CN107465917A - A kind of Lossless Compression of medical image and the method for transmission - Google Patents
A kind of Lossless Compression of medical image and the method for transmission Download PDFInfo
- Publication number
- CN107465917A CN107465917A CN201710599255.8A CN201710599255A CN107465917A CN 107465917 A CN107465917 A CN 107465917A CN 201710599255 A CN201710599255 A CN 201710599255A CN 107465917 A CN107465917 A CN 107465917A
- Authority
- CN
- China
- Prior art keywords
- medical image
- image
- features space
- image features
- projection coordinate
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/103—Selection of coding mode or of prediction mode
- H04N19/114—Adapting the group of pictures [GOP] structure, e.g. number of B-frames between two anchor frames
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/136—Incoming video signal characteristics or properties
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/177—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a group of pictures [GOP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/30—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/42—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
Abstract
The present invention is applied to image processing field, there is provided a kind of Lossless Compression of medical image and the method for transmission, the treating method comprises following steps：Medical image features space storehouse is established, and is stored in input and receiving terminal；The medical image that equipment gathers is projected and obtains projection coordinate into input medical image features space storehouse；By the medical image of collection and projected image contrast generation error image, and receiving terminal will be sent to after error image and projection coordinate's coding compression；Restored map is generated by projection coordinate and error image after the receiving terminal decompression and shown.The medical image features space storehouse of the present invention（Or it is medical image knowledge base）Without transmission, reach and improve compression ratio, save bandwidth and improve the purpose of efficiency of transmission, and medical image features space storehouse reduces input picture and its error between the projected image of feature space, so as to improve compression ratio and efficiency of transmission by classification.
Description
Technical field
The invention belongs to image processing field, more particularly to a kind of Lossless Compression of medical image and the method for transmission.
Background technology
With the development of modern medicine, the more and more inspections dependent on medical image of diagnosis and treatment work of medical institutions, example
Such as, the medical image such as CT, MR, wherein its data volume of patient's run-down MR nuclear-magnetisms image are just often up to 200M even 1G.In order to
Improve the utilization rate of medical imaging device, more different types of image documentation equipments of hospital or image center usually continuous work simultaneously
Make, produce the view data of flood tide, this brings choosing for sternness to the remote diagnosis of the access of medical image, transmission and image
War.Especially low bandwidth or network peak period all bring challenge to the real-time Transmission of image and access.In order to save bandwidth, subtract
Few amount of storage and raising efficiency of transmission, while keep the information of medical image not lose, medical image can all be done at present lossless
Compression.In currently available technology, can only solve the optimization of the Lossless Compression to batch medical image, but can not solve this batch
The efficient lossless compression of image beyond spirogram picture, or can only solve the compression of single image, so between image can not be utilized
Correlation so as to reaching higher compression efficiency.
The content of the invention
It is an object of the invention to provide a kind of processing of the medical image of the medical image knowledge base based on typing ＆ grading
Method, it is intended to solve in currently available technology, can only solve the optimization of the Lossless Compression to batch medical image, but can not
Solve the efficient lossless compression of the image beyond the batch images, or can only solve the compression of single image, so can not utilize
The problem of correlation between image is so as to reach higher compression efficiency.
A kind of method that the present invention is achieved in that the Lossless Compression and transmission of medical image, the processing method bag
Include following steps：
A：Medical image features space storehouse is established, and is stored in input and receiving terminal；
B：The medical image that equipment gathers is projected and obtains projection coordinate into input medical image features space storehouse；
C：By the medical image of collection and projected image contrast generation error image, and by after error image and projection coordinate's compression
It is sent to receiving terminal；
D：The receiving terminal by projection coordinate after the data decompression of reception to obtaining projected image, then by error image and projection
Image merges generation medical image restored map and shown.
The present invention further technical scheme be：The step A comprises the following steps：
A1：By Medical Images Classification；
A2：The similar medical image is classified；
A3：By the medical image generation medical image features space at the same level；
A4：By the generation medical image features space storehouses in medical image features space at different levels；
A5：Medical image features space storehouse is stored in input and receiving terminal.
The present invention further technical scheme be：The step A3 is that the medical image at the same level is passed through into principal component point
Analysis, and dimensionality reduction, form the medical image features space.
The present invention further technical scheme be：The step B comprises the following steps：
B1：The header of input picture is analyzed, is obtained and the corresponding medical image features space of the input picture；
B2：Input picture is projected into the medical image features space, and obtains projection coordinate.
The present invention further technical scheme be：It is further comprising the steps of after the step B1：
B11：When not medical image features space corresponding with the input picture, then the medical image of upper level is looked for
Feature space；
B12：Using the input picture as sample image, the medical image features space of new rank is generated.
The present invention further technical scheme be：Also include step B13 after the step B12：By all new inputs
Image is accumulated in the medical image features space with its appropriate level as sample.
