CN109620288A - A kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method - Google Patents

A kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method Download PDF

Info

Publication number
CN109620288A
CN109620288A CN201910039680.0A CN201910039680A CN109620288A CN 109620288 A CN109620288 A CN 109620288A CN 201910039680 A CN201910039680 A CN 201910039680A CN 109620288 A CN109620288 A CN 109620288A
Authority
CN
China
Prior art keywords
image
module
ultrasonic diagnostic
department
diagnostic device
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
Application number
CN201910039680.0A
Other languages
Chinese (zh)
Inventor
王立坤
武雪亮
屈明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201910039680.0A priority Critical patent/CN109620288A/en
Publication of CN109620288A publication Critical patent/CN109620288A/en
Pending legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
    • A61B8/4411—Device being modular
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5207—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of raw data to produce diagnostic data, e.g. for generating an image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • 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
    • G06T2207/20081—Training; Learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Pathology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

The invention belongs to ultrasonic diagnostic technique fields, a kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method are disclosed, department of general surgery's abdominal ultrasonic diagnostic device and its application method system include: power supply module, image capture module, operation module, central control module, image conversion module, image segmentation module, image storage module, print module, display module.The present invention obtains the neural network parameter for ultrasound image conversion by training of the image conversion module to same object different frequency image contrast group, so that ultrasonic system formation speed is fast, image quality is high, and depth is big, high resolution, the small image of noise；Overcome the shortcomings of that traditional images dividing method is applied to ultrasound image defect intelligent scissor scene by image segmentation module simultaneously, with to ultrasound image strong noise complicated and changeable is insensitive, segmentation precision is high, robustness and generalization are strong, segmenting edge flatness is good, be conducive to medicine detection.

