CN108932973A - A kind of kidney case digitlization information management system and management method, terminal - Google Patents
A kind of kidney case digitlization information management system and management method, terminal Download PDFInfo
- Publication number
- CN108932973A CN108932973A CN201810827631.9A CN201810827631A CN108932973A CN 108932973 A CN108932973 A CN 108932973A CN 201810827631 A CN201810827631 A CN 201810827631A CN 108932973 A CN108932973 A CN 108932973A
- Authority
- CN
- China
- Prior art keywords
- image
- data
- module
- cluster head
- patient
- 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
- 210000003734 kidney Anatomy 0.000 title claims abstract description 44
- 238000007726 management method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 70
- 238000001514 detection method Methods 0.000 claims abstract description 44
- 102000013127 Vimentin Human genes 0.000 claims abstract description 35
- 108010065472 Vimentin Proteins 0.000 claims abstract description 35
- 210000005048 vimentin Anatomy 0.000 claims abstract description 35
- 238000003709 image segmentation Methods 0.000 claims abstract description 17
- 230000011218 segmentation Effects 0.000 claims abstract description 15
- 238000010827 pathological analysis Methods 0.000 claims abstract description 13
- 206010038389 Renal cancer Diseases 0.000 claims abstract description 11
- 210000001519 tissue Anatomy 0.000 claims abstract description 11
- 238000003745 diagnosis Methods 0.000 claims abstract description 10
- 241000854291 Dianthus carthusianorum Species 0.000 claims description 63
- 206010028980 Neoplasm Diseases 0.000 claims description 46
- 238000001914 filtration Methods 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 24
- 239000000243 solution Substances 0.000 claims description 24
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 21
- 210000004027 cell Anatomy 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 18
- 238000013459 approach Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 15
- 239000012153 distilled water Substances 0.000 claims description 12
- 230000001575 pathological effect Effects 0.000 claims description 12
- 230000007170 pathology Effects 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 208000008839 Kidney Neoplasms Diseases 0.000 claims description 9
- 238000007598 dipping method Methods 0.000 claims description 9
- 238000011010 flushing procedure Methods 0.000 claims description 9
- 201000010982 kidney cancer Diseases 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 7
- 239000000427 antigen Substances 0.000 claims description 6
- 102000036639 antigens Human genes 0.000 claims description 6
- 108091007433 antigens Proteins 0.000 claims description 6
- 239000000872 buffer Substances 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- CTQNGGLPUBDAKN-UHFFFAOYSA-N O-Xylene Chemical compound CC1=CC=CC=C1C CTQNGGLPUBDAKN-UHFFFAOYSA-N 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005265 energy consumption Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- WZUVPPKBWHMQCE-XJKSGUPXSA-N (+)-haematoxylin Chemical compound C12=CC(O)=C(O)C=C2C[C@]2(O)[C@H]1C1=CC=C(O)C(O)=C1OC2 WZUVPPKBWHMQCE-XJKSGUPXSA-N 0.000 claims description 3
- VHUUQVKOLVNVRT-UHFFFAOYSA-N Ammonium hydroxide Chemical compound [NH4+].[OH-] VHUUQVKOLVNVRT-UHFFFAOYSA-N 0.000 claims description 3
- WZUVPPKBWHMQCE-UHFFFAOYSA-N Haematoxylin Natural products C12=CC(O)=C(O)C=C2CC2(O)C1C1=CC=C(O)C(O)=C1OC2 WZUVPPKBWHMQCE-UHFFFAOYSA-N 0.000 claims description 3
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 claims description 3
- 241001062009 Indigofera Species 0.000 claims description 3
- 239000000908 ammonium hydroxide Substances 0.000 claims description 3
- 238000009835 boiling Methods 0.000 claims description 3
- 239000007979 citrate buffer Substances 0.000 claims description 3
- 229960000935 dehydrated alcohol Drugs 0.000 claims description 3
- 230000018044 dehydration Effects 0.000 claims description 3
- 238000006297 dehydration reaction Methods 0.000 claims description 3
- 239000008367 deionised water Substances 0.000 claims description 3
- 229910021641 deionized water Inorganic materials 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims description 3
- 238000001035 drying Methods 0.000 claims description 3
- 229960004756 ethanol Drugs 0.000 claims description 3
- 239000003292 glue Substances 0.000 claims description 3
- 238000010438 heat treatment Methods 0.000 claims description 3
- 238000007654 immersion Methods 0.000 claims description 3
- 238000011534 incubation Methods 0.000 claims description 3
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000002156 mixing Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 239000007921 spray Substances 0.000 claims description 3
- 238000010186 staining Methods 0.000 claims description 3
- 229910001220 stainless steel Inorganic materials 0.000 claims description 3
- 239000010935 stainless steel Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 claims description 2
- 238000005192 partition Methods 0.000 claims description 2
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 claims 2
- KRKNYBCHXYNGOX-UHFFFAOYSA-K Citrate Chemical compound [O-]C(=O)CC(O)(CC([O-])=O)C([O-])=O KRKNYBCHXYNGOX-UHFFFAOYSA-K 0.000 claims 1
- 238000009415 formwork Methods 0.000 claims 1
- 238000009738 saturating Methods 0.000 claims 1
- 208000006265 Renal cell carcinoma Diseases 0.000 abstract description 11
- 238000005516 engineering process Methods 0.000 abstract description 6
- 201000010099 disease Diseases 0.000 abstract description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 4
- 239000000463 material Substances 0.000 abstract description 3
- 238000002224 dissection Methods 0.000 abstract description 2
- 238000011897 real-time detection Methods 0.000 abstract description 2
- 201000010174 renal carcinoma Diseases 0.000 abstract description 2
- 238000001356 surgical procedure Methods 0.000 abstract description 2
- YXFVVABEGXRONW-UHFFFAOYSA-N Toluene Chemical compound CC1=CC=CC=C1 YXFVVABEGXRONW-UHFFFAOYSA-N 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 201000011510 cancer Diseases 0.000 description 3
- 210000005239 tubule Anatomy 0.000 description 3
- 235000005979 Citrus limon Nutrition 0.000 description 2
- 244000131522 Citrus pyriformis Species 0.000 description 2
- 208000030808 Clear cell renal carcinoma Diseases 0.000 description 2
- 230000001919 adrenal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- XNGIFLGASWRNHJ-UHFFFAOYSA-L phthalate(2-) Chemical compound [O-]C(=O)C1=CC=CC=C1C([O-])=O XNGIFLGASWRNHJ-UHFFFAOYSA-L 0.000 description 2
- 208000015347 renal cell adenocarcinoma Diseases 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 239000008096 xylene Substances 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 208000009060 clear cell adenocarcinoma Diseases 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 210000003360 nephrocyte Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 208000026830 renal pelvis benign neoplasm Diseases 0.000 description 1
- 201000008946 renal pelvis neoplasm Diseases 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- 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
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to field of medical technology, a kind of kidney case digitlization information management system and management method, terminal are disclosed, it includes: patient information acquisition module, vimentin detection module, image capture module, central processing module, image segmentation module, pathological analysis module, data update module, display module that kidney case, which digitizes information management system,.The present invention, which does not have to materials renal carcinoma tissue by vimentin detection module, can be detected patients with renal cell carcinoma Vimentin situation, the technology belong to it is minimally invasive or even noninvasive, and being capable of real-time detection；It is carried out simultaneously by image segmentation module by computer, the workload that doctor delineates by hand can be greatly reduced, while avoiding delineating bring error by hand.Important dissection and physiologic parameters needed for the result of segmentation will be used to obtain related disease diagnosis and surgery planning, to improve the efficiency and accuracy of medical diagnosis on disease and treatment.