The present invention further technical scheme be：The accumulative upper limit of the step B13 is 1024.
The present invention further technical scheme be：The step C comprises the following steps：
C1：The projection coordinate of input picture medical image features space corresponding with the projection coordinate is multiplied, obtained
Projected image；
C2：The input picture and the projected image are subtracted each other, obtain Error Graph；
C3：The Error Graph and the projection coordinate are encoded, and sent to receiving terminal.
The present invention further technical scheme be：The algorithm encoded in the step C3 is：Run-length encoding, Huffman are compiled
Code, JPEG2000 Lossless Compressions or LZ77 dictionaries coding.
The present invention further technical scheme be：The step D comprises the following steps：
D1：Receiving terminal is decoded by decoder, obtains the Error Graph and the projection coordinate；
D2：Projection coordinate medical image features space corresponding with the projection coordinate is multiplied, obtains projected image；
D3：The projected image is added with the Error Graph, obtains restored map.
The beneficial effects of the invention are as follows：The medical image knowledge base of the present invention is present in image input and image receives
End, without transmission, compression ratio is improved, save bandwidth and improves the purpose of efficiency of transmission, and traditional Chinese medicine figure of the present invention so as to reach
As knowledge base by classification, i.e., be by universal class to particular type type thinning process, reduce input picture and its
Error between the projected image of feature space, so as to improve compression ratio and efficiency of transmission.
Brief description of the drawings
Fig. 1 is medical image transmission flow chart provided in an embodiment of the present invention；
Fig. 2 is input picture projection particular flow sheet provided in an embodiment of the present invention.
Embodiment
Flow diagram as shown in Figure 1, step of the invention is as described below,
Step S1：Classification, by medical image according to its definition be divided into it is different classes of, such as be divided into nuclear-magnetism medical image or X-ray doctor
Learn image.
Step S2：Classification, by medical image by thick class to subclass, and generates different grades of medical image features space,
Ranking score must be thinner, then input picture is smaller in the projection in the medical image features space of the type and artwork error, so as to reach
To high Lossless Compression rate and the purpose of low-bandwidth transmission efficiency, in the present invention by taking nuclear-magnetism medical image as an example, first level is figure
The position of picture, i.e. human brain；Its next stage subclass is that image obtains direction, i.e. sagittal plane（Sagital）；Its next stage again is thin
Class is the position of image in this direction, i.e. the first of the sequence；By that analogy, it is specific as shown in table 1.Different classes of doctor
Learn the grade divide of image can difference, such as nuclear-magnetism medical image is generally by being divided into six grades in table, and x-ray image is only divided into five
Level, but hierarchical subdivision can more reduce the error of projected image and artwork.
| Medical image typing ＆ grading | Image locations | Image obtains direction | Image is in the position of the direction | Device type | Image sequence type | Image obtains environment or parameter |
| Citing | Human brain | Sagittal plane（Sagital） | The 1st of the sequence | Nuclear-magnetism | T1 or T2（Structure chart or pathology figure）, or fat suppression image | Magnetic field intensity 1.5T |
Table 1
Step S3：Medical image features space is established, the medical image of same levels in some classification is passed through into principal component analysis
（Principal Component Analysis, PCA）, carry out dimensionality reduction, generation medical image features space.
Step S4：Medical image features space storehouse is established, the medical image features of each grade in each classification are empty
Between combine, medical image features space storehouse is created as, for preserving the characteristic information of sample medical image or being knowledge information.
Step S5：Projection coordinate is calculated, the header for analyzing input picture can be by finding in the storehouse of medical image features space
Corresponding medical image features space, medical image features space are made up of multiple vectors, and input picture is a vector, if defeated
It is vectorial I to enter image, and medical image features space is W1, W2, ... , Wm, pass through inner product of vectors formula：(a1, a2, a3,
... , an)*（b1, b2, b3, ... , bn）= a1*b1 + a2 * b2 + a3 * b3 + ... + an * bn, pass through
The projection with the corresponding medical image features space of the input picture is calculated（Or it is projected image）For x1*W1
+ x2*W2 + ... + xm*Wm, input picture is projected into the medical image features space, and obtain projection coordinate and be
（I*W1, I*W2, ... , I*Wm) = (x1, x2, ... , xm)。
Step S6：Calculation error figure, by the projection coordinate of input picture medical science figure corresponding with the projection coordinate
As feature space multiplication, projected image is obtained, the input picture and the projected image are subtracted each other, obtain Error Graph.
Step S7：Compression transmission, the Error Graph and the projection coordinate are encoded, the algorithm of coding is run-length encoding,
Huffman coding, JPEG2000 Lossless Compressions or LZ77 dictionaries coding, and send to receiving terminal.
