CN105405123A - Calibration method of brain CT image space coordinate - Google Patents
Calibration method of brain CT image space coordinate Download PDFInfo
- Publication number
- CN105405123A CN105405123A CN201510702115.XA CN201510702115A CN105405123A CN 105405123 A CN105405123 A CN 105405123A CN 201510702115 A CN201510702115 A CN 201510702115A CN 105405123 A CN105405123 A CN 105405123A
- Authority
- CN
- China
- Prior art keywords
- image
- brain
- cerebral
- pixel
- pixel points
- 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.)
- Granted
Links
Classifications
-
- 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
- G06T2207/30016—Brain
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
In the invention, through analyzing pixel points in a brain CT image, a correlation characteristic is extracted and a space coordinate of the brain CT images collected at different time is calibrated. Two collected brain CT image sets are a set A and a set B. From the set A, the four pixel points which are not located on a same plane are randomly extracted and a respective characteristic vector is recorded. For the set B, the four pixel points whose characteristic vectors form one-to-one correspondence with the characteristic vectors of the four pixel points in the set A. In order to verify correctness, a Euclidean distance among the four pixel points is calculated in the set B and is compared with the Euclidean distance among the corresponding four pixel points in the set A. Finally, through the space coordinates of the eight pixel points, calibration of the brain CT image space coordinate is performed. By using the method in an embodiment of the invention, there are the following advantages that the brain CT image space coordinate of a patient can be calibrated through analyzing the patient brain CT image sets collected at different time; and an effective calibration effect can be acquired through an experiment.
Description
Technical field
The present invention relates to field of computer technology, be specifically related to a kind of volume coordinate calibration steps of cerebral CT image.
Background technology
Cerebral CT inspection is a kind of method checked cranium brain by CT (CT scan).Cerebral CT image clearly can show the anatomy relationship of the different transversal section of cranium brain and concrete brain tissue structure.
In daily life, doctor is in order to accurately for patient diagnoses, can understand patient's intracerebral lesion situation, often require that patient does relevant cerebral CT inspection at different times.At present, for the assurance of patient's brain health situation, doctor can only by rule of thumb from CT image naked eyes observe.And the brain CT image collection that same patient collects at different times, between its image collection, the volume coordinate of institute's foundation is different.If can calibrate the volume coordinate between these brains CT image collection accurately, two secondary data are carried out the comparison of detailed, meticulous (grade data), so the recall rate of pathology and the accuracy of diagnosis will increase.
Summary of the invention
The object of this invention is to provide a kind of calibration steps of cerebral CT image space coordinate.Use embodiment provided by the invention, the volume coordinate of the cerebral CT image collection that can collect different times is calibrated.
The present invention, by analyzing the pixel in cerebral CT image, extracts the volume coordinate of correlated characteristic to the cerebral CT image that different times collects and calibrates.All brain CT images that a cerebral CT inspection collects by the present invention regard a set as, from cerebral CT image collection, first pre-service (CT value relevant treatment, rotation, convergent-divergent, enhancing etc.) is carried out to all images of this set, more multiple feature is extracted to each pixel often opened in image: gray scale, color, threshold value, gradient, texture, shape etc.Like this, an a pixel just corresponding proper vector.The cerebral CT image collection that twice collects by the present invention is designated as set A and set B respectively.From set A, randomly draw not 4 pixels at grade, record its respective proper vector, then calculate and record the Euclidean distance between these 4 points.For set B, then always can find 4 pixels, the proper vector one_to_one corresponding of 4 pixels in its proper vector and set A.In order to verify its correctness, the Euclidean distance between 4 pixels that can find in set of computations B, and the Euclidean distance between corresponding with set A 4 pixels is compared.Finally, the present invention utilizes the volume coordinate of these 8 pixels to carry out the calibration of cerebral CT image space coordinate.
The step of the method comprises:
1, cerebral CT image collection A and set B that same patient collects at different times is obtained;
2, pre-service is done to all images in two cerebral CT image collections;
3, image correlated characteristic is extracted, morphogenesis characters matrix;
4, from set A, randomly draw not 4 pixels at grade, record its respective proper vector a
1, a
2, a
3, a
4;
5, calculate and record the Euclidean distance between these 4 points;
6, undertaken getting rid of, comparing by the Euclidean distance between pixel, from set B, find 4 pixels, its proper vector b
1, b
2, b
3, b
4with the proper vector one_to_one corresponding of 4 pixels in set A, i.e. a
1=b
1, a
2=b
2, a
3=b
3, a
4=b
4;
7, the Euclidean distance corresponding with set A of the Euclidean distance in set of computations B between 4 pixels compares, and verifies;
8, the calibration of cerebral CT image space coordinate is carried out by the volume coordinate of above 8 pixels;
9, result is obtained;
Finally, implement the present invention and there is following beneficial effect:
The beneficial effect of the embodiment of the present invention is, by analyzing the cerebral CT image collection that same patient's different times collects, can calibrate, can obtain effectively calibrate effect through experimental verification patient's cerebral CT image space coordinate.
Accompanying drawing explanation
Accompanying drawing is the flow process of a kind of cerebral CT image space coordinate calibration method that the present invention proposes.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described, so that those skilled in the art understands the present invention better.
In the present embodiment, as shown in the figure, an algorithm flow is provided:
Step 101, obtain cerebral CT image collection A and set B that same patient collects at different times;
Step 102, pre-service is done to all images in two cerebral CT image collections;
Step 103, extraction image correlated characteristic, morphogenesis characters matrix.For one large little be the cerebral CT image of 512*512, multiple feature is extracted to each pixel, so a corresponding proper vector of pixel, the eigenmatrix of image then corresponding 512*512.
Step 104, from set A, randomly draw not 4 pixels at grade, record its respective proper vector a
1, a
2, a
3, a
4;
Step 105, calculate and record the Euclidean distance between these 4 points;
Step 106, undertaken getting rid of, comparing by the Euclidean distance between pixel, from set B, find 4 pixels, its proper vector b
1, b
2, b
3, b
4with the proper vector one_to_one corresponding of 4 pixels in set A, i.e. a
1=b
1, a
2=b
2, a
3=b
3, a
4=b
4;
Euclidean distance in step 107, set of computations B between 4 pixels Euclidean distance corresponding with set A compares, and verifies;
Step 108, carried out the calibration of cerebral CT image space coordinate by the volume coordinate of above 8 pixels;
Step 109, obtain result;
Although be described the illustrative embodiment of the present invention above; so that the technician of this technology neck understands the present invention; but should be clear; the invention is not restricted to the scope of embodiment; to those skilled in the art; as long as various change to limit and in the spirit and scope of the present invention determined, these changes are apparent, and all innovation and creation utilizing the present invention to conceive are all at the row of protection in appended claim.
Claims (1)
1. the calibration steps of a cerebral CT image space coordinate: it is characterized in that, the cerebral CT image that a cerebral CT inspection collects is regarded as a set, first cerebral CT image collection A and set B that same patient collects at different times is obtained, first pre-service is carried out to all images in two set, again multiple feature is extracted to each pixel often opening image, like this, a corresponding proper vector of pixel.From set A, randomly draw not 4 pixels at grade, record its respective proper vector a
1, a
2, a
3, a
4, then calculate and record the Euclidean distance between these 4 points.For set B, by getting rid of the Euclidean distance between the proper vector of pixel and pixel, compare, we always can find 4 pixels from set B, its proper vector b
1, b
2, b
3, b
4with the proper vector one_to_one corresponding of the pixel of 4 in set A, i.e. a
1=b
1, a
2=b
2, a
3=b
3, a
4=b
4.In order to verify its correctness, the Euclidean distance between 4 pixels found in we set of computations B, and and Euclidean distance in set A between corresponding pixel points compare.Finally, we carry out the calibration of cerebral CT image space coordinate by the volume coordinate of these 8 pixels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510702115.XA CN105405123B (en) | 2015-10-26 | 2015-10-26 | A kind of calibration method of cerebral CT image space coordinate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510702115.XA CN105405123B (en) | 2015-10-26 | 2015-10-26 | A kind of calibration method of cerebral CT image space coordinate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105405123A true CN105405123A (en) | 2016-03-16 |
| CN105405123B CN105405123B (en) | 2018-04-06 |
Family
ID=55470590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510702115.XA Expired - Fee Related CN105405123B (en) | 2015-10-26 | 2015-10-26 | A kind of calibration method of cerebral CT image space coordinate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105405123B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113091661A (en) * | 2021-03-29 | 2021-07-09 | 中国兵器科学研究院宁波分院 | Test block for acquiring accuracy of measuring aperture position accuracy of CT equipment and measuring method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090115867A1 (en) * | 2007-11-07 | 2009-05-07 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, image processing program, and program recording medium |
| CN101556692A (en) * | 2008-04-09 | 2009-10-14 | 西安盛泽电子有限公司 | Image mosaic method based on neighborhood Zernike pseudo-matrix of characteristic points |