Description
Technical field
The invention belongs to field of medical technology more particularly to a kind of kidney case digitlization information management system and managers
Method, terminal.
Background technique
Currently, the prior art commonly used in the trade is such that
Kidney is initiated by the malignant tumour image of kidney essence uriniferous tubule epithelial systems, and academic noun full name is nephrocyte
Cancer, also known as Grawitz's tumor, referred to as kidney.Including originating from the various clear-cell carcinoma hypotypes of uriniferous tubule different parts, but do not wrap
Include the tumor image and tumor of renal pelvis image from renal interstitial.Early in 1883, German virologist Grawitz was according to aobvious
It sees that cancer cell form is similar to adrenal cells under micro mirror, proposes that kidney is that the adrenal tissue origin remained in kidney is learned
It says, kidney is known as Grawitz tumor or hypernephroma in the books before state's reform and opening-up still.Until nineteen sixty just by
Oberling is according to the observation of electron microscope as a result, proximal convoluted tubule of the proposition kidney originating from kidney, just corrects for this mistake.
Surgical indication is lacked for part or there are the patients with renal cell carcinoma of surgical contraindication (such as advanced renal cell cancer patient) however, clinical at present,
Since tumor image tissue can not be cut off, fine needle puncture tissue be easy to cause tumor image to send out again, vimentin status assessment
It becomes difficult；Manual interaction is needed to the image segmentation of tumor image acquisition simultaneously；The image data of acquisition to noise-sensitive, therefore
Accurate segmentation is more difficult；Image processing time is long, it is difficult to meet clinical requirement.
In conclusion problem of the existing technology is:
It is clinical at present that for part shortage surgical indication or there are the patients with renal cell carcinoma of surgical contraindication, (such as advanced renal cell cancer is suffered from
Person), since tumor image tissue can not be cut off, fine needle puncture tissue be easy to cause tumor image to send out again, vimentin state
Assessment becomes difficult；Manual interaction is needed to the image segmentation of tumor image acquisition simultaneously；The image data of acquisition is quick to noise
Sense, therefore accurate segmentation is more difficult；Image processing time is long, it is difficult to meet clinical requirement.
The information collection of the prior art, image procossing performance is poor, and accurate foundation cannot be provided for medicine.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of kidney case digitlization information management system and pipes
Reason method, terminal.
The invention is realized in this way a kind of kidney case digitizes approaches to IM, the kidney case digitlization
Approaches to IM includes:
Patient basis and clinical examination data are acquired by patient information acquisition module；In wireless sensor network area
In domain, the integrated wireless sensor network node of several identical patient information acquisition modules is shed at random, and will be at data
Reason is centrally disposed on the center in wireless sensor network region；Wherein, data processing centre is for initiating query task and receiving
The data that the cluster head of target area transmits；According to mixing energy saving distributed clustering algorithm for wireless sensor network node sub-clustering pipe
Reason；
Data processing centre initiates query task to multiple target areas, and the cluster head in each target area passes through first
AFTQCK algorithm calculates the query task in the case where meeting quality of service requirement, and the mean free error time is made to reach maximization
Optimum redundancy degree；
Cluster head in each target area sends data to data processing centre using the optimum redundancy degree calculated；?
To patient basis and clinical examination data information；
Patient's vimentin status data information is detected by vimentin detection module；
Patient's renal cancer tumor image data are acquired by image capture module；The shadow integrated by image capture module
As collector obtains patient's renal cancer tumor image data to be evaluated；
Image gray processing, for convenience of the edge extracting of image, R, G, B using RGB image in Digital Image Processing are each
Color image is converted gray level image by the pixel value in channel and the transformational relation of gray level image pixel value, and formula is as follows:
Gray=R*0.3+G*0.59+B*0.11；
Edge extraction is carried out, the Roberts operator edge detection technical role in digital image processing method is utilized
The edge of image is obtained in gray level image, different detective operators have different edge detection templates, according to specific template meter
The difference of calculation intersection pixel is as follows using model as current pixel value:
E (i, j)=| F (i, j)-F (i+1, j+1) |+| F (i+1, j)-F (i, j+1) |；
Central processing module is by image segmentation module to the automatic Fast Segmentation of tumor image pathological image；
Patient's pathology is analyzed according to the data of detection by pathological analysis module；
By data update module according to patient's detection case, aftertreatment and inspection result, doctor is and guided in real time more
New diagnosis and treatment scheme policies；
Pass through the data information and image information of display patient's detection.
Further, the method managed wireless sensor network node sub-clustering according to energy saving distributed clustering algorithm is mixed
Are as follows:
Initial cluster head is screened in each wireless sensor network node；
Cluster head in target area broadcasts cluster head message, and cluster head of the non-leader cluster node into target area issues request plus cluster
Message, the cluster head received in the target area for adding cluster message allow to add cluster message to non-leader cluster node transmission；
The smallest reachable cluster head of non-cluster-head node selection communication cost is as its cluster head；
The data processing centre initiates query task to multiple target areas, and the cluster head in each target area is logical first
It crosses AFTQCK algorithm and calculates the query task in the case where meeting quality of service requirement, and the mean free error time is made to reach maximum
In the optimum redundancy degree of change,
If the cluster head in each target area is (m by the optimum redundancy degree that AFTQC algorithm calculates query tasks,
mp), wherein msIndicate source node redundancy, mpIndicate path redundancy degree；Obtain optimum redundancy degree (ms,mp) method are as follows:
It calculates once by msCluster head data reporting of a general sensor nodes into its target area, then the cluster head passes through
Cross mpThe probability R of road through being transmitted to the successful inquiring of data processing centre's transmission dataq；
It is P by the probability of k cluster head response of the t times query requirementt(k), the average probability R of the t times successful inquiring is obtainedQ
(t)；
It calculates once by msCluster head data reporting of a general sensor nodes into its target area, then the cluster head passes through
Cross mpRoad is through the energy consumption E to data processing centre's transmission dataq；
It is P by the probability of k cluster head response of the t times query requirementt(k), the mean consumption energy of the t times inquiry consumption is obtained
Measure EQ(t)；
Calculate the ENERGY E of each sub-clustering consumptionclustering；
For different (ms,mp), corresponding MTTF is calculated, is recorded so that MTTF maximum (ms, mp) it is best superfluous
The calculation formula of remaining, MTTF is as follows:
In formula, λq=1 time/min is query rate, Ethreshold=0 is energy threshold, Tclustering∈ [5-20] sec is
Sub-clustering interval；
Cluster head in each target area utilizes the optimum redundancy degree (m calculateds,mp) to data processing centre
Send data, comprising:
Cluster head in each target area randomly chooses msGeneral sensor nodes in a cluster, it is desirable that commonly passed in each cluster
Sensor node is to its data reporting, and then cluster head is based on voting mechanism and handles msThe data that a general sensor nodes transmit, house
Abandon can not letter data, and can not the corresponding general sensor nodes of letter data be denoted as malicious node, finally trust data is taken
Average value obtains final data；
Cluster head in each target area selects m according to multipath multi tate Routing ProtocolpThe disjoint arrival data of item
The path of processing center, and carry out the transmission of data.
