CN111445407A - Improved genetic algorithm-based reconstruction parameter optimization method for photoacoustic image - Google Patents
Improved genetic algorithm-based reconstruction parameter optimization method for photoacoustic image Download PDFInfo
- Publication number
- CN111445407A CN111445407A CN202010215818.0A CN202010215818A CN111445407A CN 111445407 A CN111445407 A CN 111445407A CN 202010215818 A CN202010215818 A CN 202010215818A CN 111445407 A CN111445407 A CN 111445407A
- Authority
- CN
- China
- Prior art keywords
- image
- matrix
- parameters
- genetic algorithm
- algorithm
- 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.)
- Withdrawn
Links
- 230000002068 genetic effect Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000005457 optimization Methods 0.000 title abstract description 9
- 239000011159 matrix material Substances 0.000 claims abstract description 42
- 238000005070 sampling Methods 0.000 claims description 22
- 210000000349 chromosome Anatomy 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims 1
- 239000012634 fragment Substances 0.000 claims 1
- 238000002986 genetic algorithm method Methods 0.000 claims 1
- 230000002093 peripheral effect Effects 0.000 claims 1
- 230000002028 premature Effects 0.000 claims 1
- 238000003384 imaging method Methods 0.000 abstract description 27
- 238000005516 engineering process Methods 0.000 abstract description 13
- 238000011160 research Methods 0.000 abstract description 5
- 210000001519 tissue Anatomy 0.000 description 9
- 108090000623 proteins and genes Proteins 0.000 description 4
- 239000000523 sample Substances 0.000 description 4
- 230000035772 mutation Effects 0.000 description 3
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002759 chromosomal effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005865 ionizing radiation Effects 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013421 nuclear magnetic resonance imaging Methods 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 238000009401 outcrossing Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000010895 photoacoustic effect Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Genetics & Genomics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention relates to the research field of photoacoustic imaging application in biomedicine, in particular to an optimization method for image reconstruction parameters in a photoacoustic imaging technology by utilizing an improved genetic algorithm. However, the photoacoustic image reconstructed by the traditional algorithm has more artifacts, which seriously affect the quality of the image. The optimization method for the image reconstruction parameters in the photoacoustic imaging technology based on the improved genetic algorithm is characterized in that the current optimal sparse matrix is searched for by utilizing the improved genetic algorithm to perform inversion iteration on the image parameters according to the initialized image, and then the image which is in accordance with the preset value is iteratively reconstructed by utilizing the optimized matrix parameters through a compressed sensing algorithm, so that the artifact-free high-quality photoacoustic image is reconstructed.
Description
Technical Field
The invention relates to the research field of photoacoustic imaging application in biomedicine, in particular to an optimization method for image reconstruction parameters in a photoacoustic imaging technology by utilizing an improved genetic algorithm.
Background
The image is used as the simplest and most direct information transmission mode by researchers as a tool for disease diagnosis, and has very important significance for the deep research of diseases. Nowadays, imaging techniques in the biomedical field are very abundant, and the applications of these medical imaging techniques in the medical clinical research field are becoming more extensive, and the medical imaging modes mainly applied at present include: nuclear magnetic resonance imaging, ultrasonic imaging, X-ray imaging, radionuclide imaging, photoacoustic imaging, and the like.
The photoacoustic imaging technology mainly relates to a plurality of fields such as medicine, optics, acoustics and image processing, the theoretical basis is to utilize the photoacoustic effect, and the photoacoustic imaging technology is a non-invasive and non-ionizing radiation biomedical imaging technology emerging in recent years. It has become a popular research technique in biomedical imaging. The photoacoustic imaging technology integrates the characteristics of high selectivity of a tissue body to pure light and deep penetrability of pure ultrasound in the tissue, and has the advantages of high contrast of optical imaging, high resolution of ultrasonic imaging and the like, so that an image reconstructed by the technology has good definition and contrast. The working principle of photoacoustic imaging is as follows: the biological tissue is heated and expanded under the irradiation of the laser pulse, the periodic vibration in the tissue generates ultrasonic waves, and the ultrasonic detectors distributed on the surface of the tissue detect the generated ultrasonic signals and complete the reconstruction of the light absorption image in the biological tissue by using a reconstruction algorithm. Researchers can study and diagnose the characteristics of the physiological tissues in the organisms by observing the photoacoustic images obtained by the reconstruction algorithm. At this time, the image reconstruction algorithm with excellent performance is important for the photoacoustic imaging work, which is also the key point of the photoacoustic imaging technology. At present, under the condition of limited angle scanning, more reconstruction artifacts exist in photoacoustic images generated by a traditional reconstruction algorithm. Aiming at the problems, the method for optimizing the image reconstruction parameters in the photoacoustic imaging technology based on the improved genetic algorithm is provided, and the artifact of the reconstructed image is eliminated so as to obtain a high-quality photoacoustic image with less artifacts.
