CN108447046A - The detection method and device of lesion, equipment, computer readable storage medium - Google Patents
The detection method and device of lesion, equipment, computer readable storage medium Download PDFInfo
- Publication number
- CN108447046A CN108447046A CN201810115277.7A CN201810115277A CN108447046A CN 108447046 A CN108447046 A CN 108447046A CN 201810115277 A CN201810115277 A CN 201810115277A CN 108447046 A CN108447046 A CN 108447046A
- Authority
- CN
- China
- Prior art keywords
- area
- dimensional image
- detected
- lesion
- information
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- 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
- G06T2207/30096—Tumor; Lesion
Abstract
The invention discloses a kind of detection methods of lesion and device, equipment, computer readable storage medium.The detection method of the lesion includes:It detects and instructs in response to lesion, obtain at least one medical threedimensional images of tissue to be detected;Tissue signature's information of the tissue to be detected is obtained, and each medical threedimensional images are cut according to tissue signature's information, obtains at least one area three-dimensional image;Each area three-dimensional image is detected, the corresponding suspected abnormality location information of each area three-dimensional image is obtained;Classify to each area three-dimensional image, obtains the corresponding area classification information of each area three-dimensional image;According to each suspected abnormality location information and each area classification information, the lesions position information of the tissue to be detected is obtained.Using the present invention, the efficiency being detected to lesion and accuracy can be improved.
Description
Technical field
The present invention relates to the detection method and device of field of computer technology more particularly to a kind of lesion, equipment, computers
Readable storage medium storing program for executing.
Background technology
In medical procedure, the position of lesion is determined be medical diagnosis on disease important link.Lesion refers to tissue
Or organ causes the position of lesion by the effect of virulence factor, is the part that lesion occurs on body.For example, human lung
Certain a part destroyed by tulase, then this part is exactly pulmonary tuberculosis lesion.
Lesion can be divided into measurable lesion and immeasurability lesion.Wherein, measurable lesion refers at least at one
The lesion (being recorded as maximum gauge) that can be accurately measured on radial line, tumour maximum diameter answers >=20mm, spiral shell under the conditions of conventional detection
Tumour maximum diameter answers >=10mm when rotation CT detections.Immeasurability lesion refers to the lesion in addition to measurable lesion, conventional to examine
Tumour maximum diameter answers < 20mm under the conditions of survey, and tumour maximum diameter answers < 10mm when spiral CT detects, such as osteopathy stove spinal meninges lesion, inflammation
The abdominal mass and cystic lesion that property breast cancer lesion, skin or the angioleucitis of lung, imageological examination cannot be confirmed and be evaluated
Deng.
In the prior art, the judgement of immeasurability lesion is usually all realized by artificial naked eyes identification, is imitated
Rate is low.In addition, since immeasurability lesion volume is small, it is difficult to identify, and the energy of people is limited, recognition capability is largely
The problem of upper to depend on physical condition and clinical experience, therefore manual identified is susceptible to mistakes and omissions, to subsequent diagnosing and treating
It has adverse effect on, is also possible to that the health of patient can be influenced when serious.
Invention content
The embodiment of the present invention proposes a kind of detection method and device, equipment, computer readable storage medium of lesion, can
Improve the efficiency being detected to lesion and accuracy.
A kind of detection method of lesion provided in an embodiment of the present invention, specifically includes:
It detects and instructs in response to lesion, obtain at least one medical threedimensional images of tissue to be detected;
Tissue signature's information of the tissue to be detected is obtained, and according to tissue signature's information to each medicine
3-D view is cut, and at least one area three-dimensional image is obtained;
Each area three-dimensional image is detected, the corresponding suspected abnormality of each area three-dimensional image is obtained
Location information;
Classify to each area three-dimensional image, obtains the corresponding area classification of each area three-dimensional image
Information;
According to each suspected abnormality location information and each area classification information, the tissue to be detected is obtained
Lesions position information.
Further, it is instructed in described detected in response to lesion, obtains at least one medical 3 D figure of tissue to be detected
As after, the tissue signature's information for obtaining the tissue to be detected, and according to tissue signature's information to each described
Medical threedimensional images are cut, and before obtaining at least one area three-dimensional image, further include:
Denoising is carried out to each medical threedimensional images.
Further, in the tissue signature's information for obtaining the tissue to be detected, and believed according to the tissue signature
Breath cuts each medical threedimensional images, described to each described after obtaining at least one area three-dimensional image
Area three-dimensional image is detected, and before obtaining the corresponding suspected abnormality location information of each area three-dimensional image, is also wrapped
It includes:
Processing is amplified to each area three-dimensional image.
Further, in the tissue signature's information for obtaining the tissue to be detected, and believed according to the tissue signature
Breath cuts each medical threedimensional images, described to each described after obtaining at least one area three-dimensional image
Area three-dimensional image is detected, and before obtaining the corresponding suspected abnormality location information of each area three-dimensional image, is also wrapped
It includes:
Each area three-dimensional image is identified, the corresponding characteristics of image of each area three-dimensional image is obtained
Information;
According to each described image characteristic information, each area three-dimensional image is carried out at corresponding characteristic strengthening
Reason.
Further, the basis each suspected abnormality location information and each area classification information, acquisition
The lesions position information of the tissue to be detected, specifically includes:
According to each area classification information, unite to belonging to same category of all area three-dimensional images
Meter obtains the corresponding 3-D view sum of each area classification information;
According to each area classification information and each suspected abnormality location information, to belonging to same category of institute
There are all suspected abnormalities in the area three-dimensional image in same position to be counted, obtains each area classification information
Corresponding at least one suspected abnormality sum;
According to the ratio between each suspected abnormality sum and corresponding 3-D view sum, generate described to be detected
The lesions position information of tissue.
Further, each medical threedimensional images are made of at least one medicine two dimensional image.
Further, it is described it is to be detected be organized as human lung tissue;Then at least one area three-dimensional image includes
Upper lobe of left lung area three-dimensional image, lobe of left lung area three-dimensional image, superior lobe of right lung area three-dimensional image and inferior lobe of right lung region
3-D view.
Correspondingly, the embodiment of the present invention additionally provides a kind of detection device of lesion, specifically includes:
Medical threedimensional images obtain module, are instructed for being detected in response to lesion, obtain at least one of tissue to be detected
Medical threedimensional images;
Area three-dimensional image acquisition module, tissue signature's information for obtaining the tissue to be detected, and according to described
Tissue signature's information cuts each medical threedimensional images, obtains at least one area three-dimensional image;
Suspected abnormality position detecting module obtains each described for being detected to each area three-dimensional image
The corresponding suspected abnormality location information of area three-dimensional image;
Area three-dimensional image classification module obtains each described for classifying to each area three-dimensional image
The corresponding area classification information of area three-dimensional image;And
True lesion identification obtains module, for according to each suspected abnormality location information and each region class
Other information obtains the lesions position information of the tissue to be detected.
The embodiment of the present invention additionally provides a kind of equipment, specifically includes at least one processor and at least one processing
Device;
The memory, including it is stored at least one executable program therein;
The executable program by the processor when being executed so that the processor realizes lesion as described above
Detection method.
The embodiment of the present invention additionally provides a kind of computer readable storage medium, specifically includes the computer program of storage;
Wherein, equipment where controlling the computer readable storage medium when the computer program is run executes disease as described above
The detection method of stove.
Implement the embodiment of the present invention, has the advantages that:
The detection method and device of lesion provided in an embodiment of the present invention, equipment, computer readable storage medium, by right
The medical threedimensional images of tissue to be detected detect and identify automatically, obtain the corresponding lesions position letter of the tissue to be detected
Breath can be improved and be carried out to lesion so that the process for being detected and identifying to lesion is not necessarily to artificial interference and participation
The efficiency of detection and accuracy.
Description of the drawings
Fig. 1 is the flow diagram of a preferred embodiment of the detection method of lesion provided by the invention;
Fig. 2 is the structural schematic diagram of a preferred embodiment of the detection device of lesion provided by the invention;
Fig. 3 is the structural schematic diagram of a preferred embodiment of equipment provided by the invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, the flow diagram of a preferred embodiment for the detection method of lesion provided by the invention,
It is specific as follows including step S11 to S15:
S11:It detects and instructs in response to lesion, obtain at least one medical threedimensional images of tissue to be detected.
It should be noted that the embodiment of the present invention is executed by the system.Wherein, the system can be installed on mobile phone, tablet,
System in the terminal devices such as computer, or the system being installed in server.
Above-mentioned lesion detection instruction can be sent out by user by clicking some button or executing a certain trigger action,
It can at regular intervals or often be detected by system and be sent out when specific trigger event.
System obtains m initial medical threedimensional images, and by using dynamic after receiving above-mentioned lesion detection instruction
State threshold segmentation method carries out image segmentation respectively to every initial medical threedimensional images, to obtain m of tissue to be detected
Medical threedimensional images.Wherein, m >=1.Above-mentioned initial medical threedimensional images can be the CT graphics that acquisition is scanned to human body
Picture.
It is highly preferred that each medical threedimensional images are made of at least one medicine two dimensional image.
It should be noted that every above-mentioned medical threedimensional images can be made of n medicine two dimensional images.Wherein, n >=1.
Therefore, in the present embodiment, system actually obtains m*n medicine X-Y schemes when obtaining m medical threedimensional images
Picture.
It is understood that every medicine two dimensional image is the cross sectional image on above-mentioned tissue different location to be detected.
In another preferred embodiment, further include step before following step S12 after above-mentioned steps S11
S012, it is specific as follows:
S012:Denoising is carried out to each medical threedimensional images.
It should be noted that when in each medical threedimensional images including one or more medicine two dimensional image, it is practical
On be that denoising is carried out respectively to each medicine two dimensional image.
The present embodiment can be further increased and be detected to lesion by carrying out denoising to medical threedimensional images
Accuracy.
S12:Tissue signature's information of the tissue to be detected is obtained, and according to tissue signature's information to each described
Medical threedimensional images are cut, and at least one area three-dimensional image is obtained.
It should be noted that since tissue signature's information based on cutting is identical, system is to each medical 3 D
The cutting mode of image is identical.When in each medical threedimensional images including one or more medicine two dimensional image, actually
It is to be cut respectively to each medicine two dimensional image.
It is highly preferred that it is described it is to be detected be organized as human lung tissue;Then at least one area three-dimensional image includes
Upper lobe of left lung area three-dimensional image, lobe of left lung area three-dimensional image, superior lobe of right lung area three-dimensional image and inferior lobe of right lung region
3-D view.
In yet another preferred embodiment, further include step before following step S13 after above-mentioned steps S12
S023_1, it is specific as follows:
S023_1:Processing is amplified to each area three-dimensional image.
It should be noted that the amplification factor being amplified to area three-dimensional image when processing can be by system according to reality
Situation (e.g., screen size, screen resolution, operating personnel identification code etc.) be adaptively adjusted, can also be by operator
Member presets.When in each medical threedimensional images including one or more medicine two dimensional image, actually to each
Medicine two dimensional image is amplified processing respectively.
It is highly preferred that after above-mentioned steps S12, it, can also be including step S023_2 extremely before following step S13
S023_3, it is specific as follows:
S023_2:Each area three-dimensional image is identified, it is corresponding to obtain each area three-dimensional image
Image feature information.
S023_3:According to each described image characteristic information, corresponding feature is carried out to each area three-dimensional image
Intensive treatment.
It should be noted that features described above intensive treatment can be image enhancement processing, or at image binaryzation
Reason, can also be other feature intensive treatment.Wherein, image enhancement processing can pass through greyscale transformation algorithm, histogram equalization
Change the realizations such as algorithm;Image binaryzation processing can be by preset threshold value, and by each of above-mentioned zone 3-D view
The gray value that gray value is more than the pixel of the threshold value is set as 255, and each gray value is less than or equal to the picture of the threshold value
The gray value of vegetarian refreshments is set as 0 to realize.When in each medical threedimensional images including one or more medicine two dimensional image,
Characteristic strengthening processing is actually carried out respectively to each medicine two dimensional image.
It should be further noted that it is above-mentioned to area three-dimensional image be amplified processing and characteristic strengthening processing can tie
It closes and uses, can also be used separately, can be combined with the use of other image processing methods.Most preferably, above-mentioned steps S023_1
Execution sequence to S023_3 is S023_1 → S023_2 → S023_3.
The present embodiment can be further increased by being amplified processing, characteristic strengthening processing etc. to medical threedimensional images
The accuracy that lesion is detected.
S13:Each area three-dimensional image is detected, it is corresponding doubtful to obtain each area three-dimensional image
Lesions position information.
It should be noted that system is after obtaining each region 3-D view, to each region 3-D view respectively into
Row detection, to identify the suspected abnormality in each area three-dimensional image, and obtains the corresponding doubtful disease of each suspected abnormality
Stove location information.
S14:Classify to each area three-dimensional image, obtains the corresponding region of each area three-dimensional image
Classification information.
It should be noted that when it is above-mentioned it is to be detected be organized as human lung and organize when, can be under upper lobe of left lung, left lung
Leaf, superior lobe of right lung and inferior lobe of right lung are that standard classifies to each region 3-D view.
S15:According to each suspected abnormality location information and each area classification information, obtain described to be detected
The lesions position information of tissue.
Further, above-mentioned steps S15 may further include step S1501 to S1503, specific as follows:
S1501:According to each area classification information, to belong to same category of all area three-dimensional images into
Row statistics obtains the corresponding 3-D view sum of each area classification information.
It should be noted that when it is above-mentioned it is to be detected be organized as human lung and organize when, statistics belongs to upper lobe of left lung, a left side respectively
The number of lobi inferior, superior lobe of right lung and the area three-dimensional of inferior lobe of right lung image, to obtain the corresponding three-dimensional of upper lobe of left lung respectively
The corresponding 3-D view sum of total number of images, lobe of left lung, the corresponding 3-D view sum of superior lobe of right lung and inferior lobe of right lung correspond to
3-D view sum.
S1502:According to each area classification information and each suspected abnormality location information, to belonging to same class
All suspected abnormalities in other all area three-dimensional images in same position are counted, and each region class is obtained
The corresponding at least one suspected abnormality sum of other information.
It should be noted that when it is to be detected be organized as human lung and organize when, to belonging to the area three-dimensional figure of upper lobe of left lung
All suspected abnormalities as in same position are counted respectively, to obtain doubting corresponding to each lesions position information
Like lesion sum;And so on, it is total that each suspected abnormality belonged to corresponding to the area three-dimensional image of lobe of left lung is obtained respectively
Number belongs to each suspected abnormality sum corresponding to the area three-dimensional image of superior lobe of right lung and belongs to the area three-dimensional of inferior lobe of right lung
Each suspected abnormality sum corresponding to image.
S1503:According to the ratio between each suspected abnormality sum and corresponding 3-D view sum, described in generation
The lesions position information of tissue to be detected.
It should be noted that system after obtaining each suspected abnormality sum and each 3-D view sum, calculates respectively
Ratio between a suspected abnormality sum and corresponding 3-D view sum judges that the suspected abnormality is total if the ratio is more than α
The corresponding suspected abnormality of number is true lesion, and generates corresponding lesions position information, if the ratio is less than or equal to α,
Then judge that the suspected abnormality corresponding to the suspected abnormality sum is not true lesion, therefore ignores the suspected abnormality.And so on,
Obtain the lesions position information of all true lesions in above-mentioned tissue to be detected.
The detection method for the lesion that the embodiment of the present invention is provided passes through the medical threedimensional images progress to tissue to be detected
Automatic detection and identification obtain the corresponding lesions position information of the tissue to be detected, so that being detected and knowing to lesion
Other process is not necessarily to artificial interference and participation, can improve the efficiency being detected to lesion and accuracy.In addition, by adopting
The case where tissue to be detected is described, can really reflect tissue to be detected with medical threedimensional images and details, so as to
Enough further increase the accuracy being detected to lesion;Classified and distinguished by each region to medical threedimensional images
Processing so as to the detection of lesion can have specific aim and fining, therefore can also further increase to lesion into
The accuracy of row detection.
Correspondingly, the present invention also provides a kind of detection device of lesion, the inspection of the lesion in above-described embodiment can be realized
All flows of survey method.
As shown in Fig. 2, the structural schematic diagram of a preferred embodiment for the detection device of lesion provided by the invention,
It is specific as follows:
Medical threedimensional images obtain module 21, are instructed for being detected in response to lesion, obtain at least the one of tissue to be detected
A medical threedimensional images;
Area three-dimensional image acquisition module 22, tissue signature's information for obtaining the tissue to be detected, and according to institute
It states tissue signature's information to cut each medical threedimensional images, obtains at least one area three-dimensional image;
Suspected abnormality position detecting module 23 obtains each institute for being detected to each area three-dimensional image
State the corresponding suspected abnormality location information of area three-dimensional image;
Area three-dimensional image classification module 24 obtains each institute for classifying to each area three-dimensional image
State the corresponding area classification information of area three-dimensional image;And
True lesion identification obtains module 25, for according to each suspected abnormality location information and each region
Classification information obtains the lesions position information of the tissue to be detected.
Further, the detection device of the lesion further includes:
Image denoising processing module, for carrying out denoising to each medical threedimensional images.
Further, the detection device of the lesion further includes:
Image magnification processing module, for being amplified processing to each area three-dimensional image.
Further, the detection device of the lesion further includes:
Characteristics of image identification module obtains each region for each area three-dimensional image to be identified
The corresponding image feature information of 3-D view;And
Image intensification processing module is used for according to each described image characteristic information, to each area three-dimensional image
Carry out corresponding characteristic strengthening processing.
Further, the true lesion identification obtains module, specifically includes:
3-D view sum statistic unit, for each area classification information of basis, to belonging to same category of institute
There is the area three-dimensional image to be counted, obtains the corresponding 3-D view sum of each area classification information;
Suspected abnormality sum statistic unit, for according to each area classification information and each suspected abnormality position
Confidence ceases, and unites to belonging to all suspected abnormalities in same category of all area three-dimensional images in same position
Meter obtains the corresponding at least one suspected abnormality sum of each area classification information;And
Lesions position information generating unit, for according to each suspected abnormality sum and corresponding 3-D view sum
Between ratio, generate the lesions position information of the tissue to be detected.
Further, each medical threedimensional images are made of at least one medicine two dimensional image.
Further, it is described it is to be detected be organized as human lung tissue;Then at least one area three-dimensional image includes
Upper lobe of left lung area three-dimensional image, lobe of left lung area three-dimensional image, superior lobe of right lung area three-dimensional image and inferior lobe of right lung region
3-D view.
The detection device of lesion provided in an embodiment of the present invention is carried out certainly by the medical threedimensional images to tissue to be detected
Dynamic detection and identification obtain the corresponding lesions position information of the tissue to be detected, so that being detected and identifying to lesion
Process be not necessarily to artificial interference and participation, the efficiency being detected to lesion and accuracy can be improved.In addition, by using
The case where medical threedimensional images are described to tissue to be detected, can really reflect tissue to be detected and details, so as to
Further increase the accuracy being detected to lesion;By each region to medical threedimensional images classify and respectively locate
Reason so that can have specific aim and fining to the detection of lesion, therefore can also be further increased and be carried out to lesion
The accuracy of detection.
The present invention also provides a kind of equipment.
As shown in figure 3, for equipment provided by the invention a preferred embodiment structural schematic diagram, specifically include to
A few memory 31 and at least one processor 32;
The memory 31, including it is stored at least one executable program therein;
The executable program by the processor 32 when being executed so that the processor 32 realizes any implementation as above
The detection method of lesion described in example.
It should be noted that Fig. 3 only by the equipment a memory and a processor be connected for shown
Meaning can also be specific including multiple memories and/or multiple processors in the equipment in some specific embodiments
Number and connection type can need to be configured and be adaptively adjusted according to actual conditions.
Equipment provided in an embodiment of the present invention by the medical threedimensional images to tissue to be detected detect and know automatically
Not, the corresponding lesions position information of tissue to be detected is obtained, so that the process for being detected and identifying to lesion is not necessarily to
Artificial interference and participation, can improve the efficiency being detected to lesion and accuracy.In addition, by using medical 3 D figure
The case where as being described to tissue to be detected, can really reflect tissue to be detected and details, so as to further increase
The accuracy that lesion is detected;By each region to medical threedimensional images classify and handle respectively, to make
To the detection of lesion can have specific aim and fining, therefore can also further increase lesion is detected it is accurate
Degree.
The present invention also provides a kind of computer readable storage mediums, specifically include the computer program of storage, wherein
Equipment where controlling the computer readable storage medium when computer program operation executes described in any embodiment as above
Lesion detection method.
It should be noted that the present invention realizes all or part of flow in above-described embodiment method, meter can also be passed through
Calculation machine program is completed to instruct relevant hardware, and the computer program can be stored in a computer readable storage medium
In, the computer program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the calculating
Machine program includes computer program code, and the computer program code can be source code form, object identification code form, can hold
Style of writing part or certain intermediate forms etc..The computer-readable medium may include:The computer program code can be carried
Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disc, CD, computer storage, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunications letter
Number and software distribution medium etc..It should be further noted that the content that the computer-readable medium includes can basis
Legislation and the requirement of patent practice carry out increase and decrease appropriate in jurisdiction, such as in certain jurisdictions, according to legislation
And patent practice, computer-readable medium do not include electric carrier signal and telecommunication signal.
Computer readable storage medium provided in an embodiment of the present invention, by the medical threedimensional images to tissue to be detected into
The automatic detection of row and identification obtain the corresponding lesions position information of the tissue to be detected so that lesion is detected and
The process of identification is not necessarily to artificial interference and participation, can improve the efficiency being detected to lesion and accuracy.In addition, passing through
The case where tissue to be detected is described, can really reflect tissue to be detected using medical threedimensional images and details, to
The accuracy being detected to lesion can be further increased;Classified and divided by each region to medical threedimensional images
Other places are managed, so that can have specific aim and fining to the detection of lesion, therefore can also be further increased to lesion
The accuracy being detected.
The above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principle of the present invention, it can also make several improvements and retouch, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of detection method of lesion, which is characterized in that including:
It detects and instructs in response to lesion, obtain at least one medical threedimensional images of tissue to be detected;
Tissue signature's information of the tissue to be detected is obtained, and according to tissue signature's information to each medical 3 D
Image is cut, and at least one area three-dimensional image is obtained;
Each area three-dimensional image is detected, the corresponding suspected abnormality position of each area three-dimensional image is obtained
Information;
Classify to each area three-dimensional image, obtains the corresponding area classification letter of each area three-dimensional image
Breath;
According to each suspected abnormality location information and each area classification information, the disease of the tissue to be detected is obtained
Stove location information.
2. the detection method of lesion as described in claim 1, which is characterized in that instruct, obtain in described detected in response to lesion
After at least one medical threedimensional images for obtaining tissue to be detected, the tissue signature's information for obtaining the tissue to be detected,
And each medical threedimensional images are cut according to tissue signature's information, obtain at least one area three-dimensional image
Before, further include:
Denoising is carried out to each medical threedimensional images.
3. the detection method of lesion as described in claim 1, which is characterized in that in the group for obtaining the tissue to be detected
Characteristic information is knitted, and each medical threedimensional images are cut according to tissue signature's information, is obtained at least one
It is described that each area three-dimensional image is detected after area three-dimensional image, obtain each area three-dimensional image
Before corresponding suspected abnormality location information, further include:
Processing is amplified to each area three-dimensional image.
4. the detection method of lesion as described in claim 1, which is characterized in that in the group for obtaining the tissue to be detected
Characteristic information is knitted, and each medical threedimensional images are cut according to tissue signature's information, is obtained at least one
It is described that each area three-dimensional image is detected after area three-dimensional image, obtain each area three-dimensional image
Before corresponding suspected abnormality location information, further include:
Each area three-dimensional image is identified, the corresponding characteristics of image letter of each area three-dimensional image is obtained
Breath;
According to each described image characteristic information, corresponding characteristic strengthening processing is carried out to each area three-dimensional image.
5. the detection method of lesion as described in claim 1, which is characterized in that each suspected abnormality position of the basis
Information and each area classification information, obtain the lesions position information of the tissue to be detected, specifically include:
According to each area classification information, counts, obtain to belonging to same category of all area three-dimensional images
Obtain the corresponding 3-D view sum of each area classification information;
According to each area classification information and each suspected abnormality location information, to belonging to same category of all institutes
It states all suspected abnormalities in area three-dimensional image in same position to be counted, obtains each area classification information and correspond to
At least one suspected abnormality sum;
According to the ratio between each suspected abnormality sum and corresponding 3-D view sum, the tissue to be detected is generated
Lesions position information.
6. the detection method of the lesion as described in any one of claim 1 to 5, which is characterized in that each medical 3 D
Image is made of at least one medicine two dimensional image.
7. the detection method of the lesion as described in any one of claim 1 to 5, which is characterized in that described to be detected to be organized as
Human lung organizes;Then at least one area three-dimensional image includes upper lobe of left lung area three-dimensional image, lobe of left lung region
3-D view, superior lobe of right lung area three-dimensional image and inferior lobe of right lung area three-dimensional image.
8. a kind of detection device of lesion, which is characterized in that including:
Medical threedimensional images obtain module, are instructed for being detected in response to lesion, obtain at least one medicine of tissue to be detected
3-D view;
Area three-dimensional image acquisition module, tissue signature's information for obtaining the tissue to be detected, and according to the tissue
Characteristic information cuts each medical threedimensional images, obtains at least one area three-dimensional image;
Suspected abnormality position detecting module obtains each region for being detected to each area three-dimensional image
The corresponding suspected abnormality location information of 3-D view;
Area three-dimensional image classification module obtains each region for classifying to each area three-dimensional image
The corresponding area classification information of 3-D view;And
True lesion identification obtains module, for according to each suspected abnormality location information and each area classification letter
Breath obtains the lesions position information of the tissue to be detected.
9. a kind of equipment, which is characterized in that including at least one processor and at least one processor;
The memory, including it is stored at least one executable program therein;
The executable program by the processor when being executed so that the processor is realized as any in claim 1 to 7
The detection method of lesion described in.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program;Wherein, equipment where controlling the computer readable storage medium when the computer program is run is executed as weighed
Profit requires the detection method of the lesion described in any one of 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810115277.7A CN108447046B (en) | 2018-02-05 | 2018-02-05 | The detection method and device of lesion, computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810115277.7A CN108447046B (en) | 2018-02-05 | 2018-02-05 | The detection method and device of lesion, computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108447046A true CN108447046A (en) | 2018-08-24 |
CN108447046B CN108447046B (en) | 2019-07-26 |
Family
ID=63191896
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810115277.7A Active CN108447046B (en) | 2018-02-05 | 2018-02-05 | The detection method and device of lesion, computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108447046B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255782A (en) * | 2018-09-03 | 2019-01-22 | 图兮深维医疗科技(苏州)有限公司 | A kind of processing method, device, equipment and the storage medium of Lung neoplasm image |
CN110648311A (en) * | 2019-09-03 | 2020-01-03 | 南开大学 | Acne image focus segmentation and counting network model based on multitask learning |
CN111292301A (en) * | 2018-12-07 | 2020-06-16 | 北京市商汤科技开发有限公司 | Focus detection method, device, equipment and storage medium |
CN111339899A (en) * | 2020-02-21 | 2020-06-26 | 腾讯科技(深圳)有限公司 | Catheter feature acquisition method and device based on computer vision and intelligent microscope |
CN111539944A (en) * | 2020-04-28 | 2020-08-14 | 安徽科大讯飞医疗信息技术有限公司 | Lung focus statistical attribute acquisition method and device, electronic equipment and storage medium |
CN111667468A (en) * | 2020-05-28 | 2020-09-15 | 平安科技(深圳)有限公司 | OCT image focus detection method, device and medium based on neural network |
WO2021081839A1 (en) * | 2019-10-30 | 2021-05-06 | 未艾医疗技术(深圳)有限公司 | Vrds 4d-based method for analysis of condition of patient, and related products |
CN113344921A (en) * | 2021-08-04 | 2021-09-03 | 浙江太美医疗科技股份有限公司 | Image detection method and device, computer readable storage medium and electronic equipment |
US11348228B2 (en) | 2017-06-26 | 2022-05-31 | The Research Foundation For The State University Of New York | System, method, and computer-accessible medium for virtual pancreatography |
CN115578554A (en) * | 2021-06-21 | 2023-01-06 | 数坤(北京)网络科技股份有限公司 | Blood vessel focus identification method, device, electronic equipment and readable storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101727537A (en) * | 2009-11-16 | 2010-06-09 | 杭州电子科技大学 | Computer determining method of mammary gland CR image based on double visual angle information fusion |
CN103366183A (en) * | 2013-07-19 | 2013-10-23 | 南方医科大学 | Nonparametric automatic detection method of focal niduses |
CN105488781A (en) * | 2015-06-01 | 2016-04-13 | 深圳市第二人民医院 | Dividing method based on CT image liver tumor focus |
CN106504232A (en) * | 2016-10-14 | 2017-03-15 | 北京网医智捷科技有限公司 | A kind of pulmonary nodule automatic testing method based on 3D convolutional neural networks |
CN106530296A (en) * | 2016-11-07 | 2017-03-22 | 首都医科大学 | Lung detection method and device based on PET/CT image features |
CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
CN106780728A (en) * | 2017-02-28 | 2017-05-31 | 成都金盘电子科大多媒体技术有限公司 | A kind of single organ method for splitting and system based on medical image |
CN106887039A (en) * | 2017-02-28 | 2017-06-23 | 成都金盘电子科大多媒体技术有限公司 | The three-D imaging method and system of a kind of organ and focus based on medical image |
CN106940816A (en) * | 2017-03-22 | 2017-07-11 | 杭州健培科技有限公司 | Connect the CT image Lung neoplasm detecting systems of convolutional neural networks entirely based on 3D |
CN107480673A (en) * | 2017-06-30 | 2017-12-15 | 上海联影医疗科技有限公司 | Determine the method, apparatus and image editing system of area-of-interest in medical image |
CN107485446A (en) * | 2017-09-07 | 2017-12-19 | 安徽紫薇帝星数字科技有限公司 | It is a kind of can fast positioning belly operation guided positioning system |
CN107563983A (en) * | 2017-09-28 | 2018-01-09 | 上海联影医疗科技有限公司 | Image processing method and medical imaging devices |
-
2018
- 2018-02-05 CN CN201810115277.7A patent/CN108447046B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101727537A (en) * | 2009-11-16 | 2010-06-09 | 杭州电子科技大学 | Computer determining method of mammary gland CR image based on double visual angle information fusion |
CN103366183A (en) * | 2013-07-19 | 2013-10-23 | 南方医科大学 | Nonparametric automatic detection method of focal niduses |
CN105488781A (en) * | 2015-06-01 | 2016-04-13 | 深圳市第二人民医院 | Dividing method based on CT image liver tumor focus |
CN106504232A (en) * | 2016-10-14 | 2017-03-15 | 北京网医智捷科技有限公司 | A kind of pulmonary nodule automatic testing method based on 3D convolutional neural networks |
CN106530296A (en) * | 2016-11-07 | 2017-03-22 | 首都医科大学 | Lung detection method and device based on PET/CT image features |
CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
CN106780728A (en) * | 2017-02-28 | 2017-05-31 | 成都金盘电子科大多媒体技术有限公司 | A kind of single organ method for splitting and system based on medical image |
CN106887039A (en) * | 2017-02-28 | 2017-06-23 | 成都金盘电子科大多媒体技术有限公司 | The three-D imaging method and system of a kind of organ and focus based on medical image |
CN106940816A (en) * | 2017-03-22 | 2017-07-11 | 杭州健培科技有限公司 | Connect the CT image Lung neoplasm detecting systems of convolutional neural networks entirely based on 3D |
CN107480673A (en) * | 2017-06-30 | 2017-12-15 | 上海联影医疗科技有限公司 | Determine the method, apparatus and image editing system of area-of-interest in medical image |
CN107485446A (en) * | 2017-09-07 | 2017-12-19 | 安徽紫薇帝星数字科技有限公司 | It is a kind of can fast positioning belly operation guided positioning system |
CN107563983A (en) * | 2017-09-28 | 2018-01-09 | 上海联影医疗科技有限公司 | Image processing method and medical imaging devices |
Non-Patent Citations (2)
Title |
---|
DONIA BEN HASSEN 等: "Lesion Detection in Lung Regions that are Segmented Using Spatial Relations", 《2012 INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND E-SERVICES》 * |
MOHD FAZLI HASHIM 等: "Diabetic Retinopathy Lesion Detection using Region-based Approach", 《2014 8TH MALAYSIAN SOFTWARE ENGINEERING CONFERENCE(MYSEC)》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11348228B2 (en) | 2017-06-26 | 2022-05-31 | The Research Foundation For The State University Of New York | System, method, and computer-accessible medium for virtual pancreatography |
CN109255782A (en) * | 2018-09-03 | 2019-01-22 | 图兮深维医疗科技(苏州)有限公司 | A kind of processing method, device, equipment and the storage medium of Lung neoplasm image |
CN111292301A (en) * | 2018-12-07 | 2020-06-16 | 北京市商汤科技开发有限公司 | Focus detection method, device, equipment and storage medium |
CN110648311A (en) * | 2019-09-03 | 2020-01-03 | 南开大学 | Acne image focus segmentation and counting network model based on multitask learning |
WO2021081839A1 (en) * | 2019-10-30 | 2021-05-06 | 未艾医疗技术(深圳)有限公司 | Vrds 4d-based method for analysis of condition of patient, and related products |
CN111339899A (en) * | 2020-02-21 | 2020-06-26 | 腾讯科技(深圳)有限公司 | Catheter feature acquisition method and device based on computer vision and intelligent microscope |
CN111339899B (en) * | 2020-02-21 | 2020-12-22 | 腾讯科技(深圳)有限公司 | Catheter feature acquisition method, device, equipment, medium and intelligent microscope |
CN111539944A (en) * | 2020-04-28 | 2020-08-14 | 安徽科大讯飞医疗信息技术有限公司 | Lung focus statistical attribute acquisition method and device, electronic equipment and storage medium |
CN111539944B (en) * | 2020-04-28 | 2024-04-09 | 讯飞医疗科技股份有限公司 | Method, device, electronic equipment and storage medium for acquiring statistical attribute of lung focus |
CN111667468A (en) * | 2020-05-28 | 2020-09-15 | 平安科技(深圳)有限公司 | OCT image focus detection method, device and medium based on neural network |
CN115578554A (en) * | 2021-06-21 | 2023-01-06 | 数坤(北京)网络科技股份有限公司 | Blood vessel focus identification method, device, electronic equipment and readable storage medium |
CN115578554B (en) * | 2021-06-21 | 2024-02-02 | 数坤(上海)医疗科技有限公司 | Vascular focus identification method, device, electronic equipment and readable storage medium |
CN113344921A (en) * | 2021-08-04 | 2021-09-03 | 浙江太美医疗科技股份有限公司 | Image detection method and device, computer readable storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108447046B (en) | 2019-07-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108447046B (en) | The detection method and device of lesion, computer readable storage medium | |
US9317918B2 (en) | Apparatus, method, and computer program product for medical diagnostic imaging assistance | |
Gandomkar et al. | Visual search in breast imaging | |
US20120166211A1 (en) | Method and apparatus for aiding imaging diagnosis using medical image, and image diagnosis aiding system for performing the method | |
KR101768812B1 (en) | Computer intervened diagnosis system and program at pulmonary nodules in thoracic CT scans | |
JPH10503961A (en) | Automated method and apparatus for computerized detection of masses and parenchymal tissue deformation in medical images | |
Berbaum et al. | Role of faulty visual search in the satisfaction of search effect in chest radiography | |
CN105979872A (en) | Patient-specific analysis of positron emission tomography data | |
WO2021114638A1 (en) | Image processing method, apparatus, electronic device, and storage medium | |
EP3973539A1 (en) | System and method for interpretation of multiple medical images using deep learning | |
JP2020010805A (en) | Specification device, program, specification method, information processing device, and specifier | |
US20230206435A1 (en) | Artificial intelligence-based gastroscopy diagnosis supporting system and method for improving gastrointestinal disease detection rate | |
Raghavendra et al. | 2DSM vs FFDM: A computeraided diagnosis based comparative study for the early detection of breast cancer | |
Raja et al. | Lung segmentation and nodule detection in 3D medical images using convolution neural network | |
Gunasekaran | Leveraging object detection for the identification of lung cancer | |
Krupinski et al. | Comparison of eye position versus computer identified microcalcification clusters on mammograms | |
US20220036558A1 (en) | Method and system for predicting expression of biomarker from medical image | |
Zhang et al. | Key issues and specificities for the objective medical image quality assessment | |
JP7390666B2 (en) | Image processing method and system for detecting stomatognathic disease sites | |
US11928817B2 (en) | Method for filtering normal medical image, method for interpreting medical image, and computing device implementing the methods | |
CN116186575B (en) | Mammary gland sampling data processing method based on machine learning | |
CN114742836B (en) | Medical image processing method and device and computer equipment | |
Sanford* et al. | MP74-10 deep learning for semi-automated PIRADSV2 scoring on multiparametric prostate MRI | |
Nannapaneni et al. | Enhanced Image-based Histopathology Lung Cancer Detection | |
Yan et al. | The use of low-dose ct intra-and extra-nodular image texture features to improve small lung nodule diagnosis in lung cancer screening |
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 | ||
CP02 | Change in the address of a patent holder |
Address after: 519031 office 1316, No. 1, lianao Road, Hengqin new area, Zhuhai, Guangdong Patentee after: LONGMA ZHIXIN (ZHUHAI HENGQIN) TECHNOLOGY Co.,Ltd. Address before: 519031 room 417, building 20, creative Valley, Hengqin New District, Zhuhai City, Guangdong Province Patentee before: LONGMA ZHIXIN (ZHUHAI HENGQIN) TECHNOLOGY Co.,Ltd. |
|
CP02 | Change in the address of a patent holder |