Further,
After Edge extraction, also needs to carry out image procossing, gray level image is filtered using high pass/low pass filter
Processing traverses each picture of image using Filtering Template using 3*3 mean filter with the reference picture for constructing image to be evaluated
Template center is placed in current pixel every time by element, and the average value of all pixels is newly worth as current pixel using in template, and template is such as
Under:
Image border statistical information calculates, and respective edge grayscale information before and after image filtering is calculated separately, before filtering processing
Image F statistical information to be evaluated be sum_orig, reference picture F2 statistical information after filtering processing is sum_filter, tool
Body calculation formula is as follows:
Wherein, w1 and w2 is according to the weight set with a distance from center pixel, w1=1, w2=1/3；
Image blur index calculates, and the ratio for the image filtering front and rear edges grey-level statistics that step 5 is obtained is made
For fuzziness index, for convenience of evaluating, taking biggish is denominator, and lesser is molecule, keeps the value between (0,1)；
A corresponding fuzziness indication range [min, max] is obtained according to the DMOS range of the best visual effect, specifically
Are as follows:
It obtains fuzziness adjusting range, utilizes 174 panel heights in the ambiguity evaluation method evaluation LIVE2 in above-mentioned steps
This blurred picture calculates their own ambiguity evaluation value, is then established using fitting tool plot (value, DMOS)
Mapping relations between evaluation of estimate value and DMOS obtain corresponding one according to the corresponding DMOS range of the best visual effect
Fuzzy evaluation value range [min, max]；
Image blur adjustment, it is very big according to variation before and after determining image filtering if image blur index is less than min,
Original image excessively sharpens, then is filtered adjustment using low-pass filter；If more than max, determine to change very before and after image filtering
Small, original image is excessively fuzzy, then adjustment is filtered using high-pass filter, to reach more preferably visual effect；
It obtains final image and the image blur evaluation index, and shows on the display module.
Further, vimentin detection method includes:
(1) circulating tumor image cell block thin layer slice is subjected to dewaxing and aquation according to the following steps in staining jar:
Xylene solution impregnates 3 times, every time 10 minutes；Ethanol solution impregnates 3 times, every time 5 minutes；95% alcohol solution dipping 5
Minute；85% alcohol solution dipping 5 minutes；75% alcohol solution dipping 5 minutes；Distilled water immersion 2 times, every time 3 minutes；PH=
7.4 PBS impregnates 3 times, every time 3 minutes；
(2) tissue antigen is repaired using citrate buffer solution high temperature and pressure antigen retrieval method: takes pH=6.0 lemon
In pressure cooker, the histotomy after the aquation that dewaxes is placed in resistance to phthalate buffer 800-1500ml by high fire heating until boiling
In high temperature stainless steel slide holding frame, it is put into the buffer to have boiled, pot cover continues to be heated to spray vapour and starts timing, after 1-2 minutes,
Pressure cooker leaves heat source, is cooled to room temperature, and takes out slide, twice with distilled water flushing first, uses the PBS of pH=7.2-7.4 later
It rinses twice, each 3 minutes every time；
(3) 3%H2O2 deionized water is incubated for 5 minutes, and to block endogenous peroxydase, PBS is rinsed 3 times, every time 2 points
Clock；
(4) vimentin primary antibody is added dropwise, room temperature or 37 DEG C are stayed overnight for incubation 1-2 hours or 4 DEG C, and PBS is rinsed 3 times, every time 2 points
Clock；
(5) universal I gG antibody is added dropwise, room temperature or 37 DEG C are incubated for 15 minutes, and PBS is rinsed 3 times, every time 2 minutes；
(6) it develops the color using DAB solution: getting rid of PBS liquid, the DAB solution of every slice plus 2 drops or 100 μ l Fresh is shown
Micro- microscopic observation 3-10 minutes；
(7) distilled water flushing, redye, be dehydrated, transparent mounting: distilled water flushing 2 times, every time 3 minutes；Haematoxylin redyes 1
Minute；The differentiation of 0.1% hydrochloride alcohol；0.1% ammonium hydroxide returns indigo plant；50%, 70%, 85%, 95%, dehydrated alcohol dehydration and drying；Two
Toluene is transparent, resinene glue mounting；
(8) cell pathology expert diagosis, according to cell color deciding degree Vimentin situation.
Further, image partition method includes:
(1) tumor image classification based training, test database based on bag of words BoW model are established, texton dictionary is constructed, and
Train linear SVM LinearSVM model；
(2) it by tumor image pathological image to be split, is generated respectively from 1 times, 2 times, 4 times, 8 times, 16 times resolution ratio
Pathological image；
(3) RGB color histogram model and morphology closed operation is begun to use to obtain comprising tumour from 1 times of image in different resolution
The initial area-of-interest of image；
(4) on the basis of obtained primary segmentation result, step 3) is repeated, obtains updated area-of-interest, and lead to
The difference that bar formula distance calculates 2 area-of-interests is crossed to continue to repeat step (3), until difference is small if difference is greater than threshold value
The image in different resolution that doubles is jumped in threshold value, termination condition reaches threshold value or reaches 4 times of resolution ratio, the sense after being optimized
Interest region；
(5) after optimization in area-of-interest, the image of 200 × 200 pixel frames is selected in central area；
(6) cell detection is carried out to region selected by step (5) with convergence exponent filtering algorithm, if cell quantity is less than
Threshold value then jumps to high one layer of resolution ratio, continues to repeat step (5), (6)；Termination condition reaches threshold value, obtains BoW classification most
Good resolution ratio；
(7) after optimum resolution mapped optimization that step (6) determine in area-of-interest, according to length and width 200 ×
200 pixels are divided into several pieces of pictures, are filtered with MR8 filter to each block picture, obtain MR8 feature；
(8) on the basis of step (7), dimensionality reduction is carried out to image with accidental projection algorithm, obtains the MR8 feature of rarefaction；
(9) with after rarefaction MR8 feature and the obtained texton dictionary of step (1) carry out data encoding obtain it is new
Histogram feature；
(10) the LinearSVM model obtained with step 1) classifies to obtained histogram feature, filters out
Tumor image part in area-of-interest after optimization, is finally partitioned into tumor image.
Another object of the present invention is to provide a kind of calculating for realizing the kidney case digitlization approaches to IM
Machine program.
Another object of the present invention is to provide a kind of terminal, the terminal is realized described in Claims 1 to 5 any one
Kidney case digitizes approaches to IM.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation, so that computer executes the kidney case and digitizes approaches to IM.