| CN101714254A (en) * | 2009-11-16 | 2010-05-26 | 哈尔滨工业大学 | Registering control point extracting method combining multi-scale SIFT and area invariant moment features |
| CN103236064A (en) * | 2013-05-06 | 2013-08-07 | 东南大学 | Point cloud automatic registration method based on normal vector |
| CN104867137A (en) * | 2015-05-08 | 2015-08-26 | 中国科学院苏州生物医学工程技术研究所 | Improved RANSAC algorithm-based image registration method |
-
2015
- 2015-10-26 CN CN201510702115.XA patent/CN105405123B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090115867A1 (en) * | 2007-11-07 | 2009-05-07 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, image processing program, and program recording medium |
| CN101556692A (en) * | 2008-04-09 | 2009-10-14 | 西安盛泽电子有限公司 | Image mosaic method based on neighborhood Zernike pseudo-matrix of characteristic points |
| CN101714254A (en) * | 2009-11-16 | 2010-05-26 | 哈尔滨工业大学 | Registering control point extracting method combining multi-scale SIFT and area invariant moment features |
| CN103236064A (en) * | 2013-05-06 | 2013-08-07 | 东南大学 | Point cloud automatic registration method based on normal vector |
| CN104867137A (en) * | 2015-05-08 | 2015-08-26 | 中国科学院苏州生物医学工程技术研究所 | Improved RANSAC algorithm-based image registration method |
Non-Patent Citations (2)
| Title |
|---|
| 王邦国: "基于SIFT特征点精确匹配的图像拼接技术研究", 《大连大学学报》 * |
| 谷宗运 等: "基于SURF和改进的RANSAC算法的医学图像配准", 《中国医学影像学杂志》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113091661A (en) * | 2021-03-29 | 2021-07-09 | 中国兵器科学研究院宁波分院 | Test block for acquiring accuracy of measuring aperture position accuracy of CT equipment and measuring method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105405123B (en) | 2018-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2017292642B2 (en) | System and method for automatic detection, localization, and semantic segmentation of anatomical objects | |
| Liu et al. | Towards clinical diagnosis: Automated stroke lesion segmentation on multi-spectral MR image using convolutional neural network | |
| Kermi et al. | Fully automated brain tumour segmentation system in 3D‐MRI using symmetry analysis of brain and level sets | |
| EP2888718B1 (en) | Methods and systems for automatic location of optic structures in an image of an eye, and for automatic retina cup-to-disc ratio computation | |
| Roy et al. | A simple skull stripping algorithm for brain MRI | |
| WO2022088581A1 (en) | Training method for image detection model, related apparatus, device, and storage medium | |
| Mahmoudzadeh et al. | Extended hidden Markov model for optimized segmentation of breast thermography images | |
| Yeung et al. | Learning to map 2D ultrasound images into 3D space with minimal human annotation | |
| JP2014042684A (en) | Medical image processing device, and program | |
| Han et al. | Robust anatomical landmark detection with application to MR brain image registration | |
| TWI509534B (en) | Method of automatically calculating link strength of brain fiber tracts | |
| Singh et al. | Multivariate statistical analysis of deformation momenta relating anatomical shape to neuropsychological measures | |
| Khan et al. | Dual-3DM 3-AD: mixed transformer based semantic segmentation and triplet pre-processing for early multi-class Alzheimer’s diagnosis | |
| CN118037714A (en) | GPU-based medical endoscope image processing method, system and medium | |
| CN105405123A (en) | Calibration method of brain CT image space coordinate | |
| Li et al. | Segmentation of brain tissue based on connected component labeling and mathematic morphology | |
| CN114463288B (en) | Brain medical image scoring method and device, computer equipment and storage medium | |
| Elnakib et al. | Image-based detection of corpus callosum variability for more accurate discrimination between autistic and normal brains | |
| Ullah et al. | Histogram equalization based enhancement and mr brain image skull stripping using mathematical morphology | |
| Ekin | Feature-based brain mid-sagittal plane detection by RANSAC | |
| Chen et al. | Actual midline estimation from brain CT scan using multiple regions shape matching | |
| CN111127492B (en) | Method, apparatus, and computer-readable storage medium for brain image registration | |
| Mu et al. | A new pansharp based method for PET/CT image fusion | |
| CN104933712B (en) | Graph model methods of exhibiting based on brain CT images | |
| Liu et al. | Automatic detection of the anterior and posterior commissures on MRI scans using regression forests |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180406 Termination date: 20181026 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |