CN113536575A - Organ contour delineation method, medical imaging system and storage medium - Google Patents
Organ contour delineation method, medical imaging system and storage medium Download PDFInfo
- Publication number
- CN113536575A CN113536575A CN202110817145.0A CN202110817145A CN113536575A CN 113536575 A CN113536575 A CN 113536575A CN 202110817145 A CN202110817145 A CN 202110817145A CN 113536575 A CN113536575 A CN 113536575A
- Authority
- CN
- China
- Prior art keywords
- organ
- delineation
- medical image
- image data
- contour
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000000056 organ Anatomy 0.000 title claims abstract description 338
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000002059 diagnostic imaging Methods 0.000 title claims description 30
- 238000003384 imaging method Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 210000004999 sex organ Anatomy 0.000 claims 1
- 210000000920 organ at risk Anatomy 0.000 description 16
- 238000001959 radiotherapy Methods 0.000 description 12
- 210000001015 abdomen Anatomy 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 210000000038 chest Anatomy 0.000 description 6
- 206010028980 Neoplasm Diseases 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 5
- 210000004185 liver Anatomy 0.000 description 4
- 210000004072 lung Anatomy 0.000 description 4
- 238000002595 magnetic resonance imaging Methods 0.000 description 4
- 210000000496 pancreas Anatomy 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 210000004291 uterus Anatomy 0.000 description 4
- 210000004394 hip joint Anatomy 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 210000003478 temporal lobe Anatomy 0.000 description 3
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 2
- 210000000133 brain stem Anatomy 0.000 description 2
- 210000000481 breast Anatomy 0.000 description 2
- 210000001072 colon Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 208000014829 head and neck neoplasm Diseases 0.000 description 2
- 210000003734 kidney Anatomy 0.000 description 2
- 201000005202 lung cancer Diseases 0.000 description 2
- 208000020816 lung neoplasm Diseases 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 210000004373 mandible Anatomy 0.000 description 2
- 210000001328 optic nerve Anatomy 0.000 description 2
- 210000003899 penis Anatomy 0.000 description 2
- 210000002307 prostate Anatomy 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000002271 resection Methods 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 210000000278 spinal cord Anatomy 0.000 description 2
- 210000000952 spleen Anatomy 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 208000006678 Abdominal Neoplasms Diseases 0.000 description 1
- 235000001674 Agaricus brunnescens Nutrition 0.000 description 1
- 235000011299 Brassica oleracea var botrytis Nutrition 0.000 description 1
- 240000003259 Brassica oleracea var. botrytis Species 0.000 description 1
- 208000026310 Breast neoplasm Diseases 0.000 description 1
- 206010062767 Hypophysitis Diseases 0.000 description 1
- 206010061336 Pelvic neoplasm Diseases 0.000 description 1
- 208000024770 Thyroid neoplasm Diseases 0.000 description 1
- 208000025865 Ulcer Diseases 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003238 esophagus Anatomy 0.000 description 1
- 210000001624 hip Anatomy 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 208000025426 neoplasm of thorax Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000003681 parotid gland Anatomy 0.000 description 1
- 230000001817 pituitary effect Effects 0.000 description 1
- 210000003635 pituitary gland Anatomy 0.000 description 1
- 238000002600 positron emission tomography Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 210000000813 small intestine Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000001738 temporomandibular joint Anatomy 0.000 description 1
- 210000001550 testis Anatomy 0.000 description 1
- 201000003957 thoracic cancer Diseases 0.000 description 1
- 208000013076 thyroid tumor Diseases 0.000 description 1
- 231100000397 ulcer Toxicity 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
-
- 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
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/41—Medical
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The embodiment of the invention discloses an organ contour delineation method, a medical image system and a storage medium, wherein the method comprises the following steps: acquiring medical image data to be sketched currently, and determining an organ sketching range in the medical image data; determining a delineation template according to the organ delineation range, wherein the delineation template comprises at least two organ identifications; and calling a delineation model corresponding to the delineation template to carry out contour delineation on of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data. The method solves the problem that the existing organ contour delineation method can not give consideration to both flexibility and timeliness.
Description
Technical Field
The embodiment of the invention relates to the field of medical image processing, in particular to an organ contour delineation method, a medical imaging system and a storage medium.
Background
Clinically, after acquiring medical image data of a patient, a radiotherapy doctor needs to browse the medical image data, determine patient information, a cancerous region and an organ at risk, complete the delineation of the cancerous region and the organ at risk in the medical image data, and upload the medical image data containing the organ contour data to a radiotherapy planning system, so that a radiotherapy physicist makes a radiotherapy plan for the medical image data. Therefore, the workflow of the radiotherapy doctor is complicated, and the manual delineation of the organ contour has high flexibility, but can consume much energy and time of the radiotherapy doctor.
With the development of automatic identification technology, an automatic delineation model based on deep learning comes along, but the automatic delineation model usually corresponds to a certain scanning part, and a doctor needs to manually select an organ to be delineated, and after delineation is finished, the doctor performs auditing. The process has poor flexibility, various clinical requirements cannot be met, the establishing process is complex, a large amount of computing resources need to be consumed in the operation process, and the timeliness of the outline drawing is difficult to guarantee.
In conclusion, the existing organ contour delineation method has the problem that both flexibility and timeliness cannot be considered.
Disclosure of Invention
The embodiment of the invention provides an organ contour delineation method, a medical imaging system and a storage medium, and solves the problem that the existing organ contour delineation method cannot give consideration to both flexibility and timeliness.
In a first aspect, an embodiment of the present invention provides an organ contouring method, including:
acquiring medical image data to be sketched currently, and determining an organ sketching range in the medical image data;
determining a delineation template according to the organ delineation range, wherein the delineation template comprises at least two organ identifications;
and calling a delineation model corresponding to the delineation template to carry out contour delineation on of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data.
In a second aspect, an embodiment of the present invention further provides a medical imaging system, where the system includes: a CPU, a GPU and a storage device;
the storage device is used for storing one or more first programs and one or more second programs;
when the one or more first programs are executed by the CPU, the CPU acquires medical image data from corresponding imaging equipment;
when the one or more second programs are executed by the GPU, causing the GPU to perform the organ contouring method of any of the embodiments.
In a third aspect, embodiments of the present invention further provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the organ contouring method according to any of the embodiments.
According to the technical scheme of the organ contour delineation method provided by the embodiment of the invention, the medical image data to be delineated currently is obtained, and the organ delineation range in the medical image data is determined; determining a delineation template according to the organ delineation range, wherein the delineation template comprises at least two organ identifications; and calling the delineation model corresponding to the delineation template to carry out contour delineation on of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data. Establishing the relation between the organ delineation range and at least two organs corresponding to the organ delineation range through the delineation template, and being beneficial to improving the efficiency of determining the organ corresponding to each organ delineation range; the corresponding delineation model is called through the delineation template to carry out the delineation of the organ contour, which is beneficial to improving the speed and the flexibility of the organ contour delineation.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for contouring an organ according to an embodiment of the present invention;
fig. 2 is a block diagram of a medical imaging system according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described through embodiments with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
Example one
Fig. 1 is a flowchart of an organ contouring method according to an embodiment of the present invention. The technical scheme of the embodiment is suitable for automatically finishing the organ contour delineation of the medical image data. The method is preferably executed by a GPU (Graphics Processing Unit, abbreviated as GPU) of the medical imaging system provided by the embodiment of the present invention. The medical image system comprises a CPU (Central Processing Unit, CPU for short) and a GPU (graphics Processing Unit), and the CPU and the GPU are in communication connection. The method specifically comprises the following steps:
s101, obtaining medical image data to be sketched currently, and determining an organ sketching range in the medical image data.
The medical image data may be clinical image data such as a CT (Computed Tomography, abbreviated as CT) image, an MRI (Magnetic Resonance Imaging, abbreviated as MRI) image, a PET (Positron Emission Tomography, abbreviated as PET) image, an ultrasound image, and an X-ray film.
Wherein, the organ delineation range is an image range for organ contour delineation in the medical image data. It is understood that the organ delineation area contains a number of body slices less than or equal to the number of body slices contained in the medical image data.
The method for determining the organ delineation range comprises the following steps: determining the number of body layers of each scanning part contained in the medical image data; and determining the organ delineation range according to the actual size of each scanning part corresponding to the number of the body layers of each scanning part. Or determining the number of the body layers of each scanning part contained in the medical image data based on a pre-trained recognition model, acquiring preset TAG information containing the thickness of the body layer, determining the actual size of each scanning part according to the thickness of the body layer and the number of the body layers of each scanning part, and determining the organ delineation range according to the actual size of each scanning part. By adopting the method, the organ delineation range can be quickly and efficiently obtained, images of redundant parts can be quickly eliminated, the accuracy of determining the contour delineation organ is improved, and the number of images needing to be traversed in the organ delineation process can be reduced.
In one embodiment, medical image data of a lung cancer patient is input into a pre-trained recognition model that outputs recognition results in which the ratio of the number of neck body slices to the total number of layers of the entire medical image data is 2%, corresponding to a physical size of 10mm, the ratio of the number of upper abdomen body slices to the total number of body slices of the entire medical image data is 2%, corresponding to a physical size of 10mm, the ratio of the number of chest body slices to the total number of body slices of the medical image data is 96%, corresponding to a physical size of 480 mm. Therefore, the target scanning range of the medical image data is the chest, and the neck and the upper abdomen are non-target scanning ranges, namely non-organ delineation ranges, so that the medical image data corresponding to the chest is used as the organ delineation range, and when each organ, such as the outline of the lung, is delineated, only images in the organ delineation range are traversed; or deleting the body layers of the neck and the upper abdomen from the medical image data to update the medical image data, and using the updated medical image data as the organ delineation range. In another embodiment, the number of body slices at each scan site is identified, and the organ delineation range can also be determined by segmentation, registration, or the like, or manually.
The pre-trained recognition model can classify the scanning part in any layer of the cross section, the coronal plane or the sagittal plane of the medical image data, and can also directly classify the scanning part of the three-dimensional data or the reconstructed data. The recognition model in the embodiment is preferably implemented by using a deep learning model such as image classification or target detection.