Another object of the present invention is to provide a kind of kidneys for realizing the kidney case digitlization approaches to IM
Case digitizes information management system, and the kidney case digitlization information management system includes:
Patient information acquisition module, connect with central processing module, for acquiring patient basis and clinical examination money
Material；
Vimentin detection module, connect with central processing module, for detecting patient's vimentin status data information；
Image capture module is connect with central processing module, for acquiring patient's renal cancer tumor image data；
Central processing module, with patient information acquisition module, vimentin detection module, image capture module, image point
Module, pathological analysis module, data update module, display module connection are cut, is worked normally for controlling modules；
Image segmentation module is connect with central processing module, is used for the automatic Fast Segmentation of tumor image pathological image；
Pathological analysis module, connect with central processing module, for being analyzed according to the data of detection patient's pathology；
Data update module is connect with central processing module, for being tied according to patient's detection case, aftertreatment and inspection
Fruit and guides doctor's real-time update diagnosis and treatment scheme；
Display module is connect with central processing module, for showing the data information and image information of patient's detection.
Another object of the present invention is to provide a kind of kidney cases to digitize information management platform, the kidney case load
Word information management platform at least carries the kidney case digitlization information management system.
Advantages of the present invention and good effect are as follows:
The present invention, which does not have to materials renal carcinoma tissue by vimentin detection module, can be detected patients with renal cell carcinoma vimentin
Expression, the technology belong to it is minimally invasive or even noninvasive, and being capable of real-time detection；Clinical doctor is simulated by image segmentation module simultaneously
Raw operating habit, in low resolution, is grasped using adaptive multiresolution strategy by RGB color model and morphology
Make to obtain initial tumor interesting image regions, then initial area-of-interest is optimized by Pasteur's distance, it is therefore an objective to subtract
Few operand, improves efficiency；Cell detection is carried out to the image of different resolution by convergence exponent filtering algorithm again, when being greater than
Threshold value determines that the resolution ratio is best bag of words classification resolution ratio, and the high-resolution is arrived in the area-of-interest reflection after optimization
In image, dimensionality reduction is carried out to bag of words input feature vector by accidental projection, then by being encoded with bag of words dictionary texton
Histogram feature is generated, is classified finally by LinearSVM, is reached and tumor image tissue in area-of-interest is divided
It cuts.The present invention fully relies on computer progress, the workload that doctor delineates by hand can be greatly reduced, while avoiding manual hook
Draw bring error.Important dissection and life needed for the result of segmentation will be used to obtain related disease diagnosis and surgery planning
Parameter of science, to improve the efficiency and accuracy of medical diagnosis on disease and treatment.
The present invention carries out sub-clustering to node and has comprehensively considered many factors, these factors include network node range data
The factors such as the hop count of processing center DPC, the dump energy of node and node energy consumption, convenient for controlling the topological structure sum number of network
According to collection and transmission.
When the present invention collects data in cluster, give up the wrong data that malicious node transmits using voting mechanism, effectively
Improve the reliability of data.
The present invention is based on the transmission that optimum redundancy degree adaptively carries out data, are complying fully with wireless sensor communication spy
Under the premise of sign, without reference to conditions such as wire link, mobile nodes so that method of the invention can not improve it is logical
The acquisition performance of network data is improved under the premise of believing cost.
Picture appraisal of the invention is different from traditional evaluation method, and the present invention establishes special in image self structure to be evaluated
On the basis of point, from the angle of relative evaluation, the reference picture of image to be evaluated is constructed using filter, calculates variation front and back
The ratio of image border statistical information is as evaluation index；The principle of the present invention is simple, realizes the interior of image blur evaluation
Hold independence and real-time, fuzziness that can quick and precisely between any image of evaluation comparison.
Detailed description of the invention
Fig. 1 is kidney case digitlization information management system structural block diagram provided in an embodiment of the present invention.
In figure: 1, patient information acquisition module；2, vimentin detection module；3, image capture module；4, central processing
Module；5, image segmentation module；6, pathological analysis module；7, data update module；8, display module.
Fig. 2 is image segmentation module dividing method flow chart provided in an embodiment of the present invention.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, kidney case digitlization information management system provided by the invention includes: patient information acquisition module
1, vimentin detection module 2, image capture module 3, central processing module 4, image segmentation module 5, pathological analysis module 6,
Data update module 7, display module 8.
Patient information acquisition module 1 is connect, for acquiring patient basis and clinical examination with central processing module 4
Data；
Vimentin detection module 2 is connect with central processing module 4, for detecting patient's vimentin status number it is believed that
Breath；
Image capture module 3 is connect with central processing module 4, for acquiring patient's renal cancer tumor image data；
Central processing module 4, with patient information acquisition module 1, vimentin detection module 2, image capture module 3, figure
As segmentation module 5, pathological analysis module 6, data update module 7, the connection of display module 8, for controlling the normal work of modules
Make；
Image segmentation module 5 is connect with central processing module 4, is used for the automatic Fast Segmentation of tumor image pathological image；
Pathological analysis module 6 is connect with central processing module 4, for being divided according to the data of detection patient's pathology
Analysis；
Data update module 7 is connect with central processing module 4, for according to patient's detection case, aftertreatment and inspection
As a result, and guiding doctor's real-time update diagnosis and treatment scheme；
Display module 8 is connect with central processing module 4, for showing the data information and image information of patient's detection.
2 detection method of vimentin detection module provided by the invention is as follows:
(1) circulating tumor image cell block thin layer slice is subjected to dewaxing and aquation according to the following steps in staining jar:
Xylene solution impregnates 3 times, every time 10 minutes；Ethanol solution impregnates 3 times, every time 5 minutes；95% alcohol solution dipping 5
Minute；85% alcohol solution dipping 5 minutes；75% alcohol solution dipping 5 minutes；Distilled water immersion 2 times, every time 3 minutes；PH=
7.4 PBS impregnates 3 times, every time 3 minutes；
(2) tissue antigen is repaired using citrate buffer solution high temperature and pressure antigen retrieval method: takes pH=6.0 lemon
In pressure cooker, the histotomy after the aquation that dewaxes is placed in resistance to phthalate buffer 800-1500ml by high fire heating until boiling
In high temperature stainless steel slide holding frame, it is put into the buffer to have boiled, pot cover continues to be heated to spray vapour and starts timing, after 1-2 minutes,
Pressure cooker leaves heat source, is cooled to room temperature, and takes out slide, twice with distilled water flushing first, uses the PBS of pH=7.2-7.4 later
It rinses twice, each 3 minutes every time；
(3) 3%H2O2 deionized water is incubated for 5 minutes, and to block endogenous peroxydase, PBS is rinsed 3 times, every time 2 points
Clock；
(4) vimentin primary antibody is added dropwise, room temperature or 37 DEG C are stayed overnight for incubation 1-2 hours or 4 DEG C, and PBS is rinsed 3 times, every time 2 points
Clock；
(5) universal I gG antibody is added dropwise, room temperature or 37 DEG C are incubated for 15 minutes, and PBS is rinsed 3 times, every time 2 minutes；
(6) it develops the color using DAB solution: getting rid of PBS liquid, the DAB solution of every slice plus 2 drops or 100 μ l Fresh is shown
Micro- microscopic observation 3-10 minutes；
(7) distilled water flushing, redye, be dehydrated, transparent mounting: distilled water flushing 2 times, every time 3 minutes；Haematoxylin redyes 1
Minute；The differentiation of 0.1% hydrochloride alcohol；0.1% ammonium hydroxide returns indigo plant；50%, 70%, 85%, 95%, dehydrated alcohol dehydration and drying；Two
Toluene is transparent, resinene glue mounting；
(8) cell pathology expert diagosis, according to cell color deciding degree Vimentin situation.
