CN113781477A - Calculus image identification method, device and equipment based on artificial intelligence - Google Patents
Calculus image identification method, device and equipment based on artificial intelligence Download PDFInfo
- Publication number
- CN113781477A CN113781477A CN202111270917.XA CN202111270917A CN113781477A CN 113781477 A CN113781477 A CN 113781477A CN 202111270917 A CN202111270917 A CN 202111270917A CN 113781477 A CN113781477 A CN 113781477A
- Authority
- CN
- China
- Prior art keywords
- calculus
- image
- stone
- contour
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 35
- 239000004575 stone Substances 0.000 claims abstract description 115
- 238000001514 detection method Methods 0.000 claims abstract description 64
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 12
- 230000001629 suppression Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 210000004705 lumbosacral region Anatomy 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 238000002604 ultrasonography Methods 0.000 description 3
- 210000001015 abdomen Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 208000001130 gallstones Diseases 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 208000000913 Kidney Calculi Diseases 0.000 description 1
- 201000001883 cholelithiasis Diseases 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Geometry (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application belongs to the field of artificial intelligence and provides a calculus image identification method, a calculus image identification device and calculus image identification equipment based on artificial intelligence. The method comprises the following steps: acquiring an image to be identified including a calculus by a sensing device; carrying out target detection on the image to be recognized including the calculus, and determining the position of the calculus included in the image to be recognized; identifying a contour of the stone from the determined location of the stone; determining the size of the calculus in the calculus image according to the contour of the calculus; and generating an identification report corresponding to the calculus image according to the sizes of the multiple calculus at different acquisition angles. The method can automatically identify and detect the position and the outline of the calculus in the image and automatically record the sizes of the calculus at different acquisition angles, so that the operation difficulty of detection personnel can be greatly reduced, and the calculus detection efficiency is improved.
Description
Technical Field
The application belongs to the field of artificial intelligence, and particularly relates to a calculus image identification method, device and equipment based on artificial intelligence.
Background
When people perform physical examination in a hospital, B-mode ultrasound examination items are often included. For example, the B-ultrasonic can be used for examining the calculi of people, including kidney calculi, gallstones, etc. Through the examination of the items, people can more clearly know the physical condition of the people or make corresponding prevention and treatment measures according to the examination result, so that the further deterioration of the illness state is avoided.
In performing a B-ultrasound examination, typically an examiner, such as a doctor, presses on the examination site using a B-ultrasound sensor, then marks the bonds on the displayed image, including parameters such as the maximum diameter of the mark, and then saves the marked image. Because the calculus is in a three-dimensional shape, inspectors often need to collect images at different angles, and the collected images are marked for multiple times and then the required images are stored, so that the whole operation process is troublesome, and the B-ultrasonic inspection efficiency is low.
Disclosure of Invention
In view of this, the embodiment of the present application provides a calculus image identification method, device and apparatus based on artificial intelligence, so as to solve the problems in the prior art that when calculus detection is performed, the operation process is troublesome and the detection efficiency is low.
A first aspect of an embodiment of the present application provides a calculus image recognition method based on artificial intelligence, where the method includes:
acquiring an image to be identified including a calculus by a sensing device;
carrying out target detection on the image to be recognized including the calculus, and determining the position of the calculus included in the image to be recognized;
identifying a contour of the stone from the determined location of the stone;
determining the size of the calculus in the calculus image according to the contour of the calculus;
and generating an identification report corresponding to the calculus image according to the sizes of the multiple calculus at different acquisition angles.
With reference to the first aspect, in a first possible implementation manner of the first aspect, performing target detection on the image to be recognized including the stone, and determining a position of the stone included in the image to be recognized includes:
dividing the image to be recognized into a first preset number of grids;
inputting the divided grids into a boundary box generation network which is trained in advance, and acquiring a second preset number of boundary boxes and the probability of the boundary boxes belonging to calculus;
and determining the boundary frame of the calculus in the image to be identified through non-maximum suppression according to the probability that the boundary frame belongs to the calculus, and determining the position of the calculus according to the identified boundary frame.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, identifying a contour of the stone according to the determined position of the stone includes:
carrying out binarization processing on the image in the determined boundary frame of the calculus to obtain a binarized image of the image in the boundary frame;
and searching contour points in the boundary box according to the binary image, and drawing according to the contour points to generate a calculus contour.