Step S8：Restored image, receiving terminal are decoded by decoder, obtain the Error Graph and the projection is sat
Mark, projection coordinate medical image features space corresponding with the projection coordinate is multiplied, obtains projected image, by described in
Projected image is added with the Error Graph, obtains restored map.In Medical Image Compression data transmission procedure, medical image features
Space storehouse need not transmit.
Flow diagram as shown in Figure 2, step of the invention are as described below
Step N1：Projection coordinate, the header of input picture is analyzed, obtained and the corresponding medical image of the input picture
Feature space, input picture is projected into the medical image features space, and obtain projection coordinate.
Step N2：Projection is to the thick class of upper level, when medical image features not corresponding with the input picture are empty
Between when, then look for the medical image features space of upper level.
Step N3：The medical image features space of new rank is generated, using the input picture as sample image, generation is new
The medical image features space of rank.
Step N4：Accumulative sample medical image, accumulates new input picture as sample image, with dynamic generation, this is thin
Classification medical image features space, just no longer have accumulated when sample medical image has been accumulated to certain quantity, generally by this
Transformation is set to 1024.Sample image constitutive characteristic space after dimensionality reduction converts, this feature space can not include sample graph again
Picture or template image.
A kind of compression transmission device for being used to realize the inventive method, including input equipment, image access service device, reception
Equipment, display, compressor reducer and decompression machine, the input equipment connect the compressor reducer, and the compressor reducer connects described image
Access server, described image access server connect the decompression machine, and the decompression machine connects the receiving device, described to connect
Receiving unit connects the display, medical image features space storehouse be stored in respectively the input, the receiving terminal and
Described image access server, the compressor reducer and medical image features space storehouse can in same computer or equipment,
Can be in the different computers or equipment by network connection.Input picture and the compressor reducer in same computer or can be set
, also can be in the different computers or equipment by network connection in standby, the decompression machine can with medical image features space storehouse
, also can be in the different computers or equipment by network connection with same computer or equipment.The restored image with
The decompression machine can be in same computer or equipment, also can be in the different computers or equipment by network connection.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of Lossless Compression of medical image and the method for transmission, it is characterised in that the treating method comprises following steps：
A：Medical image features space storehouse is established, and is stored in input and receiving terminal;
B：The medical image that equipment gathers is projected and obtains projection coordinate into input medical image features space storehouse；
C：By the medical image of collection and projected image contrast generation error image, and compress the error image and project and sit
Mark, is sent to receiving terminal；
D：The receiving terminal by projection coordinate after the data decompression of reception to obtaining projected image, then by error image and projection
Image merges generation medical image restored map and shown.
2. according to the method for claim 1, it is characterised in that the step A comprises the following steps：
A1：By Medical Images Classification；
A2：The similar medical image is classified；
A3：By the template drawing generation medical image features space at the same level；
A4：By the generation medical image features space storehouses in medical image features space at different levels；
A5：Medical image features space storehouse is stored in input and receiving terminal.
3. according to the method for claim 2, it is characterised in that the step A3 is to pass through the medical image at the same level
Principal component analysis, and dimensionality reduction, form the medical image features space.
4. according to the method for claim 1, it is characterised in that the step B comprises the following steps：
B1：The header of input picture is analyzed, is obtained and the corresponding medical image features space of the input picture；
B2：Input picture is projected into the medical image features space, and obtains projection coordinate.
5. according to the method for claim 4, it is characterised in that the step B1 comprises the following steps：
B11：When not medical image features space corresponding with the input picture, then the medical image of upper level is looked for
Feature space；
B12：Using the input picture as sample image, the medical image features space of new rank is generated.
6. according to the method for claim 5, it is characterised in that also include step B13 after the step B12：Will be all
New input picture is accumulated in the medical image features space with its appropriate level as sample.
7. according to the method for claim 6, it is characterised in that the accumulative upper limit of the step B13 is 1024.
8. according to the method for claim 1, it is characterised in that the step C comprises the following steps：
C1：The projection coordinate of input picture medical image features space corresponding with the projection coordinate is multiplied, obtained
Projected image；
C2：The input picture and the projected image are subtracted each other, obtain Error Graph；
C3：The Error Graph and the projection coordinate are encoded, and sent to receiving terminal.
9. according to the method for claim 8, it is characterised in that the algorithm encoded in the step C3 is：Run-length encoding, suddenly
Fu Man codings, JPEG2000 Lossless Compressions or LZ77 dictionaries coding.
10. according to the method for claim 1, it is characterised in that the step D comprises the following steps：
D1：Receiving terminal is decoded by decoder, obtains the Error Graph and the projection coordinate；
D2：Projection coordinate medical image features space corresponding with the projection coordinate is multiplied, obtains projected image；
D3：The projected image is added with the Error Graph, obtains restored map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710599255.8A CN107465917B (en) | 2017-07-21 | 2017-07-21 | Lossless compression and transmission method for medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710599255.8A CN107465917B (en) | 2017-07-21 | 2017-07-21 | Lossless compression and transmission method for medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107465917A true CN107465917A (en) | 2017-12-12 |
| CN107465917B CN107465917B (en) | 2020-07-21 |
Family
ID=60543862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710599255.8A Active CN107465917B (en) | 2017-07-21 | 2017-07-21 | Lossless compression and transmission method for medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107465917B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109591012A (en) * | 2018-12-03 | 2019-04-09 | 深圳市越疆科技有限公司 | Reinforce learning method, robot and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104869425A (en) * | 2015-05-13 | 2015-08-26 | 信阳师范学院 | Compression and decompression method based on texture image similarity |
| CN104954786A (en) * | 2015-06-19 | 2015-09-30 | 武汉大学 | Periodic coding method of video satellite big data |
| US20170155900A1 (en) * | 2001-09-14 | 2017-06-01 | Dolby Laboratories Licensing Corporation | Adaptive Filtering Based Upon Boundary Strength |
-
2017
- 2017-07-21 CN CN201710599255.8A patent/CN107465917B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170155900A1 (en) * | 2001-09-14 | 2017-06-01 | Dolby Laboratories Licensing Corporation | Adaptive Filtering Based Upon Boundary Strength |
| CN104869425A (en) * | 2015-05-13 | 2015-08-26 | 信阳师范学院 | Compression and decompression method based on texture image similarity |
| CN104954786A (en) * | 2015-06-19 | 2015-09-30 | 武汉大学 | Periodic coding method of video satellite big data |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109591012A (en) * | 2018-12-03 | 2019-04-09 | 深圳市越疆科技有限公司 | Reinforce learning method, robot and storage medium |
| CN109591012B (en) * | 2018-12-03 | 2022-03-29 | 日照市越疆智能科技有限公司 | Reinforcement learning method, robot and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107465917B (en) | 2020-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wen et al. | A survey on nonconvex regularization-based sparse and low-rank recovery in signal processing, statistics, and machine learning | |
| Hosseini et al. | Medical ultrasound image compression using contextual vector quantization | |
| Dimililer | Backpropagation neural network implementation for medical image compression | |
| CN110222758A (en) | A kind of image processing method, device, equipment and storage medium | |
| WO2022151586A1 (en) | Adversarial registration method and apparatus, computer device and storage medium | |
| CN107465917A (en) | A kind of Lossless Compression of medical image and the method for transmission | |
| CN108742678B (en) | Image registration method and device and computer-readable storage medium | |
| Rahim et al. | Total variant based average sparsity model with reweighted analysis for compressive sensing of computed tomography | |
| Yang et al. | Low‐dose CT denoising with a high‐level feature refinement and dynamic convolution network | |
| Aldemir et al. | Reversible 3D compression of segmented medical volumes: usability analysis for teleradiology and storage | |
| Khashman et al. | Medical radiographs compression using neural networks and haar wavelet | |
| Lalitha et al. | Lossless and lossy compression of DICOM images with scalable ROI | |
| Pandey et al. | Optimum value of scale and threshold for compression of 99mTc-MDP bone scan images using Haar wavelet transform | |
| Akhtar et al. | Significance of ROI coding using MAXSHIFT scaling applied on MRI images in teleradiology-telemedicine | |
| CN107277528A (en) | Big image transmission optimization display methods | |
| Kotter et al. | Evaluation of lossy data compression of chest X-rays: a receiver operating characteristic study | |
| JP2014048884A (en) | Medical image storage device and medical image storage reference system | |
| Khawne et al. | Optimum watermark detection of ultrasonic echo medical images | |
| Huang et al. | Medical image denoising and compressing using discrete orthonormal S-transform | |
| Layek et al. | Center-emphasized gradient-feature based quality assessment method for screen content images | |
| Fahrni et al. | Three-dimensional adaptive image compression concept for medical imaging: application to computed tomography angiography for peripheral arteries | |
| Ali et al. | Significance of region of interest applied on MRI and CT images in teleradiology-telemedicine | |
| Kim et al. | Removing false contour artifact for bit-depth expansion | |
| Lin et al. | Contrast enhancement of x-ray image based on singular value selection | |
| CN112819761B (en) | Model training method, score determining method, device, equipment, medium and product |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200630 Address after: Room 1516, 15 / F, office area, block a and B (block a and B, east of Guangxi supporting engineering complex), No. 9 Gehai Road, Liangqing District, Nanning City, Guangxi Zhuang Autonomous Region Applicant after: Guangxi Academy of Mathematical Sciences Technology Co.,Ltd. Address before: 430034 Hubei province in Qiaokou District of Wuhan city Gutian four Road No. 49 concentric Health Industrial Park building A room 1341 Applicant before: WUHAN XINHAO HEALTH TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right |