Such as Fig. 2, image segmentation module dividing method provided by the invention is as follows:
S101: establishing tumor image classification based training, test database based on bag of words BoW model, constructs texton dictionary,
And train linear SVM LinearSVM model；
S102: tumor image pathological image to be split is generated respectively from 1 times, 2 times, 4 times, 8 times, 16 times of resolution ratio
Pathological image；
S103: RGB color histogram model and morphology closed operation is begun to use to obtain comprising swollen from 1 times of image in different resolution
The initial area-of-interest of tumor image；
S104: on the basis of obtained primary segmentation result, repeating step 3), obtain updated area-of-interest, and
The difference that 2 area-of-interests are calculated by bar formula distance continues to repeat step S103, until difference if difference is greater than threshold value
The different threshold value that is less than jumps to the image in different resolution that doubles, and termination condition reaches threshold value or reaches 4 times of resolution ratio, after obtaining optimization
Area-of-interest；
S105: after optimization in area-of-interest, the image of 200 × 200 pixel frames is selected in central area；
S106: cell detection is carried out to region selected by step S105 with convergence exponent filtering algorithm, if cell quantity
Less than threshold value, then high one layer of resolution ratio is jumped to, continues to repeat step S105, S106；Termination condition reaches threshold value, obtains BoW
Classification optimum resolution；
S107: after the optimum resolution mapped optimization that step S106 is determined in area-of-interest, according to length and width 200
× 200 pixels are divided into several pieces of pictures, are filtered with MR8 filter to each block picture, obtain MR8 feature；
S108: on the basis of step S107, carrying out dimensionality reduction to image with accidental projection algorithm, and the MR8 for obtaining rarefaction is special
Sign；
S109: with after rarefaction MR8 feature and the obtained texton dictionary of step S101 carry out data encoding and obtain
New histogram feature；
S1010: the LinearSVM model obtained with step S101 classifies to obtained histogram feature, screening
Tumor image part in area-of-interest after optimization out, is finally partitioned into tumor image.
When the present invention manages, patient basis and clinical examination data are acquired by patient information acquisition module 1；Pass through
Vimentin detection module 2 detects patient's vimentin status data information；It is swollen that patient's kidney is acquired by image capture module 3
Tumor image data；Central processing module 4 is by image segmentation module 5 to the automatic Fast Segmentation of tumor image pathological image；
Patient's pathology is analyzed according to the data of detection by pathological analysis module 6；Then, pass through 7 basis of data update module
Patient's detection case, aftertreatment and inspection result and guide doctor's real-time update diagnosis and treatment scheme；Finally, passing through display patient
The data information and image information of detection.
Below with reference to concrete analysis, the invention will be further described.
Kidney case provided in an embodiment of the present invention digitizes approaches to IM, comprising:
Patient basis and clinical examination data are acquired by patient information acquisition module；In wireless sensor network area
In domain, the integrated wireless sensor network node of several identical patient information acquisition modules is shed at random, and will be at data
Reason is centrally disposed on the center in wireless sensor network region；Wherein, data processing centre is for initiating query task and receiving
The data that the cluster head of target area transmits；According to mixing energy saving distributed clustering algorithm for wireless sensor network node sub-clustering pipe
Reason；
Data processing centre initiates query task to multiple target areas, and the cluster head in each target area passes through first
AFTQCK algorithm calculates the query task in the case where meeting quality of service requirement, and the mean free error time is made to reach maximization
Optimum redundancy degree；
Cluster head in each target area sends data to data processing centre using the optimum redundancy degree calculated；?
To patient basis and clinical examination data information；
Patient's vimentin status data information is detected by vimentin detection module；
Patient's renal cancer tumor image data are acquired by image capture module；The shadow integrated by image capture module
As collector obtains patient's renal cancer tumor image data to be evaluated；
Image gray processing, for convenience of the edge extracting of image, R, G, B using RGB image in Digital Image Processing are each
Color image is converted gray level image by the pixel value in channel and the transformational relation of gray level image pixel value, and formula is as follows:
Gray=R*0.3+G*0.59+B*0.11；
Edge extraction is carried out, the Roberts operator edge detection technical role in digital image processing method is utilized
The edge of image is obtained in gray level image, different detective operators have different edge detection templates, according to specific template meter
The difference of calculation intersection pixel is as follows using model as current pixel value:
E (i, j)=| F (i, j)-F (i+1, j+1) |+| F (i+1, j)-F (i, j+1) |；
Central processing module is by image segmentation module to the automatic Fast Segmentation of tumor image pathological image；
Patient's pathology is analyzed according to the data of detection by pathological analysis module；
By data update module according to patient's detection case, aftertreatment and inspection result, doctor is and guided in real time more
New diagnosis and treatment scheme policies；
Pass through the data information and image information of display patient's detection.
The method for managing wireless sensor network node sub-clustering according to energy saving distributed clustering algorithm is mixed are as follows:
Initial cluster head is screened in each wireless sensor network node；
Cluster head in target area broadcasts cluster head message, and cluster head of the non-leader cluster node into target area issues request plus cluster
Message, the cluster head received in the target area for adding cluster message allow to add cluster message to non-leader cluster node transmission；
The smallest reachable cluster head of non-cluster-head node selection communication cost is as its cluster head；
The data processing centre initiates query task to multiple target areas, and the cluster head in each target area is logical first
It crosses AFTQCK algorithm and calculates the query task in the case where meeting quality of service requirement, and the mean free error time is made to reach maximum
In the optimum redundancy degree of change,
If the cluster head in each target area is (m by the optimum redundancy degree that AFTQC algorithm calculates query tasks,
mp), wherein msIndicate source node redundancy, mpIndicate path redundancy degree；Obtain optimum redundancy degree (ms, mp) method are as follows:
It calculates once by msCluster head data reporting of a general sensor nodes into its target area, then the cluster head passes through
Cross mpThe probability R of road through being transmitted to the successful inquiring of data processing centre's transmission dataq；
It is P by the probability of k cluster head response of the t times query requirementt(k), the average probability R of the t times successful inquiring is obtainedQ
(t)；
It calculates once by msCluster head data reporting of a general sensor nodes into its target area, then the cluster head passes through
Cross mpRoad is through the energy consumption E to data processing centre's transmission dataq；
It is P by the probability of k cluster head response of the t times query requirementt(k), the mean consumption energy of the t times inquiry consumption is obtained
Measure EQ(t)；
Calculate the ENERGY E of each sub-clustering consumptionclustering；
For different (ms,mp), corresponding MTTF is calculated, is recorded so that the maximum (m of MTTFs,mp) it is best superfluous
The calculation formula of remaining, MTTF is as follows:
In formula, λq=1 time/min is query rate, Ethreshold=0 is energy threshold, Tclustering∈ [5-20] sec is
Sub-clustering interval；
Cluster head in each target area utilizes the optimum redundancy degree (m calculateds,mp) to data processing centre
Send data, comprising:
Cluster head in each target area randomly chooses msGeneral sensor nodes in a cluster, it is desirable that commonly passed in each cluster
Sensor node is to its data reporting, and then cluster head is based on voting mechanism and handles msThe data that a general sensor nodes transmit, house
Abandon can not letter data, and can not the corresponding general sensor nodes of letter data be denoted as malicious node, finally trust data is taken
Average value obtains final data；
Cluster head in each target area selects m according to multipath multi tate Routing ProtocolpThe disjoint arrival data of item
The path of processing center, and carry out the transmission of data.