With reference to the first possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, after determining a stone size in the stone image according to the contour of the stone, the method further includes:
and removing the determined boundary box of the calculus, and displaying the contour of the calculus image at the current acquisition angle and the size of the contour.
With reference to the first aspect, in a fourth possible implementation manner of the first aspect, determining a size of a stone in the stone image according to the contour of the stone includes:
determining the central position of the calculus according to the contour of the calculus;
and determining a plurality of diameters of the calculus image under the current acquisition angle according to the central position of the calculus, and determining the maximum diameter and the minimum diameter of the calculus.
With reference to the first aspect, in a fifth possible implementation manner of the first aspect, the method further includes:
acquiring the outline of the calculus acquired by the sensing equipment at different acquisition angles;
and generating a three-dimensional image of the calculus according to the contour of the calculus acquired from different acquisition angles.
With reference to the first aspect, in a sixth possible implementation manner of the first aspect, acquiring the profiles of the stones acquired by the sensing device at different acquisition angles includes:
when the sensing equipment acquires a first contour of the calculus, acquiring a first angle for acquiring the first contour through an angle sensor;
determining the angle which is not subjected to the contour acquisition currently according to the preset angle which is required to be subjected to the contour acquisition;
and generating prompt information of the part which is not subjected to contour acquisition according to the preset corresponding relation between the angle and the acquisition part, and acquiring the contour of the calculus when the part which is required to be subjected to contour acquisition is detected.
A second aspect of an embodiment of the present application provides an artificial intelligence-based stone image recognition apparatus, the apparatus including:
the calculus image acquisition unit is used for acquiring an image to be identified comprising calculus through sensing equipment;
the calculus position determining unit is used for carrying out target detection on the image to be identified comprising the calculus and determining the position of the calculus in the image to be identified;
a stone contour identification unit for identifying the contour of the stone according to the determined position of the stone;
the calculus size identification unit is used for determining the size of the calculus in the calculus image according to the contour of the calculus;
and the identification report generating unit is used for generating an identification report corresponding to the calculus image according to the sizes of the multiple calculus at different acquisition angles.
A third aspect of embodiments of the present application provides an artificial intelligence based stone image recognition apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any one of the first aspect when executing the computer program.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, performs the steps of the method according to any one of the first aspect.
Compared with the prior art, the embodiment of the application has the advantages that: the method and the device have the advantages that the target detection is carried out on the acquired calculus image, the position of the calculus in the image is determined, the outline of the calculus is identified according to the detected position of the calculus, the size of the calculus is obtained, and the identification report is generated based on the sizes of the calculus acquired at different acquisition angles. The method can automatically identify and detect the position and the outline of the calculus in the image and automatically record the sizes of the calculus at different acquisition angles, so that the operation difficulty of detection personnel can be greatly reduced, and the calculus detection efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a schematic flow chart illustrating an implementation of an artificial intelligence-based calculus image recognition method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating an implementation of a method for determining a location of a stone according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a bounding box identified by an image to be identified provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of an artificial intelligence based calculus image recognition apparatus according to an embodiment of the present application;
fig. 5 is a schematic diagram of an artificial intelligence based calculus image recognition apparatus provided by an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.
Currently, when a detection mechanism, such as a hospital or a physical examination center, detects stones, it is usually necessary for a detection person to align a detection device with the position of stones according to his own experience, and display the currently acquired images through a display device. The inspector estimates the size of the stone based on the size of the stone displayed in the image. Moreover, the size of the calculus displayed in the calculus image can be influenced due to different distances and detection angles between the detection equipment and the calculus, so that the calculus size can not be accurately evaluated by detection personnel, and the efficiency of calculus detection operation can not be improved.
Based on this, the embodiment of the present application proposes an artificial intelligence-based calculus image recognition method, as shown in fig. 1, the method includes:
in S101, an image to be recognized including a stone is acquired by a sensing device.
In the embodiment of the application, the sensing device can comprise a calculus detection device such as a B-ultrasonic device, a CT device and the like. When calculus image acquisition is carried out through the sensing equipment, a plurality of calculus images can be acquired according to different acquisition angles, so that the size information of calculus can be better reduced. For example, when the length direction of the calculus is consistent with the direction of the acquisition angle, the acquired calculus image may not reflect the length information of the calculus, and the acquisition angle is switched, so that the acquired calculus image can effectively reflect the length information of the calculus, and a more accurate calculus size is obtained.
