CN114663653B - Window level window width calculation method for medical image region of interest - Google Patents
Window level window width calculation method for medical image region of interest Download PDFInfo
- Publication number
- CN114663653B CN114663653B CN202210526046.1A CN202210526046A CN114663653B CN 114663653 B CN114663653 B CN 114663653B CN 202210526046 A CN202210526046 A CN 202210526046A CN 114663653 B CN114663653 B CN 114663653B
- Authority
- CN
- China
- Prior art keywords
- interest
- region
- frequency
- frequency histogram
- max
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 15
- 230000011218 segmentation Effects 0.000 claims abstract description 6
- 210000004072 lung Anatomy 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 8
- 230000003321 amplification Effects 0.000 claims description 2
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 210000001519 tissue Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002685 pulmonary effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000630 rising 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
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/30061—Lung
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a window level and window width calculation method for a medical image region of interest, which comprises the following steps: converting voxel gray values of the medical image data into Hu values; constructing a frequency histogram of the Hu value, and rejecting invalid groups in the frequency histogram according to a set threshold proportion; and calculating the Hu value range of the region of interest according to the frequency histogram after the invalid group is removed, and calculating the window level width according to the Hu value range. The invention can obtain the window width of the focus part by segmentation calculation aiming at the medical images collected by different image devices or medical images after other processing, and the window width is mapped to the display screen for display.
Description
Technical Field
The invention relates to the technical field of medical images, in particular to a window level and window width calculation method for a region of interest of a medical image.
Background
Most medical images come from CT, DR, US and other image equipment, the bit depth is usually 12-16 bit, and if doctors need to diagnose, the proper window level and window width need to be adjusted according to different parts, and the gray level of a specific color gamut range can be displayed on a display screen (most 8 bit).
In the aspects of diagnosis, treatment and the like of a focus of a patient, particularly a pulmonary nodule, doctors pay attention to the fact that the texture of the focus part, peripheral organs of the focus part and the like can be clearly and accurately displayed, and medical images acquired by different imaging devices or medical images processed by other software cannot well display the characteristics of the focus part on a display screen.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the defects, the invention provides a self-adaptive window method of a medical image region of interest, aiming at medical images acquired by different image equipment or medical images processed by other software, the window level window width of a focus part can be obtained by segmentation calculation and is mapped to a display screen for display.
The technical scheme is as follows:
a window level window width calculation method for a region of interest of a medical image comprises the following steps:
converting voxel gray values of the medical image data into Hu values;
constructing a frequency histogram of the Hu value, and rejecting invalid groups in the frequency histogram according to a set threshold proportion;
and calculating the Hu value range of the region of interest according to the frequency histogram after the invalid group is removed, and calculating the window level width according to the Hu value range.
The removing of the invalid group in the frequency histogram according to the set threshold proportion specifically comprises:
dividing the number of wave crests in the frequency histogram;
if the number of the maximum wave crests is not less than the maximum number of the wave crests set according to the region of interest, eliminating the interference wave crests at the two ends of the frequency histogram according to a set threshold proportion, and taking a group where the first wave trough is located and a group where the last wave trough is located in the effective group obtained after the interference wave crests are eliminated as groups where the two ends of the effective group are located;
and if the number of the wave crests is less than the maximum number of the wave crests set according to the region of interest, eliminating interference groups at two ends of the frequency histogram according to a set threshold value proportion, and taking a starting group and an ending group in the effective group obtained after the interference groups are eliminated as groups at two ends of the effective group.
The number of peaks in the segmentation frequency histogram is specifically as follows:
according to the maximum frequency F in the frequency histogram max Setting a frequency threshold F of a frequency histogram p Definition of the cut-off frequency F C Starting from 0, continuously according to the step length d of the iteration frequency p Lifting F C Dividing the frequency histogram according to the number of the identified troughs in the frequency histogram to obtain isolated peaks in the frequency histogram until the number n of the peaks in the obtained frequency histogram peak The maximum number N of wave crests greater than the set peak Or the cut-off frequency F C Exceeding a frequency threshold F p 。
The frequency threshold value F p Is set to 0.1F max 。
The Hu value range of the region of interest calculated according to the frequency histogram after the invalid group is removed is specifically as follows:
defining minimum value Y of Hu values on frequency histogram min And maximum value Y max The number of groups of the frequency histogram is N hist Then the width of the histogram is g = (Y) max -Y min )/N hist ；
Defining the group at two ends of the effective group of the frequency histogram as N min And N max Then N is min And N max The corresponding Hu values are:
P min =Y min +(N min -α)*g
P max =Y max +(N max +β)*g
wherein, alpha and beta are respectively a reduction coefficient and an amplification coefficient;
so as to calculate the Hu value range [ P ] of the interested region of the medical image data min , P max ]。
And if the region of interest is a lung, the maximum number of peaks is set to 2.
The β > α.
The α =0 and the β = 1.
The set threshold ratio is set to 10%.
Further comprising the step of mapping to a display screen:
transforming Hu value range of region of interest into corresponding voxel gray value range [ pixel ] min , pixel max ]And mapping the image to the display range of the display screen by the following formula:
(pixel-pixel min )/(pixel max -pixel min )*256
wherein pixels represent the gray value of a certain voxel in the medical image data.
Has the advantages that: the invention can obtain the window width of the focus part by segmentation calculation aiming at the medical images collected by different image devices or the medical images processed by other software, and the window width is mapped to the display screen to be displayed, thereby showing the substantial characteristics of the interested region to doctors more clearly.
Drawings
FIG. 1 is a flowchart illustrating a window level and window width calculation method for a region of interest of a medical image according to the present invention;
FIG. 2 is a diagram of a four-view of a default window width of a CT image;
FIG. 3 is a frequency histogram of medical images;
FIG. 4 is a histogram with multiple peaks present;
FIG. 5 shows the divisionUnder the condition that the number of the obtained wave crests exceeds the maximum number of the wave crests, calculating the groups N where the two ends of the concentrated wave crests are located min And N max A schematic diagram of (a);
FIG. 6 is a diagram showing the calculation of the groups N where the two ends of the concentrated peaks are located when the number of the divided peaks does not exceed the maximum number of the peaks min And N max A schematic diagram of (a);
fig. 7 is a result image after window level window width adjustment.
Detailed Description
The invention is further elucidated with reference to the drawings and the embodiments.
The window level window width calculation method of the medical image region of interest of the invention is shown in fig. 1, and comprises the following steps:
(1) converting voxel gray values of the medical image data into Hu values;
the method comprises the steps of converting voxel gray values of medical image data from different sources (such as medical image data acquired by CT, DR, US and other image equipment or medical image data processed by other software) into Hu values, taking DICOM image data as an example, as shown in FIG. 2, because a doctor focuses on Hu values in the operation process, the medical image data needs to be converted;
the method specifically comprises the following steps: reading Slope (Tag 0028| 1052) and Intercept (Tag 0028| 1053) from the medical image data, and converting voxel gray values in the medical image data into Hu values commonly used by doctors according to a formula Hu = pixel × Slope + Intercept, wherein pixel represents the gray value of a certain voxel in the medical image data;
(2) constructing a frequency histogram of the Hu value in the medical image data;
as shown in FIG. 3, the leftmost end and the rightmost end of the frequency histogram are the minimum value Y of the Hu values of the medical image data min And maximum value Y max The number of groups of the frequency histogram is N hist (recommended set to 256), the width of the histogram is g = (Y) max -Y min )/N hist ；
(3) Eliminating invalid data;
in the invention, the Hu values converted from the voxel gray value in the lung image data in the step (1) show peak values in different regions in a frequency histogram, as shown in FIG. 4, the Hu values in the lung image data are mainly concentrated in a low-value region, the Hu values in the lung part account for a greater proportion in the low-value region relative to the Hu values of hard tissues such as bones, and troughs are inevitably separated between two adjacent peak values; in addition, there may be interference of air Hu values of alveoli, outside of the body, etc., but the overall specific gravity is not high; the Hu value of the lung part shows that concentrated peaks exist in the image data of the lung tissue in the frequency histogram, and invalid peaks are removed according to the concentrated peaks; the method specifically comprises the following steps:
number n of wave crests in iterative segmentation frequency histogram peak ：
According to the maximum frequency F in the frequency histogram max (i.e. the percentage of voxels in the highest peak in the frequency histogram to all voxels), a frequency threshold F for the frequency histogram is set p In the present invention, the frequency threshold F p Is set to 0.1F max (ii) a Defining the cut-off frequency as F C Starting from 0, continuously according to the iteration frequency step d p Raising the cut-off frequency F C At a frequency of 0 to a cut-off frequency F C In the interval, the number of isolated peaks in the frequency histogram is obtained by dividing according to the number of identified troughs in the frequency histogram until the number n of peaks in the frequency histogram peak The number of the wave crests N is larger than or equal to the preset maximum number peak Or the cut-off frequency F C Exceeding a frequency threshold F p (ii) a Wherein, the maximum number of wave crests N peak Determined according to the actual focus part, if the focus is lung, the maximum number of wave crests N peak The recommended setting is 2.
In the present invention, the iteration frequency step d p Is set to 0.1F p ；
All wave crests are segmented in an envelope curve of the frequency histogram, so that invalid data can be filtered subsequently to obtain medical image data of the region of interest, and the appropriate window level width can be calculated.
Aiming at an interested region (namely a focus part), because concentrated interference of high Hu value regions such as local bones and metal ornaments or low Hu value regions such as external air may exist, interference of wave crests exists at two ends of a frequency histogram and needs to be removed;
number n of wave crests obtained by division peak ≥N peak If the local interference of the high gray value cluster or the low gray value cluster exists and is distributed at two ends, filtering the data lower than N according to the set threshold value proportion T hist T and higher than N hist Interference peaks of (1-T), i.e. if the group in which the peak is located is not in N hist T to N hist Within the range of 1-T, removing to obtain a group with the first wave trough and a group with the last wave trough in the effective group left after filtering the interference wave crest, and obtaining a group N with the two ends of the effective group min And N max As shown in fig. 5; in the invention, the set threshold value proportion T is determined according to the actual focus part, and if the focus is a lung, the threshold value proportion T is set to be 10%.
Peak n obtained by dividing peak < N peak If the background is interfered or the background is image data of lung textures, which indicates that the frequency histogram can not segment the Hu value of the lung medical image from other surrounding tissues, the histogram group in the concentrated wave crest is deleted in the same way, except that the filtering is lower than N according to the set threshold value proportion T hist T and higher than N hist The interference group of (1-T) is filtered to obtain the start group and the end group in the remaining effective groups, namely the groups N where the two ends of the effective group are located min And N max As shown in FIG. 6, data in the scale of T and 1-T is retained;
(4) after eliminating invalid data, calculating the Hu value range of the region of interest of the medical image data;
calculating the group N of both ends of the active group min And N max Corresponding Hu values:
P min =Y min +(N min -α)*g
P max =Y max +(N max +β)*g
the focus is taken as a lung, the lung tissue comprises lung parenchyma, skin, heart and other tissues, the lung parenchyma part is more concentrated on the tail part of the rising edge of the peak, the tail part of the falling edge has a higher Hu value and can be the skin, the heart and the like, a doctor pays more attention to the lung parenchyma, and therefore the focus is set to be beta > alpha to keep more images of the lung parenchyma; preferably, α =0, β = 1;
so as to obtain Hu value range [ P ] of the interested region of the medical image data min , P max ]And calculating the window level wl and the window width ww of the region of interest according to the calculation:
wl=(P max +P min )/2
ww=P max –P min
then, according to the calculation of the step (1), the Hu value range of the interested region is transformed into a corresponding voxel gray value range [ pixel ] min , pixel max ]Linearly mapping the medical image data in the corresponding voxel gray value range to a display range (0-256) of a display screen, as shown in fig. 7, so that the lung parenchymal texture can be more clearly shown to a doctor;
the specific mapping formula is as follows:
(pixel-pixel min )/(pixel max -pixel min )*256。
the method comprises the steps of designing an algorithm through the characteristic that a frequency histogram corresponding to voxels of a lung is mainly concentrated in a low Hu value, converting an image from a voxel value to the Hu value, calculating the number of peaks of the frequency histogram, eliminating anomalies in the peaks, calculating end point values of concentrated peak groups to obtain a Hu range value of an interested area, and finally linearly mapping medical image data in a corresponding voxel gray value range to a display range of a display screen, so that the substantial features of the interested area can be more clearly shown to a doctor.
Although the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the details of the foregoing embodiments, and various equivalent changes (such as number, shape, position, etc.) may be made to the technical solution of the present invention within the technical spirit of the present invention, and these equivalent changes are all within the protection scope of the present invention.
Claims (9)
1. A window level window width calculation method for a medical image region of interest is characterized by comprising the following steps: the method comprises the following steps:
converting voxel gray values of the medical image data into Hu values;
constructing a frequency histogram of the Hu value, and dividing the number of wave crests in the frequency histogram; if the number of the maximum wave crests is not less than the maximum number of the wave crests set according to the region of interest, eliminating the interference wave crests at the two ends of the frequency histogram according to a set threshold proportion, and taking a group where the first wave trough is located and a group where the last wave trough is located in the effective group obtained after the interference wave crests are eliminated as groups where the two ends of the effective group are located; if the number of the maximum wave crests is less than the maximum number of the wave crests set according to the region of interest, eliminating interference groups at two ends of the frequency histogram according to a set threshold value proportion, and taking a starting group and an ending group in an effective group obtained after the interference groups are eliminated as groups where two ends of the effective group are located;
and mapping and calculating according to the groups at the two ends of the effective group of the frequency histogram, the width of the frequency histogram and the minimum value and the maximum value of the Hu value of the frequency histogram to obtain the Hu value range of the region of interest, and calculating according to the Hu value range to obtain the window level width.
2. The method of claim 1, wherein the window level and width of the region of interest in the medical image is calculated by: the number of peaks in the segmentation frequency histogram is specifically as follows:
according to the maximum frequency F in the frequency histogram max Setting a frequency threshold F of a frequency histogram p Definition of the cut-off frequency F C Starting from 0, continuously according to the iteration frequency step d p Lifting F C Dividing the frequency histogram according to the number of the identified troughs in the frequency histogram to obtain isolated peaks in the frequency histogram until the number n of the peaks in the obtained frequency histogram peak The maximum number N of wave crests greater than the set peak Or the cut-off frequency F C Exceeding a frequency threshold F p 。
3. The window width of the region of interest in medical images of claim 2The calculation method is characterized in that: the frequency threshold value F p Is set to 0.1F max 。
4. The method of claim 1, wherein the window level and width of the region of interest in the medical image is calculated by: the Hu value range of the region of interest calculated according to the frequency histogram after the invalid group is removed is specifically as follows:
defining minimum value Y of Hu values on frequency histogram min And maximum value Y max The number of groups of the frequency histogram is N hist Then the width of the histogram is g = (Y) max -Y min )/N hist ；
Defining the group at two ends of the effective group of the frequency histogram as N min And N max Then N is min And N max The corresponding Hu values are:
P min =Y min +(N min -α)*g
P max =Y max +(N max +β)*g
wherein, alpha and beta are respectively a reduction coefficient and an amplification coefficient;
so as to calculate the Hu value range [ P ] of the interested region of the medical image data min , P max ]。
5. The method of claim 4, wherein the window level and width of the region of interest in the medical image is calculated by: and if the region of interest is a lung, the maximum number of peaks is set to 2.
6. The method of claim 5, wherein the window level and width of the region of interest in the medical image is calculated by: the β > α.
7. The method of claim 6, wherein the window level and width of the region of interest in the medical image is calculated by: the α =0 and the β = 1.
8. The method of claim 1, wherein the window level and width of the region of interest in the medical image is calculated by: the set threshold ratio is set to 10%.
9. The method of claim 1, wherein the window level and width of the region of interest in the medical image is calculated by: further comprising the step of mapping to a display screen:
transforming Hu value range of region of interest into corresponding voxel gray value range [ pixel ] min , pixel max ]And mapping the image to the display range of the display screen by the following formula:
(pixel-pixel min )/(pixel max -pixel min )*256
wherein pixels represent the gray value of a certain voxel in the medical image data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210526046.1A CN114663653B (en) | 2022-05-16 | 2022-05-16 | Window level window width calculation method for medical image region of interest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210526046.1A CN114663653B (en) | 2022-05-16 | 2022-05-16 | Window level window width calculation method for medical image region of interest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114663653A CN114663653A (en) | 2022-06-24 |
| CN114663653B true CN114663653B (en) | 2022-08-12 |
Family
ID=82037859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210526046.1A Active CN114663653B (en) | 2022-05-16 | 2022-05-16 | Window level window width calculation method for medical image region of interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114663653B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115457039B (en) * | 2022-11-14 | 2023-04-07 | 北京精诊医疗科技有限公司 | Window width and window position self-adaptive adjusting method for HCC multi-phase data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105023273A (en) * | 2015-07-01 | 2015-11-04 | 张逸凡 | ROI (Region of Interest) window width and position adjusting method of medical image |
| CN108601570A (en) * | 2016-02-04 | 2018-09-28 | 三星电子株式会社 | Tomographic image processing equipment and method and recording medium related with method |
| CN110570424A (en) * | 2019-10-08 | 2019-12-13 | 中国人民解放军陆军军医大学 | aortic valve semi-automatic segmentation method based on CTA dynamic image |
| CN110853024A (en) * | 2019-11-14 | 2020-02-28 | 北京推想科技有限公司 | Medical image processing method, medical image processing device, storage medium and electronic equipment |
| CN111166362A (en) * | 2019-12-31 | 2020-05-19 | 北京推想科技有限公司 | Medical image display method and device, storage medium and electronic equipment |
| CN112562829A (en) * | 2021-02-19 | 2021-03-26 | 南京景三医疗科技有限公司 | Method for adaptively generating DICOM image default window width and window level |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709929A (en) * | 2016-12-30 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for displaying interesting region of medical image |
| CN114098769A (en) * | 2020-08-31 | 2022-03-01 | 上海西门子医疗器械有限公司 | Medical image display method and module and medical image equipment |
-
2022
- 2022-05-16 CN CN202210526046.1A patent/CN114663653B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105023273A (en) * | 2015-07-01 | 2015-11-04 | 张逸凡 | ROI (Region of Interest) window width and position adjusting method of medical image |
| CN108601570A (en) * | 2016-02-04 | 2018-09-28 | 三星电子株式会社 | Tomographic image processing equipment and method and recording medium related with method |
| CN110570424A (en) * | 2019-10-08 | 2019-12-13 | 中国人民解放军陆军军医大学 | aortic valve semi-automatic segmentation method based on CTA dynamic image |
| CN110853024A (en) * | 2019-11-14 | 2020-02-28 | 北京推想科技有限公司 | Medical image processing method, medical image processing device, storage medium and electronic equipment |
| CN111166362A (en) * | 2019-12-31 | 2020-05-19 | 北京推想科技有限公司 | Medical image display method and device, storage medium and electronic equipment |
| CN112562829A (en) * | 2021-02-19 | 2021-03-26 | 南京景三医疗科技有限公司 | Method for adaptively generating DICOM image default window width and window level |
Non-Patent Citations (1)
| Title |
|---|
| 一种16位灰度图像自动调窗算法;吕磊等;《光电技术应用》;20160815(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114663653A (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7792339B2 (en) | Method and apparatus for intracerebral hemorrhage lesion segmentation | |
| CN106909947B (en) | Mean Shift algorithm-based CT image metal artifact elimination method and system | |
| JPH08329242A (en) | Method for enhancement of image quality | |
| JP2011514822A (en) | Method and system for segmenting CT scan data | |
| CN114529475B (en) | Image enhancement method and system based on two-dimensional gamma correction and tone mapping | |
| JPH10124664A (en) | Homogeneous and heterogeneous dynamic range remapping device for optimum image display and its method | |
| JP2008048906A (en) | Medical image processing apparatus and medical image processing method | |
| CN101105862A (en) | Medical image window parameter self-adaptive regulation method | |
| CN114663653B (en) | Window level window width calculation method for medical image region of interest | |
| US8520916B2 (en) | Enhancement of region of interest of radiological image | |
| DE102005036412A1 (en) | Improved GGN segmentation in lung recordings for accuracy and consistency | |
| CN110163825B (en) | Human embryo heart ultrasonic image denoising and enhancing method | |
| CN114677391A (en) | Spine image segmentation method | |
| CN117474823B (en) | CT data processing system for pediatric infectious inflammation detection assistance | |
| US20220138936A1 (en) | Systems and methods for calcium-free computed tomography angiography | |
| CN110335203B (en) | Method for reinforcing object contour of image in real-time image | |
| WO2019220825A1 (en) | Chest x-ray image tone scale conversion method, image tone scale conversion program, image tone scale conversion device, server device, and conversion method | |
| CN112712540B (en) | Lung bronchus extraction method based on CT image | |
| CN112308823B (en) | Method and device for positioning region of interest in medical image | |
| CN112562829B (en) | Method for adaptively generating DICOM image default window width and window level | |
| CN117201800B (en) | Medical examination big data compression storage system based on space redundancy | |
| Dawood et al. | The importance of contrast enhancement in medical images analysis and diagnosis | |
| Na'am et al. | Filter technique of medical image on multiple morphological gradient (MMG) method | |
| Kalhor et al. | Assessment of histogram-based medical image contrast enhancement techniques; an implementation | |
| CN116363020A (en) | Lung cancer image intelligent recognition enhancement system |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 210000 building 3, No. 34, Dazhou Road, Yuhuatai District, Nanjing, Jiangsu Province Patentee after: Tuodao Medical Technology Co.,Ltd. Address before: 210000 building 3, No. 34, Dazhou Road, Yuhuatai District, Nanjing, Jiangsu Province Patentee before: Nanjing Tuodao Medical Technology Co.,Ltd. |