Wherein the TAG value of a Dicom file contains substantially all attributes of one Dicom file. In medical images based on the dicom3.0 standard, each image carries a lot of information, which can be classified into patent, study, series and image 4. Each TAG is determined by a combination of two hexadecimal numbers, Group and Element respectively. E.g., (0010 ), this TAG value represents Patient's Name, which stores the Patient Name for the corresponding image. Based on this, the present embodiment obtains the slice thickness of the corresponding medical image data and other required information by reading the corresponding TAG information of the medical image data.
In one embodiment, this step is performed by a GPU of the medical imaging system, and the GPU obtains the medical image data to be delineated from the CPU. Specifically, the GPU sends an image acquisition request to the CPU, the CPU sends the medical image data currently in the first rank to the GPU according to the image acquisition request when receiving the image acquisition request, and the GPU receives the medical image data. It is understood that the CPU is further configured to receive medical image data from each imaging device, and perform image preprocessing on the received medical image data to update the corresponding medical image data. The CPU can also acquire the updated contour delineation time limit information and scanning time of each medical image data, and rank the current medical image data according to the updated contour delineation time limit information and scanning time of each medical image data so as to obtain the ranking result of each medical image data. Wherein the contour delineation time limit information can be obtained by reading corresponding TAG information of the medical image data. The timing of organ outline delineation of each medical image data is determined according to the ranking result of the medical image data, emergency tasks can be completed preferentially, and the efficiency and accuracy of resource allocation are improved.
In one embodiment, the contouring time limit information may be specific time information or may be a flag indicating time limit information. Exemplarily, the marking of "1" indicates that the organ contour delineation of the corresponding medical image data has no higher requirement on time limit, and the delineation of the organ contour is completed within three days; the identifier 2 indicates that the organ contour delineation of the corresponding medical image data has high requirement on time limit, and the organ contour delineation needs to be completed within two days; the organ contour delineation indicated by the label "3" of the corresponding medical image data has a very high requirement on time limit, and the delineation of the organ contour needs to be completed within one day.
S102, determining a delineation template according to the organ delineation range, wherein the delineation template comprises at least two organ identifications.
In one embodiment, each organ delineation range corresponds to one delineation template, each delineation template comprises at least two organ identifications including at least one organ identification for representing a cancerous range and at least one organ identification for representing an organ at risk. Therefore, after the organ delineation range is determined, the delineation template corresponding to the organ delineation range can be determined, and the organ needing to be subjected to contour delineation is determined.
Different tumors have large geometrical shape difference, for example, head and neck tumors are generally small, common thyroid tumors, otorhinolaryngologic tumors and oral and maxillofacial tumors have small organs at risk, for example, breast tumors have small and large tumors, abdominal tumors generally relate to large organs, and the shape difference among different organs is also large, for example, tumors have polypoid, papillary, villous, nodular, lobular, saccular, cauliflower, mushroom, infiltration packet block, diffuse fat and thick, ulcer and the like, and organs at risk have various shapes such as block and strip, so that the problems of incapability of universal applicability and low accuracy rate can be caused by adopting the same template for sketching.
In one embodiment, the delineation template may be determined according to the organ delineation range and at least one of TAG information or additional information entered by a physician, which may be gender information, age information, height and weight information, radiotherapy information, biological information, etc. Further, each organ scanning range containing the organ with the preset gender corresponds to at least two delineation templates, wherein the organ with the preset gender can be a breast, a uterus, a prostate and the like. And when the organ delineation range is determined, preset TAG information containing gender information is also acquired, and the delineation template is determined according to the organ delineation range and the gender information. Exemplarily, for any medical image data containing the lower abdomen, after determining the organ delineation range thereof, preset TAG information containing gender information is also required to be acquired, and if the gender information shows that the patient is female, the organ delineation range is required to correspond to the delineation template suitable for the female patient; if the sex information shows that the patient is male, the organ delineation range needs to correspond to the delineation template suitable for the male patient. The delineation template is determined through the TAG information used for representing the sex of the patient and the organ delineation range, so that the determination process of the delineation template can be simplified, and the determination accuracy of the delineation template can be improved.
In one embodiment, each organ delineation range corresponds to one preset delineation template and at least one custom delineation template. The preset delineation template is a general delineation template, and the user-defined delineation template is preferably a delineation template defined by a doctor according to own habits. After the organ delineation range is determined, preset TAG information containing doctor information is obtained, and a delineation template is determined according to the organ delineation range and the doctor information. It can be understood that the sketch template is customized by the doctor corresponding to the doctor information. The setting of the user-defined sketching template can meet various organ sketching requirements of different radiotherapy doctors.
In one embodiment, each organ delineation range corresponds to one preset delineation template and at least one custom delineation template. Illustratively, the preset TAG information includes preset appointment information, and the delineation template is determined according to the organ delineation range and the preset appointment information. The customized sketch template is customized based on preset appointment information. The preset appointment information may be abnormal organ information such as artificial joint information (e.g., artificial hip joint) or organ resection information (e.g., pancreas).