After Edge extraction, also needs to carry out image procossing, gray level image is filtered using high pass/low pass filter
Processing traverses each picture of image using Filtering Template using 3*3 mean filter with the reference picture for constructing image to be evaluated
Template center is placed in current pixel every time by element, and the average value of all pixels is newly worth as current pixel using in template, and template is such as
Under:
Image border statistical information calculates, and respective edge grayscale information before and after image filtering is calculated separately, before filtering processing
Image F statistical information to be evaluated be sum_orig, reference picture F2 statistical information after filtering processing is sum_filter, tool
Body calculation formula is as follows:
Wherein, w1 and w2 is according to the weight set with a distance from center pixel, w1=1, w2=1/3；
Image blur index calculates, and the ratio for the image filtering front and rear edges grey-level statistics that step 5 is obtained is made
For fuzziness index, for convenience of evaluating, taking biggish is denominator, and lesser is molecule, keeps the value between (0,1)；
A corresponding fuzziness indication range [min, max] is obtained according to the DMOS range of the best visual effect, specifically
Are as follows:
It obtains fuzziness adjusting range, utilizes 174 panel heights in the ambiguity evaluation method evaluation LIVE2 in above-mentioned steps
This blurred picture calculates their own ambiguity evaluation value, is then established using fitting tool plot (value, DMOS)
Mapping relations between evaluation of estimate value and DMOS obtain corresponding one according to the corresponding DMOS range of the best visual effect
Fuzzy evaluation value range [min, max]；
Image blur adjustment, it is very big according to variation before and after determining image filtering if image blur index is less than min,
Original image excessively sharpens, then is filtered adjustment using low-pass filter；If more than max, determine to change very before and after image filtering
Small, original image is excessively fuzzy, then adjustment is filtered using high-pass filter, to reach more preferably visual effect；
It obtains final image and the image blur evaluation index, and shows on the display module.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid
State Disk (SSD)) etc..
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of kidney case digitizes approaches to IM, the kidney case digitlization approaches to IM includes:
Patient basis and clinical examination data are acquired by patient information acquisition module；In wireless sensor network region
It is interior, shed the integrated wireless sensor network node of several identical patient information acquisition modules at random, and by data processing
It is centrally disposed on the center in wireless sensor network region；Wherein, data processing centre is for initiating query task and receiving mesh
The data that the cluster head in mark region transmits；According to mixing energy saving distributed clustering algorithm for wireless sensor network node sub-clustering pipe
Reason；
Data processing centre initiates query task to multiple target areas, and the cluster head in each target area passes through AFTQCK first
Algorithm calculates the query task in the case where meeting quality of service requirement, and the mean free error time is made to reach maximized best
Redundancy；
Cluster head in each target area sends data to data processing centre using the optimum redundancy degree calculated；Suffered from
Person's essential information and clinical examination data information；
Patient's vimentin status data information is detected by vimentin detection module；
Patient's renal cancer tumor image data are acquired by image capture module；It is adopted by the image that image capture module integrates
Storage obtains patient's renal cancer tumor image data to be evaluated；
Image gray processing utilizes each channel R, G, B of RGB image in Digital Image Processing for convenience of the edge extracting of image
Pixel value and the transformational relation of gray level image pixel value convert gray level image for color image, formula is as follows:
Gray=R*0.3+G*0.59+B*0.11；
Edge extraction is carried out, using the Roberts operator edge detection technical role in digital image processing method in ash
The edge that image obtains image is spent, different detective operators have different edge detection templates, hand over according to specific formwork calculation
The difference of fork pixel is as follows using model as current pixel value:
E (i, j)=| F (i, j)-F (i+1, j+1) |+| F (i+1, j)-F (i, j+1) |；
Central processing module is by image segmentation module to the automatic Fast Segmentation of tumor image pathological image；
Patient's pathology is analyzed according to the data of detection by pathological analysis module；
By data update module according to patient's detection case, aftertreatment and inspection result, doctor's real-time update is and guided to examine
Treat scheme policies；
Pass through the data information and image information of display patient's detection.
2. kidney case as described in claim 1 digitizes approaches to IM, which is characterized in that
The method for managing wireless sensor network node sub-clustering according to energy saving distributed clustering algorithm is mixed are as follows:
Initial cluster head is screened in each wireless sensor network node；
Cluster head in target area broadcasts cluster head message, and cluster head of the non-leader cluster node into target area issues request plus cluster disappears
Breath, the cluster head received in the target area for adding cluster message allow to add cluster message to non-leader cluster node transmission；
The smallest reachable cluster head of non-cluster-head node selection communication cost is as its cluster head；
The data processing centre initiates query task to multiple target areas, and the cluster head in each target area passes through first
AFTQCK algorithm calculates the query task in the case where meeting quality of service requirement, and the mean free error time is made to reach maximization
Optimum redundancy degree in,
If the cluster head in each target area is (m by the optimum redundancy degree that AFTQC algorithm calculates query tasks,mp),
In, msIndicate source node redundancy, mpIndicate path redundancy degree；Obtain optimum redundancy degree (ms,mp) method are as follows:
It calculates once by msCluster head data reporting of a general sensor nodes into its target area, then the cluster head passes through mp
The probability R of road through being transmitted to the successful inquiring of data processing centre's transmission dataq；
It is P by the probability of k cluster head response of the t times query requirementt(k), the average probability R of the t times successful inquiring is obtainedQ(t)；
It calculates once by msCluster head data reporting of a general sensor nodes into its target area, then the cluster head passes through mp
Road is through the energy consumption E to data processing centre's transmission dataq；
It is P by the probability of k cluster head response of the t times query requirementt(k), the mean consumption ENERGY E of the t times inquiry consumption is obtainedQ
(t)；
Calculate the ENERGY E of each sub-clustering consumptionclustering；
For different (ms,mp), corresponding MTTF is calculated, is recorded so that the maximum (m of MTTFs,mp) it is optimum redundancy degree,
The calculation formula of MTTF is as follows:
In formula, λq=1 time/min is query rate, Ethreshold=0 is energy threshold, Tclustering∈ [5-20] sec is sub-clustering
Interval；
Cluster head in each target area utilizes the optimum redundancy degree (m calculateds,mp) sent to data processing centre
Data, comprising:
Cluster head in each target area randomly chooses msGeneral sensor nodes in a cluster, it is desirable that ordinary sensors in each cluster
Node is to its data reporting, and then cluster head is based on voting mechanism and handles msThe data that a general sensor nodes transmit, give up not
Trust data, and can not the corresponding general sensor nodes of letter data be denoted as malicious node, finally trust data is averaged
Value obtains final data；
Cluster head in each target area selects m according to multipath multi tate Routing ProtocolpThe disjoint arrival Data processing of item
The path of the heart, and carry out the transmission of data.
3. kidney case as described in claim 1 digitizes approaches to IM, which is characterized in that
After Edge extraction, also needs to carry out image procossing, gray level image is filtered using high pass/low pass filter
To construct the reference picture of image to be evaluated, using 3*3 mean filter, each pixel of image is traversed using Filtering Template, often
Secondary that template center is placed in current pixel, the average value of all pixels is newly worth as current pixel using in template, and template is as follows:
Image border statistical information calculates, and calculates separately before and after image filtering respectively edge grayscale information, before filtering processing to
Evaluation image F statistical information is sum_orig, and the reference picture F2 statistical information after filtering processing is sum_filter, specific to count
It is as follows to calculate formula:
Wherein, w1 and w2 is according to the weight set with a distance from center pixel, w1=1, w2=1/3；
Image blur index calculates, and the ratio for the image filtering front and rear edges grey-level statistics that step 5 is obtained is as mould
Paste degree index, for convenience of evaluating, taking biggish is denominator, and lesser is molecule, keeps the value between (0,1)；
A corresponding fuzziness indication range [min, max] is obtained according to the DMOS range of the best visual effect, specifically:
It obtains fuzziness adjusting range, utilizes 174 width Gaussian modes in the ambiguity evaluation method evaluation LIVE2 in above-mentioned steps
Image is pasted, their own ambiguity evaluation value is calculated, then establishes evaluation using fitting tool plot (value, DMOS)
Mapping relations between value value and DMOS show that corresponding one obscures according to the corresponding DMOS range of the best visual effect
Evaluation of estimate range [min, max]；
Image blur adjustment, if image blur index is less than min, according to very big, the original image of variation before and after judgement image filtering
As excessively sharpening, then adjustment is filtered using low-pass filter；If more than max, determine to vary less before and after image filtering, it is former
Image is excessively fuzzy, then adjustment is filtered using high-pass filter, to reach more preferably visual effect；
It obtains final image and the image blur evaluation index, and shows on the display module.
4. kidney case as described in claim 1 digitizes approaches to IM, which is characterized in that vimentin detection method packet
It includes:
(1) circulating tumor image cell block thin layer slice is subjected to dewaxing and aquation: diformazan according to the following steps in staining jar
Benzole soln impregnates 3 times, every time 10 minutes；Ethanol solution impregnates 3 times, every time 5 minutes；95% alcohol solution dipping 5 minutes；
85% alcohol solution dipping 5 minutes；75% alcohol solution dipping 5 minutes；Distilled water immersion 2 times, every time 3 minutes；PH=7.4's
PBS impregnates 3 times, every time 3 minutes；
(2) tissue antigen is repaired using citrate buffer solution high temperature and pressure antigen retrieval method: takes pH=6.0 citrate
For buffer 800-1500ml in pressure cooker, the histotomy after the aquation that dewaxes is placed in high temperature resistant until boiling by high fire heating
In stainless steel slide holding frame, it is put into the buffer to have boiled, pot cover continues to be heated to spray vapour and starts timing, after 1-2 minutes, pressure
Pot leaves heat source, is cooled to room temperature, and takes out slide, twice with distilled water flushing first, is rinsed later with the PBS of pH=7.2-7.4
Twice, each 3 minutes each；
(3) 3%H2O2 deionized water is incubated for 5 minutes, and to block endogenous peroxydase, PBS is rinsed 3 times, every time 2 minutes；
(4) vimentin primary antibody is added dropwise, room temperature or 37 DEG C are stayed overnight for incubation 1-2 hours or 4 DEG C, and PBS is rinsed 3 times, every time 2 minutes；
(5) universal I gG antibody is added dropwise, room temperature or 37 DEG C are incubated for 15 minutes, and PBS is rinsed 3 times, every time 2 minutes；
(6) it develops the color using DAB solution: getting rid of PBS liquid, the DAB solution of every slice plus 2 drops or 100 μ l Fresh, microscope
Lower observation 3-10 minutes；
(7) distilled water flushing, redye, be dehydrated, transparent mounting: distilled water flushing 2 times, every time 3 minutes；Haematoxylin is redyed 1 minute；
The differentiation of 0.1% hydrochloride alcohol；0.1% ammonium hydroxide returns indigo plant；50%, 70%, 85%, 95%, dehydrated alcohol dehydration and drying；Dimethylbenzene is saturating
It is bright, resinene glue mounting；
(8) cell pathology expert diagosis, according to cell color deciding degree Vimentin situation.
5. kidney case as described in claim 1 digitizes approaches to IM, which is characterized in that image partition method includes:
(1) tumor image classification based training, test database based on bag of words BoW model are established, texton dictionary, and training are constructed
Linear SVM LinearSVM model out；
(2) by tumor image pathological image to be split, the pathology from 1 times, 2 times, 4 times, 8 times, 16 times resolution ratio is generated respectively
Image；
(3) RGB color histogram model and morphology closed operation is begun to use to obtain comprising tumor image from 1 times of image in different resolution
Initial area-of-interest；
(4) on the basis of obtained primary segmentation result, repeat step 3), obtain updated area-of-interest, and by bar
Formula distance calculates the difference of 2 area-of-interests, if difference is greater than threshold value, continues to repeat step (3), until difference is less than threshold
Value jumps to the image in different resolution that doubles, and termination condition reaches threshold value or reaches 4 times of resolution ratio, interested after being optimized
Region；
(5) after optimization in area-of-interest, the image of 200 × 200 pixel frames is selected in central area；
(6) cell detection is carried out to region selected by step (5) with convergence exponent filtering algorithm, if cell quantity is less than threshold
Value, then jump to high one layer of resolution ratio, continues to repeat step (5), (6)；Termination condition reaches threshold value, and it is best to obtain BoW classification
Resolution ratio；
(7) after the optimum resolution mapped optimization that step (6) determine in area-of-interest, according to 200 × 200 picture of length and width
Element is divided into several pieces of pictures, is filtered with MR8 filter to each block picture, obtains MR8 feature；
(8) on the basis of step (7), dimensionality reduction is carried out to image with accidental projection algorithm, obtains the MR8 feature of rarefaction；
(9) with after rarefaction MR8 feature and the obtained texton dictionary of step (1) carry out data encoding and obtain new histogram
Figure feature；
(10) the LinearSVM model obtained with step 1) classifies to obtained histogram feature, filters out and is optimizing
Tumor image part in area-of-interest afterwards, is finally partitioned into tumor image.
6. a kind of computer program for realizing the digitlization approaches to IM of kidney case described in Claims 1 to 5 any one.
7. a kind of terminal, which is characterized in that the terminal realizes the digitlization of kidney case described in Claims 1 to 5 any one
Approaches to IM.
8. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires kidney case described in 1-5 any one to digitize approaches to IM.
9. a kind of kidney case digitlization information management for realizing the digitlization approaches to IM of kidney case described in claim 1
System, which is characterized in that the kidney case digitizes information management system and includes:
Patient information acquisition module, connect with central processing module, for acquiring patient basis and clinical examination data；
Vimentin detection module, connect with central processing module, for detecting patient's vimentin status data information；
Image capture module is connect with central processing module, for acquiring patient's renal cancer tumor image data；
Central processing module, with patient information acquisition module, vimentin detection module, image capture module, image segmentation mould
Block, pathological analysis module, data update module, display module connection, work normally for controlling modules；
Image segmentation module is connect with central processing module, is used for the automatic Fast Segmentation of tumor image pathological image；
Pathological analysis module, connect with central processing module, for being analyzed according to the data of detection patient's pathology；
Data update module is connect with central processing module, is used for according to patient's detection case, aftertreatment and inspection result,
And guide doctor's real-time update diagnosis and treatment scheme；
Display module is connect with central processing module, for showing the data information and image information of patient's detection.
10. a kind of kidney case digitizes information management platform, which is characterized in that the kidney case digitlization message tube pats
Platform at least carries the digitlization information management system of kidney case described in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810827631.9A CN108932973A (en) | 2018-07-25 | 2018-07-25 | A kind of kidney case digitlization information management system and management method, terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810827631.9A CN108932973A (en) | 2018-07-25 | 2018-07-25 | A kind of kidney case digitlization information management system and management method, terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108932973A true CN108932973A (en) | 2018-12-04 |
Family
ID=64444728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810827631.9A Pending CN108932973A (en) | 2018-07-25 | 2018-07-25 | A kind of kidney case digitlization information management system and management method, terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108932973A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685798A (en) * | 2018-12-26 | 2019-04-26 | 北京邮电大学 | A kind of method and device determining effective medical image |
| CN109785336A (en) * | 2018-12-18 | 2019-05-21 | 深圳先进技术研究院 | Image partition method and device based on multipath convolutional neural networks model |
| CN111462005A (en) * | 2020-03-30 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Method, apparatus, computer device and storage medium for processing microscopic image |
| CN112712878A (en) * | 2020-12-30 | 2021-04-27 | 四川桑瑞思环境技术工程有限公司 | Digital operating room system and control method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104202787A (en) * | 2014-09-10 | 2014-12-10 | 西安电子科技大学 | Optimum redundancy based adaptive wireless sensor network routing method |
| CN104200480A (en) * | 2014-09-17 | 2014-12-10 | 西安电子科技大学宁波信息技术研究院 | Image fuzzy degree evaluation method and system applied to intelligent terminal |
| CN104933711A (en) * | 2015-06-10 | 2015-09-23 | 南通大学 | Automatic fast segmenting method of tumor pathological image |
| CN105699657A (en) * | 2016-01-28 | 2016-06-22 | 山东省肿瘤防治研究院 | Detection method of peripheral blood Vimentin of renal cancer patient |
| CN106650229A (en) * | 2016-11-09 | 2017-05-10 | 中国人民解放军第二军医大学第二附属医院 | Kidney cancer case digitized information management system |
| CN108010003A (en) * | 2018-01-29 | 2018-05-08 | 佳木斯大学附属第医院 | A kind of computer based ear nose larynx auxiliary treatment checks control system |
-
2018
- 2018-07-25 CN CN201810827631.9A patent/CN108932973A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104202787A (en) * | 2014-09-10 | 2014-12-10 | 西安电子科技大学 | Optimum redundancy based adaptive wireless sensor network routing method |
| CN104200480A (en) * | 2014-09-17 | 2014-12-10 | 西安电子科技大学宁波信息技术研究院 | Image fuzzy degree evaluation method and system applied to intelligent terminal |
| CN104933711A (en) * | 2015-06-10 | 2015-09-23 | 南通大学 | Automatic fast segmenting method of tumor pathological image |
| CN105699657A (en) * | 2016-01-28 | 2016-06-22 | 山东省肿瘤防治研究院 | Detection method of peripheral blood Vimentin of renal cancer patient |
| CN106650229A (en) * | 2016-11-09 | 2017-05-10 | 中国人民解放军第二军医大学第二附属医院 | Kidney cancer case digitized information management system |
| CN108010003A (en) * | 2018-01-29 | 2018-05-08 | 佳木斯大学附属第医院 | A kind of computer based ear nose larynx auxiliary treatment checks control system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785336A (en) * | 2018-12-18 | 2019-05-21 | 深圳先进技术研究院 | Image partition method and device based on multipath convolutional neural networks model |
| CN109785336B (en) * | 2018-12-18 | 2020-11-27 | 深圳先进技术研究院 | Image segmentation method and device based on multipath convolutional neural network model |
| CN109685798A (en) * | 2018-12-26 | 2019-04-26 | 北京邮电大学 | A kind of method and device determining effective medical image |
| CN111462005A (en) * | 2020-03-30 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Method, apparatus, computer device and storage medium for processing microscopic image |
| CN112712878A (en) * | 2020-12-30 | 2021-04-27 | 四川桑瑞思环境技术工程有限公司 | Digital operating room system and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932973A (en) | A kind of kidney case digitlization information management system and management method, terminal | |
| CN109325942B (en) | Fundus image structure segmentation method based on full convolution neural network | |
| Bechar et al. | Semi-supervised superpixel classification for medical images segmentation: application to detection of glaucoma disease | |
| CN110136809A (en) | A kind of medical image processing method, device, electromedical equipment and storage medium | |
| CN107506770A (en) | Diabetic retinopathy eye-ground photography standard picture generation method | |
| CN109815888B (en) | Novel Pasteur staining method-based abnormal cervical cell automatic identification method | |
| Xu et al. | Look, investigate, and classify: a deep hybrid attention method for breast cancer classification | |
| CN108416379A (en) | Method and apparatus for handling cervical cell image | |
| KR102155381B1 (en) | Method, apparatus and software program for cervical cancer decision using image analysis of artificial intelligence based technology | |
| CN109758113B (en) | Retinopathy quantitative analysis system based on image recognition | |
| Xie et al. | Anisotropic path searching for automatic neuron reconstruction | |
| CN113261012B (en) | Method, device and system for processing image | |
| CN113724842B (en) | Cervical tissue pathology auxiliary diagnosis method based on attention mechanism | |
| CN104299242A (en) | Fluorescence angiography fundus image extraction method based on NGC-ACM | |
| CN105139390A (en) | Image processing method for detecting pulmonary tuberculosis focus in chest X-ray DR film | |
| CN112543934A (en) | Method for determining degree of abnormality, corresponding computer readable medium and distributed cancer analysis system | |
| CN116993736B (en) | Intelligent identification system for osteoporosis area | |
| CN111281387B (en) | Segmentation method and device for left atrium and atrial scar based on artificial neural network | |
| CN109087284A (en) | A kind of cardiovascular cannula Image-aided detection device and detection method | |
| KR20210033902A (en) | Method, apparatus and software program for cervical cancer diagnosis using image analysis of artificial intelligence based technology | |
| WO2023226217A1 (en) | Microsatellite instability prediction system and construction method therefor, terminal device, and medium | |
| CN114648509B (en) | Thyroid cancer detection system based on multi-classification task | |
| CN110428437A (en) | The GGO dividing method of SLIC and secondary Density Clustering based on edge sensitive | |
| Li et al. | A recognition method of urine cast based on deep learning | |
| CN109872307A (en) | Method, relevant device and the medium of lump in a kind of detection biological tissue images |
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 |