CN113554663B - System for automatically analyzing PET (positron emission tomography) images of dopamine transporter based on CT (computed tomography) structural images - Google Patents
System for automatically analyzing PET (positron emission tomography) images of dopamine transporter based on CT (computed tomography) structural images Download PDFInfo
- Publication number
- CN113554663B CN113554663B CN202110637657.9A CN202110637657A CN113554663B CN 113554663 B CN113554663 B CN 113554663B CN 202110637657 A CN202110637657 A CN 202110637657A CN 113554663 B CN113554663 B CN 113554663B
- Authority
- CN
- China
- Prior art keywords
- image
- striatum
- pet
- images
- dat
- 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
- 102000006441 Dopamine Plasma Membrane Transport Proteins Human genes 0.000 title claims abstract description 26
- 108010044266 Dopamine Plasma Membrane Transport Proteins Proteins 0.000 title claims abstract description 26
- 238000002591 computed tomography Methods 0.000 title description 58
- 238000002600 positron emission tomography Methods 0.000 title description 23
- 210000001577 neostriatum Anatomy 0.000 claims abstract description 75
- 238000005192 partition Methods 0.000 claims abstract description 42
- 230000011218 segmentation Effects 0.000 claims abstract description 24
- 206010034010 Parkinsonism Diseases 0.000 claims abstract description 17
- 208000027089 Parkinsonian disease Diseases 0.000 claims abstract description 15
- 238000010586 diagram Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 239000012216 imaging agent Substances 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 210000004556 brain Anatomy 0.000 claims description 24
- 230000002146 bilateral effect Effects 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 18
- 230000037406 food intake Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 210000003625 skull Anatomy 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 210000001175 cerebrospinal fluid Anatomy 0.000 claims description 5
- 210000004884 grey matter Anatomy 0.000 claims description 5
- 210000004872 soft tissue Anatomy 0.000 claims description 5
- 210000004885 white matter Anatomy 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000009413 insulation Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 6
- 230000001360 synchronised effect Effects 0.000 abstract description 5
- 238000003748 differential diagnosis Methods 0.000 abstract 1
- 210000002637 putamen Anatomy 0.000 description 19
- 210000001159 caudate nucleus Anatomy 0.000 description 8
- 208000018737 Parkinson disease Diseases 0.000 description 7
- 238000002595 magnetic resonance imaging Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000004445 quantitative analysis Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000007659 motor function Effects 0.000 description 2
- 230000037152 sensory function Effects 0.000 description 2
- 208000024827 Alzheimer disease Diseases 0.000 description 1
- 238000012879 PET imaging Methods 0.000 description 1
- 206010033799 Paralysis Diseases 0.000 description 1
- 206010035664 Pneumonia Diseases 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000008407 joint function Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 210000001161 mammalian embryo Anatomy 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004770 neurodegeneration Effects 0.000 description 1
- 208000015122 neurodegenerative disease Diseases 0.000 description 1
- 238000002610 neuroimaging Methods 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 238000009206 nuclear medicine Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 208000037821 progressive disease Diseases 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- 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
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10104—Positron emission tomography [PET]
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Physiology (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- High Energy & Nuclear Physics (AREA)
- Optics & Photonics (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Nuclear Medicine (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a system for automatically analyzing a dopamine transporter PET image based on a CT structural image, which comprises an image acquisition module, an image preprocessing module, a DAT-PET functional image automatic segmentation module and an automatic numerical extraction and calculation module for double-sided striatum sub-partitions, wherein the fine automatic segmentation of striatum areas and striatum sub-partitions (comprising double-sided front and rear shell cores and double-sided front and rear tail cores) in the DAT-PET functional image is performed based on the CT structural image. According to the invention, the striatum of the DAT-PET functional image is subjected to fine automatic segmentation through the structural CT structure diagram of synchronous scanning, three-dimensional reconstruction display is performed, the imaging agent uptake value and the uptake value ratio of the striatum sub-partition are automatically calculated, the interpretation of the DAT-PET functional image can be effectively assisted by a clinician, a reliable basis is provided for diagnosis and differential diagnosis of parkinsonism, and high robustness is realized.
