CN110838103A - Image processing method, image processing device, diagnostic equipment and computer storage medium - Google Patents
Image processing method, image processing device, diagnostic equipment and computer storage medium Download PDFInfo
- Publication number
- CN110838103A CN110838103A CN201911036199.2A CN201911036199A CN110838103A CN 110838103 A CN110838103 A CN 110838103A CN 201911036199 A CN201911036199 A CN 201911036199A CN 110838103 A CN110838103 A CN 110838103A
- Authority
- CN
- China
- Prior art keywords
- diagnosed
- picture
- diagnostic
- target
- diagnosis
- 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.)
- Granted
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides an image processing method, an image processing device, diagnostic equipment and a computer storage medium, wherein the method comprises the following steps: the method comprises the steps that a diagnostic device obtains a picture to be diagnosed of a detection object, determines a first diagnostic result according to the picture to be diagnosed, the first diagnostic result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnostic value corresponding to the target to be diagnosed, then obtains a local picture comprising the target to be diagnosed from the picture to be diagnosed, determines a second diagnostic result according to the local picture, the second diagnostic result comprises a second diagnostic value corresponding to the target to be diagnosed, further determines a target diagnostic result of the picture to be diagnosed according to the first diagnostic result and the second diagnostic result, and the target diagnostic result comprises the target to be diagnosed and the diagnostic value corresponding to the target to be diagnosed, so that the accuracy in lesion detection can be effectively improved, and the occurrence of missing judgment or misjudgment is reduced.
Description
Technical Field
The present invention relates to the field of medical imaging technologies, and in particular, to an image processing method, an image processing apparatus, a diagnostic device, and a computer storage medium.
Background
At present, artificial intelligence technology is generally applied to medical image lesion detection and identification, and the existing detection algorithm can perform relevant processing after an input picture to be diagnosed is reduced in proportion. In the process of reducing the picture, some detailed information of the target to be diagnosed in the original picture is lost, so that the condition of missed judgment or misjudgment of the focus may exist in the focus detection process. Therefore, how to effectively improve the accuracy of focus detection to reduce the missing or erroneous judgment has become an urgent problem to be solved.
Disclosure of Invention
Embodiments of the present invention provide an image processing method, an image processing apparatus, a diagnostic device, and a computer storage medium, which can effectively improve accuracy in lesion detection to reduce occurrence of missing or erroneous determination.
In a first aspect, an embodiment of the present invention provides an image processing method, where the method includes:
the diagnostic equipment acquires a picture to be diagnosed of the detection object.
And the diagnosis equipment determines a first diagnosis result according to the picture to be diagnosed, wherein the first diagnosis result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnosis value corresponding to the target to be diagnosed.
The diagnostic equipment acquires a local picture including the target to be diagnosed from the picture to be diagnosed, and determines a second diagnostic result according to the local picture, wherein the second diagnostic result includes a second diagnostic value corresponding to the target to be diagnosed.
And the diagnosis equipment determines a target diagnosis result of the picture to be diagnosed according to the first diagnosis result and the second diagnosis result, wherein the target diagnosis result comprises the target to be diagnosed and a diagnosis value corresponding to the target to be diagnosed.
In a second aspect, an embodiment of the present invention provides an image processing apparatus, including:
and the acquisition module is used for acquiring the picture to be diagnosed of the detection object.
And the determining module is used for determining a first diagnosis result according to the picture to be diagnosed, wherein the first diagnosis result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnosis value corresponding to the target to be diagnosed.
The acquisition module is further configured to acquire a local image including the target to be diagnosed from the image to be diagnosed.
The determining module is further configured to determine a second diagnosis result according to the local image, where the second diagnosis result includes a second diagnosis value corresponding to the target to be diagnosed.
The determining module is further configured to determine a target diagnosis result of the to-be-diagnosed picture according to the first diagnosis result and the second diagnosis result, where the target diagnosis result includes the to-be-diagnosed target and a diagnosis value corresponding to the to-be-diagnosed target.
In a third aspect, an embodiment of the present invention provides a diagnostic apparatus, which includes a processor, a high-speed data interface, and a storage device, where the processor, the high-speed data interface, and the storage device are connected to each other, where the high-speed data interface is controlled by the processor to transmit and receive data, and the storage device is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the image processing method according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium, in which program instructions are stored, and when executed, the computer storage medium is configured to implement the image processing method according to the first aspect.
In the embodiment of the invention, the diagnostic device can obtain a to-be-diagnosed picture of a detection object, determine a first diagnostic result according to the to-be-diagnosed picture, wherein the first diagnostic result comprises a to-be-diagnosed target existing in the to-be-diagnosed picture and a first diagnostic value corresponding to the to-be-diagnosed target, then obtain a local picture comprising the to-be-diagnosed target from the to-be-diagnosed picture, determine a second diagnostic result according to the local picture, wherein the second diagnostic result comprises a second diagnostic value corresponding to the to-be-diagnosed target, further determine a target diagnostic result of the to-be-diagnosed picture according to the first diagnostic result and the second diagnostic result, wherein the target diagnostic result comprises the to-be-diagnosed target and the diagnostic value corresponding to the to-be-diagnosed target, thereby combining the diagnostic result of the local picture comprising the to-be-diagnosed target, avoiding the loss of detail information related to the to-be-diagnosed target, and effectively improving the, so as to reduce the occurrence of missed judgment or misjudgment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1a is a block diagram of an image processing system according to an embodiment of the present invention;
FIG. 1b is a schematic diagram of an application scenario of image processing according to an embodiment of the present invention;
FIG. 1c is a schematic structural diagram of a processing system of a diagnostic device according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an image processing method according to an embodiment of the present invention;
fig. 3a is a schematic diagram of a picture to be diagnosed according to an embodiment of the present invention;
FIG. 3b is a schematic diagram of a partial picture according to an embodiment of the present invention;
FIG. 4 is a flow chart of another image processing method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an output diagnostic result provided by an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a diagnostic apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Aiming at the problem of missed judgment or erroneous judgment of the focus possibly existing in the process of focus detection at present, the embodiment of the invention provides an image processing method, which can be combined with the diagnosis result of a local picture comprising a target to be diagnosed to avoid the loss of the detail information related to the target to be diagnosed, and can effectively improve the accuracy in focus detection so as to reduce the occurrence of missed judgment or erroneous judgment.