When the sensing equipment is B-ultrasonic equipment, a detector can contact a detection part through a B-ultrasonic probe and detect the detection part at different angles, so that more comprehensive calculus size information is obtained.
In a possible implementation manner, an angle sensor can be arranged on the B-ultrasonic probe, for example, a compass or a gyroscope can be arranged. When a detector detects the calculus by the B-ultrasonic probe, the angle data of the angle sensor is read when the calculus image is acquired, and the corresponding relation between the calculus image and the acquisition angle is recorded, so that the size calculation and the three-dimensional reconstruction processing of the calculus are facilitated subsequently.
In a possible implementation mode, a detection angle required by one-time calculus inspection operation can be set, and after image acquisition of one acquisition angle is completed, the angle of incomplete contour acquisition is determined according to the preset angle required for contour acquisition. The method and the device can generate prompt information of the operation angle needing to be subjected to contour acquisition according to the angle of incomplete contour acquisition, so that a worker can perform angle acquisition operation according to the prompt information, and the problem that the accuracy of an image is influenced by acquiring images at repeated angles is avoided. For example, the detection personnel can be prompted to acquire images according to the next acquisition angle by means of image, text and/or voice prompt of the screen display operation angle.
Or, the corresponding relation between the acquisition angle and the acquisition part may be set, and the detection person may be prompted to acquire the acquisition part corresponding to the next acquisition angle according to the acquisition part corresponding to the next acquisition angle. For example, in the gallstone detection process, after the detection personnel finish the detection on the front side of the abdomen, the detection personnel can prompt the detection personnel to acquire images on the side of the abdomen according to a preset inclination angle.
In S102, target detection is performed on the image to be recognized, and a position of a stone included in the image to be recognized is determined.
In the embodiment of the application, the target detection is performed on the image to be recognized, that is, a stone included in the image to be recognized is detected. Thereby facilitating the analysis of the size of the calculus according to the detection result.
When the target detection is performed on the image to be recognized, as shown in fig. 2, the method includes:
in S201, the image to be recognized is divided into a first predetermined number of grids.
The image to be recognized including the calculus can be uniformly divided into a plurality of grids according to a preset grid division mode. For example, the image to be recognized including the calculi may be divided into S × S meshes, where S is a predetermined numerical value.
In S202, the divided grids are input to the boundary box generation network that is trained in advance, and a second predetermined number of boundary boxes and the probability that the boundary boxes belong to stones are obtained.
When calculus detection is carried out, the divided grids can be input into a boundary box generation network which is trained in advance, a second preset number of boundary boxes are generated in each grid through calculation processing of the boundary box generation network, and the probability that an object framed by each boundary box belongs to calculus is obtained.
The probability that the bounding box belongs to a calculus, i.e., the confidence of the bounding box, may include two aspects, namely the likelihood that the bounding box contains the target and the accuracy of the bounding box. The bounding box contains the likelihood of the object, i.e., the likelihood that the bounding box contains a stone. When a stone is contained in the bounding box, the probability of that bounding box is 1, and if no stone is contained, the probability of the bounding box is 0. The accuracy of the bounding box can be expressed by the intersection of the predicted box with the actual box. The intersection-to-union ratio is the ratio of the intersection and union of the prediction box and the actual box.
In S203, determining a bounding box of the stone in the image to be identified through non-maximum suppression according to the probability that the bounding box belongs to the stone, and determining the position of the stone according to the identified bounding box.
The position of the calculus is determined by adopting a non-maximum suppression algorithm, and the method can be used for solving the problem that the same calculus is detected for multiple times. For example, a single stone belonging to multiple grids may be detected by multiple bounding boxes, and the most accurate bounding box may be determined by a non-maximum suppression algorithm.
When the non-maximum value suppression algorithm is adopted to select the boundary frames, the boundary frames can be sorted according to the accuracy of the boundary frames, a first boundary frame with the maximum accuracy is selected, then the intersection ratio of the first boundary frame and other boundary frames is calculated, if the intersection ratio of the first boundary frame and one other boundary frame, such as a second boundary frame, is calculated to be larger than a certain value, the second boundary frame is removed, and the above processes are repeated until all the boundary frames and the first boundary frame are processed and detected. And selecting the boundary frame with the second highest accuracy from the undeleted boundary frames, sequentially calculating with other undeleted boundary frames, and deleting the boundary frames with the intersection ratio larger than a certain value until the calculation processing of all the boundary frames is completed, thereby deleting redundant boundary frames. And according to the determined boundary frame, the position of the calculus can be used. For example, the location of the stone is within the bounding box, or the center point of the stone is at the center of the bounding box. As shown in fig. 3, after the non-maximum suppression processing, a bounding box of a calculus included in the image to be recognized including the calculus can be obtained, in which the calculus is included.