Description
Technical Field
The invention relates to the technical fields of medical image processing and nuclear medicine, in particular to a system for automatically analyzing PET images of dopamine transporter based on CT structural images.
Background
Parkinson's Disease (PD) is a second major neurodegenerative Disease following alzheimer's Disease. PD is a chronic progressive disease, patients gradually lose working capacity and autonomous movement capacity, patients become stiff, difficult to move and paralyzed in bed until the disease is advanced, and finally, the patients often die from various complications such as pneumonia and the like, so that great pain is brought to the patients, and serious mental and economic burden is brought to families and society. At present, the prevalence rate of PD in people over 65 years old in China is as high as 1.7%. And it is predicted that in the 5 countries with the largest European population and the 10 countries with the largest global population, the number of parkinsonism will double in 2030, and China will become one of the fastest world parkinsonism patients, and the number of parkinsonism patients can reach 500 ten thousand by 2030, accounting for 57% of the total number of patients in the 15 countries. Therefore, along with the increasing degree of aging of China society, the Parkinson's disease brings serious challenges to China.
The early and accurate diagnosis of the parkinsonism and the timely intervention of the parkinsonism can effectively control and delay the development of parkinsonism, can obviously improve the life quality of patients and obviously reduce the death rate of the patients. PET molecular imaging techniques, particularly dopamine transporter-based imaging techniques (DAT-PET), have become a key basis for the early and accurate diagnosis of parkinson's disease. The dopamine transporter is mainly concentrated in the brain striatum structure, and the striatum of different types of parkinsonism patients can show different dopamine transporter change modes. Therefore, quantitative analysis of dopamine transporter for striatal sub-division is key to DAT-PET functional image assessment and diagnosis. However, the striatum volume is small, the sub-partition division is complex, the manual sketching and measurement are only performed by a doctor, a certain operation difficulty is achieved, a large amount of time is consumed, the measurement accuracy is affected by the experience of the doctor, and the repeatability and the robustness are poor. In addition, the transect image cannot intuitively reflect the overall change in the uptake value of the striatal dopamine transporter, affecting the effect of visual observation. Therefore, it is important to provide an accurate, fast, three-dimensionally viewable automated analysis system for DAT-PET functional images.
The challenges faced by the prior art are mainly: 1. the uptake value of the striatum DAT imaging agent of the patient suffering from the Parkinson's syndrome can be obviously reduced, and the striatum segmentation based on the DAT-PET functional image alone can cause a great amount of information loss of a lesion area; 2. the different brain structures, particularly the striatum structures, have larger difference, the DAT-PET functional image segmentation by using the template constructed by the normal DAT-PET functional image cannot avoid stretching or twisting the true striatum structure, and the diagnosis result of the DAT-PET functional image is likely to be affected by the subtle structural change; 3. the method of registering and segmenting based on MRI structural images is currently used in a large number, but in the case of scanning by a non-PET/MR synchronous examination device, patient PET and MRI data are not completely matched, and the registration segmentation using such images also causes large errors. And, this type of method cannot be applied to patients lacking MRI scan data of the skull.
In summary, providing a system for automated segmentation of striatum and automated extraction and quantitative analysis of striatum sub-partition uptake values by using structural information of CT structural images of PET/CT synchronous scanning is an important technical problem to be solved.
Disclosure of Invention
Aiming at the defects of the existing automatic analysis technology of the PET imaging image of the dopamine transporter of the parkinsonism patient, the invention provides a system for automatically analyzing the PET image of the dopamine transporter based on a CT structural image, which is used for automatically segmenting the striatum of the parkinsonism patient and analyzing the uptake condition of the imaging agent of the dopamine transporter so as to assist in improving the accuracy and the efficiency of parkinsonism diagnosis.
The aim of the invention is realized by the following technical scheme: a system for automatically analyzing a PET image of a dopamine transporter based on a CT structural image comprises an image acquisition module, an image preprocessing module, a DAT-PET functional image automatic segmentation module and an automatic numerical extraction and calculation module of double-sided striatum sub-partitions;
the image acquisition module is used for acquiring images, the subject acquires 3D brain images on the PET/CT scanner, simultaneously acquires DAT-PET functional images and CT structural images under the same body position state, and converts the DAT-PET functional images and CT structural images into NIFTI image formats.
The image preprocessing module is used for preprocessing the image acquired by the image acquisition module, fusing the DAT-PET functional image and the CT structural image acquired by the image acquisition module through the SPM12, and displaying the DAT-PET functional image and the CT structural image data as three-dimensional images, so that a clinician can conveniently perform omnibearing visual assessment.
The automated segmentation module of the DAT-PET functional image automatically segments striatum and striatum sub-partitions of the DAT-PET functional image based on a CT structure diagram, wherein the striatum sub-partitions comprise a bilateral front shell core, a bilateral rear shell core, a bilateral front tail core, a bilateral back tail core and a bilateral volt-insulation core, and the automated segmentation module comprises the following specific processes:
1) Brain structures within the CT image are segmented into background signals, skull, grey matter, white matter, cerebrospinal fluid and soft tissue. And (3) carrying out CT structural image space standardization according to the segmentation result to obtain a conversion matrix for converting the CT structural image from the individual space to the MNI space.
2) Masks for each sub-partition of the striatum are made by a GSK template.
3) And carrying out inverse transformation on the shade of each sub-partition of the striatum through a transformation matrix, and further acquiring DAT-PET segmented images of the striatum and each sub-partition based on the CT and DAT-PET functional images of synchronous scanning.
The automatic numerical extraction and calculation module of the double-sided striatum subarea is used for automatically calculating the uptake value of the imaging agent of the double-sided subarea and the uptake value ratio with identification significance for the parkinsonism and is used for quantitatively analyzing the change condition of the dopamine transporter.
Further, the automatic numerical extraction and calculation module of the double-sided striatum sub-partition sets a striatum fine sub-partition mask of the individual space as a region of interest (region of interest, ROI), extracts gray values of all pixels in the ROI, and takes an average value as an imaging agent uptake value of the region.
Further, the automatic numerical extraction and calculation module of the double-sided striatum sub-partition has an identifiable ingestion value ratio of left side shell core rear ingestion value/right side shell core rear ingestion value, single side shell core front specific ingestion value/shell core rear ingestion value, and single side tail core ingestion value/shell core rear ingestion value.
Further, the mask of each sub-partition of the striatum is inverse transformed to the individual space by using the transformation matrix, and the DAT-PET functional image is segmented using the mask to extract the striatum and each sub-partition segmented image.
The beneficial effects of the invention are as follows:
(1) The method can automatically divide the striatum of the Parkinson syndrome patient and accurately analyze the ingestion condition of the dopamine transporter imaging agent, and the traditional quantitative analysis needs a doctor to observe and judge frame by frame, is very dependent on the experience and technical level of the doctor, causes low repeatability and low robustness, and consumes a great deal of time.
(2) The method can display fine sub-partition distribution of the striatum three-dimensional space by using a GSK template to manufacture a mask and extract the ROI, compared with the traditional manual method for drawing the ROI on a single two-dimensional layer, the sub-partition division of the system is more accurate, and the condition of a plurality of layers is considered, so that the information is more complete.
(3) The method is more in line with the habit of clinical traditional quantitative analysis, and the segmentation quality is more convenient to evaluate visually. In addition, the method is less dependent on a spatial normalization algorithm, and errors caused by spatial normalization are not easy to introduce.
(4) The DAT-PET functional image segmentation is based on CT brain structure images obtained by synchronous scanning, is easier to obtain than an MRI structure phase, and reduces errors caused by information loss in the image registration and fusion processes to the greatest extent.
(5) The three-dimensional structure type dopamine transporter imaging agent can display the uptake condition of the striatum dopamine transporter imaging agent, so that a clinician can conveniently judge the reduction part, degree and range of the patient dopamine transporter in an integral and visual view, and convenience is provided for clinical diagnosis.
(6) The fine striatum sub-partition segmentation results may be a basis for further image analysis techniques including conventional ROI analysis, image histology, deep learning, etc.
Drawings
FIG. 1 is a block diagram of an automated analysis system for DAT-PET functional images based on PET/CT structural images, in accordance with one embodiment of the present invention;
FIG. 2 is a flow chart of an implementation of one embodiment of the present invention;
FIG. 3 is a DAT-PET/CT original image, wherein the left side of FIG. 3 is a CT structure image, and the right side of FIG. 3 is a DAT-PET functional image;
FIG. 4 is a fusion map of a DAT-PET functional image and a CT structural image;
FIG. 5 is an automatic segmentation diagram of CT structural images;
FIG. 6 is a striatum fine sub-partitioned template made from a GSK template and a striatum structure template;
fig. 7 applies the inverse transformed striatum fine sub-partition template to a DAT-PET image.
Detailed Description
The invention will be described in further detail with reference to the drawings and the specific examples.
As shown in fig. 1 and 2, the invention provides a system for automatically analyzing a dopamine transporter PET image based on a CT structural image, which comprises an image acquisition module, an image preprocessing module, a DAT-PET functional image automatic segmentation module and an automatic numerical extraction and calculation module of double-sided striatum sub-partitions;
the image acquisition module is used for acquiring images, the subject acquires 3D brain images on a PET/CT scanner, DAT-PET (Dopamine Transporter PET, DAT-PET) functional images and CT structural images are acquired simultaneously under the same body position state, and image format conversion is carried out after the image acquisition, namely an original acquired image sequence in a DICOM format is converted into an image in a NIFTI (Neuroimaging Informatics Technology Initiative) format which is easy to process.
The image preprocessing module is used for preprocessing the image acquired by the image acquisition module, fusing the DAT-PET functional image and the CT structural image acquired by the image acquisition module through SPM12 (Statistical Parametric Mapping), and displaying the DAT-PET functional image and the CT structural image data as three-dimensional images, so that a clinician can conveniently perform omnibearing visual assessment.
The automated segmentation module of the DAT-PET functional image automatically segments striatum and striatum sub-partitions of the DAT-PET functional image based on a CT structure diagram, wherein the striatum sub-partitions comprise a bilateral front shell core, a bilateral rear shell core, a bilateral front tail core, a bilateral back tail core and a bilateral volt-insulation core, and the automated segmentation module comprises the following specific processes:
1) Brain structures within the CT image are segmented into background signals, skull, grey matter, white matter, cerebrospinal fluid and soft tissue. And (3) carrying out CT structural image space standardization by using an open source algorithm CTseg according to the segmentation result (the algorithm is based on Matlab environment and SPM 12), and obtaining a conversion matrix for converting the CT structural image from an individual space to an MNI space. The spatial normalization steps are as follows: first, the algorithm uses a Bayesian model to generate an average brain feature template from crowd craniocerebral CT and MRI, and the generated model can represent the equation p (F; A; S) =p (Fj A; S) p (A; S). Dividing a CT brain structure diagram of an individual into background signals, skull, gray matter, white matter, cerebrospinal fluid and soft tissues based on the characteristic template; secondly, the algorithm applies the segmentation result, and the CT brain structure diagram is approximately registered to the front joint-rear joint connection line position by using rigid body transformation; finally, using differential embryo mapping to spatially normalize the CT brain structure map to a brain template; in addition, the algorithm simultaneously applies a multi-scale and multi-fitting method to avoid sinking into a locally optimal solution. In the space standardization process, a conversion matrix can be obtained, and the DAT-PET functional image and the CT structural image in the PET/CT are synchronously scanned, so that the conversion matrix has good space matching degree, and can be regarded as the conversion matrix for converting the individual DAT-PET functional image into MNI (Montreal Neurological Institute) space.
2) The mask of each sub-partition of the striatum is manufactured through a GSK template, and specifically comprises the following steps: a three-partition template of GSK striatal connection template (Oxford-GlaxoSmithKline-Imanova Striatal Connectivity Atlas) was used as the striatal sub-partition basis, setting a probability threshold of 0.25. The template represents the striatum sensory and motor function area, the joint function area and the emotion function area by different values, and the putamen is divided into a front putamen and a rear putamen in a three-dimensional space based on functional evidence. And then combining the striatum structure template to divide the striatum into a bilateral anterior putamen, a posterior putamen, a caudate nucleus, and a caudate nucleus. The numerical value of each sub-region was set to 1, and a mask (mask) for each sub-region of the striatum in the MNI space was prepared.
3) The striatum fine subdivision mask under MNI space is inverse transformed to individual space by a transform matrix. The obtained fine sub-zonal shade of the striatum of the individual space can represent the striatum of the individual DAT-PET functional image and the sub-zonal positions of the striatum, the shade and the DAT-PET functional image are subjected to Hadamard product, and the DAT-PET segmented image of the striatum and each sub-zone is further obtained based on the CT and the DAT-PET functional images which are synchronously scanned.
The automatic numerical extraction and calculation module of the bilateral striatum subareas is used for automatically calculating the imaging agent uptake value of the bilateral subareas, the uptake value ratio with identification significance for the parkinsonism and the condition of quantitatively analyzing the change of the dopamine transporter. The method comprises the following steps: the fine sub-division mask of striatum in the individual space is set as a region of interest (region of interest, ROI), gray values of all pixels in the ROI are extracted, and an average value is taken as an imaging agent uptake value of the region. The ratio of uptake values of discriminative significance includes left-side core-shell-rear uptake value/right-side core-shell-rear uptake value, single-side core-front specific uptake value/core-rear uptake value, single-side tail core uptake value/core-rear uptake value.
Examples:
the automatic analysis of the DAT-PET functional image based on the PET/CT structural image comprises the following specific steps:
1. PET/CT scanners are used to acquire PET images of the brain, with the subject remaining in the same position during acquisition, and PET images and CT structural images as in fig. 3 are acquired.
2. The acquired images are imported into an image preprocessing module for image format conversion, an original acquired image sequence in a DICOM format is converted into an NIFTI format image, the acquired DAT-PET functional image and CT structural image are subjected to image fusion, the DAT-PET and CT structural image data are displayed as three-dimensional images as shown in fig. 4, and a doctor observes the image quality and registration condition and can perform preliminary visual assessment.
3. The CT structure image is imported into an automated segmentation module. The module uses an open source algorithm CTseg to segment CT brain structure images of PET/CT. The CT brain structure image of the individual is segmented into background signal, skull, grey matter, white matter, cerebrospinal fluid, soft tissue, and a CT structure image of the removed skull as shown in FIG. 5 is obtained.
4. And (3) introducing the segmentation result of the CT brain structure diagram in the step (3) into a spatial standardization module, resampling the CT brain structure diagram to 23 multiplied by 28 multiplied by 23 voxels, roughly registering the CT brain structure diagram to a front joint-rear joint connection position by using rigid body transformation, and then spatially standardizing the CT brain structure diagram to a brain template of CTseg by using differential homoembryo mapping. In addition, the method simultaneously applies a multi-scale multi-fitting method, and the CT brain structure diagram is respectively resampled to 23×28×23, 46×55×46, 91×109×91 and 182×218×182 and is matched with the template in sequence so as to avoid sinking into a local optimal solution. In the space normalization process, a transformation matrix of the CT brain structure diagram from the individual space to the MNI space is obtained.
5. Masks are made for each sub-partition of the striatum. A three-partition template of GSK striatal connection template was used, setting the tissue probability threshold to 0.25. The shell and core parts in the striatum structure template are independently proposed, compared with the GSK template, the region in the shell and core responsible for sensory and motor functions is set as a rear shell and core, and the region in the shell and core responsible for joint and emotion functions is set as a front shell and core. The tail-shaped nucleus heads and the tail-shaped nucleus sub-partitions of the striatum are obtained from the striatum structure template. The gradation value of the corresponding sub-region is set to 1, the gradation value of the rest position is set to 0, and a mask for each sub-region of the striatum in the MNI space is created, and each sub-region is represented by a different gradation in fig. 6.
6. And (3) inversely transforming the striatum fine sub-partition mask under the MNI space obtained in the step (5) to the individual space by using the transformation matrix obtained in the step (4). The fine sub-zonal shade of the striatum of the individual space is obtained, the shade can represent the striatum of the individual DAT-PET functional image and the sub-zonal positions of the striatum, the shade and the DAT-PET functional image are subjected to Hadamard product, and the segmented image of the whole striatum and each sub-zone is obtained as shown in figure 7.
7. The sub-partition segmented image obtained in the step 6 is imported into an automatic numerical extraction and calculation module, the striatum fine sub-partition mask of the individual space is taken as the region of interest, the gray values of all voxels in the region of interest are extracted, the average value is taken, and the divided dose correction factor (Dose Calibration Factor) is taken as the average Standard Uptake Value (SUV) mean )。
8. Automatically calculating index with diagnostic and identifying significance for parkinsonism, including left side shell and core rear SUV mean Right side shell core posterior SUV mean Unilateral putamen anterior SUV mean Posterior putamen SUV mean Unilateral caudate nucleus SUV mean Posterior putamen SUV mean . In this example, the patient's right caudal nude SUV mean =0.99, right caudate nucleus SUV mean =0.96, right anterior putamen SUV mean =1.25, right posterior putamen SUV mean =0.89, left caudate nucleus SUV mean =1.16, left caudate nucleus SUV mean =1.29, left anterior putamen SUV mean =1.53, left posterior putamen SUV mean =1.28, left posterior putamen SUV mean Right side shell core posterior SUV mean =1.44, right anterior putamen SUV mean Posterior putamen SUV mean =1.40, left anterior putamen SUV mean Posterior putamen SUV mean =1.19, right caudate nucleus SUV mean Posterior putamen SUV mean =1.11, left caudate nucleus SUV mean Posterior putamen SUV mean =1.01, the patient was a parkinson's disease patient with left onset.
The present patent is not limited to the above-described preferred embodiments. Any person can obtain other various automatic analysis systems for DAT-PET functional images based on PET/CT structural images under the teaching of the patent, and all equivalent changes and modifications made according to the scope of the patent application are covered by the patent.
Claims (4)
1. The system for automatically analyzing the PET image of the dopamine transporter based on the CT structural image is characterized by comprising an image acquisition module, an image preprocessing module, a DAT-PET functional image automatic segmentation module and an automatic numerical value extraction and calculation module of double-sided striatum sub-subareas;
the image acquisition module is used for acquiring images, the subject acquires 3D brain images on the PET/CT scanner, simultaneously acquires DAT-PET functional images and CT structural images under the same body position state, and converts the DAT-PET functional images and CT structural images into an NIFTI image format;
the image preprocessing module is used for preprocessing the image acquired by the image acquisition module, fusing the DAT-PET functional image and the CT structural image acquired by the image acquisition module through the SPM12, and displaying the DAT-PET functional image and the CT structural image data as three-dimensional images, so that a clinician can conveniently perform omnibearing visual assessment;
the automated segmentation module of the DAT-PET functional image automatically segments striatum and striatum sub-partitions of the DAT-PET functional image based on a CT structure diagram, wherein the striatum sub-partitions comprise a bilateral front shell core, a bilateral rear shell core, a bilateral front tail core, a bilateral back tail core and a bilateral volt-insulation core, and the automated segmentation module comprises the following specific processes:
1) Dividing brain structures in the CT images into background signals, skull, gray matter, white matter, cerebrospinal fluid and soft tissues; carrying out CT structural image space standardization according to the segmentation result to obtain a conversion matrix of CT structural image from individual space to MNI space;
2) Manufacturing a mask of each sub-partition of the striatum through a GSK template;
3) Inversely transforming the shade of each sub-partition of the striatum through a transformation matrix, and further acquiring DAT-PET segmented images of the striatum and each sub-partition based on the CT image and the DAT-PET functional image which are synchronously scanned;
the automatic numerical extraction and calculation module of the double-sided striatum subarea is used for automatically calculating the uptake value of the imaging agent of the double-sided subarea and the uptake value ratio with identification significance for the parkinsonism and is used for quantitatively analyzing the change condition of the dopamine transporter.
2. The system for automated analysis of dopamine transporter PET images based on CT structural images of claim 1, wherein: the automatic numerical extraction and calculation module of the double-sided striatum sub-partition sets a striatum fine sub-partition mask of an individual space as a region of interest (ROI), extracts gray values of all pixels in the ROI, and takes an average value as an imaging agent uptake value of the region.
3. The system for automated analysis of dopamine transporter PET images based on CT structural images of claim 1, wherein: the automatic numerical extraction and calculation module for the sub-zonation of the bilateral striatum has the characteristic that the ratio of the ingestion values with discrimination meaning comprises a left shell-core rear ingestion value/a right shell-core rear ingestion value, a single-side shell-core front specific ingestion value/a shell-core rear ingestion value and a single-side tail-shaped core ingestion value/a shell-core rear ingestion value.
4. The system for automated analysis of dopamine transporter PET images based on CT structural images of claim 1, wherein: and inversely transforming the mask of each sub-partition of the striatum to an individual space by utilizing a transformation matrix, and extracting the striatum and each sub-partition image by using the mask to partition the DAT-PET functional image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110637657.9A CN113554663B (en) | 2021-06-08 | 2021-06-08 | System for automatically analyzing PET (positron emission tomography) images of dopamine transporter based on CT (computed tomography) structural images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110637657.9A CN113554663B (en) | 2021-06-08 | 2021-06-08 | System for automatically analyzing PET (positron emission tomography) images of dopamine transporter based on CT (computed tomography) structural images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113554663A CN113554663A (en) | 2021-10-26 |
| CN113554663B true CN113554663B (en) | 2023-10-31 |
Family
ID=78130404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110637657.9A Active CN113554663B (en) | 2021-06-08 | 2021-06-08 | System for automatically analyzing PET (positron emission tomography) images of dopamine transporter based on CT (computed tomography) structural images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554663B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114334130B (en) * | 2021-12-25 | 2023-08-22 | 浙江大学 | Brain symmetry-based PET molecular image computer-aided diagnosis system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104720840A (en) * | 2015-02-11 | 2015-06-24 | 清华大学深圳研究生院 | Semi-automatic quantification method based on development specificity extraction ratio of dopamine transporter |
| JP2019124672A (en) * | 2018-01-19 | 2019-07-25 | 日本メジフィジックス株式会社 | Image processing apparatus, image processing method and program |
| CN110838173A (en) * | 2019-11-15 | 2020-02-25 | 天津医科大学 | Three-dimensional texture feature-based individual brain covariant network construction method |
| CN110992332A (en) * | 2019-11-29 | 2020-04-10 | 复旦大学 | Image processing-based full-automatic semi-quantitative value detection method for dopamine transporter |
| CN112070809A (en) * | 2020-07-22 | 2020-12-11 | 中国科学院苏州生物医学工程技术研究所 | Accurate diagnosis system of pancreatic cancer based on two time formation of image of PET/CT |
| CN112767393A (en) * | 2021-03-03 | 2021-05-07 | 常州市第一人民医院 | Machine learning-based bimodal imaging omics ground glass nodule classification method |
-
2021
- 2021-06-08 CN CN202110637657.9A patent/CN113554663B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104720840A (en) * | 2015-02-11 | 2015-06-24 | 清华大学深圳研究生院 | Semi-automatic quantification method based on development specificity extraction ratio of dopamine transporter |