Fig. 1a is a schematic diagram of an architecture of an image processing system according to an embodiment of the present invention, where the image processing system includes a diagnostic apparatus 10, an endoscope system 20, a display device 30, and a display device 40, and a communication connection may be established between the diagnostic apparatus 10 and the endoscope system 20 in a wired manner (for example, a high-speed signal line) or a wireless manner, and data such as an image may be transmitted through the communication connection; similarly, communication connections can be established between the endoscope system 20 and the display device 30 and between the diagnostic apparatus 10 and the display device 40 in a wired or wireless manner, and data such as images can be transmitted through the communication connections; the diagnostic device 10 may specifically be an Artificial Intelligence (AI) diagnostic device using AI technology, and the diagnostic device 10 includes a processing system 101 for performing tasks such as image recognition processing.
Wherein:
the endoscope system 20 is configured to collect a picture to be diagnosed of the inspection object, output the picture to be diagnosed through the display device 30, and transmit the picture to be diagnosed to the diagnostic apparatus 10.
The diagnostic device 10 is configured to, after acquiring a to-be-diagnosed picture of a detection object transmitted by the endoscope system 20, perform image recognition on the to-be-diagnosed picture by using a deep learning algorithm to determine whether a to-be-diagnosed target and a corresponding diagnostic value exist in the to-be-diagnosed picture, and generate a first diagnostic result, where the first diagnostic result includes the to-be-diagnosed target existing in the to-be-diagnosed picture and the first diagnostic value corresponding to the to-be-diagnosed target, and the diagnostic value corresponding to the to-be-diagnosed target reflects a possibility that the to-be-diagnosed target exists in the to-be-diagnosed picture.
The diagnostic device 10 is further configured to, when a diagnostic image includes a diagnostic target, intercept a local image including the diagnostic target from the diagnostic image according to position information (e.g., pixel coordinates, etc.) of the diagnostic target in the diagnostic image, where the local image mainly includes image information of the diagnostic target, perform image recognition on the local image by using a deep learning algorithm, determine a diagnostic value corresponding to the diagnostic target according to the local image, and generate a second diagnostic result, where the second diagnostic result includes a second diagnostic value corresponding to the diagnostic target, and further determine a final diagnostic result (denoted as a target diagnostic result) returned to the diagnostic image of the endoscope system 20 according to a global first diagnostic result of the diagnostic image and a local second diagnostic result of the diagnostic image, where the target diagnostic result includes the diagnostic target and the diagnostic value corresponding to the diagnostic target, therefore, the diagnosis result of the local picture in the picture to be diagnosed is combined for comprehensive judgment, so that the loss of the detail information related to the target to be diagnosed can be avoided, the accuracy in focus detection can be effectively improved, and the occurrence of missed judgment or erroneous judgment is reduced.
The diagnosis device 10 is further configured to output the image to be diagnosed and the target diagnosis result through the display device 40, and specifically, the target to be diagnosed and the corresponding diagnosis value included in the target diagnosis result may be marked in the image to be diagnosed, so that the diagnosis result is displayed in a visual manner.
In some possible embodiments, as shown in fig. 1b, which is a specific application scenario provided by the embodiment of the present invention, the endoscope system 20 may enter the human body through a natural duct (e.g. esophagus) of the human body (i.e. the detected object), or through a small incision made by surgery, and acquire a diagnostic image of the part of the human body to be examined.
In some possible embodiments, the processing system 101 of the diagnosis apparatus 10 may be configured as shown in fig. 1c, where the processing system 101 specifically includes two processors, namely a first processor 1011 and a second processor 1012, one processor (assuming that the first processor 1011) is responsible for performing image recognition on the whole of the picture to be diagnosed and obtaining a first diagnosis result, the other processor (i.e. the second processor 1012) is responsible for performing image recognition on the part of the picture to be diagnosed (i.e. the above-mentioned local picture) and obtaining a second diagnosis result, the second processor 1012 may send the second diagnosis result to the first processor 1011, the first processor 1011 performs comprehensive determination according to the first diagnosis result and the second diagnosis result to obtain a target diagnosis result of the picture to be diagnosed, and the picture to be diagnosed and the target diagnosis result are output through the display device 40, and diagnosis on the picture to be diagnosed by multiple processors can quickly obtain a diagnosis result, the diagnosis efficiency is improved, the lesion detection accuracy is ensured, and the display delay of the whole image processing system is effectively reduced, that is, after the endoscope system 20 outputs the acquired picture to be diagnosed through the display device 30, the diagnosis device 10 can rapidly obtain the diagnosis result of the picture to be diagnosed by using the processing system 101 including the multiprocessor, and output the diagnosis result through the display device 40.
In some possible embodiments, the display device 30 and the display device 40 may also be combined into a display device, a part of the display device is used for displaying the picture to be diagnosed collected by the endoscope system 20, another part of the display device is used for displaying the diagnosis result obtained by the diagnosis apparatus 10 and the picture to be diagnosed, and the number of the display devices deployed in the image processing system is not limited by the embodiment of the present invention.
The implementation details of the technical scheme of the embodiment of the invention are explained in detail as follows:
referring to fig. 2, it is a schematic flow chart of an image processing method provided by the image processing system shown in fig. 1a according to an embodiment of the present invention, where the image processing method includes the following steps:
201. the diagnostic equipment acquires a picture to be diagnosed of the detection object.
Specifically, the endoscope system may acquire a picture to be diagnosed of a detection object (e.g., a human body) in real time, and the diagnostic device receives the picture to be diagnosed of the detection object sent by the endoscope system.
202. And the diagnosis equipment determines a first diagnosis result according to the picture to be diagnosed, wherein the first diagnosis result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnosis value corresponding to the target to be diagnosed.
Specifically, the diagnostic device may perform image recognition on the image to be diagnosed by using a deep learning algorithm to determine whether the image to be diagnosed has the target to be diagnosed and the corresponding diagnostic value, and generate a first diagnostic result, where the first diagnostic result includes the target to be diagnosed which exists in the image to be diagnosed and the first diagnostic value which corresponds to the target to be diagnosed, where the diagnostic value which corresponds to the target to be diagnosed reflects the possibility that the image to be diagnosed has the target to be diagnosed, the diagnostic value may specifically be a probability value, for example, 0 to 100%, and a larger probability value means a larger possibility that the image to be diagnosed has the target to be diagnosed.
In some possible embodiments, the diagnosis value may specifically be a score value, for example, 0 to 10, and a higher score value means that the probability of the target to be diagnosed being present in the image to be diagnosed is higher. Of course, the diagnosis value may also be expressed by other indexes capable of reflecting the size of the possibility of the existence of the target to be diagnosed, and the embodiment of the present invention is not limited.
203. The diagnostic equipment acquires a local picture including the target to be diagnosed from the picture to be diagnosed, and determines a second diagnostic result according to the local picture, wherein the second diagnostic result includes a second diagnostic value corresponding to the target to be diagnosed.
Specifically, if the first diagnosis result indicates that the to-be-diagnosed target exists in the to-be-diagnosed picture, the diagnosis device intercepts a local picture including the to-be-diagnosed target from the to-be-diagnosed picture according to position information (for example, pixel coordinates and the like) of the to-be-diagnosed target in the to-be-diagnosed picture, the local picture mainly includes image information of the to-be-diagnosed target, and can perform image recognition on the local picture by using a depth learning algorithm, so as to determine a diagnosis value corresponding to the to-be-diagnosed target according to the local picture, and generate a second diagnosis result, the second diagnosis result includes a second diagnosis value corresponding to the to-be-diagnosed target, and the local picture including the to-be-diagnosed target is recognized and diagnosed, so that loss of detail information related to the to-be-.
As shown in fig. 3a, a is a picture to be diagnosed, and a is a target to be diagnosed, the diagnostic device may capture a local picture including the target to be diagnosed a from the picture to be diagnosed a according to the pixel coordinates of the edge region of the target to be diagnosed a in the picture to be diagnosed a, and capture a local picture b including the target to be diagnosed a as shown in fig. 3 b.
204. And the diagnosis equipment determines a target diagnosis result of the picture to be diagnosed according to the first diagnosis result and the second diagnosis result, wherein the target diagnosis result comprises the target to be diagnosed and a diagnosis value corresponding to the target to be diagnosed.
Specifically, after the diagnostic device generates a global first diagnostic result of the picture to be diagnosed and a local second diagnostic result of the picture to be diagnosed, a final diagnostic result (denoted as a target diagnostic result) of the picture to be diagnosed obtained this time may be determined according to the first diagnostic result and the second diagnostic result, and the target diagnostic result includes a target to be diagnosed and a diagnostic value corresponding to the target to be diagnosed.
In some feasible embodiments, in consideration of the requirement of the deep learning algorithm on the size of the picture, the diagnostic device may perform reduction processing on the picture to be diagnosed according to a first scaling, and perform image recognition on the reduced picture to be diagnosed by using the deep learning algorithm to generate a first diagnostic result; for the local picture intercepted from the picture to be diagnosed, the size of the local picture is obviously smaller than that of the picture to be diagnosed, if the size of the local picture meets the requirement, the diagnostic equipment can directly carry out image recognition on the local picture with the original size by adopting a depth learning algorithm to generate a second diagnostic result, so that the loss of detail information related to the target to be diagnosed is avoided; even if the size of the local picture does not meet the requirement, the diagnostic equipment can reduce the local picture according to a second scaling, and the local picture after the reduction processing is carried out by adopting a deep learning algorithm is subjected to image recognition to generate a second diagnostic result, wherein the second scaling is smaller than the first scaling, so that the corresponding scaling is smaller than the corresponding scaling when the picture to be diagnosed is reduced even if the local picture needs to be reduced, and therefore the second diagnostic result can be generated according to more complete detail information related to the object to be diagnosed, the finally obtained diagnostic result has higher accuracy, and the occurrence of missing judgment or erroneous judgment is reduced.
In some feasible embodiments, the processing system of the diagnostic device may include a first processor and a second processor, the diagnostic device may call the first processor to obtain a first diagnostic result according to a to-be-diagnosed picture, where the first diagnostic result includes position information of a to-be-diagnosed target in the to-be-diagnosed picture, the diagnostic device may call the second processor to intercept a local picture including the to-be-diagnosed target from the to-be-diagnosed picture according to the position information, and obtain a second diagnostic result according to the local picture, the second processor may send the second diagnostic result to the first processor, the first processor performs comprehensive determination according to the first diagnostic result and the second diagnostic result to obtain a target diagnostic result of the to-be-diagnosed picture, and the diagnostic result may be obtained quickly by diagnosing the to-be-diagnosed picture with the multiple processors, so that the diagnostic efficiency is improved, and the accuracy of lesion detection is ensured.
In some possible embodiments, if the processing capability of the processor is sufficiently powerful, the processing system of the diagnosis device may also include only one processor, and the diagnosis is specifically performed by different processes or processing units of the processor, for example, one process or processing unit is responsible for performing image recognition on the whole of the picture to be diagnosed and obtaining the first diagnosis result, and another process or processing unit is responsible for performing image recognition on the part of the picture to be diagnosed (i.e., the above-mentioned local picture) and obtaining the second diagnosis result.
In the embodiment of the invention, the diagnostic device can obtain a to-be-diagnosed picture of a detected object, determine a first diagnostic result according to the to-be-diagnosed picture, wherein the first diagnostic result comprises a to-be-diagnosed target existing in the to-be-diagnosed picture and a first diagnostic value corresponding to the to-be-diagnosed target, then obtain a local picture comprising the to-be-diagnosed target from the to-be-diagnosed picture, determine a second diagnostic result according to the local picture, wherein the second diagnostic result comprises a second diagnostic value corresponding to the to-be-diagnosed target, further determine a target diagnostic result of the to-be-diagnosed picture according to the first diagnostic result and the second diagnostic result, wherein the target diagnostic result comprises the to-be-diagnosed target and the diagnostic value corresponding to the to-be-diagnosed target, thereby performing comprehensive judgment by combining the diagnostic results of the local pictures in the to-be-diagnosed picture, avoiding the loss of detail information related to the to-be-diagnosed target, and, so as to reduce the occurrence of missed judgment or misjudgment.
Referring to fig. 4, it is a schematic flow chart of another image processing method provided by the image processing system shown in fig. 1a according to the embodiment of the present invention, where the image processing method includes the following steps:
401. the diagnostic equipment acquires a picture to be diagnosed of the detection object.
402. And the diagnosis equipment determines a first diagnosis result according to the picture to be diagnosed, wherein the first diagnosis result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnosis value corresponding to the target to be diagnosed.
Specifically, after acquiring a to-be-diagnosed picture of a detection object sent by an endoscope system, a diagnostic device may perform reduction processing on the to-be-diagnosed picture according to a first scaling ratio, and perform image recognition on the reduced to-be-diagnosed picture by using a deep learning algorithm to determine whether a to-be-diagnosed target and a corresponding diagnostic value exist in the to-be-diagnosed picture, and generate a first diagnostic result, where the first diagnostic result includes the to-be-diagnosed target and the first diagnostic value corresponding to the to-be-diagnosed target.
403. The diagnostic equipment judges whether the first diagnostic value is smaller than or equal to a preset diagnostic threshold value, if so, executing steps 404-407; if not, steps 408 and 409 are performed.
Considering that the diagnostic value corresponding to the target to be diagnosed reflects the size of the possibility that the target to be diagnosed exists in the picture to be diagnosed, a diagnostic threshold (recorded as a preset diagnostic threshold) can be set, and if the diagnostic value is greater than the preset diagnostic threshold, the possibility that the target to be diagnosed exists in the picture to be diagnosed is very high, and the target to be diagnosed exists in the picture to be diagnosed can be determined; on the contrary, if the diagnosis value is less than or equal to the preset diagnosis threshold value, it means that there is less possibility that the target to be diagnosed exists in the picture to be diagnosed.
Specifically, the diagnostic device may determine a first diagnostic value corresponding to the target to be diagnosed in the first diagnostic result, and if the first diagnostic value is greater than the preset diagnostic threshold, it means that the possibility that the target to be diagnosed exists in the picture to be diagnosed is very high, and at this time, the diagnostic device may perform steps 408 and 409, and directly use the first diagnostic result obtained by performing image recognition on the whole of the picture to be diagnosed as the final diagnostic result; if the first diagnostic value is less than or equal to the preset diagnostic threshold, it means that the possibility of the existence of the target to be diagnosed in the picture to be diagnosed is low, but considering that the missed judgment or the erroneous judgment caused by the reduction processing of the picture to be diagnosed according to the first scaling ratio may occur, the diagnostic device may perform steps 404 to 407 at this time to perform further image recognition on the local part of the picture to be diagnosed.
For example, taking the probability value of the diagnosis value as an example, the first diagnosis value is 53%, the preset diagnosis threshold value is 80%, and 53% < 80% means that there is a low possibility that the image to be diagnosed has the target to be diagnosed, but in consideration of possible missing judgment or erroneous judgment, the diagnosis device may not make the final diagnosis result at this time, and execute steps 404 to 407 to perform further image recognition on the local part of the image to be diagnosed.
404. The diagnostic equipment acquires a local picture including the target to be diagnosed from the picture to be diagnosed, and determines a second diagnostic result according to the local picture, wherein the second diagnostic result includes a second diagnostic value corresponding to the target to be diagnosed.
Specifically, because the first diagnostic value is less than or equal to the preset diagnostic threshold, the diagnostic device may intercept a local picture including the target to be diagnosed from the picture to be diagnosed, and if the size of the local picture meets the requirement, the diagnostic device may directly perform image recognition on the local picture of the original size by using a depth learning algorithm to generate a second diagnostic result, thereby avoiding loss of detail information related to the target to be diagnosed; even if the size of the local picture does not meet the requirement, the diagnostic equipment can reduce the local picture according to a second scaling, and the local picture after the reduction processing is carried out by adopting a deep learning algorithm is subjected to image recognition to generate a second diagnostic result, wherein the second scaling is smaller than the first scaling.
405. The diagnostic device determines whether the second diagnostic value is greater than the first diagnostic value.
406. And if the second diagnosis value is larger than the first diagnosis value, the diagnosis equipment takes the target to be diagnosed and the second diagnosis value as a target diagnosis result of the picture to be diagnosed.
Specifically, the diagnostic device compares a second diagnostic value obtained by diagnosing a local part of the picture to be diagnosed with a first diagnostic value obtained by diagnosing a global part of the picture to be diagnosed, if the second diagnostic value is greater than the first diagnostic value, it is likely that the detection accuracy is reduced due to loss of detail information of the target to be diagnosed caused by reduction processing of the picture to be diagnosed, and at this time, to prevent missing or erroneous judgment, the diagnostic device should take the diagnostic result of the local picture of the picture to be diagnosed as the reference, and take the target to be diagnosed and the second diagnostic value as the target diagnostic result (i.e., the final diagnostic result) of the picture to be diagnosed.
407. And the diagnostic equipment outputs the picture to be diagnosed through a display device, wherein the picture to be diagnosed is marked with the target to be diagnosed and the second diagnostic value.
Specifically, after the diagnostic device determines a target diagnostic result according to the first diagnostic value and the second diagnostic value, the diagnostic device may output a to-be-diagnosed picture through the display device, and mark the target diagnostic result in the to-be-diagnosed picture, that is, mark the existing to-be-diagnosed target and a corresponding second diagnostic value in the to-be-diagnosed picture, so that under the condition that the second diagnostic value obtained by diagnosing the local picture is greater than the first diagnostic value obtained by globally diagnosing the to-be-diagnosed picture, medical staff can conveniently perform further inspection and confirmation on the to-be-diagnosed target by outputting the second diagnostic value, thereby effectively reducing occurrence of missing or erroneous judgment.
For example, taking the probability value of the diagnostic value as an example, the first diagnostic value is 53%, the preset diagnostic threshold value is 80%, since 53% < 80%, the second diagnostic value obtained by the diagnostic device performing further image recognition on the local image of the image to be diagnosed is 65%, since 65% > 53%, the diagnostic device may output the target to be diagnosed and the second diagnostic value (65%) as the target diagnostic result, the effect of outputting the diagnostic result may be as shown in fig. 5, the target to be diagnosed may be marked by a dashed line frame to achieve a more striking prompt effect, and the diagnostic value of 65% may be displayed at a designated position (for example, the upper right or around the target to be diagnosed) on the display interface. Of course, the marking of the target to be diagnosed may also be implemented by other feasible ways, such as color marking, arrow indication, etc., and the embodiments of the present invention are not limited thereto.
408. And the diagnostic equipment takes the target to be diagnosed and the first diagnostic value as a target diagnostic result of the picture to be diagnosed.
409. And the diagnostic equipment outputs the picture to be diagnosed through a display device, wherein the picture to be diagnosed is marked with the target to be diagnosed and the first diagnostic value.
Specifically, since the first diagnostic value is greater than the preset diagnostic threshold, for example, the first diagnostic value is 92%, the preset diagnostic threshold is 80%, and 92% > 80%, which means that the possibility of the target to be diagnosed existing in the picture to be diagnosed is very high, at this time, the diagnostic device may directly use the first diagnostic result obtained by performing image recognition on the whole of the picture to be diagnosed as the target diagnostic result, and may output the picture to be diagnosed through the display device, and mark the target to be diagnosed and the first diagnostic value in the picture to be diagnosed, and a specific display form may refer to fig. 5, which is not described herein again.
In some possible embodiments, if the second diagnostic value obtained by the diagnostic device is less than or equal to the first diagnostic value in the case that the first diagnostic value is less than or equal to the preset diagnostic threshold value, for example, the first diagnostic value is 53%, and the second diagnostic value is 30%, that is, the diagnostic result obtained by image recognition on the partial picture indicates that the diagnostic target is less likely to exist in the diagnostic picture, the diagnostic device may determine that the target diagnostic result is that the diagnostic target does not exist in the diagnostic picture at this time, and output only the diagnostic picture through the display device.
In some feasible embodiments, after determining the target diagnosis result of the image to be diagnosed, the diagnostic device may store the target diagnosis result including the target to be diagnosed and the corresponding diagnosis value into the diagnosed library, and for the image to be diagnosed of the detection object obtained again, if the diagnostic device diagnoses the whole image of the image to be diagnosed to determine that the target to be diagnosed exists in the image to be diagnosed obtained again, the diagnostic device may directly obtain the diagnosis value corresponding to the target to be diagnosed from the diagnosed library, and use the target to be diagnosed and the diagnosis value obtained from the diagnosed library as the diagnosis result. For example, the endoscope system may not move or only moves a short distance within a period of time, in this case, the picture to be diagnosed acquired by the endoscope system and acquired by the diagnostic device again is substantially the same as or has a small difference from the picture to be diagnosed acquired by the endoscope system and acquired by the diagnostic device once before, so that the same object to be diagnosed is included, the diagnostic device only needs to diagnose the whole picture to be diagnosed, if the diagnostic result indicates that the object to be diagnosed included in the diagnosed library exists in the picture to be diagnosed and acquired again, the diagnostic device directly adopts the corresponding diagnostic result in the diagnosed library, and can directly output the corresponding diagnostic result without diagnosing a local picture of the picture to be diagnosed, so that the diagnostic result can be obtained quickly, the diagnostic efficiency is improved, and the display delay is effectively reduced.
In some possible embodiments, the endoscope system may send a picture to be diagnosed of the detected object to the diagnostic device, and may also send position information when the picture to be diagnosed is acquired to the diagnostic device, and for the picture to be diagnosed of the detected object to be acquired again, the diagnostic device determines whether first position information corresponding to the picture to be diagnosed acquired again is consistent with second position information corresponding to a picture to be diagnosed acquired last time or a difference between the first position information and the second position information is within a certain limit range (for example, 5mm), and if the first position information is consistent with the second position information or a difference between the first position information and the second position information is within a certain limit range, the diagnostic device may directly acquire a diagnostic result of the picture to be diagnosed acquired last time from a diagnosed library, and use the diagnostic result of the picture to be diagnosed acquired last time as a diagnostic result of the picture to be diagnosed acquired again, and output a corresponding diagnostic result, the diagnosis device can obtain a diagnosis result with high accuracy without diagnosing the picture to be diagnosed, so that the diagnosis efficiency can be obviously improved, and the display delay is effectively reduced.
In the embodiment of the invention, a diagnostic device can obtain a picture to be diagnosed of a detection object, determine a first diagnostic result according to the picture to be diagnosed, if a first diagnostic value corresponding to a target to be diagnosed in the first diagnostic result is less than or equal to a preset diagnostic threshold, obtain a local picture including the target to be diagnosed from the picture to be diagnosed, determine a second diagnostic result according to the local picture, wherein the second diagnostic result includes a second diagnostic value corresponding to the target to be diagnosed, and output the target to be diagnosed and the second diagnostic value as a target diagnostic result of the picture to be diagnosed under the condition that the second diagnostic value is greater than the first diagnostic value; if the first diagnosis value is greater than the preset diagnosis threshold value, the diagnosis device directly outputs the target to be diagnosed and the first diagnosis value as a target diagnosis result of the picture to be diagnosed, so that the local picture of the picture to be diagnosed can be further diagnosed under the condition that the diagnosis value obtained by carrying out image recognition on the whole picture to be diagnosed is small, and the diagnosis result of the local picture is comprehensively judged, so that the loss of detail information related to the target to be diagnosed can be avoided, the accuracy in focus detection can be effectively improved, and the occurrence of missed judgment or erroneous judgment can be reduced.
Referring to fig. 6, a schematic structural diagram of an image processing apparatus according to an embodiment of the present invention is shown, where the apparatus includes:
the obtaining module 601 is configured to obtain a to-be-diagnosed picture of the detection object.
A determining module 602, configured to determine a first diagnosis result according to the picture to be diagnosed, where the first diagnosis result includes a target to be diagnosed existing in the picture to be diagnosed and a first diagnosis value corresponding to the target to be diagnosed.
The obtaining module 601 is further configured to obtain a local image including the target to be diagnosed from the image to be diagnosed.
The determining module 602 is further configured to determine a second diagnosis result according to the local image, where the second diagnosis result includes a second diagnosis value corresponding to the target to be diagnosed.
The determining module 602 is further configured to determine a target diagnosis result of the to-be-diagnosed picture according to the first diagnosis result and the second diagnosis result, where the target diagnosis result includes the to-be-diagnosed target and a diagnosis value corresponding to the to-be-diagnosed target.
Optionally, the determining module 602 is specifically configured to:
and reducing the picture to be diagnosed according to a first scaling, and determining a first diagnosis result according to the reduced picture to be diagnosed.
And determining a second diagnosis result according to the local picture with the original size, or performing reduction processing on the local picture according to a second scaling, and determining the second diagnosis result according to the reduced local picture, wherein the second scaling is smaller than the first scaling.
Optionally, the apparatus further comprises:
the determining module 603 is configured to determine whether the first diagnostic value is less than or equal to a preset diagnostic threshold, and trigger the obtaining module 601 to obtain a local picture including the target to be diagnosed from the picture to be diagnosed when the first diagnostic value is less than or equal to the preset diagnostic threshold.
Optionally, the determining module 602 is specifically configured to:
determining whether the second diagnostic value is greater than the first diagnostic value.
And if the second diagnosis value is larger than the first diagnosis value, taking the target to be diagnosed and the second diagnosis value as a target diagnosis result of the picture to be diagnosed.
Optionally, the apparatus further comprises:
an output module 604, configured to output the image to be diagnosed through a display device, where the image to be diagnosed is marked with the target to be diagnosed and the second diagnostic value.
Optionally, the determining module 602 is further configured to use the target to be diagnosed and the first diagnostic value as a target diagnosis result of the picture to be diagnosed if the first diagnostic value is greater than the preset diagnostic threshold.
The output module 604 is further configured to output the picture to be diagnosed through a display device, where the picture to be diagnosed is marked with the target to be diagnosed and the first diagnostic value.
Optionally, the processing system of the diagnostic device includes a first processor and a second processor, and the determining module 602 is specifically configured to invoke the first processor to obtain a first diagnostic result according to the picture to be diagnosed, where the first diagnostic result further includes location information of the target to be diagnosed in the picture to be diagnosed.
The obtaining module 601 is specifically configured to invoke the second processor to capture a local picture including the target to be diagnosed from the picture to be diagnosed according to the position information.
The determining module 602 is specifically configured to invoke the second processor to obtain a second diagnosis result according to the local picture.
Optionally, the apparatus further comprises a storage module 605, wherein:
the storage module 605 is configured to store the target diagnosis result of the to-be-diagnosed picture in the diagnosed library.
The obtaining module 601 is further configured to, for the obtained picture to be diagnosed of the detection object again, obtain a diagnosis value corresponding to the target to be diagnosed from the diagnosed repository if it is determined that the target to be diagnosed exists in the obtained picture to be diagnosed of the detection object again.
The determining module 602 is further configured to use the target to be diagnosed and a diagnostic value corresponding to the target to be diagnosed, which is obtained from the diagnosed library, as a diagnostic result.
It should be noted that the functions of each functional module of the image processing apparatus according to the embodiment of the present invention may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.
Fig. 7 is a schematic structural diagram of a diagnostic apparatus according to an embodiment of the present invention, where the diagnostic apparatus includes a power supply module and the like, and includes a processor 701, a storage device 702, a high-speed data interface 703, and a display device 704. Data can be exchanged between the processor 701, the storage device 702, the high-speed data interface 703 and the display device 704.
The storage 702 may include a volatile memory (volatile memory), such as a random-access memory (RAM); the storage device 702 may also include a non-volatile memory (non-volatile memory), such as a flash memory (flash memory), a solid-state drive (SSD), or the like; the storage means 702 may also comprise a combination of memories of the kind described above.
The processor 701 may be a Central Processing Unit (CPU) 701. In one embodiment, the processor 701 may also be a Graphics Processing Unit (GPU) 701. The processor 701 may also be a combination of a CPU and a GPU. The high-speed data interface 703 may include a network interface, the high-speed data interface 703 is configured to receive and transmit data, and the display device 704 is configured to output information such as images and text. In one embodiment, the storage 702 is used to store program instructions. The processor 701 may call the program instructions to perform the following operations:
and acquiring a picture to be diagnosed of the detection object.
And determining a first diagnosis result according to the picture to be diagnosed, wherein the first diagnosis result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnosis value corresponding to the target to be diagnosed.
And acquiring a local picture including the target to be diagnosed from the picture to be diagnosed, and determining a second diagnosis result according to the local picture, wherein the second diagnosis result includes a second diagnosis value corresponding to the target to be diagnosed.
And determining a target diagnosis result of the picture to be diagnosed according to the first diagnosis result and the second diagnosis result, wherein the target diagnosis result comprises the target to be diagnosed and a diagnosis value corresponding to the target to be diagnosed.
Optionally, the processor 701 is specifically configured to:
and reducing the picture to be diagnosed according to a first scaling, and determining a first diagnosis result according to the reduced picture to be diagnosed.
And determining a second diagnosis result according to the local picture with the original size, or performing reduction processing on the local picture according to a second scaling, and determining the second diagnosis result according to the reduced local picture, wherein the second scaling is smaller than the first scaling.
Optionally, the processor 701 is further configured to:
and judging whether the first diagnostic value is less than or equal to a preset diagnostic threshold value.
And if the first diagnosis value is smaller than or equal to the preset diagnosis threshold value, acquiring a local picture including the target to be diagnosed from the picture to be diagnosed.
Optionally, the processor 701 is specifically configured to:
determining whether the second diagnostic value is greater than the first diagnostic value.
And if the second diagnosis value is larger than the first diagnosis value, taking the target to be diagnosed and the second diagnosis value as a target diagnosis result of the picture to be diagnosed.
Optionally, the processor 701 is further configured to:
and outputting the picture to be diagnosed through a display device 704, wherein the target to be diagnosed and the second diagnostic value are marked in the picture to be diagnosed.
Optionally, the processor 701 is further configured to:
and if the first diagnosis value is larger than the preset diagnosis threshold value, taking the target to be diagnosed and the first diagnosis value as a target diagnosis result of the picture to be diagnosed.
And outputting the picture to be diagnosed through a display device 704, wherein the target to be diagnosed and the first diagnostic value are marked in the picture to be diagnosed.
Optionally, the processor 701 includes a first processor and a second processor.
Wherein the first processor is specifically configured to:
and obtaining a first diagnosis result according to the picture to be diagnosed, wherein the first diagnosis result also comprises the position information of the target to be diagnosed in the picture to be diagnosed.
Wherein the second processor is specifically configured to:
and intercepting a local picture comprising the target to be diagnosed from the picture to be diagnosed according to the position information.
And obtaining a second diagnosis result according to the local picture.
Optionally, the processor 701 is further configured to:
and storing the target diagnosis result of the picture to be diagnosed into a diagnosed library.
And for the re-acquired picture to be diagnosed of the detection object, if the re-acquired picture to be diagnosed of the detection object is determined to have the target to be diagnosed, acquiring a diagnosis value corresponding to the target to be diagnosed from the diagnosed library.
And taking the target to be diagnosed and the diagnosis value corresponding to the target to be diagnosed, which is obtained from the diagnosed library, as a diagnosis result.
In a specific implementation, the processor 701, the storage device 702, the high-speed data interface 703 and the display device 704 described in this embodiment of the present invention may perform the implementation described in the related embodiment of the image processing method provided in fig. 2 or fig. 4 in this embodiment of the present invention, or may also perform the implementation described in the related embodiment of the image processing device provided in fig. 6 in this embodiment of the present invention, which is not described herein again.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, 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 of some interfaces, devices or units, and may be an electric 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 invention 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 unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute all or part of the steps of the above-described method according to the embodiments of the present invention. The storage medium may include: a U-disk, a removable hard disk, a magnetic disk, an optical disk, a Read-Only Memory (ROM) or a Random Access Memory (RAM), and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (11)
1. An image processing method, characterized in that the method comprises:
the diagnostic equipment acquires a picture to be diagnosed of a detection object;
the diagnostic equipment determines a first diagnostic result according to the picture to be diagnosed, wherein the first diagnostic result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnostic value corresponding to the target to be diagnosed;
the diagnostic equipment acquires a local picture comprising the target to be diagnosed from the picture to be diagnosed, and determines a second diagnostic result according to the local picture, wherein the second diagnostic result comprises a second diagnostic value corresponding to the target to be diagnosed;
and the diagnosis equipment determines a target diagnosis result of the picture to be diagnosed according to the first diagnosis result and the second diagnosis result, wherein the target diagnosis result comprises the target to be diagnosed and a diagnosis value corresponding to the target to be diagnosed.
2. The method according to claim 1, wherein the diagnosis device determines a first diagnosis result according to the picture to be diagnosed, and comprises:
the diagnostic equipment performs reduction processing on the picture to be diagnosed according to a first scaling, and determines a first diagnostic result according to the picture to be diagnosed after the reduction processing;
wherein the diagnostic device determines a second diagnostic result according to the local picture, including:
and the diagnostic equipment determines a second diagnostic result according to the local picture with the original size, or reduces the local picture according to a second scaling, and determines the second diagnostic result according to the reduced local picture, wherein the second scaling is smaller than the first scaling.
3. The method according to claim 1 or 2, wherein before the diagnostic device acquires a partial picture including the target to be diagnosed from the picture to be diagnosed, the method further comprises:
the diagnostic device determines whether the first diagnostic value is less than or equal to a preset diagnostic threshold;
and if the first diagnosis value is smaller than or equal to the preset diagnosis threshold value, the diagnosis equipment executes the step of acquiring a local picture including the target to be diagnosed from the picture to be diagnosed.
4. The method according to claim 3, wherein the determining, by the diagnostic device, the target diagnostic result of the picture to be diagnosed according to the first diagnostic result and the second diagnostic result comprises:
the diagnostic device determining whether the second diagnostic value is greater than the first diagnostic value;
and if the second diagnosis value is larger than the first diagnosis value, the diagnosis equipment takes the target to be diagnosed and the second diagnosis value as a target diagnosis result of the picture to be diagnosed.
5. The method according to claim 4, wherein after the diagnostic device takes the target to be diagnosed and the second diagnostic value as the target diagnosis result of the picture to be diagnosed, the method further comprises:
and the diagnostic equipment outputs the picture to be diagnosed through a display device, wherein the picture to be diagnosed is marked with the target to be diagnosed and the second diagnostic value.
6. The method of claim 3, further comprising:
if the first diagnosis value is larger than the preset diagnosis threshold value, the diagnosis equipment takes the target to be diagnosed and the first diagnosis value as a target diagnosis result of the picture to be diagnosed;
and the diagnostic equipment outputs the picture to be diagnosed through a display device, wherein the picture to be diagnosed is marked with the target to be diagnosed and the first diagnostic value.
7. The method of claim 1, wherein the processing system of the diagnostic device comprises a first processor and a second processor;
wherein, the diagnosis device determines a first diagnosis result according to the picture to be diagnosed, and comprises:
the diagnosis equipment calls the first processor to obtain a first diagnosis result according to the picture to be diagnosed, and the first diagnosis result also comprises the position information of the target to be diagnosed in the picture to be diagnosed;
the method for determining the second diagnosis result by the diagnosis equipment comprises the following steps of obtaining a local picture including the target to be diagnosed from the picture to be diagnosed, and determining the second diagnosis result according to the local picture, wherein the steps comprise:
the diagnosis equipment calls the second processor to intercept a local picture comprising the target to be diagnosed from the picture to be diagnosed according to the position information;
and the diagnosis equipment calls the second processor to obtain a second diagnosis result according to the local picture.
8. The method of claim 1, further comprising:
the diagnostic equipment stores the target diagnosis result of the picture to be diagnosed into a diagnosed library;
for the obtained picture to be diagnosed of the detection object again, if the diagnosis device determines that the obtained picture to be diagnosed of the detection object again has the target to be diagnosed, the diagnosis device obtains a diagnosis value corresponding to the target to be diagnosed from the diagnosed library;
and the diagnostic equipment takes the target to be diagnosed and the diagnostic value corresponding to the target to be diagnosed, which is acquired from the diagnosed library, as a diagnostic result.
9. An image processing apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring a picture to be diagnosed of the detection object;
the determining module is used for determining a first diagnosis result according to the picture to be diagnosed, wherein the first diagnosis result comprises a target to be diagnosed existing in the picture to be diagnosed and a first diagnosis value corresponding to the target to be diagnosed;
the acquisition module is further used for acquiring a local picture including the target to be diagnosed from the picture to be diagnosed;
the determining module is further configured to determine a second diagnosis result according to the local image, where the second diagnosis result includes a second diagnosis value corresponding to the target to be diagnosed;
the determining module is further configured to determine a target diagnosis result of the to-be-diagnosed picture according to the first diagnosis result and the second diagnosis result, where the target diagnosis result includes the to-be-diagnosed target and a diagnosis value corresponding to the to-be-diagnosed target.
10. A diagnostic apparatus comprising a processor, a high speed data interface and a storage device, the processor, the high speed data interface and the storage device being interconnected, wherein the high speed data interface is controlled by the processor for transceiving data, the storage device is for storing a computer program, the computer program comprising program instructions, the processor being configured to invoke the program instructions for performing the image processing method of any of claims 1 to 8.
11. A computer storage medium having stored thereon program instructions for implementing the image processing method of any one of claims 1 to 8 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911036199.2A CN110838103B (en) | 2019-10-29 | 2019-10-29 | Image processing method, device, diagnosis equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911036199.2A CN110838103B (en) | 2019-10-29 | 2019-10-29 | Image processing method, device, diagnosis equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110838103A true CN110838103A (en) | 2020-02-25 |
| CN110838103B CN110838103B (en) | 2023-05-16 |
Family
ID=69575680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911036199.2A Active CN110838103B (en) | 2019-10-29 | 2019-10-29 | Image processing method, device, diagnosis equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110838103B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932564A (en) * | 2020-09-24 | 2020-11-13 | 平安科技（深圳）有限公司 | Picture identification method and device, electronic equipment and computer readable storage medium |
| CN112735565A (en) * | 2020-10-30 | 2021-04-30 | 衡阳市大井医疗器械科技有限公司 | Detection result acquisition method, electronic equipment and server |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108257674A (en) * | 2018-01-24 | 2018-07-06 | 龙马智芯（珠海横琴）科技有限公司 | Disease forecasting method and apparatus, equipment, computer readable storage medium |
| CN109447966A (en) * | 2018-10-26 | 2019-03-08 | 科大讯飞股份有限公司 | Lesion localization recognition methods, device, equipment and the storage medium of medical image |
| CN110136153A (en) * | 2019-05-14 | 2019-08-16 | 上海商汤智能科技有限公司 | A kind of image processing method, equipment and storage medium |
| CN110335256A (en) * | 2019-06-18 | 2019-10-15 | 广州智睿医疗科技有限公司 | A kind of pathology aided diagnosis method |
-
2019
- 2019-10-29 CN CN201911036199.2A patent/CN110838103B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108257674A (en) * | 2018-01-24 | 2018-07-06 | 龙马智芯（珠海横琴）科技有限公司 | Disease forecasting method and apparatus, equipment, computer readable storage medium |
| CN109447966A (en) * | 2018-10-26 | 2019-03-08 | 科大讯飞股份有限公司 | Lesion localization recognition methods, device, equipment and the storage medium of medical image |
| CN110136153A (en) * | 2019-05-14 | 2019-08-16 | 上海商汤智能科技有限公司 | A kind of image processing method, equipment and storage medium |
| CN110335256A (en) * | 2019-06-18 | 2019-10-15 | 广州智睿医疗科技有限公司 | A kind of pathology aided diagnosis method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932564A (en) * | 2020-09-24 | 2020-11-13 | 平安科技（深圳）有限公司 | Picture identification method and device, electronic equipment and computer readable storage medium |
| CN111932564B (en) * | 2020-09-24 | 2021-03-02 | 平安科技（深圳）有限公司 | Picture identification method and device, electronic equipment and computer readable storage medium |
| CN112735565A (en) * | 2020-10-30 | 2021-04-30 | 衡阳市大井医疗器械科技有限公司 | Detection result acquisition method, electronic equipment and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110838103B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10810735B2 (en) | Method and apparatus for analyzing medical image | |
| JP7058373B2 (en) | Lesion detection and positioning methods, devices, devices, and storage media for medical images | |
| US10198668B2 (en) | Apparatus and method for supporting computer aided diagnosis (CAD) based on probe speed | |
| WO2019037676A1 (en) | Image processing method and device | |
| KR101926123B1 (en) | Device and method for segmenting surgical image | |
| KR102472034B1 (en) | Method and Apparatus for Detection of a Region Representing Interdental Caries in an X-ray Image | |
| EP3998579B1 (en) | Medical image processing method, apparatus and device, medium and endoscope | |
| CN109191451B (en) | Abnormality detection method, apparatus, device, and medium | |
| CN110662476B (en) | Information processing apparatus, control method, and program | |
| CN110838103B (en) | Image processing method, device, diagnosis equipment and computer storage medium | |
| CN111062947A (en) | Deep learning-based X-ray chest radiography focus positioning method and system | |
| CA3110581C (en) | System and method for evaluating the performance of a user in capturing an image of an anatomical region | |
| JPWO2019111339A1 (en) | Learning equipment, inspection system, learning method, inspection method and program | |
| US20220265228A1 (en) | Radiation imaging system, radiation imaging method, image processing apparatus, and storage medium | |
| CN113255516A (en) | Living body detection method and device and electronic equipment | |
| JPWO2020054604A1 (en) | Information processing equipment, control methods, and programs | |
| JP2024050897A (en) | Apparatus, method, and computer-readable storage medium for detecting objects in a video signal based on visual evidence using the output of a machine learning model | |
| US20230237657A1 (en) | Information processing device, information processing method, program, model generating method, and training data generating method | |
| CN111144506B (en) | Liver bag worm identification method based on ultrasonic image, storage medium and ultrasonic equipment | |
| CN110197722B (en) | AI-CPU system platform | |
| US20220110505A1 (en) | Information processing apparatus, control method, and non-transitory storage medium | |
| CN110110750B (en) | Original picture classification method and device | |
| CN115661493B (en) | Method, device, equipment and storage medium for determining object pose | |
| US20230017227A1 (en) | Program, information processing method, information processing apparatus, and model generation method | |
| CN110772210B (en) | Diagnosis interaction system and method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |