CN113538414A - Lung image registration method and lung image registration device - Google Patents
Lung image registration method and lung image registration device Download PDFInfo
- Publication number
- CN113538414A CN113538414A CN202110932280.XA CN202110932280A CN113538414A CN 113538414 A CN113538414 A CN 113538414A CN 202110932280 A CN202110932280 A CN 202110932280A CN 113538414 A CN113538414 A CN 113538414A
- Authority
- CN
- China
- Prior art keywords
- phase
- lung
- expiratory
- inspiratory
- segmentation data
- 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
- 210000004072 lung Anatomy 0.000 title claims abstract description 782
- 238000000034 method Methods 0.000 title claims abstract description 94
- 230000011218 segmentation Effects 0.000 claims abstract description 515
- 230000003434 inspiratory effect Effects 0.000 claims abstract description 300
- 238000013507 mapping Methods 0.000 claims abstract description 33
- 230000002685 pulmonary effect Effects 0.000 claims description 96
- 230000006870 function Effects 0.000 claims description 47
- 230000009466 transformation Effects 0.000 claims description 42
- 238000005192 partition Methods 0.000 claims description 36
- 230000002457 bidirectional effect Effects 0.000 claims description 19
- 206010056342 Pulmonary mass Diseases 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 3
- 238000002591 computed tomography Methods 0.000 description 15
- 230000003902 lesion Effects 0.000 description 10
- 230000029058 respiratory gaseous exchange Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000007667 floating Methods 0.000 description 5
- 210000000621 bronchi Anatomy 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010827 pathological analysis Methods 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 230000000241 respiratory effect Effects 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 238000000844 transformation Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 208000020816 lung neoplasm Diseases 0.000 description 1
- 208000037841 lung tumor Diseases 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application provides a lung image registration method and a lung image registration device, which are used for registering an expiratory phase lung image sequence and an inspiratory phase lung image sequence. The lung image registration method comprises the following steps: determining expiratory phase lung lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase lung image sequence; determining inspiratory phase lung lobe segmentation data and inspiratory phase lung segment segmentation data based on the inspiratory phase lung image sequence; registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data, the expiratory phase lung segment segmentation data, the inspiratory phase lung lobe segmentation data and the inspiratory phase lung segment segmentation data. According to the method, the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence are accurately registered by the segmented more accurate lung lobe segmentation data and lung segment segmentation data and by utilizing the space mapping relation between the lung lobes and each lung segment, so that the position of a focus is accurately determined, and the failure probability of a subsequent puncture operation is reduced.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a lung image registration method, a lung image registration apparatus, an electronic device, and a computer-readable storage medium.
Background
The pathological diagnosis of the lesion tissues has important guiding function on disease judgment. Clinically, a puncture surgery is usually performed under the guidance of a Computed Tomography (CT) image of the lung to obtain a pathological specimen for diagnosing a lung lesion.
However, the respiratory motion of the lung causes the position difference of the focus in the expiratory phase lung CT image and the inspiratory phase lung CT image, so that the accurate focus position cannot be obtained before the puncture operation, the puncture failure is caused, and the phenomenon of multiple punctures is caused.
Disclosure of Invention
In view of this, an embodiment of the present application provides a lung image registration method, a lung image registration apparatus, an electronic device, and a computer-readable storage medium, so as to solve the technical problem in the prior art that a lung breathing motion affects a lesion position, thereby causing a puncture failure.
According to an aspect of the present application, an embodiment of the present application provides a lung image registration method for registering an expiratory phase lung image sequence and an inspiratory phase lung image sequence, the lung image registration comprising: determining expiratory phase lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase lung image sequence; determining inspiratory phase lung lobe segmentation data and inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images; registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data, the expiratory phase lung segment segmentation data, the inspiratory phase lung lobe segmentation data and the inspiratory phase lung segment segmentation data.
In one embodiment, the registering the sequence of exhalation phase lung images and the sequence of inhalation phase lung images based on the exhalation phase lobe segmentation data, the exhalation phase lung segment segmentation data, the inhalation phase lobe segmentation data, and the inhalation phase lung segment segmentation data comprises: performing a rigid registration operation on the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data and the inspiratory phase lung lobe segmentation data; and performing non-rigid registration operation on the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence after the rigid registration operation based on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data so as to register the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence.
In one embodiment, the non-rigid registration of the rigidly registered sequence of exhalation phase lung images and sequence of inhalation phase lung images to register the sequence of exhalation phase lung images and the sequence of inhalation phase lung images based on the exhalation phase lung segment segmentation data and the inhalation phase lung segment segmentation data comprises: performing bidirectional space coordinate transformation on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to determine lung segment space mapping relation data; and registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence after the rigid registration operation based on the lung segment space mapping relation data.
In one embodiment, the performing bidirectional spatial coordinate transformation on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to determine lung segment spatial mapping relationship data includes: determining a first loss function corresponding to the spatial coordinate transformation of the expiratory phase to the inspiratory phase and a second loss function corresponding to the spatial coordinate transformation of the inspiratory phase to the expiratory phase based on the expiratory phase and inspiratory phase lung segment segmentation data belonging to the same lung segment; determining the lung segment spatial mapping relationship data based on the first loss function and the second loss function.
In one embodiment, the determining, based on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment, a first loss function corresponding to an expiratory-to-inspiratory phase spatial coordinate transformation and a second loss function corresponding to an inspiratory-to-expiratory phase spatial coordinate transformation includes: determining expiratory-phase lung segment segmentation edge data and inspiratory-phase lung segment segmentation edge data according to the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data which belong to the same lung segment; selecting a plurality of groups of seed points from the expiratory-phase lung segment segmentation edge data and the inspiratory-phase lung segment segmentation edge data; determining the first loss function by adopting a B-spline elastic registration algorithm based on the spatial coordinate transformation of the plurality of groups of seed points in the process of registering the inhalation-exhalation phase lung segment segmentation data to the inhalation segment segmentation data; and determining the second loss function by adopting a B-spline elastic registration algorithm based on the space coordinate transformation of the plurality of groups of seed points in the process of registering the inspiratory phase lung segment segmentation data to the expiratory phase segmentation data.
In one embodiment, the determining expiratory phase lobe segmentation data and expiratory phase segment segmentation data based on the expiratory phase lung image sequence comprises: determining expiratory phase lung segmentation data based on the expiratory phase lung image sequence; determining, based on the expiratory phase lung segmentation data, expiratory phase bronchial segmentation data and the expiratory phase lung lobe segmentation data; determining the expiratory phase lung segment segmentation data based on the expiratory phase bronchial segmentation data and the expiratory phase lung lobe segmentation data; the determining of expiratory phase lobe segmentation data and inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images comprises: determining inspiratory phase lung segmentation data based on the sequence of inspiratory phase lung images; determining inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data based on the inspiratory phase lung segmentation data; determining the inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data.
In one embodiment, the determining the expiratory phase lung segment segmentation data based on the expiratory phase bronchial segmentation data and the expiratory phase lobe segmentation data comprises: determining an expiratory phase bronchial segment and an expiratory phase bronchial sub-segment based on the topological structure of the bronchial tubes in the expiratory phase bronchial segmentation data; determining the expiratory phase lung segment segmentation data based on the expiratory phase bronchial segment and the expiratory phase lobe segmentation data; and/or, the determining the inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data comprises: determining an inspiratory bronchial segment and an inspiratory bronchial sub-segment based on the topological structure of the bronchial tubes in the inspiratory bronchial segmentation data; determining the inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segment and the inspiratory phase lobe segmentation data.
