Method and device for detecting signs

Abstract

The present invention discloses a method and device for sign detection, and relates to the field of computer technology. A specific implementation of the method includes: determining whether the region of interest has a ring sign according to the lesion data of the region of interest; determining whether the region of interest has a ring sign in the regional image by an edge detection operator; and determining whether the region of interest has a ring sign according to the lesion data of the region of interest and the regional image of the region of interest has a ring sign, determining whether the region of interest has a capsule. This implementation can automatically identify whether the region of interest has a capsule sign, which is convenient for doctors to check and diagnose.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for detecting signs. Background Art

[0002] When diagnosing a disease, it is usually necessary to first identify multiple signs of the lesion, and then diagnose whether the patient has a certain disease based on the multiple signs. However, when doctors check the signs of the lesion, they may miss some signs, which affects the diagnosis results. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and device for sign detection, which can automatically identify whether a capsule sign appears in a region of interest, so as to facilitate doctors' inspection and diagnosis.

[0004] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for detecting a sign is provided, comprising:

[0005] determining, according to the lesion data of the region of interest, whether the region of interest has a ring sign;

[0006] Determining whether there is a ring sign in the regional image of the region of interest by an edge detection operator;

[0007] When it is determined according to the lesion data of the region of interest that the region of interest has a ring sign and the regional image of the region of interest has a ring sign, it is determined that a capsule appears in the region of interest.

[0008] Optionally, determining whether there is a ring sign in the regional image of the region of interest by using an edge detection operator includes:

[0009] An edge detection operator is used to perform edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked, and it is determined whether the set of points to be tracked forms a ring; if so, it is determined that there is a ring sign in the regional image; otherwise, the convolution kernel is increased, and then the steps of performing edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked and determining whether the set of points to be tracked forms a ring are performed, and this cycle is repeated until a preset loop termination condition is reached.

[0010] Optionally, before determining that the regional image has a ring sign, the method further includes: determining that the number of cycles of edge detection on the regional image is greater than or equal to a preset lower limit of the number;

[0011] When the number of cycles of edge detection on the regional image is less than the lower limit of the number, the convolution kernel is increased, and then edge detection is performed on the regional image based on the adjusted convolution kernel.

[0012] Optionally, the loop termination condition includes at least one of the following: the number of loops is equal to an upper limit, and the size of the convolution kernel reaches a threshold size.

[0013] Optionally, determining whether the set of points to be tracked forms a ring includes:

[0014] Select a pixel point from the set of points to be tracked as a starting point, set the gradient value of the starting point to a first value, select a neighboring point whose gradient value is not equal to the first value from the neighboring point set of the starting point according to the convolution kernel as a center point, and set the gradient value of the center point to a second value;

[0015] Determine whether there is a pixel point with a gradient value of the first value in the neighborhood point set of the center point; if so, the tracking ends, and the points to be tracked are integrated into a ring; otherwise, determine whether there is a pixel point with a gradient value not equal to the second value in the neighborhood point set of the center point, if so, select a neighborhood point with a gradient value not equal to the first value as the new center point, otherwise the tracking ends, and the points to be tracked do not form a ring; the tracking is repeated in this way until the preset tracking termination condition is reached;

[0016] The tracking termination condition includes: there are pixels with gradient values ​​of the first value in the neighborhood point set of the center point, or there are no pixels with gradient values ​​other than the second value in the neighborhood point set of the center point.

[0017] Optionally, selecting a neighborhood point whose gradient value is not equal to the first value includes: selecting a neighborhood point whose gradient value is not equal to the first value according to a preset gradient direction or according to a direction with a maximum gradient amplitude.

[0018] Optionally, determining whether the set of points to be tracked forms a ring includes: extracting a gradient image from the regional image based on the convolution kernel, extracting pixel points that meet preset screening conditions from the gradient image, and obtaining the set of points to be tracked.

[0019] According to a second aspect of an embodiment of the present invention, there is provided a device for detecting a sign, comprising:

[0020] A data analysis module, which determines whether the region of interest has a ring sign according to the lesion data of the region of interest;

[0021] An image analysis module determines whether there is a ring sign in the regional image of the region of interest by using an edge detection operator;

[0022] The sign judgment module determines that a capsule appears in the region of interest when it is determined according to the lesion data of the region of interest that the region of interest has a ring sign and the region image of the region of interest has a ring sign.

[0023] Optionally, the image analysis module determines whether there is a ring sign in the regional image of the region of interest by using an edge detection operator, including:

[0024] An edge detection operator is used to perform edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked, and it is determined whether the set of points to be tracked forms a ring; if so, it is determined that there is a ring sign in the regional image; otherwise, the convolution kernel is increased, and then the steps of performing edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked and determining whether the set of points to be tracked forms a ring are performed, and this cycle is repeated until a preset loop termination condition is reached.

[0025] Optionally, before the image analysis module determines that there is a ring sign in the regional image, the method further includes: determining that the number of cycles of edge detection on the regional image is greater than or equal to a preset lower limit of the number of cycles;

[0026] When the number of cycles of edge detection on the regional image is less than the lower limit of the number, the convolution kernel is increased, and then edge detection is performed on the regional image based on the adjusted convolution kernel.

[0027] Optionally, the loop termination condition includes at least one of the following: the number of loops is equal to an upper limit, and the size of the convolution kernel reaches a threshold size.

[0028] Optionally, determining whether the set of points to be tracked forms a ring includes:

[0029] Select a pixel point from the set of points to be tracked as a starting point, set the gradient value of the starting point to a first value, select a neighboring point whose gradient value is not equal to the first value from the neighboring point set of the starting point according to the convolution kernel as a center point, and set the gradient value of the center point to a second value;

[0030] Determine whether there is a pixel point with a gradient value of the first value in the neighborhood point set of the center point; if so, the tracking ends, and the points to be tracked are integrated into a ring; otherwise, determine whether there is a pixel point with a gradient value not equal to the second value in the neighborhood point set of the center point, if so, select a neighborhood point with a gradient value not equal to the first value as the new center point, otherwise the tracking ends, and the points to be tracked do not form a ring; the tracking is repeated in this way until the preset tracking termination condition is reached;

[0031] The tracking termination condition includes: there are pixels with gradient values ​​of the first value in the neighborhood point set of the center point, or there are no pixels with gradient values ​​other than the second value in the neighborhood point set of the center point.

[0032] Optionally, the image analysis module selects neighborhood points whose gradient values ​​are not equal to the first value, including: selecting neighborhood points whose gradient values ​​are not equal to the first value according to a preset gradient direction or according to a direction with a maximum gradient amplitude.

[0033] Optionally, the image analysis module determines whether the set of points to be tracked forms a ring, including: extracting a gradient image from the regional image based on the convolution kernel, extracting pixel points that meet preset screening conditions from the gradient image, and obtaining the set of points to be tracked.

[0034] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for detecting a sign, comprising:

[0035] one or more processors;

[0036] a storage device for storing one or more programs,

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0038] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0039] One embodiment of the above invention has the following advantages or beneficial effects: by determining whether the region of interest has a ring sign based on the lesion data and the regional image of the region of interest respectively, and determining that a capsule exists in the region of interest when both determine that the region of interest has a ring sign, it is possible to automatically identify whether a capsule exists in the region of interest, which is convenient for doctors to check and diagnose.

[0040] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0042] Figure 1 is a schematic diagram of the main process of the method for sign detection according to an embodiment of the present invention;

[0043] Figure 2 is a schematic diagram of a main process of determining whether a regional image of a region of interest has a ring sign by using an edge detection operator in some embodiments of the present invention;

[0044] Figure 3 is a schematic diagram of a main process of determining whether a regional image of a region of interest has a ring sign by using an edge detection operator in some other embodiments of the present invention;

[0045] Figure 4It is a schematic diagram of the main process of determining whether the set of points to be tracked forms a ring in an optional embodiment of the present invention;

[0046] Figure 5 is a schematic diagram of a main process of detecting whether a regional image of a region of interest has a ring sign in an optional embodiment of the present invention;

[0047] Figure 6 is a schematic diagram of a region image of a region of interest having a ring sign in an optional embodiment of the present invention;

[0048] Figure 7 is a schematic diagram of main modules of a device for detecting signs according to an embodiment of the present invention;

[0049] Figure 8 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0050] Fig. 9 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0052] According to one aspect of an embodiment of the present invention, a method for detecting signs is provided.

[0053] Figure 1 FIG. 1 is a schematic diagram of the main process of the method for detecting signs in an embodiment of the present invention. Figure 1 As shown, the methods of sign detection include:

[0054] Step S101, determining whether the region of interest has a ring sign according to the lesion data of the region of interest; if so, jump to step S102, otherwise jump to step S104;

[0055] Step S102, determining whether there is a ring sign in the regional image of the region of interest by an edge detection operator; if so, jump to step S103, otherwise jump to step S104;

[0056] Step S103, determining whether a capsule appears in the region of interest;

[0057] Step S104: determine that no capsule appears in the region of interest.

[0058] Lesion data refers to data related to lesions, including but not limited to: lesion data of the portal venous phase, delayed phase, and transitional phase. The regional image of the region of interest refers to an image of the region of interest, such as an image of the corresponding position of the lesion in the MR (magnetic resonance imaging) sequence. Possessing a ring sign means that each pixel point corresponding to the lesion position forms a ring. The embodiment of the present invention determines whether the region of interest has a ring sign based on the lesion data on the one hand, and determines whether the ring sign exists based on the regional image of the region of interest on the other hand. Determining whether the capsule sign appears in the region of interest based on the judgment results of the two dimensions can improve the accuracy of sign recognition.

[0059] It should be noted that although Figure 1 In the illustrated embodiment, judgment is first made based on the lesion data of the region of interest and then based on the regional image of the region of interest. However, those skilled in the art may also adjust the execution order of the two judgment steps according to actual conditions, such as executing them simultaneously, or first making a judgment based on the regional image of the region of interest and then making a judgment based on the lesion data of the region of interest.

[0060] Figure 2 FIG. 1 is a schematic diagram of the main process of determining whether the regional image of the region of interest has a ring sign by using an edge detection operator in some embodiments of the present invention. Figure 2 As shown, determining whether there is a ring sign in the regional image of the region of interest by using an edge detection operator includes: step S201, using an edge detection operator, performing edge detection on the regional image based on a convolution kernel to obtain a set of points to be tracked; step S202, judging whether the set of points to be tracked forms a ring, if so, jumping to step S205, otherwise jumping to step S203; step S203, judging whether a preset loop termination condition is met, if so, jumping to step S206, otherwise jumping to step S204; step S204, increasing the convolution kernel, and then jumping to step S201; step S205, determining whether there is a ring sign in the regional image; step S206, determining that there is no ring sign in the regional image.

[0061] Significant changes in image attributes usually reflect important events and changes in attributes, including discontinuities in depth, surface orientation, changes in material properties, and changes in scene lighting. The edge detection operator is used to determine whether there is a ring sign in the regional image of the region of interest, which greatly reduces the amount of data and improves data processing efficiency. In an embodiment of the present invention, the edge detection operator can be a first-order edge detection operator, such as Roberts Cross operator, Prewitt operator, Sobel operator, Kirsch operator, compass operator, etc., or a second-order edge detection operator, such as Marr-Hildreth, Canny operator, Laplacian operator, etc. The enlarged convolution kernel mentioned in this embodiment refers to enlarging the size of the convolution kernel, such as enlarging the convolution kernel of a 3×3 template to a convolution kernel of a 5×5 template. When performing edge detection, using a smaller convolution kernel first can improve the accuracy of ring sign detection. When a smaller convolution kernel fails to detect the ring sign, increasing the convolution kernel can avoid the situation where the ring sign is missed due to the convolution kernel being set too small, thereby improving the accuracy of the detection result.

[0062] The loop termination condition can be selectively set according to the actual situation, for example, the number of loops is equal to the upper limit, or the size of the convolution kernel reaches the threshold size. When the number of loops is large or the convolution kernel is large, if the ring sign cannot be detected, it is very likely that there is no ring sign in the regional image. By setting the loop termination condition, it is possible to avoid loop judgment when there is no ring sign in the regional image, reduce the consumption of computing resources, and improve detection efficiency.

[0063] Optionally, before determining that the regional image has a ring sign, the method further includes: determining that the number of cycles of edge detection on the regional image is greater than or equal to a preset lower limit. If the number of cycles of edge detection on the regional image is less than the lower limit, increasing the convolution kernel, and then performing edge detection on the regional image based on the adjusted convolution kernel. Figure 3 As shown, the main process of determining whether there is a ring sign in the regional image of the region of interest by using an edge detection operator includes:

[0064] Step S301, using an edge detection operator, and performing edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked; step S302, judging whether the set of points to be tracked forms a ring, if so, jumping to step S304, otherwise jumping to step S303; step S303, judging whether a preset loop termination condition is met, if so, jumping to step S306, otherwise jumping to step S305; step S304, judging whether the number of cycles for edge detection on the regional image is greater than or equal to a preset lower limit, if so, jumping to step S307, otherwise jumping to step S305; step S305, increasing the convolution kernel, and then jumping to step S301; step S306, determining that there is no ring sign in the regional image; step S307, determining that there is a ring sign in the regional image.

[0065] When the range of the region of interest is large, if the convolution kernel is small, the region without ring signs may be judged as having ring signs. The embodiment of the present invention can avoid misjudgment caused by a convolution kernel that is too small by setting a lower limit of the number of cycles for edge detection of the regional image, thereby improving the accuracy of the detection result. The specific value of the lower limit of the number of times can be selectively set according to actual conditions.

[0066] Optionally, determining whether the set of points to be tracked forms a ring includes:

[0067] A pixel point is selected as a starting point based on the set of points to be tracked, a gradient value of the starting point is set to a first value, a neighboring point whose gradient value is not equal to the first value is selected from the neighboring point set of the center point according to the convolution kernel as the center point, and the gradient value of the center point is set to a second value;

[0068] Determine whether there are pixels with a gradient value of the first value in the neighborhood point set of the center point; if so, the tracking ends and the points to be tracked form a ring; otherwise, determine whether there are pixels with a gradient value not equal to the second value in the neighborhood point set of the center point, if so, select a neighborhood point with a gradient value not equal to the first value as the new center point, otherwise the tracking ends and the point set to be tracked does not form a ring; the tracking is repeated in this way until the preset tracking termination condition is reached. The neighborhood point set of the center point refers to the set formed by the neighborhood points of the center point in the point set to be tracked. The tracking termination conditions include: there are pixels with a gradient value of the first value in the domain point set of the center point, or there are no pixels with a gradient value not equal to the second value in the neighborhood point set of the center point.

[0069] Figure 4 FIG. 1 is a schematic diagram of the main process of determining whether the set of points to be tracked forms a ring in an optional embodiment of the present invention. Figure 4 ,The main process of judging whether the set of points to be tracked forms a ring includes:

[0070] Step S401, selecting a pixel point from the set of points to be tracked as a starting point, and setting the gradient value of the starting point to a first value;

[0071] Step S402, selecting a neighborhood point whose gradient value is not equal to the first value from the neighborhood point set of the center point according to the convolution kernel as the center point, and setting the gradient value of the center point to a second value;

[0072] Step S403, determine whether there is a pixel point with a gradient value of the first value in the neighborhood point set of the center point; if so, jump to step S406, otherwise jump to step S404;

[0073] Step S404, determine whether there is a pixel point whose gradient value is not the second value in the neighborhood point set of the center point, if so, jump to step S405, otherwise jump to step S407;

[0074] Step S405, select a neighborhood point whose gradient value is not the first value as a new center point, and then jump to step S402;

[0075] Step S406, the tracking is completed, and the tracking points are integrated into a ring;

[0076] Step S407, the tracking ends, and the set of points to be tracked does not form a loop. The tracking termination conditions include: there are pixels with a gradient value of the first value in the neighborhood point set of the center point, or there are no pixels with a gradient value not equal to the second value in the neighborhood point set of the center point.

[0077] The first value and the second value are not equal, and their values ​​can be selectively set, for example, to 1 and 2, respectively. In this embodiment, by assigning values ​​to the pixel points obtained by each tracking, subsequent analysis and judgment are facilitated, and by assigning different values ​​to the starting point and each pixel point obtained by subsequent tracking, it is convenient to quickly determine whether the starting point is tracked, thereby improving detection efficiency.

[0078] For any pixel point, when selecting a neighborhood point from a neighborhood point set as a new center point corresponding to the neighborhood points in multiple directions under a specific convolution kernel, a neighborhood point can be randomly selected or a neighborhood point can be selected according to a set direction. Optionally, selecting a neighborhood point whose gradient value is not equal to the first value includes: selecting a neighborhood point whose gradient value is not equal to the first value according to a preset gradient direction or in a direction with the largest gradient amplitude. As the number of tracking times increases, more and more neighborhood points are assigned, so the neighborhood points contained in the domain point set of the center point are getting fewer and fewer. Therefore, in the actual application process, a new center point can be selected from the neighborhood point set according to a preset gradient direction. When the neighborhood point of the preset gradient direction in the neighborhood point set corresponding to the center point has been assigned in a certain tracking, a neighborhood point can be randomly selected from the neighborhood points that have not been assigned as the new center point. Selecting a neighborhood point whose gradient value is not equal to the first value in the direction with the largest gradient amplitude can improve the tracking speed and thus improve the detection efficiency.

[0079] Optionally, edge detection is performed on the regional image based on a convolution kernel to obtain a set of points to be tracked, including: extracting a gradient image from the regional image based on the convolution kernel, extracting pixel points that meet preset screening conditions from the gradient image, and obtaining the set of points to be tracked. The screening conditions can be selectively set according to actual conditions, for example, the gradient value is greater than the gradient amplitude threshold, the brightness is greater than the brightness threshold, etc. By setting the screening conditions, this embodiment can screen out pixel points that have less impact on the tracking results, improve the tracking speed, and thus improve the detection efficiency.

[0080] Figure 5 FIG. 2 is a schematic diagram of the main process of detecting whether a regional image of a region of interest has a ring sign in an optional embodiment of the present invention. Figure 5 As shown in FIG. 1 , the main process of detecting whether there is a ring sign in the regional image of the region of interest includes:

[0081] Step S501, lesion detection, determining the region of interest, and calculating the average brightness of the region of interest as a brightness threshold;

[0082] Step S502, expanding the region of interest. The purpose of this step is to expand the range of the image region to be analyzed to avoid misjudgment due to the appearance of ring signs at the edge of the region of interest;

[0083] Step S503, extracting a gradient image from the expanded region of interest, this step uses a 3×3 template tracking operator;

[0084] Step S504, extracting pixel points whose gradient values ​​are greater than the gradient amplitude threshold or whose brightness is greater than the brightness threshold from the gradient image to obtain a set of points to be tracked;

[0085] Step S505, selecting a pixel point from the set of points to be tracked as a starting point, and setting the gradient value of the starting point to 2;

[0086] Step S506, taking the starting point as the center point, using the tracking operator of the 3×3 template, selecting a neighboring point whose gradient value is not equal to 2 from the neighboring point set of the center point as a new center point, and setting the gradient value of the center point to 1;

[0087] Step S507, using the tracking operator of the 3×3 template, determine whether there is a pixel point with a gradient value of 2 in the neighborhood point set of the center point; if so, jump to step S510, otherwise jump to step S508;

[0088] Step S508, determine whether there is a pixel point with a gradient value of 1 in the neighborhood point set of the new center point, if so, jump to step S509, otherwise jump to step S511;

[0089] Step S509, select a neighboring point whose gradient value is not 1 from the neighboring point set of the center point as a new center point, set the gradient value of the new center point to 1, and then jump to step S507;

[0090] Step S510: Tracking is completed and the region of interest has a ring sign;

[0091] Step S511: Tracking is completed and the region of interest has no ring sign.

[0092] When the lower limit of the number of cycles for edge detection of the regional image is 1, the result of whether the regional image has a ring sign can be obtained according to steps S501-S511. When the lower limit of the number of cycles for edge detection of the regional image is greater than 1, before determining in step S510 that the region of interest has a ring sign, it is necessary to ensure that the number of cycles is greater than or equal to the lower limit, otherwise steps S503-S511 are repeatedly executed until the number of cycles is greater than or equal to the lower limit. At this time, whether the regional image has a ring sign is determined according to the result of the last cycle. Figure 6 A schematic diagram showing the presence of a ring sign in a regional image of a region of interest.

[0093] The present invention can automatically identify whether the region of interest has a capsule by determining whether the region of interest has a ring sign based on the lesion data and the regional image of the region of interest, and determining whether the region of interest has a capsule when both determine that the region of interest has a ring sign, so as to facilitate doctors' viewing and diagnosis.

[0094] According to a second aspect of an embodiment of the present invention, a device for implementing the above method is provided.

[0095] Figure 7FIG. 1 is a schematic diagram showing the main modules of the device for detecting signs in an embodiment of the present invention. Figure 7 As shown, the device 700 for detecting signs includes:

[0096] The data analysis module 701 determines whether the region of interest has a ring sign according to the lesion data of the region of interest;

[0097] An image analysis module 702 determines whether there is a ring sign in the regional image of the region of interest by using an edge detection operator;

[0098] The sign judgment module 703 determines that a capsule exists in the region of interest when it is determined according to the lesion data of the region of interest that the region of interest has a ring sign and the regional image of the region of interest has a ring sign.

[0099] Optionally, the image analysis module determines whether there is a ring sign in the regional image of the region of interest by using an edge detection operator, including:

[0100] An edge detection operator is used to perform edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked, and it is determined whether the set of points to be tracked forms a ring; if so, it is determined that there is a ring sign in the regional image; otherwise, the convolution kernel is increased, and then the steps of performing edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked and determining whether the set of points to be tracked forms a ring are performed, and this cycle is repeated until a preset loop termination condition is reached.

[0101] Optionally, before the image analysis module determines that there is a ring sign in the regional image, the method further includes: determining that the number of cycles of edge detection on the regional image is greater than or equal to a preset lower limit of the number of cycles;

[0102] When the number of cycles of edge detection on the regional image is less than the lower limit of the number, the convolution kernel is increased, and then edge detection is performed on the regional image based on the adjusted convolution kernel.

[0103] Optionally, the loop termination condition includes at least one of the following: the number of loops is equal to an upper limit, and the size of the convolution kernel reaches a threshold size.

[0104] Optionally, the image analysis module determines whether the set of points to be tracked forms a ring, including:

[0105] Select a pixel point from the set of points to be tracked as a starting point, set the gradient value of the starting point to a first value, select a neighboring point whose gradient value is not equal to the first value from the neighboring point set of the starting point according to the convolution kernel as a center point, and set the gradient value of the center point to a second value;

[0106] Determine whether there is a pixel point with a gradient value of the first value in the neighborhood point set of the center point; if so, the tracking ends, and the points to be tracked are integrated into a ring; otherwise, determine whether there is a pixel point with a gradient value not equal to the second value in the neighborhood point set of the center point, if so, select a neighborhood point with a gradient value not equal to the first value as the new center point, otherwise the tracking ends, and the points to be tracked do not form a ring; the tracking is repeated in this way until the preset tracking termination condition is reached;

[0107] The tracking termination condition includes: there are pixels with gradient values ​​of the first value in the neighborhood point set of the center point, or there are no pixels with gradient values ​​other than the second value in the neighborhood point set of the center point.

[0108] Optionally, the image analysis module selects neighborhood points whose gradient values ​​are not equal to the first value, including: selecting neighborhood points whose gradient values ​​are not equal to the first value according to a preset gradient direction or according to a direction with a maximum gradient amplitude.

[0109] Optionally, the image analysis module performs edge detection on the area image based on a convolution kernel to obtain a set of points to be tracked, including: extracting a gradient image from the area image based on the convolution kernel, extracting pixel points that meet preset screening conditions from the gradient image, and obtaining the set of points to be tracked.

[0110] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for detecting a sign, comprising:

[0111] one or more processors;

[0112] a storage device for storing one or more programs,

[0113] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0114] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0115] Figure 8 An exemplary system architecture 800 is shown to which the method for sign detection or the apparatus for sign detection according to the embodiments of the present invention may be applied.

[0116] like Figure 8 As shown, system architecture 800 may include terminal devices 801, 802, 803, a network 804, and a server 805. Network 804 is used to provide a medium for communication links between terminal devices 801, 802, 803 and server 805. Network 804 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0117] Users can use terminal devices 801, 802, and 803 to interact with server 805 through network 804 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 801, 802, and 803, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0118] The terminal devices 801 , 802 , and 803 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0119] The server 805 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 801, 802, and 803. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0120] It should be noted that the method for detecting signs provided in the embodiment of the present invention is generally executed by the server 805 , and accordingly, the device for detecting signs is generally disposed in the server 805 .

[0121] It should be understood that Figure 8 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0122] Reference below Fig. 9 , which shows a schematic diagram of the structure of a computer system 900 of a terminal device suitable for implementing an embodiment of the present invention. Fig. 9 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0123] like Fig. 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the system 900 are also stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0124] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

[0125] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processing unit (CPU) 901, the above-mentioned functions defined in the system of the present invention are executed.

[0126] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0127] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0128] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor, for example, it may be described as: a processor including: a data analysis module, an image analysis module and a sign judgment module. The names of these modules do not constitute a limitation on the modules themselves in some cases, for example, the data analysis module may also be described as "a module for determining whether there is a ring sign in the regional image of the region of interest through an edge detection operator".

