CN110634107B - Standardization method for enhancing brain magnetic resonance image brightness aiming at T1 - Google Patents
Standardization method for enhancing brain magnetic resonance image brightness aiming at T1 Download PDFInfo
- Publication number
- CN110634107B CN110634107B CN201910735434.9A CN201910735434A CN110634107B CN 110634107 B CN110634107 B CN 110634107B CN 201910735434 A CN201910735434 A CN 201910735434A CN 110634107 B CN110634107 B CN 110634107B
- Authority
- CN
- China
- Prior art keywords
- image
- peak point
- brightness
- magnetic resonance
- peak
- 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.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 35
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 4
- 238000011425 standardization method Methods 0.000 title abstract description 4
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000009499 grossing Methods 0.000 claims abstract description 4
- 238000012937 correction Methods 0.000 claims description 7
- 101100129590 Schizosaccharomyces pombe (strain 972 / ATCC 24843) mcp5 gene Proteins 0.000 claims description 4
- 230000002902 bimodal effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 238000010801 machine learning Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004195 computer-aided diagnosis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- JXSJBGJIGXNWCI-UHFFFAOYSA-N diethyl 2-[(dimethoxyphosphorothioyl)thio]succinate Chemical compound CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC JXSJBGJIGXNWCI-UHFFFAOYSA-N 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research 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
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/30016—Brain
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention provides a standardization method for enhancing brain magnetic resonance image brightness aiming at T1, which comprises the following steps: carrying out size standardization on the image, extracting a histogram, and carrying out smoothing treatment to obtain a smooth histogram; acquiring a peak point, defining the peak point as a first peak point, defining a first threshold, traversing the peak point of the smooth histogram in a closed interval, and defining the peak point as a second peak point; acquiring corresponding amplitude values, and calculating the overall brightness and the overall brightness of the shadow; defining a second threshold, and if the absolute value of the difference value between the global brightness of the current image and the global brightness of the template is not more than the second threshold, determining that the current image is a standardized image; otherwise, the T1 enhanced brain magnetic resonance image is subjected to standardization processing to obtain a standardized image. The method has the advantages of high calculation speed, strong transportability and strong interpretability; the method can assist a radiologist to read the images, or serve as an image preprocessing link to improve the accuracy of the brain magnetic resonance image automatic classification system based on a machine learning algorithm.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a method for standardizing brightness of a T1 enhanced brain magnetic resonance image.
Background
T1 enhancement of brain magnetic resonance images is an important basis for doctors to judge whether tumors exist in the cranium. With the rapid development of machine learning and deep learning algorithms, the development of computer-aided diagnosis systems based on intelligent algorithms, which can assist imaging physicians in completing daily film reading, has become a focus of current research.
However, the T1 enhanced brain magnetic resonance images required for constructing the computer-aided diagnosis system are derived from different magnetic resonance scanning devices, and the T1 enhanced images in the data set have large differences in overall brightness, which is not favorable for the construction of the subsequent automatic classification system.
Currently, brightness standardization of T1 enhanced images mainly depends on manual adjustment, and the method is low in efficiency and tedious in process.
Disclosure of Invention
The invention aims to solve the technical problem of how to effectively standardize the T1 enhanced image in the data set on the overall brightness.
Therefore, the invention provides a method for standardizing brightness of a brain magnetic resonance image for T1 enhancement, which comprises the following steps:
step 1: carrying out size standardization on the original T1 enhanced brain magnetic resonance image to obtain a standard size image;
step 2: extracting a histogram of the standard size image, and smoothing the histogram through a Gaussian filter to obtain a smooth histogram;
and step 3: obtaining a peak point in the smooth histogram, defining the peak point as a first peak point peak _ medium1, defining a first threshold value threshold1, traversing the peak point of the smooth histogram in a closed interval [0, peak _ medium1-threshold1] and [ peak _ medium1+ threshold1,255], and defining the peak point as a second peak point peak _ medium2;
and 4, step 4: obtaining corresponding amplitudes of a first peak point and a second peak point in the smooth histogram, calculating the shadow global brightness of the current image, and calculating the global brightness of the current image according to the shadow global brightness;
and 5: defining a second threshold, and if the absolute value of the difference value between the global brightness of the current image and the global brightness of the template is not more than the second threshold, determining that the current image is a standardized image; otherwise, the T1 enhanced brain magnetic resonance image is standardized through the double-peak gamma correction to obtain a standardized image.
The size normalization of the original T1-enhanced brain magnetic resonance image is to convert the original T1-enhanced brain magnetic resonance image into a standard size image with 256 length and width.
The template size of the gaussian filter was 1 × 3, the mean was 0, and the standard deviation was 0.1.
And setting the maximum iteration number, wherein the first threshold value is the same as the maximum iteration number.
The obtaining of the corresponding amplitudes of the first peak point and the second peak point in the smoothed histogram includes:
and respectively obtaining the corresponding amplitudes of the first peak point of the ith iteration and the second peak point of the ith iteration in the smooth histogram by taking the smaller peak point of the first peak point and the second peak point as the first peak point of the ith iteration and the larger peak point as the second peak point of the ith iteration.
The global brightness of the current image is:
wherein, over _ gray (i) is the global brightness of the image of the ith iteration, sha _ gray (i) is the shadow global brightness of the image in the ith iteration, decay is the decay rate, and i is the current iteration number.
The shadow global brightness of the current image is as follows:
sha_gray(i)＝ln(peak 2(i)+w2(i)*peak 1(i))
where, sha _ gray (i) is the shadow global brightness of the image of the ith iteration, peak1 (i) is the first peak point of the ith iteration, peak2 (i) is the second peak point of the ith iteration, num1 (i) is the first peak point in the smoothed histogram, num2 (i) is the second peak point in the smoothed histogram, w2 (i) is the ratio of the two peaks to the first peak, and i is the current iteration number.
The template global brightness value is 4.4927.
The bimodal gamma correction is:
adjusting the global brightness of the image by the following formula:
output (i) is a normalized image of the ith iteration, input (i) is a standard size image of the ith iteration, over _ gray (i) is the global brightness of the image of the ith iteration, and temp is the template global brightness.
The invention has the following beneficial effects:
1. the method has high calculation speed, and only 10ms is needed for processing one T1 enhanced brain magnetic resonance image;
2. the method has strong portability, and can be transplanted to brain magnetic resonance images such as T2 weighting, T1 weighting and Flair;
3. according to the method, the image standardization is carried out according to the double peaks of the T1 enhanced brain magnetic resonance image, so that the interpretability is strong;
4. the T1 enhanced brain magnetic resonance image processed by the invention has similar overall brightness.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a flow chart of image iteration in an embodiment of the present invention;
FIG. 3 is a comparison graph of iteration results for multiple normalized size images in an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention, taken in conjunction with the accompanying drawings and detailed description, is set forth below. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Referring to FIG. 1, a flow chart of the method of the present invention is shown;
the invention provides a standardization method for T1 enhanced brain magnetic resonance image brightness, which is characterized by carrying out histogram denoising through Gaussian filtering, extracting denoised histogram double-peak points and finally carrying out image brightness standardization through the double-peak points and gamma correction.
The method comprises the following steps:
step 1: setting the maximum iteration number iter _ max, and setting the current iteration number i =1; the maximum number of iterations iter _ max takes the value 8.
Step 2: completing the image size standardization operation, namely converting the original T1 enhanced brain magnetic resonance image into a standard size to obtain a standard size image, and marking the standard size image as input (i); the size standardization operation is to convert the original image into a size standard image with length and width of 256.
And 3, step 3: judging whether i > iter _ max is true, if so, ending the cycle, outputting input (i) as a final standardized image, and otherwise, continuing to execute the step 4;
and 4, step 4: extracting a histogram of the standard size image;
and 5: smoothing the image histogram through a Gaussian filter to obtain a smooth histogram; gaussian filter template size was 1 × 3, mean 0, standard deviation 0.1.
Step 6: obtaining a peak point in the smooth histogram by adopting a traversal method, defining the peak point as a middle peak point 1 and marking the peak point as peak _ medium1;
and 7: defining a threshold value 1, marked as threshold1, and traversing the peak point of the histogram in two closed intervals of [0, peak _ medium1-threshold1] and [ peak _ medium1+ threshold1,255], defining it as a middle peak point 2, marked as peak _ medium2; the threshold value 1, i.e. threshold1, takes a value of 8.
And step 8: comparing the sizes of the peak _ medium1 and the peak _ medium2, wherein the smaller is a first peak point of the ith iteration and is marked as peak1 (i), the larger is a second peak point of the ith iteration and is marked as peak2 (i), and amplitudes corresponding to the first peak point and the second peak point in the histogram, num1 (i) and num2 (i) are respectively obtained;
and step 9: defining a shadow global brightness sha _ gray (i) of the ith iteration;
the shadow global luminance sha _ gray (i) is defined by formula (1) and formula (2).
sha_gray(i)＝ln(peak 2(i)+w2(i)*peak1(i)) (1)
Step 10: defining a global luminance over _ gray (i) for the ith iteration;
the global luminance over _ gray (i) is defined by equation (3), where decay is the decay rate and takes a value of 0.8.
Step 11: selecting a T1 enhanced template image with proper global brightness, converting the T1 enhanced template image into an image with a standardized size, calculating the global brightness through the steps 4 to 10, defining the global brightness as the template global brightness, and marking the template global brightness as temp by using a symbol; the template global brightness, temp, takes on a value of 4.4927.
Step 12: defining a threshold2, marking as threshold2, judging whether the absolute value of the difference value between the template global brightness and the global brightness of the current image is smaller than the threshold2, if so, outputting input (i) as a final standardized image without any processing on the standard size image, and if not, continuing to execute the step 13; the threshold2, i.e. threshold2, is 0.15.
Step 13: carrying out standardization processing on the T1 enhanced brain magnetic resonance image through double-peak gamma correction to obtain a standardized image, output (i);
and (3) adjusting the global brightness of the image by using a formula (4), wherein input (i) is a standard size image in the ith iteration, and output (i) is a standard image in the ith iteration.
Step 14: updating the iteration number, i = i +1, and additionally setting input (i) = output (i-1), and repeating steps 3 to 13.
Example (b):
taking the T1 enhanced brain magnetic resonance image as an example, after the T1 enhanced brain magnetic resonance image is obtained, the size of the original image needs to be standardized, and the image size is uniformly set to 256 × 256, so as to obtain a standard size image. The maximum number of iterations iter _ max is set, and the number of iterations i at this time is set to 1. Because the overall brightness of the image is reflected by the double-peak point of the enhanced brain magnetic resonance image through the T1, the double peaks of the size standard image need to be extracted, and the image histogram needs to be smoothed through a Gaussian filter with the size of 1 x 3, the mean value of 0 and the standard deviation of 0.1 before the double peaks are extracted, so that noise is filtered, and the smooth histogram is obtained.
The peak point of the smoothed histogram, peak _ medium1, is extracted, and the peak point of the histogram, peak _ medium2, is searched through a traversal method in the range of [ peak _ medium1+ threshold0,255] and [0, peak _ medium1-threshold0 ]. Comparing the sizes of the peak _ medium1 and the peak _ medium2, wherein the larger is the first peak point peak1 of the size standard image, and the smaller is the second peak point peak2 of the size standard image. And acquiring corresponding amplitudes num1 and num2 of the first peak point and the second peak point in the histogram.
Because the pixel points of the standard-size image are concentrated near the first peak point and the second peak point, the first peak point and the second peak point are adopted to reflect the overall brightness of the image, the image is brighter when the gray level corresponding to the second peak point is larger, the amplitude corresponding to the second peak point in the histogram is larger, and the image is brighter. Meanwhile, the image is darker as the gray level corresponding to the first peak point is smaller, and the image is darker as the amplitude corresponding to the first peak point in the histogram is larger. The shadow global brightness of the size standard image is defined by formula (1) and formula (2). The global brightness of the size standard image is defined by a moving average model, equation (3).
And selecting an image with moderate brightness as a template, and calculating the global brightness of the template image according to the steps and recording the global brightness as temp. And the normalized image is acquired using a bimodal gamma correction, equation (4).
The above steps are repeated until the maximum number of iterations or | over _ gray-temp | < threshold2 is reached, and the normalized image at this time is output.
FIG. 2 is a flow chart of image iteration according to an embodiment of the present invention;
an iterative process of normalizing the size image. The (a) is an original normalized size image, and the (b), (c), and (d) are normalized images when i =1,i =2,i =3, respectively. It can be seen that the contrast of the image is greatly improved on the premise of not losing the details of the image as much as possible.
Referring to fig. 3, an iteration result comparison image of a plurality of images with standardized sizes in an embodiment of the invention is shown.
The (a), (b), (c) are original standardized size images, the (d), (e) and (f) are corresponding final standardized images, and the standardized size images processed by the invention have similar overall brightness.
The method can assist a radiologist to read the images, or serve as an image preprocessing link to improve the accuracy of the brain magnetic resonance image automatic classification system based on a machine learning algorithm.
In the several embodiments provided in the present application, it should be understood that the disclosed method and system may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium. The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A method for normalizing brightness of a magnetic resonance image of a brain aiming at T1 is characterized by comprising the following steps:
step 1: carrying out size standardization on the original T1 enhanced brain magnetic resonance image to obtain a standard size image;
and 2, step: extracting a histogram of the standard size image, and smoothing the histogram through a Gaussian filter to obtain a smooth histogram;
and step 3: obtaining a peak point in the smooth histogram, defining the peak point as a first peak point peak _ medium1, defining a first threshold value threshold1, traversing the peak point of the smooth histogram in a closed interval [0, peak _ medium1-threshold1] and [ peak _ medium1+ threshold1,255], and defining the peak point as a second peak point peak _ medium2;
and 4, step 4: obtaining corresponding amplitudes of a first peak point and a second peak point in the smooth histogram, calculating the shadow global brightness of the current image, and calculating the global brightness of the current image according to the shadow global brightness;
and 5: defining a second threshold, and if the absolute value of the difference value between the global brightness of the current image and the global brightness of the template is not greater than the second threshold, determining that the current image is a standardized image; otherwise, the T1 enhanced brain magnetic resonance image is standardized through the double-peak gamma correction to obtain a standardized image.
2. The method for standardizing the brightness of the T1 enhanced brain magnetic resonance image according to claim 1, wherein the dimensional standardization of the original T1 enhanced brain magnetic resonance image is to convert the original T1 enhanced brain magnetic resonance image into a standard size image with 256 length and width.
3. The method of claim 1, wherein the template size of the gaussian filter is 1 x 3, the mean is 0 and the standard deviation is 0.1.
4. The method of claim 1 wherein a maximum number of iterations is set and the first threshold is the same as the maximum number of iterations.
5. The method for normalizing brightness of a magnetic resonance image for the T1 enhancement brain according to claim 1, wherein the obtaining corresponding amplitudes of a first peak point and a second peak point in a smoothed histogram comprises:
and respectively obtaining the corresponding amplitudes of the first peak point of the ith iteration and the second peak point of the ith iteration in the smooth histogram by taking the smaller peak point of the first peak point and the second peak point as the first peak point of the ith iteration and the larger peak point as the second peak point of the ith iteration.
6. The method of claim 1 for normalization of T1-enhanced brain magnetic resonance image brightness, the global brightness of the current image being:
wherein, over _ gray (i) is the global brightness of the image of the ith iteration, sha _ gray (i) is the shadow global brightness of the image in the ith iteration, decay is the attenuation rate, and i is the current iteration number.
7. The method for standardizing brightness of a magnetic resonance image for T1 enhancement of a brain according to claim 1 or 6, characterized in that the shadow global brightness of the current image is:
sha_gray(i)＝ln(peak2(i)+w2(i)*peak1(i))
where, sha _ gray (i) is the shadow global brightness of the image of the ith iteration, peak1 (i) is the first peak point of the ith iteration, peak2 (i) is the second peak point of the ith iteration, num1 (i) is the first peak point in the smoothed histogram, num2 (i) is the second peak point in the smoothed histogram, w2 (i) is the ratio of the two peaks to the first peak, and i is the current iteration number.
8. The method for standardizing brightness of a magnetic resonance image of the brain aiming at T1 according to claim 1, wherein the template global brightness value is 4.4927.
9. The method of claim 1 for enhancing brain magnetic resonance image brightness normalization for T1, the bimodal gamma correction being:
adjusting the global brightness of the image by the following formula:
output (i) is a normalized image of the ith iteration, input (i) is a standard size image of the ith iteration, over _ gray (i) is the global brightness of the image of the ith iteration, and temp is the template global brightness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910735434.9A CN110634107B (en) | 2019-08-09 | 2019-08-09 | Standardization method for enhancing brain magnetic resonance image brightness aiming at T1 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910735434.9A CN110634107B (en) | 2019-08-09 | 2019-08-09 | Standardization method for enhancing brain magnetic resonance image brightness aiming at T1 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110634107A CN110634107A (en) | 2019-12-31 |
| CN110634107B true CN110634107B (en) | 2022-11-25 |
Family
ID=68970282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910735434.9A Active CN110634107B (en) | 2019-08-09 | 2019-08-09 | Standardization method for enhancing brain magnetic resonance image brightness aiming at T1 |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110634107B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530237A (en) * | 2016-09-19 | 2017-03-22 | 中山大学 | Image enhancement method |
| WO2018082084A1 (en) * | 2016-11-07 | 2018-05-11 | 中国科学院自动化研究所 | Brain tumor automatic segmentation method by means of fusion of full convolutional neural network and conditional random field |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106377261B (en) * | 2016-09-23 | 2023-12-26 | 泰山医学院 | Magnetic resonance functional imaging quality detection phantom and method |
-
2019
- 2019-08-09 CN CN201910735434.9A patent/CN110634107B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530237A (en) * | 2016-09-19 | 2017-03-22 | 中山大学 | Image enhancement method |
| WO2018082084A1 (en) * | 2016-11-07 | 2018-05-11 | 中国科学院自动化研究所 | Brain tumor automatic segmentation method by means of fusion of full convolutional neural network and conditional random field |
Non-Patent Citations (1)
| Title |
|---|
| 基于灰度直方图的MR脑组织的提取方法;朱冠菲等;《计算机测量与控制》;20171125(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110634107A (en) | 2019-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115661144B (en) | Adaptive medical image segmentation method based on deformable U-Net | |
| CN110956632B (en) | Method and device for automatically detecting pectoralis major region in molybdenum target image | |
| CN114022383B (en) | Method and device for removing mole patterns of text and image and electronic equipment | |
| CN108305268B (en) | Image segmentation method and device | |
| CN115984312A (en) | Image segmentation method, electronic device and computer-readable storage medium | |
| CN114677525B (en) | Edge detection method based on binary image processing | |
| CN109712134B (en) | Iris image quality evaluation method and device and electronic equipment | |
| CN111091107A (en) | Face region edge detection method and device and storage medium | |
| CN117496019B (en) | Image animation processing method and system for driving static image | |
| CN117314940B (en) | Laser cutting part contour rapid segmentation method based on artificial intelligence | |
| CN114943649A (en) | Image deblurring method, device and computer readable storage medium | |
| CN111667509B (en) | Automatic tracking method and system for moving target under condition that target and background colors are similar | |
| CN113313179A (en) | Noise image classification method based on l2p norm robust least square method | |
| CN110634107B (en) | Standardization method for enhancing brain magnetic resonance image brightness aiming at T1 | |
| CN111311610A (en) | Image segmentation method and terminal equipment | |
| CN111161256A (en) | Image segmentation method, image segmentation device, storage medium, and electronic apparatus | |
| CN110232302B (en) | Method for detecting change of integrated gray value, spatial information and category knowledge | |
| Jiang et al. | Application of image sharpening based quality assessment model: Extraction of Traditional Chinese Embroidery Patterns as an Example | |
| CN112541913B (en) | Image local fuzzy detection and extraction method based on column rate spectral analysis and noise robustness | |
| CN113628235B (en) | PDE-based adaptive threshold segmentation signature image binary processing method | |
| CN118172788B (en) | OCR intelligent recognition and management system for BCG vaccine inoculation record | |
| CN112330666B (en) | Image processing method, system, device and medium based on improved twin network | |
| CN111383172B (en) | Training method and device of neural network model and intelligent terminal | |
| Yang et al. | Improved GrabCut-based method for coffee leaf segmentation | |
| CN112084888A (en) | Facial expression recognition method and device based on Gabor wavelet |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221124 Address after: No.5-2, Tianci Street, Hunnan New District, Shenyang, Liaoning Province, 110000 (804) Patentee after: Shenyang ruilida Technology Co.,Ltd. Address before: 1310, No. 5-2, Tianci Street, Hunnan District, Shenyang, Liaoning Province, 110000 Patentee before: Liaoning Lanxiao Technology Co.,Ltd. |