In one embodiment, the determining expiratory phase bronchial segmentation data and the expiratory phase lobe segmentation data based on the expiratory phase lung segmentation data comprises: dividing the expiratory phase lung segmentation data into a plurality of expiratory phase lung segmentation block data; for each expiratory phase lung segmentation block data in the plurality of expiratory phase lung segmentation block data, determining expiratory phase bronchial segmentation block data and expiratory phase fissured segmentation block data corresponding to the expiratory phase lung segmentation block data; connecting expiratory phase bronchial partition data corresponding to the plurality of expiratory phase lung partition data to determine the expiratory phase bronchial partition data based on a region growing method; connecting the expiratory phase fissured partition data corresponding to the plurality of expiratory phase fissured partition data to determine the expiratory phase fissured partition data based on a region growing method; determining the expiratory phase lobe segmentation data in combination with the expiratory phase lung segmentation data and the expiratory phase fissure segmentation data; and/or, the determining of inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data based on the inspiratory phase lung segmentation data comprises: dividing the inspiratory phase lung segmentation data into a plurality of inspiratory phase lung segmentation block data; determining, for each of the plurality of inspiratory phase lung segmentation block data, inspiratory phase bronchial segmentation block data and inspiratory phase fissured segmentation block data corresponding to the inspiratory phase lung segmentation block data; connecting inhalation phase bronchial segment data corresponding to the plurality of inhalation phase lung segment data to determine the inhalation phase bronchial segment data based on a region growing method; connecting inhalation phase lung segmentation block data corresponding to the plurality of inhalation phase lung segmentation block data based on a region growing method to determine the inhalation phase lung segmentation data; and combining the inspiratory phase lung segmentation data and the inspiratory phase lung fissure segmentation data to determine the inspiratory phase lung lobe segmentation data.
In one embodiment, a method of determining an expiratory phase lung image sequence and an inspiratory phase lung image sequence, comprises: receiving a first sequence of lung images; determining patient information corresponding to the first sequence of lung images based on the first sequence of lung images; based on the patient information, screening a second lung image sequence matched with the patient information from a hospital information system; determining the sequence of expiratory phase lung images and the sequence of inspiratory phase lung images based on the first sequence of lung images and the second sequence of lung images.
In one embodiment, further comprising determining expiratory phase pulmonary nodule segmentation data based on the expiratory phase pulmonary image sequence; determining inspiratory phase lung nodule segmentation data based on the sequence of inspiratory phase lung images; and registering the expiratory-phase pulmonary nodule and the inspiratory-phase pulmonary nodule based on the expiratory-phase pulmonary nodule segmentation data, the inspiratory-phase pulmonary nodule segmentation data and the registered expiratory-phase pulmonary image sequence and inspiratory-phase pulmonary image sequence.
According to another aspect of the present application, an embodiment of the present application provides a lung image registration apparatus for registering an expiratory phase lung image sequence and an inspiratory phase lung image sequence, the lung image registration apparatus comprising: a first determination module configured to determine an expiratory phase lung image sequence and an inspiratory phase lung image sequence; a second determining module configured to determine, for a lung image sequence of the expiratory phase lung image sequence and the inspiratory phase lung image sequence, lung lobe segmentation data and a lung segment segmentation data set corresponding to the lung image sequence; a registration module configured to determine registration information corresponding to the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence based on a registration operation performed on a set of lobe segmentation data and lung segment segmentation data corresponding to the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence, respectively.
According to another aspect of the present application, an embodiment of the present application provides an electronic device, including: a processor; a memory; and computer program instructions stored in the memory, which when executed by the processor, cause the processor to perform the method of registration of images of the lungs as described in any one of the embodiments above.
According to yet another aspect of the present application, an embodiment of the present application provides a computer-readable storage medium having stored thereon computer program instructions, which, when executed by a processor, cause the processor to perform the lung image registration method according to any one of the above embodiments.
The lung image registration method provided by the embodiment of the application is used for registering an expiratory phase lung image sequence and an inspiratory phase lung image sequence. The method comprises the following steps: determining expiratory phase lung lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase lung image sequence; determining inspiratory phase lung lobe segmentation data and inspiratory phase lung segment segmentation data based on the inspiratory phase lung image sequence; and registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data, the expiratory phase lung segment segmentation data, the inspiratory phase lung lobe segmentation data and the inspiratory phase lung segment segmentation data. According to the method, the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence are accurately registered by the segmented more accurate lung lobe segmentation data and lung segment segmentation data and by utilizing the space mapping relation between the lung lobes and each lung segment, so that the position of a focus is accurately determined, and the failure probability of a subsequent puncture operation is reduced.
Drawings
Fig. 1 is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 2 is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 3 is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 4 is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 5 is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 6a is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 6b is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 7 is a schematic flow chart illustrating registration of an expiratory phase lung image sequence and an inspiratory phase lung image sequence according to an embodiment of the present application.
Fig. 8 is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 9 is a flowchart illustrating a lung image registration method according to an embodiment of the present application.
Fig. 10 is a schematic structural diagram of a lung image registration apparatus according to an embodiment of the present application.
Fig. 11 is a schematic structural diagram of a lung image registration apparatus according to an embodiment of the present application.
Fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The pathological diagnosis of the lesion tissues has important guiding function on disease judgment. Clinically, a puncture surgery is usually performed under the guidance of a Computed Tomography (CT) image of the lung to obtain a pathological specimen for diagnosing a lung lesion. The lung CT image is an image scanned instantaneously, and based on the characteristics of the human body structure, the lung moves by breathing, and the tumor also moves along with breathing, so that the position of the lesion in the images acquired at different scanning moments is different, that is, the position of the lesion in the expiratory-phase lung CT image and the inspiratory-phase lung CT image is different. During a puncture operation, a doctor presets a puncture needle inserting direction according to a collected lung CT image, and cannot obtain an accurate focus position due to the fact that influence of lung breathing motion on the focus position cannot be avoided, and the preset puncture needle inserting direction deviates from an actual focus position, so that puncture failure is caused, and then the phenomenon of multiple times of puncture is caused.
Therefore, an image registration method is urgently needed, which is used for registering an expiratory-phase lung CT image and an inspiratory-phase lung CT image, reducing the interference of lung breathing motion on the acquisition of an accurate lesion position, and enabling a preset puncture needle insertion direction to be close to an actual lesion position, so that the puncture failure probability is reduced.
In view of the above technical problems, the basic concept of the present application is provided as follows.
For two medical images in a set of medical image data sets, one or a series of spatial transformations are sought for one medical image (floating image) to bring it into spatial correspondence with a corresponding point on the other medical image (fixed image). Or two medical images in a set of medical image data sets, i.e. two image sequences, for one set of medical images one or a series of spatial transformations is sought to bring it into spatial correspondence with corresponding points on the other set of medical images. By coincidence is meant that the same location point on the body has the same spatial location on the two matched images, and the result of the registration is such that all location points on the two images, or at least all location points of diagnostic significance, are matched.
Based on this, the embodiment of the present application provides a lung image registration method for registering an expiratory phase lung image sequence and an inspiratory phase lung image sequence. The method comprises the following steps: determining expiratory phase lung lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase lung image sequence; determining inspiratory phase lung lobe segmentation data and inspiratory phase lung segment segmentation data based on the inspiratory phase lung image sequence; registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data, the expiratory phase lung segment segmentation data, the inspiratory phase lung lobe segmentation data and the inspiratory phase lung segment segmentation data. According to the method, the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence are accurately registered by the segmented more accurate lung lobe segmentation data and lung segment segmentation data and by utilizing the space mapping relation between the lung lobes and each lung segment, so that the position of a focus is accurately determined, and the failure probability of a subsequent puncture operation is reduced.
Exemplary Lung image registration method
Fig. 1 is a flowchart illustrating a lung image registration method according to an embodiment of the present application. The method is used for registering an expiratory phase lung image sequence and an inspiratory phase lung image sequence. The lung image registration methods provided by all embodiments of the present application are all used for registering an expiratory phase lung image sequence and an inspiratory phase lung image sequence, and specific application scenarios of the lung image registration method provided by the present application are not described in detail in subsequent embodiments.
Further, the determination method of the expiratory phase lung image sequence and the inspiratory phase lung image sequence is as follows. Receiving a first sequence of lung images; determining patient information corresponding to the first sequence of lung images based on the first sequence of lung images; based on the patient information, a second sequence of lung images matching the patient information is filtered from the hospital information system, for example: screening a second lung image sequence matched with the patient information from a PACS (Picture Archiving And Communication System); based on the first and second lung image sequences, an expiratory phase lung image sequence and an inspiratory phase lung image sequence are determined. The expiratory phase lung image sequence and the inspiratory phase lung image sequence mentioned in all embodiments of the present application can be determined by the above method, and are not described in detail later.
As shown in fig. 1, the lung image registration method includes the following steps.
Step 101: determining expiratory phase lung lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase lung image sequence.
Step 102: determining inspiratory phase lobe segmentation data and inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images.
Specifically, due to the regular respiratory motion of the lung, the multi-frame image sequence acquired when the lung is in the expiratory phase is the expiratory phase lung image sequence. The multi-frame image sequence acquired when the lung is in the inspiration phase is a lung image sequence of the lung in the inspiration phase. Such as an expiratory phase CT lung image sequence and an inspiratory phase CT lung image sequence.
Aiming at the lung, the left lung is divided into an upper lung lobe and a lower lung lobe by oblique splitting, the right lung is divided into an upper lung lobe, a middle lung lobe and a lower lung lobe by a horizontal splitting besides the oblique splitting, and the total number of the lung lobes is 5, and the lung lobe segmentation information is the marking data for segmenting the lung lobes from the background. The expiratory phase lung lobe segmentation data is lung lobe segmentation data corresponding to the expiratory phase; the inhalation phase lung lobe segmentation data is lung lobe segmentation data corresponding to the inhalation phase.
Due to the existence of the bronchus, the lung can be divided into a plurality of lung segments, and the lung segment division data is the corresponding mark data of each lung segment, which divides the part belonging to the lung. The expiratory phase lung segment segmentation data is lung segment segmentation data corresponding to the expiratory phase; the inspiratory phase lung segment segmentation data is lung segment segmentation data corresponding to an inspiratory phase.
Step 103: and registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data, the expiratory phase lung segment segmentation data, the inspiratory phase lung lobe segmentation data and the inspiratory phase lung segment segmentation data.
Specifically, the expiratory-phase lung lobe segmentation data and the inspiratory-phase lung lobe segmentation data reflect the lung lobe segmentation conditions in different breathing phases, and the lung contours in the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence are initially adapted based on the expiratory-phase lung lobe segmentation data and the inspiratory-phase lung lobe segmentation number. The fine segmentation condition of each lung segment under different breathing phases can be reflected by the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data, the segmented fine expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation number are used for registration, and an accurate lung registration result is obtained based on the mapping relation of each lung segment.
In the embodiment of the application, the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence are accurately registered by the segmented more accurate lung lobe segmentation data and lung segment segmentation data and by utilizing the space mapping relation between the lung lobes and each lung segment, so that the position of a focus is accurately determined, and the failure probability of a subsequent puncture operation is reduced.
Fig. 2 is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 2, the step of registering the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence based on the expiratory-phase lung lobe segmentation data, the expiratory-phase lung segment segmentation data, the inspiratory-phase lung lobe segmentation data and the inspiratory-phase lung segment segmentation data comprises the following steps.
Step 201: and performing rigid registration operation on the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence based on the expiratory-phase lung lobe segmentation data and the inspiratory-phase lung lobe segmentation data.
In particular, rigid registration refers to registration by translation, rotation and scaling processes of images, and does not involve deformation processes of images. And performing operations such as translation and scaling on the lung lobes represented by the expiratory-phase lung lobe segmentation data and the inspiratory-phase lung lobe segmentation data to realize rigid registration of the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence so as to determine the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence after rigid registration operation.
Step 202: and performing non-rigid registration operation on the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence after rigid registration operation based on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data to register the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence.
In particular, the non-rigid registration is based on a multi-modality non-rigid image registration algorithm. Non-rigid registration operation is carried out on the expiratory phase lung segment segmentation data and the inspiratory phase lung segment segmentation data, so that the non-rigid registration of the expiratory phase lung image sequence and the inspiratory phase lung image sequence after rigid registration operation is realized, and the registration of the expiratory phase lung image sequence and the inspiratory phase lung image sequence is realized.
In the embodiment of the application, rigid registration operation is performed on the expiratory phase lung lobe segmentation data and the inspiratory phase lung lobe segmentation data, and rigid registration is performed on the initial position of the outline of the lung image, so that a basis is provided for subsequent non-rigid registration operation. And performing non-rigid registration operation on the segmentation data of the expiratory phase lung segment and the segmentation data of the inspiratory phase lung segment to determine a spatial mapping relation on each lung segment, so that the expiratory phase lung image sequence and the inspiratory phase lung image sequence are accurately registered.
Fig. 3 is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 3, the step of performing a non-rigid registration operation on the sequence of expiratory phase lung images and the sequence of inspiratory phase lung images after the rigid registration operation based on the segmentation data of the expiratory phase lung segments and the segmentation data of the inspiratory phase lung segments to register the sequence of expiratory phase lung images and the sequence of inspiratory phase lung images includes the following steps.
Step 301: and determining lung segment space mapping relation data based on bidirectional space coordinate transformation of the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment.
Specifically, since the lung is divided into a plurality of lung segments, each lung segment is registered separately, and thus the registration of the whole lung can be realized. And carrying out bidirectional space coordinate transformation on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to determine lung segment space mapping relation data. The bidirectional space coordinate transformation takes the inhalation-phase lung segment segmentation data as a reference image, the exhalation-phase lung segment segmentation data as a floating image, and the exhalation-phase lung segment segmentation data is registered to the inhalation-phase lung segment segmentation data; and taking the segmented data of the expiratory phase pulmonary segment as a reference image, taking the segmented data of the inspiratory phase pulmonary segment as a floating image, and registering the segmented data of the inspiratory phase pulmonary segment to coordinate transformation of the segmented data of the expiratory phase pulmonary segment in two directions.
Step 302: and registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence after rigid registration operation based on the lung segment space mapping relation data.
Specifically, displacement of non-rigid registration of the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data after rigid registration operation can be obtained through lung segment space mapping relation data, so that registration of lung segments is realized, non-rigid registration of the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment is performed, and an expiratory-phase lung image sequence and an inspiratory-phase lung image sequence after rigid registration operation are registered.
In the embodiment of the application, bidirectional non-rigid registration operation is performed on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to obtain a bidirectional registration mapping relation on each lung segment, and accurate matching of the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence is realized through bidirectional accurate matching on each lung segment.
Fig. 4 is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 4, the step of performing bidirectional spatial coordinate transformation on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to determine lung segment spatial mapping relationship data includes the following steps.
Step 401: and determining a first loss function corresponding to the spatial coordinate transformation of the expiratory phase to the inspiratory phase and a second loss function corresponding to the spatial coordinate transformation of the inspiratory phase to the expiratory phase based on the expiratory phase and inspiratory phase lung segment segmentation data belonging to the same lung segment.
And for the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment, taking the inspiratory-phase lung segment segmentation data as a reference image, taking the expiratory-phase lung segment segmentation data as a floating image, and registering the expiratory-phase lung segment segmentation data to the inspiratory-phase lung segment segmentation data through space coordinate transformation, thereby obtaining a first loss function. And taking the expiratory-phase lung segment segmentation data as a reference image, taking the inspiratory-phase lung segment segmentation data as a floating image, and registering the inspiratory-phase lung segment segmentation data to the expiratory-phase lung segment segmentation data through space coordinate transformation, wherein a second loss function is obtained in the process.
Step 402: and determining lung segment space mapping relation data based on the first loss function and the second loss function.
Specifically, when the sum of the losses of the first loss function and the second loss function is minimum, the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment are considered to be in the registration position, based on which the lung segment spatial mapping relationship data is determined.
In the embodiment of the application, the segmented data of the lung segment of the expiratory phase is registered to the segmented data of the lung segment of the inspiratory phase through space coordinate transformation, and a first loss function is determined; and registering the inspiratory-phase lung segment segmentation data to the expiratory-phase lung segment segmentation data through space coordinate transformation, determining a second loss function, and ensuring that the registration mapping relation of the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment is bidirectional when the sum of losses of the first loss function and the second loss function is minimum, so that the registration accuracy of the lung segments is further improved through bidirectional matching.
Fig. 5 is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 5, the step of determining a first loss function corresponding to the spatial coordinate transformation of the expiratory phase to the inspiratory phase and a second loss function corresponding to the spatial coordinate transformation of the inspiratory phase to the expiratory phase based on the expiratory phase and inspiratory phase lung segment segmentation data belonging to the same lung segment includes the following steps.
Step 501: and determining the segmentation edge data of the expiratory phase lung segment and the segmentation edge data of the inspiratory phase lung segment based on the segmentation data of the expiratory phase lung segment and the segmentation data of the inspiratory phase lung segment aiming at the segmentation data of the expiratory phase lung segment and the segmentation data of the inspiratory phase lung segment belonging to the same lung segment.
Specifically, considering that the probability of lesion deformation is in the lung segment edge region, and compared with the registration of the whole lung by selecting pixel points as control points, the lung segment segmentation edge data is registered, and the registration speed can be improved on the premise of not reducing the registration accuracy. Determining the segmentation edge data of the expiratory phase lung segment and the segmentation edge data of the inspiratory phase lung segment based on the segmentation data of the expiratory phase lung segment and the segmentation data of the inspiratory phase lung segment, and realizing the bidirectional non-rigid registration of the segmentation data of the expiratory phase lung segment and the segmentation data of the inspiratory phase lung segment belonging to the same lung segment based on the bidirectional non-rigid registration of the segmentation edge data of the expiratory phase lung segment and the segmentation edge data of the inspiratory phase lung segment.
Step 502: and selecting a plurality of groups of seed points from the expiratory phase pulmonary segment segmentation edge data and the inspiratory phase pulmonary segment segmentation edge data.
Specifically, the seed points are control points during registration, multiple groups of seed points are selected from the expiratory-phase lung segment segmentation edge data and the inspiratory-phase lung segment segmentation edge data, and bidirectional non-rigid elastic registration is realized based on space coordinate transformation of the multiple groups of control points.
Step 503: and determining a first loss function by adopting a B-spline elastic registration algorithm based on the space coordinate transformation of a plurality of groups of seed points in the process of registering the inhalation-exhalation-phase lung segment segmentation data to the inhalation-exhalation-phase lung segment segmentation data.
Specifically, based on spatial coordinate transformation of a plurality of groups of seed points in the process of registering inhalation-exhalation-phase lung segment segmentation data to inhalation segment segmentation data, a B-spline interpolation algorithm is adopted to interpolate discrete pixel points into spatial coordinate points, so that a first loss function is determined.
Step 504: and determining a second loss function by adopting a B-spline elastic registration algorithm based on the space coordinate transformation of a plurality of groups of seed points in the process of registering the segmentation data of the inspiratory phase lung segment to the segmentation data of the expiratory phase.
Specifically, based on spatial coordinate transformation of a plurality of groups of seed points in the process of registering inspiratory phase pulmonary segment segmentation data to expiratory segment segmentation data, a B-spline interpolation algorithm is adopted to interpolate discrete pixel points into spatial coordinate points, so that a second loss function is determined.
In the embodiment of the application, a plurality of groups of seed points are selected at the edge of the lung segment to perform bidirectional space coordinate transformation, a dual-B-spline elastic registration algorithm is adopted to determine a loss function, so that the lung segment space mapping relation data is determined, and then based on the lung segment space mapping relation data, bidirectional non-rigid registration of the expiratory phase lung segment segmentation data and the inspiratory phase lung segment segmentation data belonging to the same lung segment is realized. Based on the method, the registration speed is provided, and the bidirectional accurate registration is realized.
Fig. 6a is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 6a, the step of determining the expiratory phase lobe segmentation data and the expiratory phase segment segmentation data based on the expiratory phase lung image sequence includes the following steps.
Step 601: based on the expiratory phase lung image sequence, expiratory phase lung segmentation data is determined.
Specifically, the expiratory phase lung image sequence is input into a pre-trained neural network model, and expiratory phase lung segmentation data is obtained.
Step 602: based on the expiratory-phase lung segmentation data, expiratory-phase bronchial segmentation data and expiratory-phase lung lobe segmentation data are determined.
Specifically, the bronchial segmentation data is label data for segmenting the bronchi. The expiratory phase bronchial segmentation data are bronchial segmentation data corresponding to the expiratory phase; the inspiratory phase bronchial segmentation data is bronchial segmentation data corresponding to an inspiratory phase.
Optionally, the step of determining the expiratory-phase bronchial segmentation data and the expiratory-phase lung lobe segmentation data based on the expiratory-phase lung segmentation data comprises the following steps. The expiratory phase lung partition data is divided into a plurality of expiratory phase lung partition data. And determining the expiratory phase bronchial partition data and the expiratory phase fissured partition data corresponding to the expiratory phase pulmonary partition data aiming at each expiratory phase pulmonary partition data in the plurality of expiratory phase pulmonary partition data. And connecting the expiratory phase bronchial partition data corresponding to the plurality of expiratory phase lung partition data based on the region growing method to determine the expiratory phase bronchial partition data. And connecting the expiratory phase fissured partition data corresponding to the plurality of expiratory phase fissured partition data based on the region growing method to determine the expiratory phase fissured partition data. And determining expiratory phase lung lobe segmentation data by combining the expiratory phase lung segmentation data and the expiratory phase lung fissure segmentation data.
Step 603: and determining expiratory phase lung segment segmentation data based on the expiratory phase bronchial segmentation data and the expiratory phase lung lobe segmentation data.
Optionally, the step of determining the expiratory phase lung segment segmentation data based on the expiratory phase bronchial segmentation data and the expiratory phase lung lobe segmentation data comprises the following steps. And determining an expiratory phase bronchial segment and an expiratory phase bronchial sub-segment based on the topological structure of the bronchial tubes in the expiratory phase bronchial segmentation data. And determining expiratory phase lung segment segmentation data based on the expiratory phase bronchial segment and the expiratory phase lung lobe segmentation data.
In the embodiment of the application, through the steps, the expiratory phase lung lobe segmentation data and the expiratory phase lung segment segmentation data are determined based on the expiratory phase lung image sequence, and a basis is provided for subsequent registration.
Fig. 6b is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 6b, the step of determining the inspiratory phase lobe segmentation data and the inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images comprises the following steps.
Step 604: based on the sequence of inspiratory lung images, inspiratory lung segmentation data is determined.
Specifically, the sequence of the inspiratory lung images is input into a pre-trained neural network model, and the inspiratory lung segmentation data is obtained.
Step 605: based on the inspiratory phase lung segmentation data, inspiratory phase bronchial segmentation data and inspiratory phase lung lobe segmentation data are determined.
Optionally, the step of determining inspiratory bronchus segmentation data and inspiratory lobe segmentation data based on the inspiratory lung segmentation data comprises the following steps. The inspiratory phase lung segmentation data is divided into a plurality of inspiratory phase lung segmentation block data. And determining inspiratory phase bronchial segment data and inspiratory phase fissured segment data corresponding to the inspiratory phase pulmonary segment data for each of the plurality of inspiratory phase pulmonary segment data. And connecting the inspiratory phase bronchial segment data corresponding to the plurality of inspiratory phase lung segment data based on the region growing method to determine the inspiratory phase bronchial segment data. And connecting the inhalation phase fissuring block data corresponding to the plurality of inhalation phase fissuring block data based on the region growing method to determine the inhalation phase fissuring block data. And determining the segmentation data of the inspiratory phase lung lobes by combining the segmentation data of the inspiratory phase lungs and the segmentation data of the inspiratory phase fissures.
Step 606: and determining inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data.
Optionally, the step of determining inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data comprises the following steps. And determining an inspiratory bronchial segment and an inspiratory bronchial sub-segment based on the topological structure of the bronchial tubes in the inspiratory bronchial segmentation data. And determining inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segment and the inspiratory phase lung lobe segmentation data.
In the embodiment of the application, through the steps, the inspiratory phase lung lobe segmentation data and the inspiratory phase lung segment segmentation data are determined based on the inspiratory phase lung image sequence, and a basis is provided for subsequent registration.
Fig. 7 is a schematic flow chart illustrating registration of an expiratory phase lung image sequence and an inspiratory phase lung image sequence according to an embodiment of the present application. As shown in FIG. 7, inspiratory phase lung segmentation data is determined based on a sequence of inspiratory phase lung images. Based on the inspiratory phase lung segmentation data, inspiratory phase bronchial segmentation data and inspiratory phase fissure segmentation data are determined. And combining the inspiratory phase lung segmentation data and the inspiratory phase lung fissure segmentation data to obtain expiratory phase lung lobe segmentation data. And determining inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data. Based on the expiratory phase lung image sequence, expiratory phase lung segmentation data is determined. Based on the expiratory-phase lung segmentation data, expiratory-phase bronchial segmentation data and expiratory-phase fissure segmentation data are determined. And combining the expiratory phase lung segmentation data and the expiratory phase lung fissure segmentation data to obtain the expiratory phase lung lobe segmentation data. And determining expiratory phase lung segment segmentation data based on the expiratory phase bronchial segmentation data and the expiratory phase lung lobe segmentation data. And based on the expiratory phase lung segment segmentation data and the inspiratory phase lung segment segmentation data, performing non-rigid registration operation on the expiratory phase lung image sequence and the inspiratory phase lung image sequence after rigid registration operation to register the expiratory phase lung image sequence and the inspiratory phase lung image sequence.
Fig. 8 is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 8, the lung image registration method further includes the following steps.
Step 801: based on the expiratory phase pulmonary image sequence, expiratory phase pulmonary nodule segmentation data is determined.
Specifically, the expiratory phase pulmonary image sequence is input into a pre-trained neural network model, and expiratory phase pulmonary nodule segmentation data is obtained.
Step 802: based on the sequence of inspiratory lung images, inspiratory lung nodule segmentation data is determined.
Specifically, the sequence of the inspiratory lung images is input into a pre-trained neural network model, and the inspiratory lung nodule segmentation data is obtained.
Step 803: and registering the expiratory-phase pulmonary nodule and the inspiratory-phase pulmonary nodule based on the expiratory-phase pulmonary nodule segmentation data, the inspiratory-phase pulmonary nodule segmentation data and the registered expiratory-phase pulmonary image sequence and inspiratory-phase pulmonary image sequence.
Specifically, the position of the lung nodule in the expiratory phase lung image and the position of the lung nodule in the inspiratory phase lung image are different due to the lung breathing motion, and the lung nodule can be registered by registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence to obtain the accurate position of the lung nodule, provide correct puncture guidance and reduce the occurrence probability of multiple punctures caused by puncture failure.
In the embodiment of the application, the segmentation data of the pulmonary nodules of the inspiratory phase is determined based on the pulmonary image sequence of the inspiratory phase, and the pulmonary nodules can be registered by registering the pulmonary image sequence of the expiratory phase and the pulmonary image sequence of the inspiratory phase so as to obtain the accurate position of the pulmonary nodules, provide correct puncture guidance and reduce the probability of occurrence of multiple punctures caused by puncture failure.
Fig. 9 is a flowchart illustrating a lung image registration method according to an embodiment of the present application. As shown in fig. 9, the lung image registration method further includes the following steps.
Step 901: and presetting the association relation of the lung nodule data after registration with the expiratory phase lung image sequence and the inspiratory phase lung image sequence.
Specifically, after the expiratory phase lung image sequence and the inspiratory phase lung image sequence are registered, the pulmonary nodule is also registered, and the association relationship between the registered pulmonary nodule data and the expiratory phase lung image sequence and the inspiratory phase lung image sequence is preset.
Step 902: and sending the registered pulmonary nodule data associated with the expiratory phase pulmonary image sequence and/or the inspiratory phase pulmonary image sequence displayed by the display area to the display area for reference by a doctor based on the association relation.
When a doctor watches at least one image sequence in the expiratory phase pulmonary image sequence and the inspiratory phase pulmonary image sequence in the display area, the registered pulmonary nodule data is sent to the doctor for guiding puncture according to the pre-established association relation.
In the embodiment of the application, the incidence relation between the lung nodule and the lung image sequence of the expiratory phase and the lung image sequence of the inspiratory phase after registration is preset, and the registered lung nodule is sent to a doctor for guiding puncture according to the incidence relation established in advance, so that accurate and rapid puncture guiding information is provided.
Exemplary Lung image registration device
Fig. 10 is a schematic structural diagram of a lung image registration apparatus according to an embodiment of the present application. As shown in fig. 10, the lung image registration apparatus 100 includes: a first determination module 101 configured to determine expiratory phase lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase lung image sequence; a second determination module 102 configured to determine inspiratory phase lobe segmentation data and inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images; a registration module 103 configured to register the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence based on the expiratory-phase lung lobe segmentation data, the expiratory-phase lung segment segmentation data, the inspiratory-phase lung lobe segmentation data and the inspiratory-phase lung segment segmentation data.
In the embodiment of the application, the first determining module 101 determines the expiratory-phase lung lobe segmentation data and the expiratory-phase lung segment segmentation data based on the expiratory-phase lung image sequence, the second determining module 102 determines the inspiratory-phase lung lobe segmentation data and the inspiratory-phase lung segment segmentation data based on the inspiratory-phase lung image sequence, and the registering module 103 registers the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence based on the expiratory-phase lung lobe segmentation data, the expiratory-phase lung segment segmentation data, the inspiratory-phase lung lobe segmentation data and the inspiratory-phase lung segment segmentation data. The expiratory phase lung image sequence and the inspiratory phase lung image sequence are accurately registered by the segmented more accurate lung lobe segmentation data and lung segment segmentation data and by utilizing the space mapping relation of the lung lobes and each lung segment, so that the position of a focus is accurately determined, and the failure probability of a subsequent puncture operation is reduced.
Fig. 11 is a schematic structural diagram of a lung image registration apparatus according to an embodiment of the present application. As shown in fig. 11, the registration module 103 further includes: a rigid registration unit 1031, which performs rigid registration operation on the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data and the inspiratory phase lung lobe segmentation data; a non-rigid registration unit 1032 configured to perform a non-rigid registration operation on the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence after the rigid registration operation based on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data, so as to register the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence.
In one embodiment, as shown in fig. 11, the non-rigid registration unit 1032 further comprises: a lung segment spatial mapping relationship data determining subunit 10321 configured to perform bidirectional spatial coordinate transformation on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to determine lung segment spatial mapping relationship data; a non-rigid registration unit subunit 10322 configured to register the sequence of expiratory phase lung images after the rigid registration operation with the sequence of inspiratory phase lung images after the rigid registration operation based on the lung segment spatial mapping relationship data.
In one embodiment, the lung segment spatial mapping relationship data determining subunit 10321 is further configured to determine, based on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment, a first loss function corresponding to an expiratory-to-inspiratory phase spatial coordinate transformation and a second loss function corresponding to an inspiratory-to-expiratory phase spatial coordinate transformation; and determining lung segment space mapping relation data based on the first loss function and the second loss function.
In one embodiment, the lung segment spatial mapping relationship data determining subunit 10321 is further configured to determine, for the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment, expiratory-phase lung segment segmentation edge data and inspiratory-phase lung segment segmentation edge data based on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data; selecting a plurality of groups of seed points from the expiratory phase pulmonary segment segmentation edge data and the inspiratory phase pulmonary segment segmentation edge data; determining a first loss function based on the spatial coordinate transformation of a plurality of groups of seed points in the process of registering inhalation-exhalation phase lung segment segmentation data to inhalation segment segmentation data, determining a second loss function based on the spatial coordinate transformation of a plurality of groups of seed points in the process of registering inhalation-exhalation phase lung segment segmentation data to exhalation segment segmentation data, and determining lung segment spatial mapping relation data based on the first loss function and the second loss function.
In one embodiment, as shown in fig. 11, the first determining module 101 further comprises: an expiratory phase lung segmentation data determination unit 1011 configured to determine expiratory phase lung segmentation data corresponding to the expiratory phase lung image sequence based on the expiratory phase lung image sequence; an expiratory-phase bronchial segmentation data determining unit 1012 configured to determine, based on the expiratory-phase lung segmentation data, expiratory-phase bronchial segmentation data and expiratory-phase lung lobe segmentation data corresponding to the expiratory-phase lung segmentation data; an expiratory-phase lung segment segmentation data determination unit 1013 configured to determine expiratory-phase lung segment segmentation data based on the expiratory-phase bronchial segmentation data and the expiratory-phase lung lobe segmentation data.
In one embodiment, as shown in fig. 11, the second determining module 102 further comprises: an inspiratory phase lung segmentation data determination unit 1021 configured to determine inspiratory phase lung segmentation data for the sequence of inspiratory phase lung images based on the sequence of inspiratory phase lung images; an inspiratory phase bronchial segmentation data determining unit 1022 configured to determine inspiratory phase bronchial segmentation data and inspiratory phase pulmonary lobe segmentation data corresponding to the inspiratory phase pulmonary segmentation data based on the inspiratory phase pulmonary segmentation data; the inspiratory phase lung segment segmentation data determination unit 1023 is configured to determine inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data.
In one embodiment, the expiratory phase pulmonary segment segmentation data determination unit 1013 is further configured to determine the expiratory phase bronchial segment and the expiratory phase bronchial sub-segment based on a topology of bronchial tubes in the expiratory phase bronchial segmentation data. And determining expiratory phase lung segment segmentation data based on the expiratory phase bronchial segment and the expiratory phase lung lobe segmentation data.
In an embodiment, the inspiratory phase lung segment segmentation data determination unit 1023 is further configured to determine an inspiratory phase bronchial segment and an inspiratory phase bronchial sub-segment based on a topology of bronchial tubes in the inspiratory phase bronchial segmentation data. And determining inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segment and the inspiratory phase lung lobe segmentation data.
In one embodiment, the expiratory phase bronchial and lobe segmentation data determination unit 1012 is further configured to divide the expiratory phase lung segmentation data into a plurality of expiratory phase lung segmentation block data. And determining the expiratory phase bronchial partition data and the expiratory phase fissured partition data corresponding to the expiratory phase pulmonary partition data aiming at each expiratory phase pulmonary partition data in the plurality of expiratory phase pulmonary partition data. And connecting the expiratory phase bronchial partition data corresponding to the plurality of expiratory phase lung partition data based on the region growing method to determine the expiratory phase bronchial partition data. And connecting the expiratory phase fissured partition data corresponding to the plurality of expiratory phase fissured partition data based on the region growing method to determine the expiratory phase fissured partition data. And determining expiratory phase lung lobe segmentation data by combining the expiratory phase lung segmentation data and the expiratory phase lung fissure segmentation data.
In an embodiment, the inspiratory bronchus and lobe segmentation data determination unit 1022 is further configured to divide the inspiratory lung segmentation data into a plurality of inspiratory lung segmentation block data. And determining inspiratory phase bronchial segment data and inspiratory phase fissured segment data corresponding to the inspiratory phase pulmonary segment data for each of the plurality of inspiratory phase pulmonary segment data. And connecting the inspiratory phase bronchial segment data corresponding to the plurality of inspiratory phase lung segment data based on the region growing method to determine the inspiratory phase bronchial segment data. And connecting the inhalation phase fissuring block data corresponding to the plurality of inhalation phase fissuring block data based on the region growing method to determine the inhalation phase fissuring block data. And determining the segmentation data of the inspiratory phase lung lobes by combining the segmentation data of the inspiratory phase lungs and the segmentation data of the inspiratory phase fissures.
In one embodiment, as shown in fig. 11, the lung image registration apparatus 100 further includes: an expiratory-phase pulmonary nodule segmentation data determination module 104 configured to determine expiratory-phase pulmonary nodule segmentation data based on the expiratory-phase pulmonary image sequence, and an inspiratory-phase pulmonary nodule segmentation data determination module 105 configured to determine inspiratory-phase pulmonary nodule segmentation data based on the inspiratory-phase pulmonary image sequence; and a pulmonary nodule registration module 106 configured to register the expiratory phase pulmonary nodule and the inspiratory phase pulmonary nodule based on the expiratory phase pulmonary nodule segmentation data, the inspiratory phase pulmonary nodule segmentation data, and the registered expiratory phase pulmonary image sequence and inspiratory phase pulmonary image sequence.
In one embodiment, as shown in fig. 11, the lung image registration apparatus 100, the association module 107, is configured to preset an association relationship between the registered lung nodule data and the sequence of expiratory lung images and the sequence of inspiratory lung images; a display module 108 configured to send the registered lung nodule data associated with the sequence of expiratory phase lung images and/or the sequence of inspiratory phase lung images displayed by the display area to the display area for reference by the physician based on the association relationship.
Exemplary electronic device
Fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 12, electronic device 300 includes one or more processors 310 and memory 320.
The processor 310 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 300 to perform desired functions.
Memory 320 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 310 to implement the lung image registration methods of the various embodiments of the present application described above and/or other desired functions.
In one example, the electronic device 300 may further include: an input device 330 and an output device 340, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
For example, the input device 330 may be the CT apparatus described above. When the electronic device 300 is a stand-alone device, the input device 330 may be a display screen or a communication network connector.
The output device 340 may output various information, lung tumor information, puncture control phase information, and the like to the outside.
Of course, for the sake of simplicity, only some of the components related to the present application in the electronic device 300 are shown in fig. 12, and components such as a bus, an input/output interface, and the like are omitted. In addition, electronic device 300 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the lung image registration method according to various embodiments of the present application described in the "exemplary lung image registration method" section of this specification, above.
The computer program product may write program code for carrying out operations for embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps in the lung image registration method according to various embodiments of the present application described in the "exemplary lung image registration method" section above in the present description.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (13)
1. A method of registering pulmonary images for registering a sequence of expiratory phase pulmonary images and a sequence of inspiratory phase pulmonary images, comprising:
determining expiratory phase lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase lung image sequence;
determining inspiratory phase lung lobe segmentation data and inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images;
registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data, the expiratory phase lung segment segmentation data, the inspiratory phase lung lobe segmentation data and the inspiratory phase lung segment segmentation data.
2. The method for pulmonary image registration according to claim 1, wherein the registering the sequence of expiratory phase pulmonary images and the sequence of inspiratory phase pulmonary images based on the expiratory phase lobe segmentation data, the expiratory phase pulmonary segment segmentation data, the inspiratory phase pulmonary segment segmentation data and the inspiratory phase pulmonary segment segmentation data comprises:
performing a rigid registration operation on the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data and the inspiratory phase lung lobe segmentation data;
and performing non-rigid registration operation on the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence after the rigid registration operation based on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data so as to register the expiratory-phase lung image sequence and the inspiratory-phase lung image sequence.
3. The method for registering lung images according to claim 2, wherein the non-rigid registration of the sequence of expiratory lung images and the sequence of inspiratory lung images after the rigid registration operation based on the segmentation data of the expiratory lung segments and the segmentation data of the inspiratory lung segments comprises:
performing bidirectional space coordinate transformation on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to determine lung segment space mapping relation data;
and registering the expiratory phase lung image sequence and the inspiratory phase lung image sequence after the rigid registration operation based on the lung segment space mapping relation data.
4. The lung image registration method according to claim 3, wherein the performing bi-directional spatial coordinate transformation on the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data belonging to the same lung segment to determine lung segment spatial mapping relationship data comprises:
determining a first loss function corresponding to the spatial coordinate transformation of the expiratory phase to the inspiratory phase and a second loss function corresponding to the spatial coordinate transformation of the inspiratory phase to the expiratory phase based on the expiratory phase and inspiratory phase lung segment segmentation data belonging to the same lung segment;
determining the lung segment spatial mapping relationship data based on the first loss function and the second loss function.
5. The method for registering lung images according to claim 4, wherein the determining a first loss function corresponding to the spatial coordinate transformation of the expiratory phase to the inspiratory phase and a second loss function corresponding to the spatial coordinate transformation of the inspiratory phase to the expiratory phase based on the expiratory phase and inspiratory phase lung segment segmentation data belonging to the same lung segment comprises:
determining expiratory-phase lung segment segmentation edge data and inspiratory-phase lung segment segmentation edge data according to the expiratory-phase lung segment segmentation data and the inspiratory-phase lung segment segmentation data which belong to the same lung segment;
selecting a plurality of groups of seed points from the expiratory-phase lung segment segmentation edge data and the inspiratory-phase lung segment segmentation edge data;
determining the first loss function by adopting a B-spline elastic registration algorithm based on the spatial coordinate transformation of the plurality of groups of seed points in the process of registering the inhalation-exhalation phase lung segment segmentation data to the inhalation segment segmentation data;
and determining the second loss function by adopting a B-spline elastic registration algorithm based on the space coordinate transformation of the plurality of groups of seed points in the process of registering the inspiratory phase lung segment segmentation data to the expiratory phase segmentation data.
6. The pulmonary image registration method of any of claims 1 to 5, wherein the determining expiratory phase lobe segmentation data and expiratory phase lung segment segmentation data based on the expiratory phase pulmonary image sequence comprises:
determining expiratory phase lung segmentation data based on the expiratory phase lung image sequence;
determining, based on the expiratory phase lung segmentation data, expiratory phase bronchial segmentation data and the expiratory phase lung lobe segmentation data;
determining the expiratory phase lung segment segmentation data based on the expiratory phase bronchial segmentation data and the expiratory phase lung lobe segmentation data;
and the combination of (a) and (b),
the determining of expiratory phase lobe segmentation data and inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images comprises:
determining inspiratory phase lung segmentation data based on the sequence of inspiratory phase lung images;
determining inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data based on the inspiratory phase lung segmentation data;
determining the inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data.
7. The pulmonary image registration method of claim 6, wherein the determining the expiratory phase lung segment segmentation data based on the expiratory phase bronchial segmentation data and the expiratory phase lobe segmentation data comprises:
determining an expiratory phase bronchial segment and an expiratory phase bronchial sub-segment based on the topological structure of the bronchial tubes in the expiratory phase bronchial segmentation data;
determining the expiratory phase lung segment segmentation data based on the expiratory phase bronchial segment and the expiratory phase lobe segmentation data;
and/or the presence of a gas in the gas,
the determining the inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data comprises:
determining an inspiratory bronchial segment and an inspiratory bronchial sub-segment based on the topological structure of the bronchial tubes in the inspiratory bronchial segmentation data;
determining the inspiratory phase lung segment segmentation data based on the inspiratory phase bronchial segment and the inspiratory phase lobe segmentation data.
8. The pulmonary image registration method of claim 6, wherein the determining expiratory phase bronchial segmentation data and the expiratory phase lobe segmentation data based on the expiratory phase lung segmentation data comprises:
dividing the expiratory phase lung segmentation data into a plurality of expiratory phase lung segmentation block data;
for each expiratory phase lung segmentation block data in the plurality of expiratory phase lung segmentation block data, determining expiratory phase bronchial segmentation block data and expiratory phase fissured segmentation block data corresponding to the expiratory phase lung segmentation block data;
connecting expiratory phase bronchial partition data corresponding to the plurality of expiratory phase lung partition data to determine the expiratory phase bronchial partition data based on a region growing method;
connecting the expiratory phase fissured partition data corresponding to the plurality of expiratory phase fissured partition data to determine the expiratory phase fissured partition data based on a region growing method;
determining the expiratory phase lobe segmentation data in combination with the expiratory phase lung segmentation data and the expiratory phase fissure segmentation data;
and/or the presence of a gas in the gas,
the determining inspiratory phase bronchial segmentation data and the inspiratory phase lung lobe segmentation data based on the inspiratory phase lung segmentation data comprises:
dividing the inspiratory phase lung segmentation data into a plurality of inspiratory phase lung segmentation block data;
determining, for each of the plurality of inspiratory phase lung segmentation block data, inspiratory phase bronchial segmentation block data and inspiratory phase fissured segmentation block data corresponding to the inspiratory phase lung segmentation block data;
connecting inhalation phase bronchial segment data corresponding to the plurality of inhalation phase lung segment data to determine the inhalation phase bronchial segment data based on a region growing method;
connecting inhalation phase lung segmentation block data corresponding to the plurality of inhalation phase lung segmentation block data based on a region growing method to determine the inhalation phase lung segmentation data;
and combining the inspiratory phase lung segmentation data and the inspiratory phase lung fissure segmentation data to determine the inspiratory phase lung lobe segmentation data.
9. The pulmonary image registration method of any of claims 1 to 5, wherein the method of determining the sequence of expiratory phase pulmonary images and the sequence of inspiratory phase pulmonary images comprises:
receiving a first sequence of lung images;
determining patient information corresponding to the first sequence of lung images based on the first sequence of lung images;
based on the patient information, screening a second lung image sequence matched with the patient information from a hospital information system;
determining the sequence of expiratory phase lung images and the sequence of inspiratory phase lung images based on the first sequence of lung images and the second sequence of lung images.
10. The pulmonary image registration method according to any one of claims 1 to 5, further comprising:
determining expiratory phase pulmonary nodule segmentation data based on the expiratory phase pulmonary image sequence;
determining inspiratory phase lung nodule segmentation data based on the sequence of inspiratory phase lung images;
and registering the expiratory-phase pulmonary nodule and the inspiratory-phase pulmonary nodule based on the expiratory-phase pulmonary nodule segmentation data, the inspiratory-phase pulmonary nodule segmentation data and the registered expiratory-phase pulmonary image sequence and inspiratory-phase pulmonary image sequence.
11. A pulmonary image registration apparatus for registering a sequence of expiratory phase pulmonary images and a sequence of inspiratory phase pulmonary images, comprising:
a first determination module configured to determine expiratory phase lobe segmentation data and expiratory phase segment segmentation data based on the expiratory phase lung image sequence;
a second determination module configured to determine inspiratory phase lung lobe segmentation data and inspiratory phase lung segment segmentation data based on the sequence of inspiratory phase lung images;
a registration module configured to register the expiratory phase lung image sequence and the inspiratory phase lung image sequence based on the expiratory phase lung lobe segmentation data, the expiratory phase lung segment segmentation data, the inspiratory phase lung lobe segmentation data, and the inspiratory phase lung segment segmentation data.
12. An electronic device, comprising:
a processor; and
a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform the lung image registration method of any one of claims 1 to 10.
13. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the lung image registration method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110932280.XA CN113538414B (en) | 2021-08-13 | 2021-08-13 | Lung image registration method and lung image registration device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110932280.XA CN113538414B (en) | 2021-08-13 | 2021-08-13 | Lung image registration method and lung image registration device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113538414A true CN113538414A (en) | 2021-10-22 |
| CN113538414B CN113538414B (en) | 2022-03-08 |
Family
ID=78091592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110932280.XA Active CN113538414B (en) | 2021-08-13 | 2021-08-13 | Lung image registration method and lung image registration device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538414B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114511599A (en) * | 2022-01-20 | 2022-05-17 | 推想医疗科技股份有限公司 | Model training method and device, medical image registration method and device |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110018573A (en) * | 2009-08-18 | 2011-02-24 | 서울여자대학교 산학협력단 | Apparatus and method for nonrigid lung registration between end-exhale and end-inhale computed tomography scan |
| CN102722890A (en) * | 2012-06-07 | 2012-10-10 | 内蒙古科技大学 | Non-rigid heart image grading and registering method based on optical flow field model |
| CN104021547A (en) * | 2014-05-17 | 2014-09-03 | 清华大学深圳研究生院 | Three dimensional matching method for lung CT |
| CN104361568A (en) * | 2014-09-18 | 2015-02-18 | 南方医科大学 | Lung 4D-CT image exhaling process middle phase image reconstruction method based on registration |
| US20150201910A1 (en) * | 2014-01-17 | 2015-07-23 | Centre For Imaging Technology Commercialization (Cimtec) | 2d-3d rigid registration method to compensate for organ motion during an interventional procedure |
| CN105913442A (en) * | 2016-04-29 | 2016-08-31 | 上海联影医疗科技有限公司 | Method for automatically matching pulmonary nodules |
| CN107194956A (en) * | 2017-05-16 | 2017-09-22 | 山东大学 | A kind of Non-rigid Medical Image Registration method |
| CN107230223A (en) * | 2017-06-09 | 2017-10-03 | 中国科学院苏州生物医学工程技术研究所 | Liver's three-dimensional multimode state method for registering images based on discontinuous fluid |
| CN108428245A (en) * | 2018-02-11 | 2018-08-21 | 中国科学院苏州生物医学工程技术研究所 | Sliding method for registering images based on self-adapting regular item |
| CN111242931A (en) * | 2020-01-15 | 2020-06-05 | 东北大学 | Method and device for judging small airway lesion of single lung lobe |
| CN111311612A (en) * | 2020-02-17 | 2020-06-19 | 北京推想科技有限公司 | Lung segmentation method, device, medium, and electronic apparatus |
| CN111445463A (en) * | 2020-03-31 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Retrieval method and device for similar lung disease cases and computer equipment |
| CN111539944A (en) * | 2020-04-28 | 2020-08-14 | 安徽科大讯飞医疗信息技术有限公司 | Lung focus statistical attribute acquisition method and device, electronic equipment and storage medium |
| CN111681247A (en) * | 2020-04-29 | 2020-09-18 | 杭州深睿博联科技有限公司 | Lung lobe and lung segment segmentation model training method and device |
| CN111724364A (en) * | 2020-06-12 | 2020-09-29 | 深圳技术大学 | Method and device based on lung lobes and trachea trees, electronic equipment and storage medium |
-
2021
- 2021-08-13 CN CN202110932280.XA patent/CN113538414B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110018573A (en) * | 2009-08-18 | 2011-02-24 | 서울여자대학교 산학협력단 | Apparatus and method for nonrigid lung registration between end-exhale and end-inhale computed tomography scan |
| CN102722890A (en) * | 2012-06-07 | 2012-10-10 | 内蒙古科技大学 | Non-rigid heart image grading and registering method based on optical flow field model |
| US20150201910A1 (en) * | 2014-01-17 | 2015-07-23 | Centre For Imaging Technology Commercialization (Cimtec) | 2d-3d rigid registration method to compensate for organ motion during an interventional procedure |
| CN104021547A (en) * | 2014-05-17 | 2014-09-03 | 清华大学深圳研究生院 | Three dimensional matching method for lung CT |
| CN104361568A (en) * | 2014-09-18 | 2015-02-18 | 南方医科大学 | Lung 4D-CT image exhaling process middle phase image reconstruction method based on registration |
| CN105913442A (en) * | 2016-04-29 | 2016-08-31 | 上海联影医疗科技有限公司 | Method for automatically matching pulmonary nodules |
| CN107194956A (en) * | 2017-05-16 | 2017-09-22 | 山东大学 | A kind of Non-rigid Medical Image Registration method |
| CN107230223A (en) * | 2017-06-09 | 2017-10-03 | 中国科学院苏州生物医学工程技术研究所 | Liver's three-dimensional multimode state method for registering images based on discontinuous fluid |
| CN108428245A (en) * | 2018-02-11 | 2018-08-21 | 中国科学院苏州生物医学工程技术研究所 | Sliding method for registering images based on self-adapting regular item |
| CN111242931A (en) * | 2020-01-15 | 2020-06-05 | 东北大学 | Method and device for judging small airway lesion of single lung lobe |
| CN111311612A (en) * | 2020-02-17 | 2020-06-19 | 北京推想科技有限公司 | Lung segmentation method, device, medium, and electronic apparatus |
| CN111445463A (en) * | 2020-03-31 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Retrieval method and device for similar lung disease cases and computer equipment |
| CN111539944A (en) * | 2020-04-28 | 2020-08-14 | 安徽科大讯飞医疗信息技术有限公司 | Lung focus statistical attribute acquisition method and device, electronic equipment and storage medium |
| CN111681247A (en) * | 2020-04-29 | 2020-09-18 | 杭州深睿博联科技有限公司 | Lung lobe and lung segment segmentation model training method and device |
| CN111724364A (en) * | 2020-06-12 | 2020-09-29 | 深圳技术大学 | Method and device based on lung lobes and trachea trees, electronic equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| BABAK HAGHIGHI等: "A GPU-based symmetric non-rigid image registration method in human lung", 《MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING》 * |
| 边子健等: "肺部CT图像中的解剖结构分割方法综述", 《中国图象图形学报》 * |
| 金晨望等: "基于体素的空气潴留定量测量方法的建立及初步临床应用", 《中华放射学杂志》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114511599A (en) * | 2022-01-20 | 2022-05-17 | 推想医疗科技股份有限公司 | Model training method and device, medical image registration method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113538414B (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4374234B2 (en) | Method and apparatus for medical invasive treatment planning | |
| US10460441B2 (en) | Trachea marking | |
| JP4800129B2 (en) | Medical image display processing apparatus and medical image display processing program | |
| US10825190B2 (en) | Dynamic image processing apparatus for aligning frame images obtained by photographing dynamic state of chest based on movement of lung-field region | |
| EP2375378A1 (en) | Medical image diagnosis assisting apparatus and method, and computer readable recording medium on which is recorded program for the same | |
| JP2006051359A (en) | Method and apparatus for medical intervention procedure planning and location and navigation of an intervention tool | |
| CN110301883B (en) | Image-based guidance for navigating tubular networks | |
| CN111916186A (en) | Chest X-ray intelligent diagnosis system and method by sequential AI diagnosis model | |
| CN113538414B (en) | Lung image registration method and lung image registration device | |
| CN114943714A (en) | Medical image processing system, medical image processing apparatus, electronic device, and storage medium | |
| US11783477B2 (en) | Medical image process apparatus, medical image learning method, and medical image process method | |
| JP5558793B2 (en) | Image processing method, image processing apparatus, and program | |
| JP3404675B2 (en) | Three-dimensional tomographic image interpretation method, automatic collation method, device thereof, and recording medium recording the program | |
| WO2020235461A1 (en) | Abnormality detection method, abnormality detection program, abnormality detection device, server device, and information processing method | |
| WO2023216947A1 (en) | Medical image processing system and method for interventional operation | |
| KR20100025431A (en) | Method for detection of hepatic tumors using registration of multi-phase liver ct images | |
| US9367893B2 (en) | Diagnosis assistance apparatus, method and program | |
| CN114596275A (en) | Pulmonary vessel segmentation method, device, storage medium and electronic equipment | |
| WO2021103316A1 (en) | Method, device, and system for determining target region of image | |
| US20160310094A1 (en) | Medical image processing apparatus | |
| JP7153261B2 (en) | IMAGE PROCESSING DEVICE, OPERATING METHOD OF IMAGE PROCESSING DEVICE, AND IMAGE PROCESSING PROGRAM | |
| US20240005503A1 (en) | Method for processing medical images | |
| WO2023103975A1 (en) | Medical image movement detection and correction method and system, and computer readable medium | |
| JP2009018029A (en) | Medical image processing apparatus and medical image diagnosis apparatus | |
| JP4786184B2 (en) | Computer-aided diagnostic imaging 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240219 Address after: No. 288 Xingcheng Avenue, Hannan District, Wuhan City, Hubei Province (019) Patentee after: Wuhan Longdianjing Intelligent Technology Co.,Ltd. Country or region after: China Address before: Room B401, 4 / F, building 1, No. 12, shangdixin Road, Haidian District, Beijing 100085 Patentee before: Tuxiang Medical Technology Co.,Ltd. Country or region before: China |