In S103, from the determined position of the stone, a contour of the stone is identified.
After determining the location of the stone in the stone image, the application further determines the contour of the identified stone in order to facilitate the detection personnel to determine the size of the stone.
When the contour of the calculus is identified, the image in the determined boundary frame including the calculus can be subjected to binarization processing to obtain a binarized image of the image in the boundary frame.
The image within the bounding box may be binarized, the image within the bounding box may be grayscale processed, and the grayscale value of the pixel within the bounding box may be compared with a grayscale threshold in combination with a preset grayscale threshold to determine the value of each pixel within the bounding box to be 0 or 1.
After the pixels of the image in the boundary frame are subjected to binarization processing, the intersection of the two values can be determined as a contour point, and the contour of the calculus in the boundary frame can be obtained according to the determined contour points.
Of course, in a possible implementation manner, optimization processing such as filtering can be performed on the identified contour, so that a contour of the stone with higher precision can be obtained.
In S104, the size of the stone in the stone image is determined according to the contour of the stone.
After the contour of the stone within the bounding box is obtained, the center position of the stone can be determined from the contour. And according to the determined center position of the calculus, a connecting line of any two contour points passing through the center position can be obtained. For convenience of presentation, we refer to the diameter as the line connecting two contour points passing through the center position. The distance between the calculus and the sensing equipment can be determined according to signals detected by the sensing equipment, and the scale of the calculus image and the actual image can be determined by combining the size of the calculus image acquired by the sensing equipment. According to the size of the diameter of the calculus in the calculus image, the real diameter of the calculus can be calculated by combining the ratio of the calculus image to the actual image.
Since the shape of a stone is generally irregular, there are a plurality of diameters having different lengths among the diameters passing through the center point of the stone. The multiple diameters present in the resulting stone profile can be compared to determine the maximum and minimum diameters of the stones in the stone image.
In S105, an identification report corresponding to the stone image is generated according to the plurality of stone sizes at different acquisition angles.
Since the shape of the calculus at the detected part may be irregular or a plurality of calculi may exist at the detected part, in order to more accurately obtain the size information of the calculus, acquisition of calculus images at different acquisition angles is required.
In general, a detection angle necessary for the same detection object can be set. When the detection personnel detect the detection object, the angles can be collected one by one according to the detection sequence for detection. In order to reduce the error probability of the detection personnel and simplify the detection process, the detection angle during image acquisition can be detected when the detection personnel acquire images. For example, the acquisition angle of the detection person when acquiring the current image can be acquired by an angle sensor arranged in the sensing device. When the used collection angle is compared with the necessary collection angle, the angle which needs to be collected can be determined, and the detection personnel can be prompted to collect the image of the next collection angle in a sound, image or text prompting mode.
For example, after the detection personnel collects the stone image according to the first angle, the second angle and the third angle, due to misoperation, the definition of the stone image at the third angle may not meet the preset requirement, and the system prompts the detection personnel to collect the stone image again according to the third angle.
In a possible implementation manner, the corresponding relationship between different acquisition angles and positions can be set. When the detection personnel are required to be prompted to carry out detection on the required acquisition angle, the position corresponding to the acquisition angle can be prompted. Such as the left lumbar region, the front lumbar region, the left front lumbar region, etc. Or the position to be detected can be quickly positioned by the detection personnel by prompting the first detection point, the second detection point and the third detection point according to the preset identification of the detection position.
In a possible implementation, it may also be determined whether overlapping stones are present, depending on the size of the distance of the detected stones. For example, when the difference between the distances between the stones in the same bounding box and the sensing device is detected to be greater than the predetermined distance threshold, the stones in the bounding box are considered to be blocked or overlapped stones, and the next acquisition angle can be determined according to the overlapping pattern, so that the next acquisition angle can more accurately acquire images of the overlapped stones, and a more accurate stone report can be generated.
For example, when overlapped stones exist in the bounding box and whether other stones exist in the adjacent positions of the blocked stones in the current image, the next acquisition angle is determined according to the positions of the blocked stones, so that an image reflecting the sizes of the stones can be obtained more accurately when the blocked stones are acquired.