Description

A kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method
Technical field
The invention belongs to ultrasonic diagnostic technique field more particularly to a kind of department of general surgery's abdominal ultrasonic diagnostic device and its uses Method.
Background technique
Department of general surgery, that is, general surgery, there are also outside orthopaedics, neurosurgery, ambition in addition to department of general surgery for general general hospital's surgery Section, Urology Surgery etc..It is that main method treats liver that department of general surgery (Department of general surgery), which is to perform the operation, The clinical speciality of the Other diseases such as dirty, biliary tract, pancreas, stomach and intestine, anal intestine, vascular diseases, the tumour of thyroid gland and breast and wound, It is the maximum training of surgery system.Ultrasound diagnosis (ultrasonicdiagnosis) is that ultrasonic detecting technology is applied to human body, The data and form of physiology or institutional framework are understood by measurement, are found disease, are made a kind of diagnostic method of prompt.For curing Learn the ultrasonic wave of diagnosis, mainly pulse-echo technique, including A type, Type B, D type, M type, V-type etc..B-mode ultrasonography is application Most wide, the maximum ultrasonic examination of influence.This method is interface and group that each layer tissue is constituted in acoustic beam drawing-in human body Knit the reflective echo of interior structure, with the light and shade of luminous point react its power, by numerous spot arrangements it is orderly form corresponding section Image.However, the low frequency ultrasound picture noise of existing ultrasonic diagnostic equipment acquisition is big, picture quality is low；Meanwhile ultrasound is schemed Picture segmentation precision is poor, and flatness is poor, influences to diagnose.
In conclusion problem of the existing technology is:
(1) the low frequency ultrasound picture noise of existing ultrasonic diagnostic equipment acquisition is big, and picture quality is low；Meanwhile ultrasound is schemed Picture segmentation precision is poor, and flatness is poor, influences to diagnose.
(2) during acquiring abdomen image data by ultrasonic probe in the prior art, the image of acquisition be easy by The influence of shadow effect and noise at the boundary to detection zone reduces the accuracy of image acquisition.
(3) it during the abdomen image data for storing acquisition by memory in the prior art, needs to image data It is compressed, in compression process, image can be made to make image fault to a certain extent, reduce the clarity of image.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of department of general surgery's abdominal ultrasonic diagnostic device and its uses Method.
The invention is realized in this way a kind of department of general surgery's abdominal ultrasonic diagnostic device, department of general surgery's abdominal ultrasonic diagnosis Equipment includes:
Power supply module is connect with central control module, for being powered operation for department of general surgery's abdominal ultrasonic diagnostic device；
Image capture module is connect with central control module, for acquiring abdomen image data by ultrasonic probe；
Operation module is connect with central control module, for carrying out control behaviour to ultrasonic diagnostic equipment by keyboard Make；
Central control module, with power supply module, image capture module, operation module, image conversion module, image segmentation mould Block, image storage module, print module, display module connection, work normally for controlling modules by single-chip microcontroller；
Image conversion module is connect with central control module, turns low frequency ultrasound image for converting software by image It is changed to high frequency ultrasound image；
Image segmentation module is connect with central control module, for by image segmentation software by diagnostic ultrasound images into Row cutting operation；
Image storage module is connect with central control module, for the abdomen image data by memory storage acquisition；
Print module is connect with central control module, for being printed the abdomen images of acquisition by printer；
Display module is connect with central control module, for the abdominal ultrasonic diagnostic image by display display acquisition Data.
It is described another object of the present invention is to provide a kind of application method of department of general surgery's abdominal ultrasonic diagnostic device The application method of department of general surgery's abdominal ultrasonic diagnostic device includes:
The first step is powered for department of general surgery's abdominal ultrasonic diagnostic device；
Second step operates on keyboard, carries out control operation to ultrasonic diagnostic equipment, acquires abdomen image data；
Low frequency ultrasound image is converted to high frequency ultrasound image by processor, diagnostic ultrasound images is carried out by third step Segmentation；
4th step, the image data that processor has been handled save, using printer by the abdomen images of acquisition into Row printing；
5th step passes through the abdominal ultrasonic diagnostic image data using display display acquisition.
Further, abdomen image data is acquired by ultrasonic probe, using improved image acquisition algorithm, specific steps are such as Under:
Step 1, using ultrasonic wave extraction M frame raw RF data, wherein M=12；
Step 2 extracts envelope R (x, y) absolute value of RF data Hilbert transformation；
Step 3 obtains Nakagami-m image by N number of different window；M (x, y) is enabled to represent Nakagami-m shadow It rings, Mjl(x, y), Mj2(x, y), Mj3(x, y) ..., and MjN(x, y) respectively indicates the use of jth frame (<=12 j) initial data Side length size is the Nakagami-m that the sliding window of 1,2 to N times ultrasound pulse length obtains, to the WMC Nakagami- of j frame M influences；
Step 4, by image frames numbers J from 2 to M, step 2 and step 3, repetitive cycling obtain WM C Nakagami- M influences Mjm(x, y), M2m(x, y), M3m(x, y) ..., and MMm(x, y)；
Step 5, by ImgrComposograph is averaged by the WMC Nakagami-m image summation of the M frame in step 4 Value.
Further, pass through the abdomen image data of memory storage acquisition, using improved image compression algorithm, specific mistake Journey is as follows:
Image is exported three matrixes by the imread order in matlab, calculates the size of three matrixes by step 1；
Step 2, if the gray value of required point is x, for point aijIf its a (i-1) up and downj, a (i+1)j, ai (j-1), exist in 4 points of ai (j+1) but be not congruent to the point that gray value is x, then aijFor the boundary point for the figure that gray value is x, And the gray value of the point and coordinate are stored in array；
Step 3 repeats all the points that step 2 successively searches three matrixes, and according to corresponding coordinate in three matrixes Different gray values determine color and draw, and realize its recovery.
Further, image conversion method is as follows:
1) configuration Ultrasound Instrument carries out acquiring ultrasound image operation to abdomen；
2) the low frequency ultrasound image and high frequency ultrasound image of same position are acquired；
3) three-dimensional low-frequency ultrasound image is obtained, including c layers of two dimensional image, in the same position of each layer of two dimensional image Choose n image block；Wherein c, n are positive integers；
4) the low frequency ultrasound image includes c layers of two dimensional image, chooses n figure in the same position of each layer of two dimensional image As block；Wherein c, n are positive integers；
5) the n image block includes the first image block and n-1 other image blocks of same size, the first image Block is a part of the layer original two dimensional image, the n-1 other image blocks be centered on the first image block not It is obtained with larger range of original two dimensional image through down-sampling；
6) high frequency ultrasound image by the neural network in the c*n image block input channel c*n of selection, after output conversion；
7) neural network parameter is adjusted, the high frequency ultrasound image and the high frequency ultrasound image after the conversion for making the acquisition Average variance it is minimum.
Advantages of the present invention and good effect are as follows:
The present invention is obtained by training of the image conversion module to same object different frequency image contrast group for ultrasound The neural network parameter of image conversion, to realize that low frequency ultrasound image arrives high frequency ultrasound image using the neural network parameter Conversion.The conversion method is realized by GPU, can be improved each ultrasonic system collection image quality, so that ultrasound system Formation speed of uniting is fast, and image quality is high, and depth is big, high resolution, the small image of noise；Overcome simultaneously by image segmentation module Traditional images dividing method is applied to the deficiency of ultrasound image defect intelligent scissor scene, has complicated and changeable to ultrasound image Strong noise is insensitive, segmentation precision is high, robustness and generalization are strong, segmenting edge flatness is good, training dataset in very little In the case of the advantages that capable of also obtaining ideal segmentation effect, be conducive to medicine detection.
During image capture module acquires abdomen image data by ultrasonic probe in the present invention, in order to eliminate shade The influence of effect and noise at the boundary to detection zone improves the accuracy that image obtains, and is obtained and is calculated using a kind of improved image Method.
In the present invention during abdomen image data of the image storage module by memory storage acquisition, need to figure As data are compressed, in order to avoid making image fault to a certain extent, during simplifying algorithm, the clear of image is improved Clear degree, using a kind of improved image compression algorithm.
Detailed description of the invention
Fig. 1 is the application method flow chart of department of general surgery's abdominal ultrasonic diagnostic device provided in an embodiment of the present invention.
Fig. 2 is department of general surgery's abdominal ultrasonic diagnostic device structural schematic diagram provided in an embodiment of the present invention；
In Fig. 2: 1, power supply module；2, image capture module；3, operation module；4, central control module；5, image is converted Module；6, image segmentation module；7, image storage module；8, print module；9, display module.
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, department of general surgery's abdominal ultrasonic diagnostic device application method provided by the invention the following steps are included:
S101: firstly, being powered for department of general surgery's abdominal ultrasonic diagnostic device；
S102: operating on keyboard, carries out control operation to ultrasonic diagnostic equipment, acquires abdomen image data；
S103: low frequency ultrasound image is converted into high frequency ultrasound image by processor, diagnostic ultrasound images are divided It cuts；
S104: the image data that processor has been handled saves, and is carried out the abdomen images of acquisition using printer Printing；
S105: pass through the abdominal ultrasonic diagnostic image data using display display acquisition.
As shown in Fig. 2, department of general surgery's abdominal ultrasonic diagnostic device provided by the invention includes: power supply module 1, Image Acquisition mould Block 2, operation module 3, central control module 4, image conversion module 5, image segmentation module 6, image storage module 7, impression block Block 8, display module 9.
Power supply module 1 is connect with central control module 4, for being powered behaviour for department of general surgery's abdominal ultrasonic diagnostic device Make；
Image capture module 2 is connect with central control module 4, for acquiring abdomen image data by ultrasonic probe；
Operation module 3 is connect with central control module 4, for being controlled by keyboard ultrasonic diagnostic equipment Operation；
Central control module 4, with power supply module 1, image capture module 2, operation module 3, image conversion module 5, image Divide module 6, image storage module 7, print module 8, display module 9 to connect, for controlling modules just by single-chip microcontroller Often work；
Image conversion module 5 is connect with central control module 4, for converting software for low frequency ultrasound image by image Be converted to high frequency ultrasound image；
Image segmentation module 6 is connect with central control module 4, for passing through image segmentation software for diagnostic ultrasound images It is split operation；
Image storage module 7 is connect with central control module 4, for the abdomen images number by memory storage acquisition According to；
Print module 8 is connect with central control module 4, for being printed the abdomen images of acquisition by printer；
Display module 9 is connect with central control module 4, for the abdominal ultrasonic diagnostic graph by display display acquisition As data.
During described image acquisition module 2 acquires abdomen image data by ultrasonic probe, in order to eliminate shade effect Should influence with noise at the boundary to detection zone, improve the accuracy that image obtains, using a kind of improved image acquisition algorithm, Specific step is as follows:
Step 1, using ultrasonic wave extraction M frame raw RF data, wherein M=12；
Step 2 extracts envelope R (x, y) absolute value of RF data Hilbert transformation；
Step 3 obtains Nakagami-m image by N number of different window；M (x, y) is enabled to represent Nakagami-m shadow It rings, Mjl(x, y), Mj2(x, y), Mj3(x, y) ..., and MjN(x, y) respectively indicates the use of jth frame (<=12 j) initial data Side length size is the Nakagami-m that the sliding window of 1,2 to N times ultrasound pulse length obtains, to the WMC Nakagami- of j frame M influences；
Step 4, by image frames numbers J from 2 to M, step 2 and step 3, repetitive cycling obtain WMC Nakagami-m Influence Mlm(x, y), M2m(x, y), M3m(x, y) ..., and MMm(x, y)；
Imgr composograph is averaged by step 5 by the WMC Nakagami-m image summation of the M frame in step 4 Value.
During abdomen image data of the described image memory module 7 by memory storage acquisition, need to image Data are compressed, and in order to avoid making image fault to a certain extent, during simplifying algorithm, improve the clear of image Degree, using a kind of improved image compression algorithm, detailed process is as follows:
Image is exported three matrixes by the imread order in matlab, calculates the size of three matrixes by step 1；
Step 2, if the gray value of required point is x, for point aijIf its a (i1) up and downj, a (i+1)j, ai (j-1), exist in 4 points of ai (j+1) but be not congruent to the point that gray value is x, then aijFor the boundary point for the figure that gray value is x, And the gray value of the point and coordinate are stored in array；
Step 3 repeats all the points that step 2 successively searches three matrixes, and according to corresponding coordinate in three matrixes Different gray values determine color and draw, and realize its recovery.
5 conversion method of image conversion module provided by the invention is as follows:
1) configuration Ultrasound Instrument carries out acquiring ultrasound image operation to abdomen；
2) the low frequency ultrasound image and high frequency ultrasound image of same position are acquired；
3) three-dimensional low-frequency ultrasound image is obtained, including c layers of two dimensional image, in the same position of each layer of two dimensional image Choose n image block；Wherein c, n are positive integers；
4) the low frequency ultrasound image includes c layers of two dimensional image, chooses n figure in the same position of each layer of two dimensional image As block；Wherein c, n are positive integers；
5) the n image block includes the first image block and n-1 other image blocks of same size, the first image Block is a part of the layer original two dimensional image, the n-1 other image blocks be centered on the first image block not It is obtained with larger range of original two dimensional image through down-sampling；
6) high frequency ultrasound image by the neural network in the c*n image block input channel c*n of selection, after output conversion；
7) neural network parameter is adjusted, the high frequency ultrasound image and the high frequency ultrasound image after the conversion for making the acquisition Average variance it is minimum.
6 dividing method of image segmentation module provided by the invention is as follows:
(1) ultrasound image data collection is pre-processed, obtains pretreated data set；
(2) data enhancing is carried out to pretreated ultrasound data set, dilated data set scale obtains amplification data collection；
(3) amplification data collection is input in the full convolutional neural networks based on automatic context, in a manner of end to end Training pattern realizes the primary segmentation to amplification data collection；
(4) fining post-processing is carried out to ultrasound image primary segmentation result.
Step (1) provided by the invention includes: to be labeled first by multidigit technical staff to ultrasound image data collection, is taken Label of the average value that multidigit technical staff repeatedly marks as segmentation；Then to raw ultrasound image interception area-of-interest, Area-of-interest is filtered using two-sided filter and removes noise while retaining image edge information, to denoising As a result histogram equalization is carried out to enhance the contrast of image, and histogram equalization result is improved using average drifting filtering The uniformity of ultrasound image.
Step (1) provided by the invention specifically comprises the following steps:
A, it labels, comprising the following steps:
Technical staff's mark；It is divided into m days being carried out respectively between ultrasound data set by multidigit technical staff, m takes more than or equal to 2 Integer, multiple mark, m is setting value；
Determine label；Label of the average value for taking multidigit technical staff repeatedly to mark as segmentation；
B, image preprocessing, comprising the following steps:
Intercept area-of-interest；Interception includes complete defect area and defect area placed in the middle from raw ultrasound image Image, i.e. area-of-interest；
Bilateral filtering；Denoising is completed using two-sided filter to area-of-interest, obtains denoising image；
Histogram equalization；Histogram equalization is carried out to denoising image and obtains histogram equalization to enhance contrast Image；
Average drifting；Uniformity is improved using average drifting filter to the image of histogram equalization.
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 (5)

1. a kind of department of general surgery's abdominal ultrasonic diagnostic device, which is characterized in that department of general surgery's abdominal ultrasonic diagnostic device includes:
Power supply module is connect with central control module, for being powered operation for department of general surgery's abdominal ultrasonic diagnostic device；
Image capture module is connect with central control module, for acquiring abdomen image data by ultrasonic probe；
Operation module is connect with central control module, for carrying out control operation to ultrasonic diagnostic equipment by keyboard；
Central control module, with power supply module, image capture module, operation module, image conversion module, image segmentation module, Image storage module, print module, display module connection, work normally for controlling modules by single-chip microcontroller；
Image conversion module is connect with central control module, is converted to low frequency ultrasound image for converting software by image High frequency ultrasound image；
Image segmentation module is connect with central control module, for being divided diagnostic ultrasound images by image segmentation software Cut operation；
Image storage module is connect with central control module, for the abdomen image data by memory storage acquisition；
Print module is connect with central control module, for being printed the abdomen images of acquisition by printer；
Display module is connect with central control module, for the abdominal ultrasonic diagnostic image data by display display acquisition.
2. a kind of application method of department of general surgery's abdominal ultrasonic diagnostic device as described in claim 1, which is characterized in that described general outer The application method of section's abdominal ultrasonic diagnostic device includes:
The first step is powered for department of general surgery's abdominal ultrasonic diagnostic device；
Second step operates on keyboard, carries out control operation to ultrasonic diagnostic equipment, acquires abdomen image data；
Low frequency ultrasound image is converted to high frequency ultrasound image by processor, diagnostic ultrasound images is split by third step；
4th step, the image data that processor has been handled save, and are beaten the abdomen images of acquisition using printer Print；
5th step passes through the abdominal ultrasonic diagnostic image data using display display acquisition.
3. the application method of department of general surgery's abdominal ultrasonic diagnostic device as claimed in claim 2, which is characterized in that visited by ultrasound Head acquisition abdomen image data, using improved image acquisition algorithm, the specific steps are as follows:
Step 1, using ultrasonic wave extraction M frame raw RF data, wherein M=12；
Step 2 extracts envelope R (x, y) absolute value of RF data Hilbert transformation；
Step 3 obtains Nakagami-m image by N number of different window；M (x, y) is enabled to represent Nakagami-m influence, Mj1 (x, y), Mj2(x, y), Mj3(x, y) ..., and MjN(x, y) it is big using side length to respectively indicate jth frame (<=12 j) initial data Small is the Nakagami-m that the sliding window of 1,2 to N times ultrasound pulse length obtains, and is influenced on the WMC Nakagami-m of j frame；
Step 4, by image frames numbers j from 2 to M, step 2 and step 3, repetitive cycling obtain WMC Nakagami-m influence M1m(x, y), M2m(x, y), M3m(x, y) ..., and MMm(x, y)；
Step 5, by ImgTComposograph is averaged by the WMC Nakagami-m image summation of the M frame in step 4.
4. the application method of department of general surgery's abdominal ultrasonic diagnostic device as claimed in claim 2, which is characterized in that pass through memory The abdomen image data of acquisition is stored, using improved image compression algorithm, detailed process is as follows:
Image is exported three matrixes by the imread order in matlab, calculates the size of three matrixes by step 1；
Step 2, if the gray value of required point is x, for point aijIf its a (i-1) j, a (i+1) j, a up and downi(j- 1), ai(j+1) exist in 4 points but be not congruent to the point that gray value is x, then aijFor the boundary point for the figure that gray value is x, and The gray value of the point and coordinate are stored in array；
Step 3 repeats all the points that step 2 successively searches three matrixes, and according to the difference of corresponding coordinate in three matrixes Gray value determines color and draws, and realizes its recovery.
5. the application method of department of general surgery's abdominal ultrasonic diagnostic device as claimed in claim 2, which is characterized in that image conversion side Method is as follows:
1) configuration Ultrasound Instrument carries out acquiring ultrasound image operation to abdomen；
2) the low frequency ultrasound image and high frequency ultrasound image of same position are acquired；
3) three-dimensional low-frequency ultrasound image is obtained, including c layers of two dimensional image, is chosen in the same position of each layer of two dimensional image N image block；Wherein c, n are positive integers；
4) the low frequency ultrasound image includes c layers of two dimensional image, chooses n image in the same position of each layer of two dimensional image Block；Wherein c, n are positive integers；
5) the n image block includes the first image block of same size and n-1 other image blocks, the first image block are A part of the layer original two dimensional image, the n-1 other image blocks be centered on the first image block it is different more What large-scale original two dimensional image was obtained through down-sampling；
6) high frequency ultrasound image by the neural network in the c*n image block input channel c*n of selection, after output conversion；
7) neural network parameter is adjusted, the high frequency ultrasound image of the acquisition and putting down for the high frequency ultrasound image after the conversion are made Mean square deviation is minimum.
CN201910039680.0A 2019-01-16 2019-01-16 A kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method Pending CN109620288A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910039680.0A CN109620288A (en) 2019-01-16 2019-01-16 A kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910039680.0A CN109620288A (en) 2019-01-16 2019-01-16 A kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method

Publications (1)

Publication Number Publication Date
CN109620288A true CN109620288A (en) 2019-04-16

Family

ID=66061073

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910039680.0A Pending CN109620288A (en) 2019-01-16 2019-01-16 A kind of department of general surgery's abdominal ultrasonic diagnostic device and its application method

Country Status (1)

Country Link
CN (1) CN109620288A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110522468A (en) * 2019-07-28 2019-12-03 聊城市光明医院 A kind of Ultrasonography combined type checkout and diagnosis color ultrasound system detecting method
CN113208645A (en) * 2020-02-06 2021-08-06 通用电气精准医疗有限责任公司 Method and system for providing enhanced ultrasound images
CN117204943A (en) * 2023-11-07 2023-12-12 南京康友医疗科技有限公司 Power control method and system of radio frequency ablation catheter

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110522468A (en) * 2019-07-28 2019-12-03 聊城市光明医院 A kind of Ultrasonography combined type checkout and diagnosis color ultrasound system detecting method
CN113208645A (en) * 2020-02-06 2021-08-06 通用电气精准医疗有限责任公司 Method and system for providing enhanced ultrasound images
CN117204943A (en) * 2023-11-07 2023-12-12 南京康友医疗科技有限公司 Power control method and system of radio frequency ablation catheter
CN117204943B (en) * 2023-11-07 2024-02-09 南京康友医疗科技有限公司 Power control method and system of radio frequency ablation catheter

Similar Documents

Publication Publication Date Title
CN109685809B (en) Liver infusorian focus segmentation method and system based on neural network
CN105719324B (en) Image processing apparatus and image processing method
CN111951246B (en) Multidirectional X-ray chest radiography pneumonia diagnosis method based on deep learning
CN112529894B (en) Thyroid nodule diagnosis method based on deep learning network
CN111429407B (en) Chest X-ray disease detection device and method based on double-channel separation network
CN105719295B (en) A kind of intracranial hemorrhage region segmentation method and system based on three-dimensional super voxel
CN111445481A (en) Abdominal CT multi-organ segmentation method based on scale fusion
CN111739000B (en) System and device for improving left ventricle segmentation accuracy of multiple cardiac views
CN110232383A (en) A kind of lesion image recognition methods and lesion image identifying system based on deep learning model
CN107730489A (en) Wireless capsule endoscope small intestine disease variant computer assisted detection system and detection method
CN109620288A (en) A kind of department of general surgery&#39;s abdominal ultrasonic diagnostic device and its application method
CN107203989A (en) End-to-end chest CT image dividing method based on full convolutional neural networks
CN105469419A (en) Pulmonary nodule detection method based on CT image
CN113420826B (en) Liver focus image processing system and image processing method
CN109685810A (en) A kind of recognition methods of Bile fistula lesion and system based on deep learning
CN108665454A (en) A kind of endoscopic image intelligent classification and irregular lesion region detection method
CN110163877A (en) A kind of method and system of MRI ventricular structure segmentation
CN106570930A (en) Digital biological organism modeling method based on three-dimensional super voxel description
CN112734755A (en) Lung lobe segmentation method based on 3D full convolution neural network and multitask learning
CN109820594A (en) A method of production heart part 3D printing model is guided using ultrasonic wave initial data
CN113298773A (en) Heart view identification and left ventricle detection device and system based on deep learning
CN109003280A (en) Inner membrance dividing method in a kind of blood vessel of binary channels intravascular ultrasound image
CN104915989B (en) Blood vessel three-dimensional dividing method based on CT images
CN105976339A (en) Method and device for automatically removing bed plate in CT image based on Gaussian model
CN112508943A (en) Breast tumor identification method based on ultrasonic image

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