CN111429362A - Blood vessel enhancement method of endoscope fluorescence image - Google Patents
Blood vessel enhancement method of endoscope fluorescence image Download PDFInfo
- Publication number
- CN111429362A CN111429362A CN202010102478.0A CN202010102478A CN111429362A CN 111429362 A CN111429362 A CN 111429362A CN 202010102478 A CN202010102478 A CN 202010102478A CN 111429362 A CN111429362 A CN 111429362A
- Authority
- CN
- China
- Prior art keywords
- image
- frequency
- blood vessel
- blood vessels
- smoothing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000002073 fluorescence micrograph Methods 0.000 title claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000009499 grossing Methods 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 230000001629 suppression Effects 0.000 claims abstract description 5
- 230000002146 bilateral effect Effects 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims 2
- 230000002792 vascular Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 description 6
- 238000000926 separation method Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a blood vessel enhancement method of endoscope fluorescence images, which comprises the following steps: s1, performing high-frequency extraction on the acquired image, and extracting a high-frequency image containing blood vessels; s2, performing median filtering on the extracted high-frequency image to perform nonlinear suppression on noise points in a high-frequency part, so that the noise points can be eliminated to a greater extent; s3, smoothing the acquired image by using Gaussian filtering; and S4, performing superposition processing on the high-frequency image processed in the S2 and the image subjected to smoothing processing in the S3 to realize enhancement processing on the blood vessel. The details of the blood vessels of the fluorescence image are effectively enhanced.
Description
Technical Field
The invention relates to the field of medical imaging, in particular to a blood vessel enhancement method of an endoscope fluorescence image.
Background
Regarding the fluorescence image collected by the endoscope, the white light image collected by the two cameras and the fluorescence part after processing are mainly subjected to image superposition, namely the fluorescence image collected by the device.
In the images acquired at present, the blood vessel part information belongs to high-frequency signals, but the information is often embedded in a large amount of low-frequency background signals, so that the visual visibility of detailed parts is greatly reduced, and therefore, the enhancement of the high-frequency part of the images is necessary.
The existing advanced enhancement method comprises a common improved algorithm of histogram equalization, namely Adaptive Histogram Equalization (AHE), an adaptive contrast enhancement Algorithm (ACE), a histogram equalization algorithm (HE) and an improved contrast-limiting adaptive histogram equalization algorithm (C L AHE) based on the above algorithms.
The AHE algorithm maps data using information about local histograms. This changes the contrast of the image, but requires a large amount of computation. Later, this problem was overcome using bilinear interpolation techniques, which first blocked the image and then separately computed the mapping inside these blocks. In order to enhance the value of a certain pixel point, the mapping relationship is obtained by the difference value of the mapping relationship of four blocks adjacent to the block where the pixel is located.
The ACE algorithm uses an unsharp masking technique that first divides the image into two parts. The unsharp mask part of low frequencies is mainly implemented by calculating the pixel average of a local area centered on the pixel. Local average, i.e. low frequency part. The high frequency part is obtained by subtracting the unsharp mask from the original image, and then the high frequency part is amplified and added into the unsharp mask, and finally the enhanced image is obtained.
Histogram equalization and a series of improved algorithms thereof have a good enhancement effect on blood vessel parts in an image, and because the algorithms are based on a gray image, a color image needs to be processed by multiple channels based on different color spaces respectively. Resulting in severe color shift of the processed image. Since the medical image itself has a high requirement for the fidelity of image color, it is currently seen that there is still a certain room for improvement in histogram equalization to be applied in the field of medical imaging.
In addition, the algorithm has the disadvantage of obvious artifacts or amplified noise parts, and the definition of the image is influenced to a certain extent.
The ACE algorithm has certain similarities to the algorithm of the present invention: the basic idea is to extract the high frequency part of the image containing the blood vessels. The separation used in ACE is achieved by calculating the pixel mean of a local area centered on the pixel. The separation precision of the high-frequency blood vessel part is not high, and part of fine blood vessels cannot be correctly identified, so the enhancement effect in the medical image containing the fine blood vessels still needs to be improved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a blood vessel enhancement method of an endoscope fluorescence image, which comprises the following steps:
s1, performing high-frequency extraction on the acquired image, and extracting a high-frequency image containing blood vessels;
s2, performing median filtering on the extracted high-frequency image to perform nonlinear suppression on noise points in a high-frequency part, so that the noise points can be eliminated to a greater extent;
s3, smoothing the acquired image by using Gaussian filtering;
and S4, performing superposition processing on the high-frequency image processed in the S2 and the image subjected to smoothing processing in the S3 to realize enhancement processing on the blood vessel.
The high-frequency separation precision is greatly improved compared with the ACE algorithm.
Since the separation of the high and low frequency parts is directly based on the color image, it does not cause too much color shift of the processed image.
Preferably, a bilateral filtering algorithm is adopted to perform high-frequency extraction on the acquired image.
Preferably, the acquired image is high frequency extracted using wavelet transform subchannels.
Compared with the prior art, the invention has the following beneficial effects:
1. near real-time enhancement
The use object of the algorithm is a real-time image acquired by an endoscope, so that the running time of the algorithm is high. Due to the fact that the time complexity of the algorithm is low, the near real-time enhancement effect of the video can be achieved.
2. Color fidelity
The color image is directly enhanced by using bilateral filtering, so that the image is more vivid while the details of the image are enhanced, and the phenomena of distortion, color cast and the like are not caused although the color is bright.
3. Improving blood vessel identification precision
Compared with the aforementioned ACE algorithm, the weighted value used in bilateral filtering not only takes the Euclidean distance of pixels into consideration, but also takes the radiation difference in the pixel range domain into consideration. The blood vessel identification accuracy is greatly improved.
4. Effective noise suppression
The algorithm of the invention performs secondary smoothing on the noise. Median filtering for the proposed high frequency part; gaussian smoothing of the original image before superposition. The influence of noise on image definition is effectively inhibited.
Drawings
Fig. 1 is a schematic flow chart according to a first embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the present invention provides a blood vessel enhancement method of endoscopic fluorescence image, comprising the following steps:
s1, performing high-frequency extraction on the acquired image by adopting a bilateral filtering algorithm, and extracting a high-frequency image containing blood vessels;
s2, performing median filtering on the extracted high-frequency image to perform nonlinear suppression on noise points in a high-frequency part, so that the noise points can be eliminated to a greater extent;
s3, smoothing the acquired image by using Gaussian filtering;
and S4, performing superposition processing on the high-frequency image processed in the S2 and the image subjected to smoothing processing in the S3 to realize enhancement processing on the blood vessel.
In an image, the gray scale of the edge changes rapidly, and the image edge is displayed corresponding to high frequency, namely high frequency. The blood vessels of the image are also regions with sharp changes in gray scale values, and the details appear due to the sharp changes in gray scale values.
Firstly, filtering an acquired fluorescent image by adopting a bilateral filter to obtain a low-frequency component part, performing difference operation on an original image and the low-frequency component, and obtaining a filtered high-frequency component, namely a high-frequency image containing a blood vessel part, according to an operation result.
The median filtering is a nonlinear smoothing technology, sets the gray value of each pixel point as the median of all the gray values of the pixel points in a certain neighborhood window of the point, and is a nonlinear signal processing technology capable of effectively suppressing noise based on the ordering statistical theory. The basic principle of median filtering is to replace the value of a point in a digital image or digital sequence with the median of the values of the points in a neighborhood of the point, so that the surrounding pixel values are close to the true values, thereby eliminating isolated noise points. The effect in the present algorithm is to be able to eliminate noise in the extracted high frequency part to a greater extent.
The gaussian filtering is a linear smooth filtering, is mainly suitable for eliminating gaussian noise, and is widely applied to the noise reduction process of images. The basic principle of gaussian filtering is a process of weighted averaging of the whole image, and the value of each pixel point is obtained by weighted averaging of itself or other pixels in the neighborhood. The effect in the present algorithm is to suppress noise in the original image.
And performing summation operation on the original image subjected to strengthening and smoothing of the high-frequency component, and readjusting the weight of the high-frequency component and the weight of the low-frequency component. The purpose of the algorithm is to enhance the high frequency parts representing the details, i.e. multiply the high frequency parts by a certain gain value and then superimpose back the original image after smoothing to obtain an enhanced image. The core of the third part of the algorithm is the calculation of the gain factor of the high frequency part, one is to set the gain value to a fixed value, and the other is to express the gain value as a variance related quantity. As will be explained later in the attached equations.
Let x (i, j) be flatPixel points m in the original image after slidingx(x, j) are high frequency detail part pixel points, and gain products are made for high frequency, including:
f(i,j)=x(i,j)+Gmx(x,j)
for gain G, the first scheme is to take a constant greater than 1 to achieve the enhancement effect, that is:
f(i,j)=x(i,j)+Cmx(x,j)
the second scheme represents a variation value inversely proportional to the local mean square error, namely:
in a high-frequency area of the image, the local mean square error is large, and the gain value is small, so that the situation of over-brightness cannot occur.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that modifications can be made by those skilled in the art without departing from the principle of the present invention, and these modifications should be considered within the scope of the present invention.
Claims (3)
1. A method of vascular enhancement of endoscopic fluorescence images, the method comprising the steps of:
s1, performing high-frequency extraction on the acquired image, and extracting a high-frequency image containing blood vessels;
s2, performing median filtering on the extracted high-frequency image to perform nonlinear suppression on noise points in a high-frequency part, so that the noise points can be eliminated to a greater extent;
s3, smoothing the acquired image by using Gaussian filtering;
and S4, performing superposition processing on the high-frequency image processed in the S2 and the image subjected to smoothing processing in the S3 to realize enhancement processing on the blood vessel.
2. The method for enhancing blood vessels of endoscopic fluorescence images as claimed in claim 1, wherein bilateral filtering algorithm is adopted to perform high frequency extraction on the collected images.
3. The method for enhancing blood vessels of endoscopic fluorescence images as claimed in claim 1, wherein the acquired images are high-frequency extracted using wavelet transform subchannel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010102478.0A CN111429362A (en) | 2020-02-19 | 2020-02-19 | Blood vessel enhancement method of endoscope fluorescence image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010102478.0A CN111429362A (en) | 2020-02-19 | 2020-02-19 | Blood vessel enhancement method of endoscope fluorescence image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111429362A true CN111429362A (en) | 2020-07-17 |
Family
ID=71551599
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010102478.0A Pending CN111429362A (en) | 2020-02-19 | 2020-02-19 | Blood vessel enhancement method of endoscope fluorescence image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111429362A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111968051A (en) * | 2020-08-10 | 2020-11-20 | 珠海普生医疗科技有限公司 | Endoscope blood vessel enhancement method based on curvature analysis |
CN113139929A (en) * | 2021-03-17 | 2021-07-20 | 浙江工业大学 | Gastrointestinal tract endoscope image preprocessing method comprising information screening and fusion repairing |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103514583A (en) * | 2012-06-30 | 2014-01-15 | 华为技术有限公司 | Image sharpening method and device |
CN104103040A (en) * | 2013-04-10 | 2014-10-15 | 上海联影医疗科技有限公司 | Image enhancement method |
US9508135B1 (en) * | 2015-11-05 | 2016-11-29 | Trieu-Kien Truong | System and method for image enhancement |
-
2020
- 2020-02-19 CN CN202010102478.0A patent/CN111429362A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103514583A (en) * | 2012-06-30 | 2014-01-15 | 华为技术有限公司 | Image sharpening method and device |
CN104103040A (en) * | 2013-04-10 | 2014-10-15 | 上海联影医疗科技有限公司 | Image enhancement method |
US9508135B1 (en) * | 2015-11-05 | 2016-11-29 | Trieu-Kien Truong | System and method for image enhancement |
Non-Patent Citations (2)
Title |
---|
D. REGAN等: "An Unsharp Masking Algorithm Embedded With Bilateral Filter System for Enhancement of Aerial Photographs" * |
李艳霞;: "一种改进图像增强化方法" * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111968051A (en) * | 2020-08-10 | 2020-11-20 | 珠海普生医疗科技有限公司 | Endoscope blood vessel enhancement method based on curvature analysis |
CN113139929A (en) * | 2021-03-17 | 2021-07-20 | 浙江工业大学 | Gastrointestinal tract endoscope image preprocessing method comprising information screening and fusion repairing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110428433B (en) | Canny edge detection algorithm based on local threshold | |
CN104240194B (en) | A kind of enhancement algorithm for low-illumination image based on parabolic function | |
CN103186888B (en) | A kind of method and device of removal CT picture noises | |
CN110889812B (en) | Underwater image enhancement method for multi-scale fusion of image characteristic information | |
US20030091232A1 (en) | Method and system for improving color images | |
CN107292834B (en) | Infrared image detail enhancement method | |
US20090060370A1 (en) | Filter for adaptive noise reduction and sharpness enhancement for electronically displayed pictures | |
CN104021532A (en) | Image detail enhancement method for infrared image | |
CN104157003B (en) | Thermal image detail enhancement method based on normal distribution adjustment | |
CN108280836B (en) | Image processing method and device | |
CN109447912B (en) | Fluorescent image self-adaptive enhancement and noise reduction method of fluorescent navigation endoscope system | |
CN107784639A (en) | A kind of polygon filtering and noise reduction method of unmanned aerial vehicle remote sensing image improvement | |
CN111429362A (en) | Blood vessel enhancement method of endoscope fluorescence image | |
CN116468641A (en) | Infrared blood vessel image enhancement processing method | |
CN117252773A (en) | Image enhancement method and system based on self-adaptive color correction and guided filtering | |
CN111047659B (en) | CT ring artifact correction method combined with filtering method | |
CN109064413B (en) | Image contrast enhancement method and image acquisition medical equipment adopting same | |
CN116468627A (en) | Endoscope image enhancement method based on secondary weighted rapid guided filtering | |
CN107392869B (en) | Face image filtering method based on edge-preserving filter | |
CN109685729B (en) | Poisson denoising method with pixel-level threshold self-adaption | |
CN108242049A (en) | A kind of full size DR Imaging enhanced processing methods for GPU optimizations | |
CN116630198A (en) | Multi-scale fusion underwater image enhancement method combining self-adaptive gamma correction | |
CN116188291A (en) | Rapid airborne dim light image enhancement method | |
Tie-Rui et al. | The research of X-ray bone fracture image enhancement algorithms | |
Batna | Comparative study between wavelet thresholding techniques (hard, soft and invariant-translation) in ultrasound images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200717 |