Disclosure of Invention
The invention aims to provide a method for better eliminating image artifacts generated in a photoacoustic imaging process under the condition of limited angle scanning, and the optimal sampling matrix parameters required by a compressed sensing algorithm are searched by improving iterative evolution of a genetic algorithm, so that the aim of reconstructing a high-quality photoacoustic image is fulfilled.
In order to solve the above object, the present invention adopts a technical solution comprising: first, a sampling matrix X is obtained by using sparse samplinga×cObtaining an initial reconstruction image C by using a compressed sensing algorithmiImage C by improved genetic algorithmiThe parameter reverse-pushing iteration is carried out to find the current optimal sparse matrix, and then a new image C is reconstructed by utilizing a compressed sensing algorithm according to the parameters of the optimal matrixi+1. If Ci+1If the artifact elimination degree reaches a preset value, the image reconstruction is successful, otherwise, the steps are repeated.
An initial sampling matrix is constructed. The measurement matrix M can be constructed according to sparse scan dataa×bWherein each scanning point is a, and the pixel point in the imaging area is b. Then using the measurement matrix and the measured value Rb×cCalculating to obtain a sampling matrix signal Xa×cThe general formula is:
F＝arg min{||RX-M||Z+λ||LX||Z}
where λ is the matrix regularization coefficient, L is the laplace transform, and Z is the error squared value.
And (4) performing optimal sampling matrix iteration based on a genetic algorithm. The initial sampling matrix is obtained through the calculation, the population fitness value is calculated through designing the multi-factor fitness function by utilizing the characteristic that the genetic algorithm has good global optimal solution, and the optimal matrix value is searched through inverse iteration so as to obtain the high-quality reconstructed image with the artifact eliminated. The specific process of the improved genetic algorithm is as follows:
the first step is as follows: and determining a coding mechanism and generating an initial population. Initializing a population, which consists of a given number of biological individuals, is the first step in the iterative operation of a genetic algorithm. Each row element of the sampling matrix is used as a chromosome, and the coding mode is a binary code. The number of steps of phase encoding is used as the encoding length of the chromosome, and if the phase encoding data is effective, the number is represented by 1 on the chromosome; invalid is represented by 0. At population initialization, the coding bits of each chromosome are randomly assigned a value of 0 or 1 with equal probability.
The second step is that: fitness values for each individual in the population are calculated. The individual fitness evaluation function directly influences the calculation efficiency of the genetic algorithm. The adaptive value here should reflect the quality of the reconstructed image, and the target fitness function is shown as:
where M is the measurement matrix, X is the reconstructed image, R represents the measurement data, L is the Laplace transform, which acts as a constraint to filter the results, ψ is the sparse transform, α and β are penalty coefficients to balance the weights of the sparsity and consistency of the matrix data.
The third step: an operator is selected. The algorithm in the text adopts the combination of an elite individual retention strategy and a fitness value random selection method to select operators, namely, the individual with the highest fitness is selected certainly. If M represents the population size, FiRepresenting the fitness of the ith individual, calculating the probability of each individual being selected in the population fitness as:
the genetic individuals to be selected are determined by the range interval in which the random numbers generated each time are located.
The fourth step: and (5) a crossover operator. And randomly selecting a plurality of parents to pair according to the crossing probability, and randomly selecting crossing points on the chromosome to carry out crossing operation after the pairing is finished. The cross operation can not damage individuals with excellent performance in the population, and can generate some brand new individuals, so that the population genes tend to be diversified. For the image reconstruction, the individual chromosome matrix can be used as an image sampling matrix, and the crossing of the individual chromosomes is to interchange the row units in the sampling matrix.
The fifth step: and (5) mutation operators. In order to maintain the diversity of population individuals and prevent the population individuals from falling into local optima, variant individuals need to be randomly selected according to variant probability. Usually, only one gene point of the chromosome is mutated, which cannot effectively improve the searching capability of the operation in the problem and has little influence on the final calculation result. And mutation operators obtained in the genetic algorithm. Therefore, the gene block variation is selected, and the diversity and the surrounding searching capability of the population can be greatly improved by the variation mode, so that the speed of searching the optimal solution by the algorithm is greatly improved. According to the image dissimilarity, the genetic algorithm is needed to be used for solving the image dissimilarity iteratively so as to carry out mutation, and the formula is as follows:
Ht+1＝αHt+βX-1
where X denotes the sampling matrix, H denotes the chromosomal gene block, and α and β are the respective constraints on the respective parameters.
And a sixth step: and (4) terminating the conditions. Stopping iteration if the iteration reaches a preset maximum iteration number or the fitness value in the population tends to be stable, considering the finally obtained chromosome matrix data as an optimal sampling matrix, and then reconstructing the data by using a compressed sensing algorithm to obtain a new reconstructed image; otherwise, turning to the second step and repeating the above operations.
And (5) improving the genetic algorithm, performing reverse iteration, and searching matrix data to finish, wherein the final iteration result is the current optimal sparse matrix. And reconstructing a new image by the matrix by using a compressed sensing algorithm. The image mean square error algorithm is introduced for evaluating the image quality, the image mean square error is an important measurement index in the image quality evaluation, the difference between a reconstructed image and a real image can be well reflected, and the calculation formula is as follows:
where m × n represents the size of an image, and X represents the number of photoacoustic images to be reconstructedAccording to the above-mentioned technical scheme,
as a photoacoustic image reference value. If the artifact elimination degree of the reconstructed image reaches a preset value, the image reconstruction is successful, otherwise, the steps are repeated.
And at this moment, improving the genetic algorithm to finish the artifact-removing reconstruction of the image in the photoacoustic imaging technology, wherein the final result is the optimized photoacoustic image.
Drawings
FIG. 1 is a flow chart of an implementation of a reconstruction method based on an improved genetic algorithm;
FIG. 2 is a graph of mean square error of photoacoustic images at a sampling frequency of 60 Hz;
figure 3 is a graph comparing photoacoustic imaging results before and after the improved method was performed.
Detailed Description
The invention is further described with reference to the accompanying drawings and examples.
The data is processed by Matlab, the optimization method of the image reconstruction parameters in the photoacoustic imaging technology based on the improved genetic algorithm is compiled and simulated by codes, and the photoacoustic image results processed by the method are analyzed and compared, the result shows that the improved genetic algorithm has a more obvious optimization effect compared with the basic genetic algorithm, the overall optimization effect of the algorithm is more obvious from the photoacoustic image reconstruction quality, the elimination degree of artifacts is higher, the definition is better, and the identification degree is betterc0.9, probability of variation pm0.05. The instrument is used for scanning a sample, wherein the emission wavelength of pulse laser is 532nm, the pulse width of a single laser pulse is about 10ns, the pulse energy is about 75mJ, the central frequency of a probe for receiving photoacoustic signals is 4.39MHz, the diameter of the probe is 8mm, the focal length of the probe is 2.5cm, and the signal sampling rate is 60 MHz.
Fig. 1 is a flow chart of an implementation of a method for optimizing image reconstruction parameters in a photoacoustic imaging technology by improving a genetic algorithm. In the implementation process of the method, an initial reconstruction image is obtained according to scanned sampling data, then the current optimal sparse matrix is found by carrying out reverse-deduction on image parameters through an improved genetic algorithm, and the photoacoustic image with good artifact elimination degree is iteratively reconstructed by using the optimized matrix parameters through a compressed sensing algorithm.
Fig. 2 is a graph of mean square error of photoacoustic images at a sampling frequency of 60 Hz. The mean square error of the image is an important measurement index in the image quality evaluation, the difference between the reconstructed image and a real image can be well reflected, and the image shows that compared with the traditional method, the mean square error of the reconstructed image is much smaller, the reconstructed image is clear in tissue structure and has higher quality, which shows that the method has great advantages in the optimization of sparse sampling data.
Fig. 3 is a graph comparing photoacoustic imaging results before and after the improved method was performed. The optimal sparse matrix of the current image parameters is searched by an improved genetic algorithm, and the photoacoustic image iteratively reconstructed by using a compressed sensing algorithm has obvious difference compared with the image reconstructed by the traditional method. The image contains less artifacts, so that the definition of the image is better, and the tissue details of the object to be researched can be observed and analyzed easily.
Claims (4)
1. The method is characterized in that sparse sampling is firstly used to obtain a sampling matrix, a compressed sensing algorithm is used to obtain an initial reconstructed image, the improved genetic algorithm is used to carry out backstepping iteration on image parameters to find a current optimal sparse matrix, a new image is reconstructed by using the compressed sensing algorithm according to the optimized matrix parameters, if the artifact elimination degree of the image reaches a preset value, the image reconstruction is successful, otherwise, the steps are repeated, and the aim of reconstructing a high-quality photoacoustic image without artifacts is fulfilled.
2. The improved genetic algorithm-based method for optimizing the reconstruction parameters of the photoacoustic image according to claim 1, wherein after the photoacoustic image data is initialized, sparse matrix parameters are reversely deduced, and a new image is iteratively reconstructed according to the sparse matrix parameters, which comprises the following specific processes:
constructing a measurement matrix M from the existing dataa×bAnd the measured value Rb×cThen, the sampling matrix signal X is obtained by the calculationa×cThe general formula is:
F＝argmin{||RX-M||Z+λ||LX||Z}
and encoding the obtained sampling matrix by using an improved genetic algorithm, continuously and iteratively searching optimal sparse matrix parameters under the current condition by depending on the better global search advantage of the genetic algorithm, setting an image quality standard according to parameters such as image mean square error and the like, and performing iterative reconstruction on the calculated matrix data through a compressed sensing algorithm until a preset value is reached to output a final reconstructed image.
3. The method for optimizing the reconstruction parameters of the photoacoustic image based on the improved genetic algorithm as claimed in claim 1, wherein the specific process of improving the fitness function construction of the genetic algorithm according to the requirements of image reconstruction is as follows:
the target fitness function directly influences the calculation efficiency of the improved genetic algorithm and the accuracy of the result, and the target function is constructed in the method as follows:
where M is the measurement matrix, X is the reconstructed image, R represents the measurement data, L is Laplace transform, which acts as a constraint condition to filter the result, ψ is the sparse transform, α and β are penalty coefficients for the corresponding parameters to balance the weights of the sparsity and consistency of the matrix data.
4. The method for optimizing reconstruction parameters of an photoacoustic image based on an improved genetic algorithm as claimed in claim 1, wherein in the image reconstruction problem, the search capability of the operation cannot be effectively improved by one genetic point variation of the encoded chromosome, the final calculation result is slightly affected, and the algorithm is prone to premature phenomena, so that genetic segment variation is proposed in the improved algorithm, the diversity of the population and the peripheral search capability can be greatly improved by such a variation mode, the speed of the algorithm for finding the optimal solution is greatly improved, and the optimal solution is required to be solved by iteration of the genetic algorithm according to the dissimilarity of the images so as to perform the variation, and the formula is as follows:
Ht+1＝αHt+βX-1
where X denotes the sampling matrix, H denotes the chromosome fragment, and α and β are constraints on the respective parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010215818.0A CN111445407A (en) | 2020-03-24 | 2020-03-24 | Improved genetic algorithm-based reconstruction parameter optimization method for photoacoustic image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010215818.0A CN111445407A (en) | 2020-03-24 | 2020-03-24 | Improved genetic algorithm-based reconstruction parameter optimization method for photoacoustic image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111445407A true CN111445407A (en) | 2020-07-24 |
Family
ID=71629495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010215818.0A Withdrawn CN111445407A (en) | 2020-03-24 | 2020-03-24 | Improved genetic algorithm-based reconstruction parameter optimization method for photoacoustic image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111445407A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113645457A (en) * | 2021-10-14 | 2021-11-12 | 北京创米智汇物联科技有限公司 | Method, device, equipment and storage medium for automatic debugging |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102148987A (en) * | 2011-04-11 | 2011-08-10 | 西安电子科技大学 | Compressed sensing image reconstructing method based on prior model and 10 norms |
| CN103198500A (en) * | 2013-04-03 | 2013-07-10 | 西安电子科技大学 | Compressed sensing image reconstruction method based on principal component analysis (PCA) redundant dictionary and direction information |
| CN103337087A (en) * | 2013-07-04 | 2013-10-02 | 西北工业大学 | Compressive sensing reconstruction method based on pseudo-inverse adaptive matching pursuit |
| CN104240210A (en) * | 2014-07-21 | 2014-12-24 | 南京邮电大学 | CT image iteration reconstruction method based on compressed sensing |
| CN104299201A (en) * | 2014-10-23 | 2015-01-21 | 西安电子科技大学 | Image reconstruction method based on heredity sparse optimization and Bayes estimation model |
| CN104586363A (en) * | 2015-01-14 | 2015-05-06 | 复旦大学 | Fast photoacoustic imaging image reconstruction method based on image block sparse coefficient |
| JP2017094097A (en) * | 2015-11-27 | 2017-06-01 | 株式会社東芝 | Medical image processing device, x-ray computer tomographic imaging device, and medical image processing method |
-
2020
- 2020-03-24 CN CN202010215818.0A patent/CN111445407A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102148987A (en) * | 2011-04-11 | 2011-08-10 | 西安电子科技大学 | Compressed sensing image reconstructing method based on prior model and 10 norms |
| CN103198500A (en) * | 2013-04-03 | 2013-07-10 | 西安电子科技大学 | Compressed sensing image reconstruction method based on principal component analysis (PCA) redundant dictionary and direction information |
| CN103337087A (en) * | 2013-07-04 | 2013-10-02 | 西北工业大学 | Compressive sensing reconstruction method based on pseudo-inverse adaptive matching pursuit |
| CN104240210A (en) * | 2014-07-21 | 2014-12-24 | 南京邮电大学 | CT image iteration reconstruction method based on compressed sensing |
| CN104299201A (en) * | 2014-10-23 | 2015-01-21 | 西安电子科技大学 | Image reconstruction method based on heredity sparse optimization and Bayes estimation model |
| CN104586363A (en) * | 2015-01-14 | 2015-05-06 | 复旦大学 | Fast photoacoustic imaging image reconstruction method based on image block sparse coefficient |
| JP2017094097A (en) * | 2015-11-27 | 2017-06-01 | 株式会社東芝 | Medical image processing device, x-ray computer tomographic imaging device, and medical image processing method |
Non-Patent Citations (3)
| Title |
|---|
| ZHANG LIN: "Image adaptive recovery based on compressive sensing and genetic algorithm", 《IEEE XPLORE》 * |
| 寻之川: "基于单目标和多目标遗传算法的压缩感知重构", 《万方》 * |
| 朱赟: "稀疏角度CT图像重建的一类自适应临近点算法", 《电子科技大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113645457A (en) * | 2021-10-14 | 2021-11-12 | 北京创米智汇物联科技有限公司 | Method, device, equipment and storage medium for automatic debugging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kim et al. | Deep-learning image reconstruction for real-time photoacoustic system | |
| Tong et al. | Domain transform network for photoacoustic tomography from limited-view and sparsely sampled data | |
| Zhang et al. | UHR-DeepFMT: ultra-high spatial resolution reconstruction of fluorescence molecular tomography based on 3-D fusion dual-sampling deep neural network | |
| US11986269B2 (en) | Spatiotemporal antialiasing in photoacoustic computed tomography | |
| CN112734872B (en) | Fluorescence molecule tomography method and system based on multi-wavelength concurrent reconstruction | |
| CN111445407A (en) | Improved genetic algorithm-based reconstruction parameter optimization method for photoacoustic image | |
| CN114119362A (en) | System and method for improving resolution of ultrasound image using neural network | |
| Gao et al. | Deep learning-based photoacoustic imaging of vascular network through thick porous media | |
| Kong et al. | Investigation on reconstruction for frequency domain photoacoustic imaging via TVAL3 regularization algorithm | |
| CN111223162A (en) | Deep learning method and system for reconstructing EPAT image | |
| JP6523276B2 (en) | Method and system for generating arbitrary waveform using tri-state pulser | |
| Tang et al. | Learning spatially variant degradation for unsupervised blind photoacoustic tomography image restoration | |
| CN116712038A (en) | Multispectral photoacoustic tomography system and multispectral photoacoustic tomography method based on spiral staggered sparse sampling | |
| CN113974560A (en) | Sparse array element optimization selection and compressive sensing imaging method for annular photoacoustic tomography system | |
| Sivasubramanian et al. | Deep learning for image processing and reconstruction to enhance led-based photoacoustic imaging | |
| Schein et al. | Deep learning-based ultrasound beam shaping for spatiotemporal acoustic holograms generation | |
| Wang et al. | Adaptive machine learning method for photoacoustic computed tomography based on sparse array sensor data | |
| Stotzka et al. | High resolution image reconstruction in ultrasound computer tomography using deconvolution | |
| CN105640498B (en) | subject information acquisition device | |
| CN110575202B (en) | Ultrasonic CT image reconstruction method and system based on Fermat principle | |
| CN111260742B (en) | Electrical impedance imaging method and device | |
| Stevens et al. | Accelerated intravascular ultrasound imaging using deep reinforcement learning | |
| Massa | Genetic algorithm (GA) based techniques for 2D microwave inverse scattering | |
| Athira et al. | Image enhancement in reconstructed photoacoustic microscopy images using deep learning | |
| Anjidani et al. | Efficient ultrasound image enhancement using lightweight cnns |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200724 |