In the embodiment of the application, after the size of the calculus is determined by the calculus outline, the calculus border frame can be removed, and the calculus outline is directly displayed in the image, so that detection personnel can more clearly view calculus information. In a possible implementation, the outline and size of the stone in the image may also be displayed directly. The displayed dimensions may include a maximum diameter and a minimum diameter of the profile. The detection personnel can flexibly adjust the acquisition angle according to the displayed size information, so that more accurate acquisition images can be obtained.
In a possible implementation mode, after the outlines of the stones are acquired through different angles, the acquired outlines can be fused to obtain three-dimensional images of the stones, and an electronic detection report is generated according to the obtained three-dimensional images, so that the detected object can view the detection result more intuitively.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Fig. 4 is a schematic diagram of an artificial intelligence-based calculus image recognition apparatus according to an embodiment of the present application, as shown in fig. 4, the apparatus includes:
a calculus image acquisition unit 401 for acquiring an image to be identified including a calculus by a sensing device;
a calculus position determining unit 402, configured to perform target detection on the image to be recognized including the calculus, and determine a position of the calculus included in the image to be recognized;
a stone profile recognition unit 403 for recognizing a profile of the stone according to the determined position of the stone;
a stone size identification unit 404, configured to determine a stone size in the stone image according to the contour of the stone;
and an identification report generating unit 405, configured to generate an identification report corresponding to the stone image according to a plurality of stone sizes at different acquisition angles.
The artificial intelligence based calculus image recognition apparatus shown in fig. 4 corresponds to the artificial intelligence based calculus image recognition method shown in fig. 1.
Fig. 5 is a schematic diagram of an artificial intelligence based calculus image recognition apparatus according to an embodiment of the present application. As shown in fig. 5, the artificial intelligence based calculus image recognition apparatus 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52, such as an artificial intelligence based stone image recognition program, stored in said memory 51 and executable on said processor 50. The processor 50, when executing the computer program 52, implements the steps in the various artificial intelligence based stone image recognition method embodiments described above. Alternatively, the processor 50 implements the functions of the modules/units in the above-described device embodiments when executing the computer program 52.
Illustratively, the computer program 52 may be partitioned into one or more modules/units, which are stored in the memory 51 and executed by the processor 50 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 52 in the artificial intelligence based stone image recognition device 5.
The artificial intelligence based stone image recognition device may include, but is not limited to, a processor 50, a memory 51. Those skilled in the art will appreciate that fig. 5 is merely an example of an artificial intelligence based stone image recognition device 5 and does not constitute a limitation of the artificial intelligence based stone image recognition device 5 and may include more or fewer components than shown, or combine certain components, or different components, e.g., the artificial intelligence based stone image recognition device may also include an input-output device, a network access device, a bus, etc.
The Processor 50 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 51 may be an internal storage unit of the artificial intelligence based stone image recognition device 5, such as a hard disk or a memory of the artificial intelligence based stone image recognition device 5. The memory 51 may also be an external storage device of the artificial intelligence based stone image recognition device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), and the like, provided on the artificial intelligence based stone image recognition device 5. Further, the memory 51 may also comprise both an internal storage unit and an external storage device of the artificial intelligence based stone image recognition device 5. The memory 51 is used for storing the computer programs and other programs and data required by the artificial intelligence based stone image recognition device. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the methods described above can be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. An artificial intelligence based calculus image recognition method, comprising:
acquiring an image to be identified including a calculus by a sensing device;
carrying out target detection on the image to be recognized, and determining the position of the calculus included in the image to be recognized;
identifying a contour of the stone from the determined location of the stone;
determining the size of the calculus in the calculus image according to the contour of the calculus;
and generating an identification report corresponding to the calculus image according to the sizes of the multiple calculus at different acquisition angles.
2. The method of claim 1, wherein performing object detection on the image to be recognized and determining the position of the stone included in the image to be recognized comprises:
dividing the image to be recognized into a first preset number of grids;
inputting the divided grids into a boundary box generation network which is trained in advance, and acquiring a second preset number of boundary boxes and the probability of the boundary boxes belonging to calculus;
and determining the boundary frame of the calculus in the image to be identified through non-maximum suppression according to the probability that the boundary frame belongs to the calculus, and determining the position of the calculus according to the identified boundary frame.
3. The method of claim 2, wherein identifying the stone profile based on the determined stone location comprises:
carrying out binarization processing on the image in the determined boundary frame of the calculus to obtain a binarized image of the image in the boundary frame;
and searching contour points in the boundary box according to the binary image, and drawing according to the contour points to generate a calculus contour.
4. The method of claim 2, wherein after determining a stone size in the stone image from a contour of the stone, the method further comprises:
and removing the determined boundary box of the calculus, and displaying the contour of the calculus image at the current acquisition angle and the size of the contour.
5. The method of claim 1, wherein determining a stone size in the stone image from the stone profile comprises:
determining the central position of the calculus according to the contour of the calculus;
and determining a plurality of diameters of the calculus image under the current acquisition angle according to the central position of the calculus, and determining the maximum diameter and the minimum diameter of the calculus.
6. The method of claim 1, further comprising:
acquiring the outline of the calculus acquired by the sensing equipment at different acquisition angles;
and generating a three-dimensional image of the calculus according to the contour of the calculus acquired from different acquisition angles.
7. The method of claim 6, wherein acquiring the profile of the stone acquired by the sensing device at different acquisition angles comprises:
when the sensing equipment acquires a first contour of the calculus, acquiring a first angle for acquiring the first contour through an angle sensor;
determining the angle which is not subjected to the contour acquisition currently according to the preset angle which is required to be subjected to the contour acquisition;
and generating prompt information of the part which is not subjected to contour acquisition according to the preset corresponding relation between the angle and the acquisition part, and acquiring the contour of the calculus when the part which is required to be subjected to contour acquisition is detected.
8. An artificial intelligence based stone image recognition apparatus, the apparatus comprising:
the calculus image acquisition unit is used for acquiring an image to be identified comprising calculus through sensing equipment;
the calculus position determining unit is used for carrying out target detection on the image to be identified comprising the calculus and determining the position of the calculus in the image to be identified;
a stone contour identification unit for identifying the contour of the stone according to the determined position of the stone;
the calculus size identification unit is used for determining the size of the calculus in the calculus image according to the contour of the calculus;
and the identification report generating unit is used for generating an identification report corresponding to the calculus image according to the sizes of the multiple calculus at different acquisition angles.
9. An artificial intelligence based stone image recognition device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111270917.XA CN113781477A (en) | 2021-10-29 | 2021-10-29 | Calculus image identification method, device and equipment based on artificial intelligence |
| PCT/CN2022/089994 WO2023071114A1 (en) | 2021-10-29 | 2022-04-28 | Artificial intelligence-based stone image recognition method and apparatus, and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111270917.XA CN113781477A (en) | 2021-10-29 | 2021-10-29 | Calculus image identification method, device and equipment based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113781477A true CN113781477A (en) | 2021-12-10 |
Family
ID=78873533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111270917.XA Pending CN113781477A (en) | 2021-10-29 | 2021-10-29 | Calculus image identification method, device and equipment based on artificial intelligence |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113781477A (en) |
| WO (1) | WO2023071114A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113962992A (en) * | 2021-12-21 | 2022-01-21 | 青岛大学附属医院 | Urinary calculus flat scanning CT image recognition system based on deep learning and training method |
| WO2023071114A1 (en) * | 2021-10-29 | 2023-05-04 | 平安科技（深圳）有限公司 | Artificial intelligence-based stone image recognition method and apparatus, and device |
| CN117788474A (en) * | 2024-02-27 | 2024-03-29 | 陕西省人民医院(陕西省临床医学研究院) | Urinary calculus image recognition method based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102305589A (en) * | 2011-07-28 | 2012-01-04 | 深圳创维－Rgb电子有限公司 | Method and system for laser ranging |
| CN110301940A (en) * | 2019-06-17 | 2019-10-08 | 翟凯 | A kind of abdominal cavity color ultrasound instrument based on machine learning |
| CN111380785A (en) * | 2020-03-30 | 2020-07-07 | 中南大学 | Two-dimensional geometric characteristic parameter acquisition system and method for rock particles |
| CN113034426A (en) * | 2019-12-25 | 2021-06-25 | 飞依诺科技(苏州)有限公司 | Ultrasonic image focus description method, device, computer equipment and storage medium |
| CN113344911A (en) * | 2021-07-06 | 2021-09-03 | 北京大都正隆医疗科技有限公司 | Method and device for measuring size of calculus |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8254679B2 (en) * | 2008-10-13 | 2012-08-28 | Xerox Corporation | Content-based image harmonization |
| CN113112443B (en) * | 2019-12-25 | 2024-03-22 | 飞依诺科技股份有限公司 | Method and device for segmenting ultrasonic image focus and computer equipment |
| CN113158869A (en) * | 2021-04-15 | 2021-07-23 | 深圳市优必选科技股份有限公司 | Image recognition method and device, terminal equipment and computer readable storage medium |
| CN113781477A (en) * | 2021-10-29 | 2021-12-10 | 平安科技（深圳）有限公司 | Calculus image identification method, device and equipment based on artificial intelligence |
-
2021
- 2021-10-29 CN CN202111270917.XA patent/CN113781477A/en active Pending
-
2022
- 2022-04-28 WO PCT/CN2022/089994 patent/WO2023071114A1/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102305589A (en) * | 2011-07-28 | 2012-01-04 | 深圳创维－Rgb电子有限公司 | Method and system for laser ranging |
| CN110301940A (en) * | 2019-06-17 | 2019-10-08 | 翟凯 | A kind of abdominal cavity color ultrasound instrument based on machine learning |
| CN113034426A (en) * | 2019-12-25 | 2021-06-25 | 飞依诺科技(苏州)有限公司 | Ultrasonic image focus description method, device, computer equipment and storage medium |
| CN111380785A (en) * | 2020-03-30 | 2020-07-07 | 中南大学 | Two-dimensional geometric characteristic parameter acquisition system and method for rock particles |
| CN113344911A (en) * | 2021-07-06 | 2021-09-03 | 北京大都正隆医疗科技有限公司 | Method and device for measuring size of calculus |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023071114A1 (en) * | 2021-10-29 | 2023-05-04 | 平安科技（深圳）有限公司 | Artificial intelligence-based stone image recognition method and apparatus, and device |
| CN113962992A (en) * | 2021-12-21 | 2022-01-21 | 青岛大学附属医院 | Urinary calculus flat scanning CT image recognition system based on deep learning and training method |
| CN117788474A (en) * | 2024-02-27 | 2024-03-29 | 陕西省人民医院(陕西省临床医学研究院) | Urinary calculus image recognition method based on machine vision |
| CN117788474B (en) * | 2024-02-27 | 2024-05-03 | 陕西省人民医院(陕西省临床医学研究院) | Urinary calculus image recognition method based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023071114A1 (en) | 2023-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113781477A (en) | Calculus image identification method, device and equipment based on artificial intelligence | |
| Sobhaninia et al. | Fetal ultrasound image segmentation for measuring biometric parameters using multi-task deep learning | |
| CN107480677B (en) | Method and device for identifying interest region in three-dimensional CT image | |
| CN111862044B (en) | Ultrasonic image processing method, ultrasonic image processing device, computer equipment and storage medium | |
| KR100954989B1 (en) | Ultrasound diagnostic apparatus and method for measuring size of target object | |
| CN111091562B (en) | Method and system for measuring size of digestive tract lesion | |
| CN110136153B (en) | Image processing method, device and storage medium | |
| US11657644B2 (en) | Automatic ruler detection | |
| CN110660072B (en) | Method and device for identifying straight line edge, storage medium and electronic equipment | |
| CN110969623B (en) | Lung CT multi-symptom automatic detection method, system, terminal and storage medium | |
| CN110910441A (en) | Method and device for extracting center line | |
| CN118319374A (en) | Ultrasonic imaging method and equipment | |
| CN111932492A (en) | Medical image processing method and device and computer readable storage medium | |
| CN111929328A (en) | Zipper defect detection method and device | |
| CN110738633B (en) | Three-dimensional image processing method and related equipment for organism tissues | |
| CN110464379B (en) | Fetal head circumference measuring method and device and terminal equipment | |
| CN110111293B (en) | Failure identification method and device for plastic package device | |
| CN116168029A (en) | Method, device and medium for evaluating rib fracture | |
| CN113344911B (en) | Method and device for measuring size of calculus | |
| CN115564763A (en) | Thyroid ultrasound image processing method, device, medium and electronic equipment | |
| CN111260606B (en) | Diagnostic device and diagnostic method | |
| Pena et al. | Skin prick test wheal detection in 3D images via convolutional neural networks | |
| CN112085729A (en) | Pleural line region extraction method, storage medium, and ultrasound diagnostic apparatus | |
| JP2009265998A (en) | Image processing system, image processing method, and image processing program | |
| CN110706222B (en) | Method and device for detecting bone region in image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |