CN111047567A - Kidney tumor picture determination method and related device - Google Patents
Kidney tumor picture determination method and related device Download PDFInfo
- Publication number
- CN111047567A CN111047567A CN201911233953.1A CN201911233953A CN111047567A CN 111047567 A CN111047567 A CN 111047567A CN 201911233953 A CN201911233953 A CN 201911233953A CN 111047567 A CN111047567 A CN 111047567A
- Authority
- CN
- China
- Prior art keywords
- picture
- kidney
- tumor
- determining
- file
- 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
- 208000008839 Kidney Neoplasms Diseases 0.000 title claims abstract description 166
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 63
- 238000012545 processing Methods 0.000 claims abstract description 10
- 210000003734 kidney Anatomy 0.000 claims description 40
- 206010028980 Neoplasm Diseases 0.000 claims description 16
- 238000002372 labelling Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000002604 ultrasonography 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
- G06T7/12—Edge-based segmentation
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30084—Kidney; Renal
Abstract
The application provides a kidney tumor picture determining method and a related device, and relates to the technical field of image processing. The method comprises the steps of firstly obtaining a file to be processed, converting the file to be processed into a picture file, determining the position of a kidney tumor from the picture file according to a preset training model, cutting the region where the kidney tumor is located to obtain an initial kidney tumor picture, and finally segmenting the initial kidney tumor picture to obtain a target kidney tumor picture. The kidney tumor picture determining method and the related device have the advantages of being simpler in kidney tumor picture determining and simpler in kidney tumor picture determining.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a kidney tumor picture determining method and a related device.
Background
In the process of treating the kidney tumor, the kidney tumor is determined according to the shooting result of a patient and is very important.
Currently, the kidney tumor is determined by firstly determining manual characteristics and then determining the kidney tumor from a picture file according to the received characteristics. However, since the selection of manual features varies with the change of shape, color and texture, it is difficult to obtain a suitable combination of manual features, and the final renal tumor image may have errors.
In summary, in the prior art, it is difficult to determine the kidney tumor image, and there may be an error in the determined kidney tumor image.
Disclosure of Invention
The present application aims to provide a method and a related device for determining a kidney tumor picture, so as to solve the problems that in the prior art, the determination of a kidney tumor picture is difficult, and an error may exist in the determined kidney tumor picture.
In order to achieve the above purpose, the embodiments of the present application employ the following technical solutions:
in a first aspect, an embodiment of the present application provides a method for determining a renal tumor picture, where the method includes:
acquiring a file to be processed, and converting the file to be processed into a picture file, wherein the picture file comprises kidney tumors;
determining the position of the kidney tumor from the picture file according to a preset training model;
cutting the region where the kidney tumor is located to obtain an initial kidney tumor picture;
and segmenting the initial kidney tumor picture to obtain a target kidney tumor picture.
In a second aspect, an embodiment of the present application provides an apparatus for determining a renal tumor picture, where the apparatus includes:
the system comprises a data acquisition module, a processing module and a processing module, wherein the data acquisition module is used for acquiring a file to be processed and converting the file to be processed into an image file, and the image file comprises kidney tumors;
the position determining module is used for determining the position of the kidney tumor from the picture file according to a preset training model;
the image cutting module is used for cutting the area where the kidney tumor is located so as to obtain an initial kidney tumor image;
and the image segmentation module is used for segmenting the initial kidney tumor image so as to obtain a target kidney tumor image.
In a third aspect, an embodiment of the present application further provides an electronic device, including:
a memory for storing one or more programs;
a processor;
the one or more programs, when executed by the processor, implement the methods described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method described above.
Compared with the prior art, the method has the following beneficial effects:
the application provides a kidney tumor picture determining method and a related device, wherein a file to be processed is firstly obtained and converted into a picture file, the picture file comprises a kidney tumor, then the position of the kidney tumor is determined from the picture file according to a preset training model, then the region where the kidney tumor is located is cut to obtain an initial kidney tumor picture, and finally the initial kidney tumor picture is segmented to obtain a target kidney tumor picture. After the file to be processed is obtained, the system can automatically determine the position of the kidney tumor according to the preset training model, so that the determination of the kidney tumor picture is simpler. Moreover, after the kidney tumor is determined, the picture of the kidney tumor is cut and segmented, so that the determined kidney tumor picture can be more accurate.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and it will be apparent to those skilled in the art that other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 shows a schematic structural block diagram of an electronic device provided in an embodiment of the present application.
Fig. 2 shows a schematic flowchart of a kidney tumor image determination method provided in an embodiment of the present application.
Fig. 3 shows a schematic flowchart of the sub-step of S104 in fig. 2 provided in an embodiment of the present application.
Fig. 4 shows another schematic flowchart of a kidney tumor image determination method provided in an embodiment of the present application.
Fig. 5 shows a schematic flowchart of the sub-step of S108 in fig. 2 provided in an embodiment of the present application.
Fig. 6 shows a schematic block diagram of a renal tumor image determination apparatus provided in an embodiment of the present application.
Fig. 7 shows a schematic block diagram of a position determination module provided in an embodiment of the present application.
Fig. 8 shows a schematic block diagram of a picture segmentation module provided in an embodiment of the present application.
In the figure: 100-an electronic device; 101-a memory; 102-a processor; 103-a communication interface; 200-kidney tumor picture determination device; 210-a data acquisition module; 220-a location determination module; 221-a position determination unit; 222-a data stuffing unit; 230-a picture cropping module; 240-picture segmentation module; 241-a feature information extraction unit; 242-picture segmentation unit.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. 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 application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings or orientations or positional relationships conventionally found in use of products of the application, and are used only for convenience in describing the present application and for simplification of description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present application.
In the description of the present application, it is also to be noted that, unless otherwise explicitly specified or limited, the terms "disposed" and "connected" are to be interpreted broadly, e.g., as being either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
First embodiment
As described in the background, the current renal tumor determination generally employs first determining the manual characteristics, and then determining the renal tumor from the picture file according to the received characteristics. However, since the selection of manual features varies with the change of shape, color and texture, it is difficult to obtain a suitable combination of manual features, and the final renal tumor image may have errors.
In view of this, the present application provides a method for determining a kidney tumor image, so as to solve the problems in the prior art that it is difficult to determine a kidney tumor image, and an error may exist in the determined kidney tumor image.
The kidney tumor picture determination method provided by the present application will now be exemplified by taking a server as an execution subject.
Referring to fig. 1, fig. 1 shows a schematic block diagram of an electronic device 100 according to an embodiment of the present disclosure. The electronic device 100 may be a device, such as a Personal Computer (PC), a tablet computer, a server, and the like, for implementing the method for determining a renal tumor picture provided in the embodiment of the present application.
The electronic device 100 includes a memory 101, a processor 102, and a communication interface 103, the memory 101, the processor 102, and the communication interface 103 being electrically connected to each other, directly or indirectly, to enable transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
The memory 101 may be used to store software programs and modules, such as program instructions/modules corresponding to the kidney tumor image determination apparatus provided in the embodiment of the present application, and the processor 102 executes the software programs and modules stored in the memory 101, so as to execute various functional applications and data processing. The communication interface 103 may be used for communicating signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Programmable Read-Only Memory (EEPROM), and the like.
The processor 102 may be an integrated circuit chip, with-plus + signal processing capability. The processor 102 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
It will be appreciated that the configuration shown in FIG. 1 is merely illustrative and that electronic device 100 may include more or fewer components than shown in FIG. 1 or have a different configuration than shown in FIG. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.
The method for determining a renal tumor picture provided by the embodiment of the present application is exemplarily described below by taking the electronic device 100 shown in fig. 1 as an exemplary implementation subject.
Referring to fig. 2, fig. 2 shows a schematic flowchart of a method for determining a renal tumor image according to an embodiment of the present application, which may include the following steps:
s102, obtaining a file to be processed, and converting the file to be processed into a picture file, wherein the picture file comprises kidney tumors.
And S104, determining the position of the kidney tumor from the picture file according to a preset training model.
S106, cutting the region where the kidney tumor is located to obtain an initial kidney tumor picture.
And S108, segmenting the initial kidney tumor picture to obtain a target kidney tumor picture.
The file to be processed provided by the present application may be a DICOM (Digital Imaging and communications in Medicine) file. DICOM is an international standard for medical images and related information (ISO 12052), and is widely used in the fields of radiology, cardiovascular imaging, and diagnostic radiology equipment (X-ray, CT, nuclear magnetic resonance, ultrasound, etc.), and is increasingly used in other medical fields such as ophthalmology and dentistry.
That is, when a patient is performing relevant treatment on a renal tumor, CT photography needs to be performed, and the file to be processed is a file acquired when the patient performs CT photography. In order to facilitate image processing, in the present application, after acquiring a file to be processed, an electronic device may first convert the file to be processed into a picture file. It is understood that when there is a kidney tumor in the DICOM file, the converted image file also includes the kidney tumor.
After the image file is converted, the electronic device can determine the position of the kidney tumor from the image file according to a preset training model. The preset training model is a trained model, and the position of the kidney tumor can be identified from the picture file according to the model.
And after determining the position of the kidney tumor, the electronic device cuts the region where the kidney tumor is located to obtain an initial kidney tumor picture. For example, the electronic device directly utilizes the form of matting to crop.
Because the initial kidney tumor picture cut out is only an approximate region, the edge part of the initial kidney tumor picture actually comprises a region without the kidney tumor, and therefore, in order to enable the result to be more accurate, the initial kidney tumor picture is further segmented by the method, the region without the kidney tumor is completely removed, and then the final target kidney tumor picture is obtained.
By the kidney tumor picture determining method, the kidney tumor picture can be determined by the electronic equipment completely, and the determining accuracy is higher.
As a possible implementation manner, referring to fig. 3, the step of S104 includes:
s1041, determining the position of the kidney from the picture file according to the first training model.
S1042, cutting the region where the kidney is located, and filling the boundary of the cut kidney region to obtain a kidney picture with a target size.
And S1043, determining the position of the tumor from the kidney picture according to the second training model.
That is, in the present application, when determining the position of the kidney tumor, it is necessary to first determine the kidney region, and then continue to determine the position of the tumor from the determined kidney region. It will be appreciated that the first trained model is used for the location of the kidney and the second trained model is used for determining the location of the tumor.
As can be appreciated, before performing S1041 and S1043, referring to fig. 4, the method further includes:
s101-1, acquiring a first training picture file with two-point labeling on the kidney.
S101-2, training the basic model by using the first training picture file to obtain a first training model.
S101-3, acquiring a second training picture file with two-point labeling on the tumor.
And S101-4, training the basic model by using the second training picture file to obtain a second training model.
In the present application, the first training model may be a refindet _ VGGNet _512 training network, and the size of the identified picture is 512 × 512. In addition, in the application, when the first training picture file is used for training the basic model, only two points of the small number of picture files need to be labeled manually, and the first training picture file can be used. For example, the number of the first training picture files is 3 or 5. As a possible implementation manner, the two-point labeling described in the present application may be performed on the upper left and lower right positions of the picture file, and the base model is trained through the labeled first training picture file to obtain the trained first training model.
Meanwhile, the positions of the kidneys in the picture file can be determined by using the first training model, and then whether the kidneys exist in the picture file or not and the positions of the kidneys are given are judged.
In the present application, the second training model may be a refindet _ VGGNet _256 training network, and the size of the identified picture is 256 × 256.
Therefore, after the position of the kidney is determined and the region where the kidney is located is cut, the cut kidney region needs to be subjected to boundary filling so as to obtain a kidney picture with a target size. I.e. a filled size of 256 x 256.
It should be noted that, in order to keep the texture inside the kidney unchanged and ensure the accuracy of tumor detection, when the boundary filling is performed, the RGB values of the filled region are 0, that is, black is used for filling. In addition, since the size of the kidney varies among patients, the range of the boundary filling may vary among the kidney regions of different patients.
Similarly, when the second training model is used to determine the position of the tumor from the kidney picture, only two-point labeling of the tumor in a small number of picture files needs to be performed manually, and the second training picture file can be used. For example, the number of the second training picture files may be 3 or 5. As a possible implementation manner, the two-point labeling described in the present application may be performed by labeling the upper left and lower right positions of the picture file, training the basic model through the labeled second training picture file, and acquiring the trained second training model.
The electronic device can then also determine the location of the tumor from the picture of the patient's kidney according to the second training model.
Of course, the first and second training models are only one implementation for determining the location of a renal tumor. Of course, in some other embodiments, the determination of the position of the kidney tumor can be implemented in other implementations, for example, the determination of the position of the kidney tumor is implemented in an end-to-end manner, that is, after the picture file is obtained, the position of the kidney tumor is directly determined from the picture file. In other words, the first training model and the second training model can be combined, and the weights of the first training model and the second training model can be fine-tuned, so that the position of the kidney tumor can be directly determined.
As a possible implementation manner, in the present application, when the electronic device performs clipping on the region where the kidney tumor is located, not only the bounding box but also the classification accuracy can be output. For example, the bounding box may be a rectangular box that includes a kidney tumor inside. Wherein, when there is a tumor in both kidneys of the patient, the number of the bounding boxes may be two. Meanwhile, the classification accuracy, that is, the probability of a kidney tumor in the frame is also displayed at the boundary box, for example, if the classification accuracy is 0.95, the probability of including a kidney tumor in the boundary is 95%.
Referring to fig. 5, S108 includes:
s1081, extracting feature information from the middle position of the initial kidney tumor image, wherein the feature information includes gray values of pixel points.
And S1082, segmenting the edge of the initial kidney tumor image by using the characteristic information to obtain a segmented target kidney tumor image.
In the initial kidney tumor picture obtained after the region where the kidney tumor is located is cut, if the initial kidney tumor picture is cut in a rectangular manner, the edge of the obtained initial kidney tumor picture actually includes a region which is not the kidney tumor, so that the result is more accurate, and the initial kidney tumor picture needs to be segmented.
The middle position refers to the center position of the initial kidney tumor picture, and because the accuracy of the training model is high, the center position of the initial kidney tumor picture has a very high probability (approximately equal to 1) to be judged as a tumor, and therefore, the picture segmentation can be performed according to the feature information extracted from the middle position.
It can be understood that, when the image is segmented, the feature information of the middle position of the initial kidney tumor image is obtained first, for example, the feature information may be a gray value of a pixel point, that is, the gray value of the tumor image is within an interval range, and the gray value interval of the pixel point corresponding to the kidney tumor can be determined by the gray value of the pixel point of the middle position.
After the characteristic information is determined, the electronic device can also segment the edge of the initial kidney tumor picture by using the characteristic information, and further propose to remove the region which is not the kidney tumor so as to obtain the segmented target kidney tumor picture. For example, the K-nearest neighbor and K-means algorithms are used to segment the edges of the initial renal tumor image.
In conclusion, the method for determining the kidney tumor picture provided by the application can be used for determining the kidney tumor picture more simply, and the determined kidney tumor picture is more accurate.
In addition, based on the same inventive concept as the above-mentioned kidney tumor picture determining method, referring to fig. 6, fig. 6 shows a schematic structural block diagram of a kidney tumor picture determining apparatus 200 according to an embodiment of the present application, where the kidney tumor picture determining apparatus 200 includes:
the data obtaining module 210 is configured to obtain a file to be processed, and convert the file to be processed into a picture file, where the picture file includes a kidney tumor.
And a position determining module 220, configured to determine a position of the kidney tumor from the image file according to a preset training model.
And the picture cropping module 230 is configured to crop the region where the kidney tumor is located, so as to obtain an initial kidney tumor picture.
And an image segmentation module 240, configured to segment the initial kidney tumor image to obtain a target kidney tumor image.
Referring to fig. 7, the position determining module 220 includes:
a position determining unit 221, configured to determine a position of the kidney from the picture file according to the first training model;
the data filling unit 222 is configured to cut an area where the kidney is located, and perform boundary filling on the cut kidney area to obtain a kidney picture of a target size;
the position determining unit 221 is further configured to determine a position of the tumor from the kidney image according to the second training model.
Referring to fig. 8, the picture segmentation module 240 includes:
the feature information extracting unit 241 is configured to extract feature information from an intermediate position of the initial kidney tumor image, where the feature information includes a gray value of a pixel point;
the image segmentation unit 242 is configured to segment an edge of the initial kidney tumor image by using the feature information to obtain a segmented target kidney tumor image.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.
To sum up, the application provides a kidney tumor picture determining method and a related device, firstly, a file to be processed is obtained, the file to be processed is converted into a picture file, the picture file comprises a kidney tumor, then, the position of the kidney tumor is determined from the picture file according to a preset training model, then, the region where the kidney tumor is located is cut, so that an initial kidney tumor picture is obtained, and finally, the initial kidney tumor picture is segmented, so that a target kidney tumor picture is obtained. After the file to be processed is obtained, the system can automatically determine the position of the kidney tumor according to the preset training model, so that the determination of the kidney tumor picture is simpler. Moreover, after the kidney tumor is determined, the picture of the kidney tumor is cut and segmented, so that the determined kidney tumor picture can be more accurate.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. A method for determining a renal tumor picture, the method comprising:
acquiring a file to be processed, and converting the file to be processed into a picture file, wherein the picture file comprises kidney tumors;
determining the position of the kidney tumor from the picture file according to a preset training model;
cutting the region where the kidney tumor is located to obtain an initial kidney tumor picture;
and segmenting the initial kidney tumor picture to obtain a target kidney tumor picture.
2. The method for determining a renal tumor picture according to claim 1, wherein the step of determining the position of the renal tumor from the picture file according to a predetermined training model comprises:
determining the position of the kidney from the picture file according to a first training model;
cutting the region where the kidney is located, and filling the boundary of the cut kidney region to obtain a kidney picture with a target size;
and determining the position of the tumor from the kidney picture according to a second training model.
3. The method of claim 2, wherein prior to the step of determining the location of the kidney from the picture file according to the first trained model, the method further comprises:
acquiring a first training picture file with two-point labeling on a kidney;
and training a basic model by using the first training picture file to obtain the first training model.
4. The method of claim 2, wherein prior to the step of determining the location of the tumor from the kidney picture according to the second training model, the method further comprises:
acquiring a second training picture file with two-point labeling on the tumor;
and training a basic model by using the second training picture file to obtain the second training model.
5. The method for determining a renal tumor picture according to claim 1, wherein the step of segmenting the initial renal tumor picture to obtain the target renal tumor picture comprises:
extracting characteristic information from the middle position of the initial kidney tumor picture, wherein the characteristic information comprises a gray value of a pixel point;
and segmenting the edge of the initial kidney tumor picture by using the characteristic information to obtain a segmented target kidney tumor picture.
6. A renal tumor picture determination apparatus, the apparatus comprising:
the system comprises a data acquisition module, a processing module and a processing module, wherein the data acquisition module is used for acquiring a file to be processed and converting the file to be processed into an image file, and the image file comprises kidney tumors;
the position determining module is used for determining the position of the kidney tumor from the picture file according to a preset training model;
the image cutting module is used for cutting the area where the kidney tumor is located so as to obtain an initial kidney tumor image;
and the image segmentation module is used for segmenting the initial kidney tumor image so as to obtain a target kidney tumor image.
7. The renal tumor picture determination device of claim 6, wherein the location determination module comprises:
the position determining unit is used for determining the position of the kidney from the picture file according to a first training model;
the data filling unit is used for cutting the region where the kidney is located and filling the boundary of the cut kidney region to obtain a kidney picture with a target size;
and the position determining unit is also used for determining the position of the tumor from the kidney picture according to a second training model.
8. The renal tumor picture determination device of claim 6, wherein the picture segmentation module comprises:
the characteristic information extraction unit is used for extracting characteristic information from the middle position of the initial kidney tumor picture, wherein the characteristic information comprises the gray value of a pixel point;
and the image segmentation unit is used for segmenting the edge of the initial kidney tumor image by using the characteristic information so as to obtain a segmented target kidney tumor image.
9. An electronic device, comprising:
a memory for storing one or more programs;
a processor;
the one or more programs, when executed by the processor, implement the method of any of claims 1-5.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911233953.1A CN111047567A (en) | 2019-12-05 | 2019-12-05 | Kidney tumor picture determination method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911233953.1A CN111047567A (en) | 2019-12-05 | 2019-12-05 | Kidney tumor picture determination method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111047567A true CN111047567A (en) | 2020-04-21 |
Family
ID=70234704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911233953.1A Pending CN111047567A (en) | 2019-12-05 | 2019-12-05 | Kidney tumor picture determination method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047567A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023197752A1 (en) * | 2022-04-13 | 2023-10-19 | 中南大学湘雅医院 | Margin path generation method and system for tumor surgery, and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104637056A (en) * | 2015-02-02 | 2015-05-20 | 复旦大学 | Method for segmenting adrenal tumor of medical CT (computed tomography) image based on sparse representation |
| CN205068971U (en) * | 2015-11-04 | 2016-03-02 | 南方医科大学 | A phantom for evaluating belly CT image registration precision |
| CN108596887A (en) * | 2018-04-17 | 2018-09-28 | 湖南科技大学 | A kind of abdominal CT sequence image liver neoplasm automatic division method |
| CN108618844A (en) * | 2018-04-19 | 2018-10-09 | 北京工业大学 | Air navigation aid is punctured in a kind of CT guiding liver tumour radio-frequency ablation procedure |
| CN109035197A (en) * | 2018-05-31 | 2018-12-18 | 东南大学 | CT contrastographic picture tumor of kidney dividing method and system based on Three dimensional convolution neural network |
| CN109300088A (en) * | 2018-09-17 | 2019-02-01 | 青岛海信医疗设备股份有限公司 | A kind of method and apparatus of determining organ and tumor contact area |
| CN109801272A (en) * | 2019-01-07 | 2019-05-24 | 华南师范大学 | Liver neoplasm divides localization method, system and storage medium automatically |
| CN109934832A (en) * | 2019-03-25 | 2019-06-25 | 北京理工大学 | Liver neoplasm dividing method and device based on deep learning |
| CN110533676A (en) * | 2019-09-06 | 2019-12-03 | 青岛海信医疗设备股份有限公司 | Tumor image dividing method, device and terminal device |
-
2019
- 2019-12-05 CN CN201911233953.1A patent/CN111047567A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104637056A (en) * | 2015-02-02 | 2015-05-20 | 复旦大学 | Method for segmenting adrenal tumor of medical CT (computed tomography) image based on sparse representation |
| CN205068971U (en) * | 2015-11-04 | 2016-03-02 | 南方医科大学 | A phantom for evaluating belly CT image registration precision |
| CN108596887A (en) * | 2018-04-17 | 2018-09-28 | 湖南科技大学 | A kind of abdominal CT sequence image liver neoplasm automatic division method |
| CN108618844A (en) * | 2018-04-19 | 2018-10-09 | 北京工业大学 | Air navigation aid is punctured in a kind of CT guiding liver tumour radio-frequency ablation procedure |
| CN109035197A (en) * | 2018-05-31 | 2018-12-18 | 东南大学 | CT contrastographic picture tumor of kidney dividing method and system based on Three dimensional convolution neural network |
| CN109300088A (en) * | 2018-09-17 | 2019-02-01 | 青岛海信医疗设备股份有限公司 | A kind of method and apparatus of determining organ and tumor contact area |
| CN109801272A (en) * | 2019-01-07 | 2019-05-24 | 华南师范大学 | Liver neoplasm divides localization method, system and storage medium automatically |
| CN109934832A (en) * | 2019-03-25 | 2019-06-25 | 北京理工大学 | Liver neoplasm dividing method and device based on deep learning |
| CN110533676A (en) * | 2019-09-06 | 2019-12-03 | 青岛海信医疗设备股份有限公司 | Tumor image dividing method, device and terminal device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023197752A1 (en) * | 2022-04-13 | 2023-10-19 | 中南大学湘雅医院 | Margin path generation method and system for tumor surgery, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709917B (en) | Neural network model training method, device and system | |
| CN110276411B (en) | Image classification method, device, equipment, storage medium and medical electronic equipment | |
| CN109389592B (en) | Method, device and system for calculating coronary artery calcification score | |
| US8369585B2 (en) | Automatic classification of information in images | |
| CN109716445B (en) | Similar case image search program, similar case image search device, and similar case image search method | |
| US9779505B2 (en) | Medical data processing apparatus and method | |
| US10303965B2 (en) | Defective pixel identification using machine learning | |
| CN109003269A (en) | A kind of mark extracting method for the medical image lesion that can improve doctor's efficiency | |
| EP3722996A2 (en) | Systems and methods for processing 3d anatomical volumes based on localization of 2d slices thereof | |
| US20230298759A1 (en) | Information processing apparatus, information processing method, and program | |
| CN112348819A (en) | Model training method, image processing and registering method, and related device and equipment | |
| US9538920B2 (en) | Standalone annotations of axial-view spine images | |
| CN111047567A (en) | Kidney tumor picture determination method and related device | |
| US20180068436A1 (en) | Multiple algorithm lesion segmentation | |
| CN110766682A (en) | Pulmonary tuberculosis positioning screening device and computer equipment | |
| Heuberger et al. | Lung CT segmentation for image retrieval using the Insight Toolkit (ITK) | |
| CN111477289A (en) | Method and device for storing and reading detection report | |
| CN113469963A (en) | Pulmonary artery image segmentation method and device | |
| CN113140291A (en) | Image segmentation method and device, model training method and electronic equipment | |
| CN112365512A (en) | Method for training image segmentation model, method for image segmentation and device thereof | |
| CN109767468B (en) | Visceral volume detection method and device | |
| WO2020226925A1 (en) | Apparatus for tomography repeat rate/reject rate capture | |
| CN113838557A (en) | Medical image three-dimensional reconstruction simulation method and system | |
| CN113255760A (en) | Method for training image processing model, method and device for image processing | |
| CN111513673B (en) | Image-based growth state monitoring method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200421 |
|
| RJ01 | Rejection of invention patent application after publication |