| JP2019124672A (en) * | 2018-01-19 | 2019-07-25 | 日本メジフィジックス株式会社 | Image processing apparatus, image processing method and program |
| CN110838173A (en) * | 2019-11-15 | 2020-02-25 | 天津医科大学 | Three-dimensional texture feature-based individual brain covariant network construction method |
| CN110992332A (en) * | 2019-11-29 | 2020-04-10 | 复旦大学 | Image processing-based full-automatic semi-quantitative value detection method for dopamine transporter |
| CN112070809A (en) * | 2020-07-22 | 2020-12-11 | 中国科学院苏州生物医学工程技术研究所 | Accurate diagnosis system of pancreatic cancer based on two time formation of image of PET/CT |
| CN112767393A (en) * | 2021-03-03 | 2021-05-07 | 常州市第一人民医院 | Machine learning-based bimodal imaging omics ground glass nodule classification method |
Non-Patent Citations (2)
| Title |
|---|
| Wang Gang 等.Progress of translational research on the pathogenesis,diagnosis and treatment of Parkingson's disease.EBSCO.2018,第18卷(第1期),全文. * |
| 脑多巴胺转运体显像在诊断帕金森病中的应用;史国华 等;全科医学临床与教育;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113554663A (en) | 2021-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2008211786B2 (en) | Tools for aiding in the diagnosis of neurodegenerative diseases | |
| CN109493325B (en) | Tumor heterogeneity analysis system based on CT images | |
| Namburete et al. | Learning-based prediction of gestational age from ultrasound images of the fetal brain | |
| US20050065421A1 (en) | System and method of measuring disease severity of a patient before, during and after treatment | |
| US8588486B2 (en) | Apparatus and method for isolating a region in an image | |
| EP2481349B1 (en) | Method, device, and program for processing images obtained from asl mri | |
| US20070237372A1 (en) | Cross-time and cross-modality inspection for medical image diagnosis | |
| WO2016047683A1 (en) | Medical image display processing method, medical image display processing device, and program | |
| JP2009522005A (en) | Cross-time and cross-modality medical diagnosis | |
| US20070160276A1 (en) | Cross-time inspection method for medical image diagnosis | |
| US11580642B2 (en) | Disease region extraction apparatus, disease region extraction method, and disease region extraction program | |
| Sun et al. | Automated template-based PET region of interest analyses in the aging brain | |
| CN113554663B (en) | System for automatically analyzing PET (positron emission tomography) images of dopamine transporter based on CT (computed tomography) structural images | |
| Mohtasebi et al. | Modeling of neonatal skull development using computed tomography images | |
| CN114334130A (en) | PET molecular image computer-aided diagnosis system based on brain symmetry | |
| WO2019044077A1 (en) | Medical image processing device, method, and program | |
| Kazemifar et al. | Automated algorithm to measure changes in medial temporal lobe volume in Alzheimer disease | |
| JP2019136519A (en) | Medical image display processing method, device and program | |
| KR102349360B1 (en) | Diagnosis Method and System of Idiopathic Normal Pressure Hydrocephalus Using Imaging Diagnostic Equipment | |
| Che et al. | Segmentation of bone metastases based on attention mechanism | |
| EP1969563A2 (en) | Cross-time inspection method for medical diagnosis | |
| US11369268B2 (en) | Brain-function image data augmentation method | |
| Li | The construction of a normative human lung atlas by inter-subject registration and warping of CT images | |
| Lyu et al. | A 3D Printing Scheme of Head Model for Neurosurgery | |
| CN117455845A (en) | Intelligent image processing method and system for acute cerebral hemorrhage CT image |
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 |