the ICG fluorescence detection. It can be understood that when the pixel value of a pixel point in the endoscopic image falls within the pixel range value of the ICG fluorescence detection, the pixel point is determined as the target pixel point, wherein the pixel range value of the ICG fluorescence detection is the RGB color value range of green, including various shades of green.

[0060] Step S02: combine all target pixel points in the endoscopic image to obtain a first area.

[0061] It can be understood that the first area is also the tumor area.

[0062] Step S03, determining whether there is a reflective area within a preset range of the first area, and if so, executing step S04.

[0063] Specifically, due to the presence of a light source, when light is irradiated on an organ, luminescence may occur. The reflective area is usually a bright spot area, that is, the color displayed in the area is white. Based on the range of white pixel values, it is determined whether there is a reflective area, and the preset range refers to the area within the first area or adjacent to the first area. In some other embodiments of the present invention, the preset range may also be the range of the entire endoscopic image.

[0064] In step S04, a second area is generated according to the position of the reflective area.

[0065] It should be noted that it is determined whether the reflective area is located in the first area;

[0066] If it is determined that the reflective area is within the first area, the corresponding reflective area is subjected to a first assimilation process to generate a second area. Specifically, pixel values ​​of pixel points within a preset area outside the reflective area are obtained, and a difference between a maximum pixel value and a minimum pixel value is calculated.

[0067] Determine whether the difference is within a preset difference range;

[0068] If the difference is within the preset difference range, it means that the color around the reflective area is relatively balanced, then the first pixel value average of the pixel points in the preset area outside the reflective area is calculated, and the pixel points in the reflective area are assigned values ​​according to the first pixel value average to generate a second area;

[0069] If it is determined that the difference is not within the preset difference range, a plurality of first sub-regions are determined in the preset area outside the reflective area according to a clustering algorithm, and the second pixel value mean of the pixel points in each first sub-region is calculated, wherein the clustering algorithm may adopt a K-Means algorithm;

[0070] Calculating the pixel area of ​​each first sub-region respectively, and determining the pixel area ratio of each first sub-region;

[0071] Determine the common boundary between each first sub-region and the reflective region respectively, and divide the reflective region into corresponding second sub-regions according to the common boundary and the corresponding pixel area ratio, wherein a first boundary adjacent to the common boundary in each first sub-region is determined, and the reflective region is divided into corresponding second sub-regions according to the common boundary, the corresponding pixel area ratio and the trend of the first boundary. Specifically, the trend of the first boundary can be obtained by linear fitting, which can be fitted as a straight line or a curve;

[0072] Assigning the second pixel value mean to the corresponding pixel points of the second sub-region to generate the second region, that is, completing the assimilation of the reflective region, and after image processing, no reflective image will appear;

[0073] If it is determined that the reflective area is not located in the first area, determining whether the reflective area is adjacent to the first area;

[0074] If it is determined that the reflective area is adjacent to the first area, the corresponding reflective area is subjected to a second assimilation process to generate a second area. Specifically, line segments of predicted lengths on the first area on both sides of the reflective area are obtained, and the trends of the two line segments are analyzed respectively. The trends of the two line segments can be obtained by linear fitting, which can be fitted as a straight line or a curve. According to the trends, the two line segments are controlled to extend toward the reflective area, that is, to extend in opposite directions. During the extension process, the corresponding line segments are periodically copied until they intersect, and finally the reflective area is divided into two parts.

[0075] The pixel points of the portion of the reflective area close to the first area are assigned values, wherein the assigned pixel values ​​are the third pixel value averages of the pixel points in the first area that are separated from the reflective area by a second preset distance.

[0076] In addition, the step of obtaining the pixel values ​​of the pixel points in the preset area outside the reflective area and calculating the difference between the maximum pixel value and the minimum pixel value includes:

[0077] Determine the geometric center of the reflective area boundary according to the reflective area boundary, and determine a circular area including the reflective area according to the geometric center and a preset radius;

[0078] Determine whether the circular area interferes with the non-tumor area, that is, determine whether the circular area falls entirely within the reflective area;

[0079] If it is determined that the circular area interferes with the non-tumor area, the circular area is controlled to move in a direction away from the interference until the circular area does not interfere with the non-tumor area, and the target circular area is determined to obtain a preset area outside the reflective area.

[0080] Step S05 , determining a boundary of the second area, and generating a first target boundary at the periphery of the second area according to the first preset distance and the boundary of the second area.

[0081] In this embodiment, the boundary of the second area is expanded outward according to the first preset distance to generate a first target boundary. It should be noted that since the boundary of the second area is relatively rough, the first target boundary obtained by outward expansion is also rough. Therefore, smoothing processing is required to clarify the tumor boundary.

[0082] Step S06: Process the first target boundary to obtain a smooth second target boundary.

[0083] Specifically, the first target boundary is segmented to obtain a plurality of sub-boundaries;

[0084] Perform linear fitting on the pixel points on each sub-boundary to obtain each target line segment;

[0085] The target line segments are combined to obtain the second target boundary. It should be noted that a basic segment number is first determined, and the first target boundary is segmented to obtain a preset number of sub-boundaries. Then, linear fitting is performed on the pixel points on each sub-boundary. In this embodiment, the target line segments after linear fitting are straight line segments rather than curve segments to facilitate surgical operations. Finally, the target line segments are combined to obtain the second target boundary.

[0086] Specifically, the second target boundary should at least meet the requirement of not intersecting with the boundary of the second area. If there is an intersection, the line segment intersecting with the boundary of the second area is obtained, and the corresponding part of the first target boundary is determined based on the line segment. The part is segmented again, and the segmented pixel points are linearly fitted. The boundary obtained after combination is compared with the boundary of the second area to determine whether they intersect. If they intersect, the above operation is repeated until they do not intersect.

[0087] In summary, the endoscopic image processing method in the above-mentioned embodiment of the present invention obtains an endoscopic image of a liver with a tumor, and determines the target pixel points in the endoscopic image according to the pixel range value of the fluorescence detection of ICG; combines all the target pixel points in the endoscopic image to obtain a first area; determines whether there is a reflective area within a preset range of the first area; if it is determined that there is a reflective area within the preset range of the first area, generates a second area according to the position of the reflective area; determines the boundary of the second area, and generates a first target boundary around the second area according to the first preset distance and the boundary of the second area; processes the first target boundary to obtain a smooth second target boundary, and the user can clarify the tumor boundary according to the second target boundary to provide a reference for subsequent surgery.

[0088] Embodiment 2

[0089] See also Figure 2 , Figure 2 1 is a block diagram of an endoscopic image processing system provided in Embodiment 2 of the present invention. The endoscopic image processing system 200 is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0090] Specifically, in the scenario of applying ICG to the liver and performing fluorescence detection, the endoscopic image processing system 200 includes: an acquisition module 21, a combination module 22, a judgment module 23, a first generation module 24, a second generation module 25 and a smoothing processing module 26, wherein:

[0091] An acquisition module 21 is used to acquire an endoscopic image of a liver having a tumor, and determine a target pixel point in the endoscopic image according to a pixel range value of fluorescence detection of ICG;

[0092] A combining module 22, used for combining all target pixel points in the endoscopic image to obtain a first area;

[0093] A judging module 23, used for judging whether there is a reflective area within a preset range of the first area;

[0094] A first generating module 24 is configured to generate a second area according to the position of the reflective area if it is determined that there is a reflective area within the preset range of the first area;

[0095] A second generating module 25, configured to determine a boundary of the second area, and generate a first target boundary at the periphery of the second area according to the first preset distance and the boundary of the second area;

[0096] The smoothing processing module 26 is used to process the first target boundary to obtain a smooth second target boundary.

[0097] Further, in some optional embodiments of the present invention, the first generating module 24 includes:

[0098] A first judging unit, used for judging whether the reflective area is located in the first area;

[0099] A first processing unit, configured to perform a first assimilation process on the corresponding reflective area to generate the second area if it is determined that the reflective area is located within the first area;

[0100] A second judgment unit, configured to judge whether the reflective area is adjacent to the first area if it is judged that the reflective area is not located in the first area;

[0101] The second processing unit is used to perform a second assimilation process on the corresponding reflective area to generate the second area if it is determined that the reflective area is adjacent to the first area.

[0102] Further, in some optional embodiments of the present invention, the first processing unit includes:

[0103] A first calculation subunit is used to obtain pixel values ​​of pixel points in a preset area outside the reflective area, and calculate the difference between the maximum pixel value and the minimum pixel value;

[0104] A first judging subunit, used to judge whether the difference is within a preset difference range;

[0105] A first assignment subunit is used for calculating a first pixel value mean of pixel points in a preset area outside the reflective area if it is determined that the difference is within a preset difference range, and assigning pixel points in the reflective area according to the first pixel value mean to generate the second area;

[0106] A second calculation subunit is used for determining a plurality of first sub-regions in a preset area outside the reflective area according to a clustering algorithm if it is determined that the difference is not within a preset difference range, and calculating a second pixel value average of pixel points in each first sub-region;

[0107] A third calculation subunit, used to calculate the pixel area of ​​each first sub-region respectively, and determine the pixel area ratio of each first sub-region;

[0108] a dividing sub-unit, used to respectively determine a common boundary between each first sub-region and the reflective region, and divide the reflective region into corresponding second sub-regions according to the common boundary and the corresponding pixel area ratio, wherein a first boundary adjacent to the common boundary in each first sub-region is determined, and the reflective region is divided into corresponding second sub-regions according to the common boundary, the corresponding pixel area ratio and the trend of the first boundary;

[0109] The second assignment subunit is used to assign the second pixel value mean to the pixel points of the corresponding second sub-area to generate the second area.

[0110] Furthermore, in some optional embodiments of the present invention, the first processing unit further includes:

[0111] A first determining subunit is used to determine a geometric center of the reflective area boundary according to the reflective area boundary, and determine a circular area including the reflective area according to the geometric center and a preset radius;

[0112] A second judging subunit is used to judge whether the circular area interferes with the non-tumor area;

[0113] The second determination subunit is used to control the circular area to move in a direction away from the interference if it is determined that the circular area interferes with the non-tumor area, until the circular area does not interfere with the non-tumor area, and determine the target circular area to obtain a preset area outside the reflective area.

[0114] Furthermore, in some optional embodiments of the present invention, the second processing unit further includes:

[0115] An extension subunit, used for obtaining line segments on the first area on both sides of the reflective area, analyzing the trends of the two line segments respectively, and controlling the two line segments to extend toward the reflective area according to the trends, and during the extension process, periodically copying the corresponding line segments until they intersect, and finally dividing the reflective area into two parts;

[0116] The third assignment subunit is used to assign values ​​to the pixel points in the reflective area close to the first area, wherein the assigned pixel value is an average of the third pixel values ​​of the pixel points in the first area that are separated from the reflective area by a second preset distance.

[0117] Further, in some optional embodiments of the present invention, the smoothing processing module 26 includes:

[0118] A segmentation unit, used for segmenting the first target boundary into a plurality of sub-boundaries;

[0119] A fitting unit, used to perform linear fitting on the pixel points on each sub-boundary to obtain each target line segment;

[0120] A combining unit is used to combine the target line segments to obtain the second target boundary.

[0121] Embodiment 3

[0122] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor, wherein the processor 10 implements the endoscopic image processing method as described above when executing the computer program 30.

[0123] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0124] Among them, the memory 20 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 20 may be an internal storage unit of an electronic device in some embodiments, such as a hard disk of the electronic device. The memory 20 may also be an external storage device of an electronic device in other embodiments, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Further, the memory 20 may also include both an internal storage unit and an external storage device of the electronic device. The memory 20 may be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is to be output.

[0125] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than those shown in the figure, or combine certain components, or arrange the components differently.

[0126] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the endoscopic image processing method as described above is implemented.

[0127] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0128] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0129] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0130] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0131] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. An endoscopic image processing method, characterized in that: Applied to a liver injected with ICG and performing fluorescence detection, the method comprises: Acquire an endoscopic image of a liver having a tumor, and determine a target pixel point in the endoscopic image according to a pixel range value of fluorescence detection of ICG; Combining all target pixel points in the endoscope image to obtain a first area; Determine whether there is a reflective area within a preset range of the first area; If it is determined that there is a reflective area within the preset range of the first area, generating a second area according to the position of the reflective area; Determine a boundary of the second area, and generate a first target boundary at the periphery of the second area according to the first preset distance and the boundary of the second area; Processing the first target boundary to obtain a smooth second target boundary; If it is determined that there is a reflective area within the preset range of the first area, the step of generating the second area according to the position of the reflective area includes: Determining whether the reflective area is located in the first area; If it is determined that the reflective area is located within the first area, the corresponding reflective area is subjected to a first assimilation process to generate the second area; If it is determined that the reflective area is not located in the first area, determining whether the reflective area is adjacent to the first area; If it is determined that the reflective area is adjacent to the first area, the corresponding reflective area is subjected to a second assimilation process to generate the second area; If it is determined that the reflective area is located within the first area, the step of performing a first assimilation process on the corresponding reflective area to generate the second area includes: Obtain pixel values ​​of pixel points in a preset area outside the reflective area, and calculate the difference between the maximum pixel value and the minimum pixel value; Determining whether the difference is within a preset difference range; If it is determined that the difference is within the preset difference range, then calculating the first pixel value average of the pixel points in the preset area outside the reflective area, and assigning values ​​to the pixel points in the reflective area according to the first pixel value average to generate the second area; If it is determined that the difference is not within the preset difference range, a plurality of first sub-regions are determined in a preset area outside the reflective area according to a clustering algorithm, and the average of the second pixel values ​​of the pixel points in each first sub-region is calculated; Calculating the pixel area of ​​each first sub-region respectively, and determining the pixel area ratio of each first sub-region; Determine the common boundaries between each first sub-region and the reflective region respectively, and divide the reflective region into corresponding second sub-regions according to the common boundaries and the corresponding pixel area ratios; The second pixel value mean is assigned to the pixel points of the corresponding second sub-region to generate the second region.

2. The endoscopic image processing method according to claim 1, characterized in that: The step of obtaining the pixel values ​​of the pixel points in the preset area outside the reflective area and calculating the difference between the maximum pixel value and the minimum pixel value includes: Determine the geometric center of the reflective area boundary according to the reflective area boundary, and determine a circular area including the reflective area according to the geometric center and a preset radius; Determining whether the circular area interferes with the non-tumor area; If it is determined that the circular area interferes with the non-tumor area, the circular area is controlled to move in a direction away from the interference until the circular area does not interfere with the non-tumor area, and the target circular area is determined to obtain a preset area outside the reflective area.

3. The endoscopic image processing method according to claim 2, characterized in that: In the steps of respectively determining the common boundary between each first sub-region and the reflective region, and dividing the reflective region into corresponding second sub-regions according to the common boundary and the corresponding pixel area ratio, a first boundary adjacent to the common boundary in each first sub-region is determined, and the reflective region is divided into corresponding second sub-regions according to the common boundary, the corresponding pixel area ratio and the trend of the first boundary.

4. The endoscopic image processing method according to claim 3, characterized in that: If it is determined that the reflective area is adjacent to the first area, the corresponding reflective area is subjected to a second assimilation process to generate the second area, the step comprising: Obtain line segments on the first area on both sides of the reflective area, analyze the trends of the two line segments respectively, and control the two line segments to extend toward the reflective area according to the trends. During the extension process, periodically copy the corresponding line segments until they intersect, and finally divide the reflective area into two parts; The pixel points of the portion of the reflective area close to the first area are assigned values, wherein the assigned pixel values ​​are the third pixel value averages of the pixel points in the first area that are separated from the reflective area by a second preset distance.

5. The endoscopic image processing method according to claim 4, characterized in that: The step of processing the first target boundary to obtain a smooth second target boundary comprises: Segmenting the first target boundary to obtain a plurality of sub-boundaries; Perform linear fitting on the pixel points on each sub-boundary to obtain each target line segment; The target line segments are combined to obtain the second target boundary.

6. An endoscope image processing system, characterized in that: Used to implement the endoscopic image processing method according to any one of claims 1 to 5, the system comprises: An acquisition module, used to acquire an endoscopic image of a liver having a tumor, and determine a target pixel point in the endoscopic image according to a pixel range value of fluorescence detection of ICG; A combining module, used for combining all target pixel points in the endoscopic image to obtain a first area; A judging module, used for judging whether there is a reflective area within a preset range of the first area; A first generating module, configured to generate a second area according to a position of the reflective area if it is determined that there is a reflective area within a preset range of the first area; a second generating module, configured to determine a boundary of the second area, and generate a first target boundary at the periphery of the second area according to the first preset distance and the boundary of the second area; The smoothing processing module is used to process the first target boundary to obtain a smooth second target boundary.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the endoscopic image processing method as described in any one of claims 1 to 5 is implemented.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for processing endoscopic images according to any one of claims 1 to 5 is implemented.

Images