[0129] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: determining whether the region of interest has a ring sign according to the lesion data of the region of interest; determining whether the region image of the region of interest has a ring sign by an edge detection operator; and determining whether the region of interest has a capsule when it is determined that the region of interest has a ring sign according to the lesion data of the region of interest and the region image of the region of interest has a ring sign.

[0130] According to the technical solution of the embodiment of the present invention, by determining whether the region of interest has a ring sign based on the lesion data and the regional image of the region of interest respectively, and determining whether a capsule appears in the region of interest when both determine that the region of interest has a ring sign, it is possible to automatically identify whether the region of interest has a capsule, which is convenient for doctors to check and diagnose.

[0131] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting signs, characterized in that: include: determining, according to the lesion data of the region of interest, whether the region of interest has a ring sign; Determining whether there is a ring sign in the regional image of the region of interest by an edge detection operator includes: using an edge detection operator, performing edge detection on the regional image based on a convolution kernel to obtain a set of points to be tracked, and judging whether the set of points to be tracked forms a ring; if so, determining that there is a ring sign in the regional image; otherwise, increasing the convolution kernel, and then performing the steps of performing edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked, and judging whether the set of points to be tracked forms a ring, and repeating the above steps until a preset loop termination condition is reached; When it is determined according to the lesion data of the region of interest that the region of interest has a ring sign and the regional image of the region of interest has a ring sign, it is determined that a capsule appears in the region of interest.

2. The method according to claim 1, characterized in that Before determining that the regional image has a ring sign, the method further includes: determining that the number of cycles of edge detection on the regional image is greater than or equal to a preset lower limit of the number of cycles; When the number of cycles of edge detection on the regional image is less than the lower limit of the number, the convolution kernel is increased, and then edge detection is performed on the regional image based on the adjusted convolution kernel.

3. The method according to claim 1, characterized in that The loop termination condition includes at least one of the following: the number of loops is equal to the upper limit of the number, and the size of the convolution kernel reaches a threshold size.

4. The method according to any one of claims 1 to 3, characterized in that: Determining whether the set of points to be tracked forms a ring includes: Select a pixel point from the set of points to be tracked as a starting point, set the gradient value of the starting point to a first value, select a neighboring point whose gradient value is not equal to the first value from the neighboring point set of the starting point according to the convolution kernel as a center point, and set the gradient value of the center point to a second value; Determine whether there is a pixel point with a gradient value of the first value in the neighborhood point set of the center point; if so, the tracking ends, and the points to be tracked are integrated into a ring; otherwise, determine whether there is a pixel point with a gradient value not equal to the second value in the neighborhood point set of the center point, and if so, select a neighborhood point with a gradient value not equal to the first value as the new center point, otherwise the tracking ends, and the points to be tracked do not form a ring; the tracking is repeated in this way until the preset tracking termination condition is reached; The tracking termination condition includes: there are pixels with gradient values ​​of the first value in the neighborhood point set of the center point, or there are no pixels with gradient values ​​other than the second value in the neighborhood point set of the center point.

5. The method according to claim 4, characterized in that Selecting a neighborhood point whose gradient value is not equal to the first value includes: selecting a neighborhood point whose gradient value is not equal to the first value according to a preset gradient direction or according to a direction with a maximum gradient amplitude.

6. The method according to claim 4, characterized in that Performing edge detection on the regional image based on a convolution kernel to obtain a set of points to be tracked, including: extracting a gradient image from the regional image based on the convolution kernel, extracting pixel points that meet a preset screening condition from the gradient image, and obtaining the set of points to be tracked.

7. A device for detecting signs, characterized in that: include: A data analysis module, which determines whether the region of interest has a ring sign according to the lesion data of the region of interest; The image analysis module determines whether there is a ring sign in the regional image of the region of interest by using an edge detection operator, including: using an edge detection operator, performing edge detection on the regional image based on a convolution kernel to obtain a set of points to be tracked, and judging whether the set of points to be tracked forms a ring; if so, determining that there is a ring sign in the regional image; otherwise, increasing the convolution kernel, and then performing the steps of performing edge detection on the regional image based on the convolution kernel to obtain a set of points to be tracked, and judging whether the set of points to be tracked forms a ring, and repeating the above steps until a preset loop termination condition is reached; The sign judgment module determines that a capsule appears in the region of interest when it is determined according to the lesion data of the region of interest that the region of interest has a ring sign and the region image of the region of interest has a ring sign.

8. An electronic device for detecting signs, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images