In this embodiment, the organ delineation range, the organ to be delineated, and other information such as TAG information need to be considered, and then the corresponding delineation template is selected, so that the corresponding delineation template can be selected according to the current requirement, and a doctor is better assisted in delineation. One sketching template is selected according to various requirements for sketching, so that the operation steps of doctors are saved, and the sketching efficiency is improved. One delineation template includes delineation of at least one target organ and the organs at risk, thus allowing for simultaneous consideration and delineation, which is faster, simpler and more accurate than using multiple delineation templates to delineate, respectively.
In conclusion, the radiotherapy doctor can formulate the delineation template corresponding to different TAG information for each organ delineation range according to different requirements, so that the flexibility of determining the delineation template can be improved according to the organ delineation range and the preset TAG information, and the flexibility of determining the organ corresponding to the organ delineation range is improved.
S103, calling the delineation model corresponding to the delineation template to carry out contour delineation on of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data.
In this embodiment, each delineation template may correspond to only one delineation model, and the delineation model includes delineation algorithms of at least two organs, and may perform associated delineation on of a target organ and an organ at risk in different methods; each delineation template may also correspond to at least two delineation models, with different delineation models corresponding to different organ delineation algorithms, and may also be associated with, but different methods of delineation of the target organ and the organ at risk.
In an embodiment, each organ identifier included in each delineation template corresponds to one delineation model, so that after the delineation template is determined, the delineation models corresponding to at least two organ identifiers included in the delineation template respectively can be called, and then the at least two delineation models are used for performing contour delineation on corresponding organs in an organ delineation range, so as to obtain organ contour data of the medical image data. The GPU may adopt the at least two delineating models to perform contour delineation on the at least two corresponding organs simultaneously within the organ delineating range, or may also adopt one of the at least two delineating models to perform contour delineation on the at least two corresponding organs sequentially within the organ delineating range, and the former is preferred in this embodiment. It can be understood that when each delineation model only comprises a delineation algorithm of an organ, the difficulty of establishing the delineation model and the requirement of the organ delineation on the computing resources of the processor can be reduced.
It should be noted that the delineation model may be implemented by using an existing organ delineation algorithm, and this embodiment is not specifically limited herein. Specifically, organ contouring algorithms generally focus the dose on the target organ, i.e., the target organ, while trying to avoid applying the dose to the normal critical organ, i.e., the compromised organ. Depending on the target organ, there may be different organs at risk, such as head and neck tumor corresponding temporal lobe (temporal lobe), optic nerve (optic nerve), lens (len), brain stem (brain stem), pituitary (pituitary gland), spinal cord (cord), temporomandibular joint (temporal lobe), parotid gland (parotid), mandible (mandible), thoracic tumor corresponding lung (lung), esophagus (esophageal), heart (heart), liver (liver), spinal cord (cord), abdominal pelvic tumor corresponding liver (liver), spleen (spleen), kidney (kidney), pancreas (pancreas), small intestine (intestine), colon (colon), bladder (bladder), penis (penis), testis (tegustilus), uterus (uterus), hip joint (hip), femoral head (femoral), and the like. The delineation template in this embodiment may automatically select organs at risk based on the identified or entered target organ, and may only select organs at risk present in the current delineation data. In another embodiment, the delineation model for a target organ includes segmentation information for all organs at risk for the target organ.
In one embodiment, the above steps are preferably performed by a GPU of the medical imaging system, and after performing the above steps, the GPU transmits the medical image data including the organ contour data to another processor, so that the another processor performs the following quality control steps: determining whether the medical image data containing the organ contour data contains organ contour data with an empty result, if so, deleting the organ contour data with an empty result to update the medical image data containing the organ contour data; and determining whether the positions, shapes or volumes of the organs defined by the organ contour data in the medical image data containing the organ contour data are all correct, and if not, outputting corresponding prompt information. Wherein the further processor is preferably a CPU.
Specifically, if the medical image data containing the organ contour data does not contain organ contour data with an empty result, directly determining whether the position, shape and volume of the organ defined by each organ contour data in the medical image data are all correct, and if not, outputting prompt information; if the medical image data containing the organ contour data contains organ contour data with an empty result, deleting the organ contour data with an empty result to update the medical image data containing the organ contour data; and determining whether the position, the shape and the volume of the organ defined by each organ contour data in the updated medical image data are correct or not, and if not, outputting corresponding prompt information.
According to the organ contour generation method and device, the mode that automatic organ contour drawing and manual verification are combined is adopted to generate the medical image data containing the organ contour data, the accuracy of organ contour drawing can be improved, and the accuracy of the organ contour data can be guaranteed.
In this embodiment, the GPU may perform organ contour delineation of the medical image data by using a serial strategy, that is, only one medical image data is subjected to organ contour delineation at any time, or may perform organ contour delineation of the medical image data by using a parallel strategy, that is, organ contour delineation is performed on at least two medical image data simultaneously. The latter is preferred by the embodiment because the utilization efficiency of computing resources can be improved through the parallel strategy, so that the organ contouring efficiency is improved.
In the embodiment, the GPU of the medical imaging system is used to complete organ contour delineation of the medical imaging data, and the CPU of the medical imaging system is used to complete all image processing operations except for organ contour delineation of the medical imaging data, such as preprocessing of the medical imaging data, ranking of the medical imaging data, and the like. Therefore, the medical image system can finish the organ outline delineation of the medical image data through the GPU under the condition of hardly occupying CPU resources, so that the organ outline delineation is hardly influenced by the working state of the CPU, and the timeliness of the organ outline data delineation of the received medical image data can be ensured.
According to the technical scheme of the organ contour delineation method provided by the embodiment of the invention, the medical image data to be delineated currently is obtained, and the organ delineation range in the medical image data is determined; determining a delineation template according to the organ delineation range, wherein the delineation template comprises at least two organ identifications; and calling the delineation model corresponding to the delineation template to carry out contour delineation on of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data. Establishing the relation between the organ delineation range and at least two organs corresponding to the organ delineation range through the delineation template, and being beneficial to improving the efficiency of determining the organ corresponding to each organ delineation range; the corresponding delineation model is called through the delineation template to carry out the delineation of the organ contour, which is beneficial to improving the speed and the flexibility of the organ contour delineation.
Example two
Fig. 2 is a schematic diagram of a medical imaging system according to a second embodiment of the present invention. The system includes a CPU 21, a GPU 22, and a storage device 23; the storage device 23 is used for storing one or more first programs and one or more second programs; when the one or more first programs are executed by the CPU 21, the CPU 21 is caused to acquire medical image data from the corresponding imaging device; when the one or more second programs are executed by GPU 22, GPU 22 is caused to perform the organ delineation method described in the previous embodiment.
The imaging device may be a medical imaging device such as a CT device, an MRI device, an ultrasound device, and an X device.
In this embodiment, when detecting that an idle thread currently exists, the GPU sends an image acquisition request to the CPU, when detecting the image acquisition request, the CPU sends the medical image data currently in the first rank to the GPU according to the image acquisition request, and the GPU receives the medical image data.
After receiving medical image data to be sketched, the GPU determines an organ sketching range in the medical image data. Wherein, the organ delineation range is an image range for organ contour delineation in the medical image data. It is understood that the organ delineation area contains a number of body slices less than or equal to the number of body slices contained in the medical image data.
The method for determining the organ delineation range comprises the following steps: determining the number of body layers of each scanning part contained in the medical image data; and determining the organ delineation range according to the actual size of each scanning part corresponding to the number of the body layers of each scanning part. Or determining the number of the body layers of each scanning part contained in the medical image data based on a pre-trained recognition model, acquiring preset TAG information containing the thickness of the body layer, determining the actual size of each scanning part according to the thickness of the body layer and the number of the body layers of each scanning part, and determining the organ delineation range according to the actual size of each scanning part.
In one embodiment, medical image data of a lung cancer patient is input into a pre-trained recognition model that outputs recognition results in which the ratio of the number of neck slices to the total number of slices of the entire medical image data is 2%, corresponding to a physical size of 10mm, the ratio of the number of upper abdomen slices to the total number of slices of the entire medical image data is 2%, corresponding to a physical size of 10mm, and the ratio of the number of chest slices to the total number of slices of the medical image data is 96%, corresponding to a physical size of 480 mm. Therefore, the target scanning range of the medical image data is the chest, and the neck and the upper abdomen are non-target scanning ranges, namely non-organ delineation ranges, so that the medical image data corresponding to the chest is used as the organ delineation range, and when each organ, such as the outline of the lung, is delineated, only images in the organ delineation range are traversed; or deleting the body layers of the neck and the upper abdomen from the medical image data to update the medical image data, and using the updated medical image data as the organ delineation range. In another embodiment, the number of body slices at each scan site is identified, and the organ delineation range can also be determined by segmentation, registration, or the like, or manually.
The recognition model is preferably constructed based on machine learning, and may be constructed by using an existing machine learning algorithm, which is not specifically limited herein.
In one embodiment, this step is performed by a GPU of the medical imaging system, and the GPU obtains the medical image data to be delineated from the CPU. Specifically, the GPU sends an image acquisition request to the CPU, the CPU sends the medical image data currently in the first rank to the GPU according to the image acquisition request when receiving the image acquisition request, and the GPU receives the medical image data. It is understood that the CPU is further configured to receive medical image data from each imaging device, and perform image preprocessing on the received medical image data to update the corresponding medical image data. The CPU can also acquire the updated contour delineation time limit information and scanning time of each medical image data, and rank the current medical image data according to the updated contour delineation time limit information and scanning time of each medical image data so as to obtain the ranking result of each medical image data. Wherein the contour delineation time limit information can be obtained by reading corresponding TAG information of the medical image data. The timing of organ outline delineation of each medical image data is determined according to the ranking result of the medical image data, emergency tasks can be completed preferentially, and the efficiency and accuracy of resource allocation are improved.
In one embodiment, the contouring time limit information may be specific time information or may be a flag indicating time limit information. Exemplarily, the marking of "1" indicates that the organ contour delineation of the corresponding medical image data has no higher requirement on time limit, and the delineation of the organ contour is completed within three days; the identifier 2 indicates that the organ contour delineation of the corresponding medical image data has high requirement on time limit, and the organ contour delineation needs to be completed within two days; the organ contour delineation indicated by the label "3" of the corresponding medical image data has a very high requirement on time limit, and the delineation of the organ contour needs to be completed within one day.
After determining the organ delineation range in the medical image data, the GPU determines a delineation template according to the organ delineation range, wherein the delineation template comprises corresponding organ identifications.
In one embodiment, each organ delineation range corresponds to one delineation template, each delineation template comprises at least two organ identifications including at least one organ identification for representing a cancerous range and at least one organ identification for representing an organ at risk. Therefore, after the organ delineation range is determined, the delineation template corresponding to the organ delineation range can be determined, and the organ needing to be subjected to contour delineation is determined.
In one embodiment, the delineation template may be determined according to the organ delineation range and at least one of TAG information or additional information entered by a physician, which may be gender information, age information, height and weight information, radiotherapy information, biological information, etc. Further, each organ scanning range containing the organ with the preset gender corresponds to at least two delineation templates, wherein the organ with the preset gender can be a breast, a uterus, a prostate and the like. And when the organ delineation range is determined, preset TAG information containing gender information is also acquired, and the delineation template is determined according to the organ delineation range and the gender information. For example, for any medical image data including the lower abdomen, after the organ delineation range is determined, the preset TAG information including gender information is acquired, if the gender information shows that the patient is female, the organ delineation range corresponds to the delineation template adapted to the female patient, and if the gender information shows that the patient is male, the organ delineation range corresponds to the delineation template adapted to the male patient. The delineation template is determined through the TAG information used for representing the sex of the patient and the organ delineation range, so that the determination process of the delineation template can be simplified, and the accuracy of the determination of the simplified template can be improved.
In one embodiment, each organ delineation range corresponds to one preset delineation template and at least one custom delineation template. The preset delineation template is a general delineation template, and the user-defined delineation template is preferably a delineation template defined by a doctor according to own habits. After the organ delineation range is determined, preset TAG information containing doctor information is obtained, and a delineation template is determined according to the organ delineation range and the doctor information. It can be understood that the sketch template is customized by the doctor corresponding to the doctor information. The setting of the user-defined sketching template can meet various organ sketching requirements of different radiotherapy doctors.
In one embodiment, each organ delineation range corresponds to one preset delineation template and at least one custom delineation template. Illustratively, the preset TAG information includes preset appointment information, and the delineation template is determined according to the organ delineation range and the preset appointment information. The customized sketch template is customized based on preset appointment information. The preset appointment information may be abnormal organ information such as artificial joint information (e.g., artificial hip joint), organ resection information (e.g., pancreas), and the like.
In this embodiment, the organ delineation range, the organ to be delineated, and other information such as TAG information need to be considered, and then the corresponding delineation template is selected, so that the corresponding delineation template can be selected according to the current requirement, and a doctor is better assisted in delineation. One sketching template is selected according to various requirements for sketching, so that the operation steps of doctors are saved, and the sketching efficiency is improved. One delineation template includes delineation of at least one target organ and the organs at risk, thus allowing for simultaneous consideration and delineation, which is faster, simpler and more accurate than using multiple delineation templates to delineate, respectively.
In conclusion, the radiotherapy doctor can formulate the delineation template corresponding to different TAG information for each organ delineation range according to different requirements, so that the flexibility of determining the delineation template can be improved according to the organ delineation range and the preset TAG information, and the flexibility of determining the organ corresponding to the organ delineation range is improved.
After determining the delineation template of the organ delineation range, the GPU calls the delineation model corresponding to the delineation template to carry out contour delineation of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data.
In this embodiment, each delineation template may correspond to only one delineation model, and the delineation model includes delineation algorithms of at least two organs, and may perform associated delineation on of a target organ and an organ at risk in different methods; each delineation template may also correspond to at least two delineation models, with different delineation models corresponding to different organ delineation algorithms, and may also be associated with, but different methods of delineation of the target organ and the organ at risk.
In an embodiment, each organ identifier included in each delineation template corresponds to one delineation model, so that after the delineation template is determined, the delineation models corresponding to at least two organ identifiers included in the delineation template respectively can be called, and then the at least two delineation models are used for performing contour delineation on corresponding organs in an organ delineation range, so as to obtain organ contour data of the medical image data. The GPU may adopt the at least two delineating models to perform contour delineation on the corresponding organ simultaneously within the organ delineating range, or may also adopt one of the at least two delineating models to perform contour delineation on the corresponding organ within the organ delineating range in sequence, and the former is preferred in this embodiment. It can be understood that when each delineation model only comprises a delineation algorithm of an organ, the difficulty of establishing the delineation model and the requirement of the organ delineation on the computing resources of the processor can be reduced.
It should be noted that the delineation model may be an existing organ contour delineation model, and this embodiment is not specifically limited herein.
In one embodiment, the above steps are preferably performed by a GPU of the medical imaging system, and after performing the above steps, the GPU transmits the medical image data including the organ contour data to another processor, so that the another processor performs the following quality control steps: determining whether the medical image data containing the organ contour data contains organ contour data with an empty result, if so, deleting the organ contour data with an empty result to update the medical image data containing the organ contour data; and determining whether the positions, shapes or volumes of the organs defined by the organ contour data in the medical image data containing the organ contour data are all correct, and if not, outputting corresponding prompt information. Wherein the further processor is preferably a CPU.
Specifically, if the medical image data containing the organ contour data does not contain organ contour data with an empty result, directly determining whether the position, shape and volume of the organ defined by each organ contour data in the medical image data are all correct, and if not, outputting prompt information; if the medical image data containing the organ contour data contains organ contour data with an empty result, deleting the organ contour data with an empty result to update the medical image data containing the organ contour data; and determining whether the position, the shape and the volume of the organ defined by each organ contour data in the updated medical image data are correct or not, and if not, outputting corresponding prompt information.
According to the organ contour generation method and device, the mode that automatic organ contour drawing and manual verification are combined is adopted to generate the medical image data containing the organ contour data, the accuracy of organ contour drawing can be improved, and the accuracy of the organ contour data can be guaranteed.
In this embodiment, the GPU may perform organ contour delineation of the medical image data by using a serial strategy, that is, only one medical image data is subjected to organ contour delineation at any time, or may perform organ contour delineation of the medical image data by using a parallel strategy, that is, organ contour delineation is performed on at least two medical image data simultaneously. The latter is preferred by the embodiment because the utilization efficiency of computing resources can be improved through the parallel strategy, so that the organ contouring efficiency is improved.
In the embodiment, the GPU of the medical imaging system is used to complete organ contour delineation of the medical imaging data, and the CPU of the medical imaging system is used to complete all image processing operations except for organ contour delineation of the medical imaging data, such as preprocessing of the medical imaging data, ranking of the medical imaging data, and the like. Therefore, the medical image system can finish the organ outline delineation of the medical image data through the GPU under the condition of hardly occupying CPU resources, so that the organ outline delineation is hardly influenced by the working state of the CPU, and the timeliness of the organ outline data delineation of the received medical image data can be ensured.
According to the technical scheme of the medical imaging system, the relationship between the organ delineation range and at least two organs corresponding to the organ delineation range is established through the delineation template, so that the efficiency of determining the organ corresponding to each organ delineation range is improved; the corresponding delineation model is called through the delineation template to carry out the delineation of the organ contour, which is beneficial to improving the speed and the flexibility of the organ contour delineation; the GPU is adopted to finish organ contour delineation of medical image, the CPU is adopted to finish other image processing operations except medical image data, and through the cooperation of the GPU and the CPU, normal work of a medical image system is guaranteed, timeliness of organ contour delineation of all medical image data is guaranteed, and clinical requirements on organ contour delineation can be well met.
EXAMPLE III
Embodiments of the present invention also provide a storage medium containing computer-executable instructions which, when executed by a computer processor, perform a method of organ contouring, the method comprising:
acquiring medical image data to be sketched currently, and determining an organ sketching range in the medical image data;
determining a delineation template according to the organ delineation range, wherein the delineation template comprises at least two organ identifications;
and calling a delineation model corresponding to the delineation template to carry out contour delineation on of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data.
Of course, the storage medium provided by the embodiments of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the organ contouring method provided by any embodiments of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the organ contouring method according to the embodiments of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An organ contouring method comprising:
acquiring medical image data to be sketched currently, and determining an organ sketching range in the medical image data;
determining a delineation template according to the organ delineation range, wherein the delineation template comprises at least two organ identifications;
and calling a delineation model corresponding to the delineation template to carry out contour delineation on of the corresponding organ in the organ delineation range so as to obtain organ contour data of the medical image data.
2. The method of claim 1, wherein the determining an organ delineation region in the medical image data comprises:
determining the number of body layers of each scanning part contained in the medical image data based on a pre-trained recognition model;
and determining the organ delineation range according to the actual scanning range corresponding to the body layer number of each scanning part.
3. The method of claim 1, wherein prior to determining a delineation template from the organ delineation extent, further comprising:
acquiring preset TAG information or additional information of the medical image data;
correspondingly, the determining a delineation template according to the organ delineation range includes:
and determining a delineation template according to the organ delineation range and the preset TAG information or additional information.
4. The method according to claim 3, wherein the acquiring the preset TAG information of the medical image data comprises:
and if the organ delineation range comprises a preset sex organ, acquiring preset TAG information containing sex information from the medical image data.
5. The method of claim 3,
the preset TAG information or the additional information comprises doctor information, and the delineation template is preset for a doctor corresponding to the doctor information; or
The preset TAG information or the additional information includes preset appointment information for defining an abnormal organ, and the delineation template is customized based on the preset appointment information.
6. The method according to claim 1, wherein after obtaining the organ contour data of the medical image data, further comprising:
sending the medical image data containing the organ contour data to another processor for execution by the other processor of the following steps:
determining whether the medical image data containing the organ contour data contains organ contour data with an empty result, if so, deleting the organ contour data with an empty result to update the medical image data containing the organ contour data;
and determining whether the position, the shape and the volume of the organ defined by each organ contour data in the medical image data containing the organ contour data are correct or not, and if not, outputting corresponding prompt information.
7. A medical imaging system, comprising: a CPU, a GPU and a storage device;
the storage device is used for storing one or more first programs and one or more second programs;
when the one or more first programs are executed by the CPU, the CPU acquires medical image data from corresponding imaging equipment;
when the one or more second programs are executed by the GPU, causing the GPU to perform the organ contouring method of any of claims 1-5.
8. The medical imaging system of claim 7, wherein the GPU is further configured to send medical imaging data including organ contour data to the CPU;
the CPU is further configured to perform the steps of:
determining whether the medical image data containing the organ contour data contains organ contour data with an empty result, if so, deleting the organ contour data with an empty result to update the medical image data containing the organ contour data;
and determining whether the positions, shapes or volumes of the organs defined by the organ contour data in the medical image data containing the organ contour data are all correct, and if not, outputting corresponding prompt information.
9. The medical imaging system of claim 7, wherein the CPU is further configured to:
acquiring contour delineation time limit information and scanning time of each medical image data;
ranking each current medical image data according to the contour delineation time limit information and the scanning time of each medical image data;
when an image acquisition request from the GPU for acquiring medical image data to be sketched is detected, the current first-ranking medical image data is sent to the GPU.
10. A storage medium containing computer-executable instructions for performing the organ contouring method of any one of claims 1-6 when executed by a computer processor.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110817145.0A CN113536575A (en) | 2021-07-20 | 2021-07-20 | Organ contour delineation method, medical imaging system and storage medium |
| PCT/CN2022/106780 WO2023001193A1 (en) | 2021-07-20 | 2022-07-20 | Systems and methods for image segmentation |
| US18/399,618 US20240127438A1 (en) | 2021-07-20 | 2023-12-28 | Systems and methods for image segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110817145.0A CN113536575A (en) | 2021-07-20 | 2021-07-20 | Organ contour delineation method, medical imaging system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113536575A true CN113536575A (en) | 2021-10-22 |
Family
ID=78128879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110817145.0A Pending CN113536575A (en) | 2021-07-20 | 2021-07-20 | Organ contour delineation method, medical imaging system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536575A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023001193A1 (en) * | 2021-07-20 | 2023-01-26 | United Imaging Research Institute of Innovative Medical Equipment | Systems and methods for image segmentation |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040101184A1 (en) * | 2002-11-26 | 2004-05-27 | Radhika Sivaramakrishna | Automatic contouring of tissues in CT images |
| CN106462963A (en) * | 2014-02-27 | 2017-02-22 | 因派克医药***有限公司 | System and method for auto-contouring in adaptive radiotherapy |
| CN106920234A (en) * | 2017-02-27 | 2017-07-04 | 北京连心医疗科技有限公司 | A kind of method of the automatic radiotherapy planning of combined type |
| CN107358053A (en) * | 2017-07-19 | 2017-11-17 | 上海联影医疗科技有限公司 | A kind of image processing method and device |
| CN107392897A (en) * | 2017-07-17 | 2017-11-24 | 上海联影医疗科技有限公司 | Organ contours acquisition methods, image documentation equipment, radiotherapy planning system and storage medium |
| CN107491633A (en) * | 2017-06-30 | 2017-12-19 | 上海联影医疗科技有限公司 | A kind of method and device of image procossing |
| CN109461161A (en) * | 2018-10-22 | 2019-03-12 | 北京连心医疗科技有限公司 | A method of human organ in medical image is split based on neural network |
| CN109615642A (en) * | 2018-11-05 | 2019-04-12 | 北京全域医疗技术有限公司 | Jeopardize the automatic delineation method of organ and device in a kind of radiotherapy planning |
| CN109727235A (en) * | 2018-12-26 | 2019-05-07 | 苏州雷泰医疗科技有限公司 | A kind of automatic delineation algorithms of organ based on deep learning |
| CN109785306A (en) * | 2019-01-09 | 2019-05-21 | 上海联影医疗科技有限公司 | Organ delineation method, device, computer equipment and storage medium |
| CN110739049A (en) * | 2019-10-10 | 2020-01-31 | 上海联影智能医疗科技有限公司 | Image sketching method and device, storage medium and computer equipment |
| CN112116989A (en) * | 2020-09-11 | 2020-12-22 | 海创时代(深圳)医疗科技有限公司 | Multi-organ sketching method and device |
| WO2021115313A1 (en) * | 2019-12-10 | 2021-06-17 | 广州柏视医疗科技有限公司 | System for automatically sketching contour line of normal organ in medical image |
| CN113034528A (en) * | 2021-04-01 | 2021-06-25 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Target area and organ-at-risk delineation contour accuracy testing method based on image omics |
-
2021
- 2021-07-20 CN CN202110817145.0A patent/CN113536575A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040101184A1 (en) * | 2002-11-26 | 2004-05-27 | Radhika Sivaramakrishna | Automatic contouring of tissues in CT images |
| CN106462963A (en) * | 2014-02-27 | 2017-02-22 | 因派克医药***有限公司 | System and method for auto-contouring in adaptive radiotherapy |
| CN106920234A (en) * | 2017-02-27 | 2017-07-04 | 北京连心医疗科技有限公司 | A kind of method of the automatic radiotherapy planning of combined type |
| CN107491633A (en) * | 2017-06-30 | 2017-12-19 | 上海联影医疗科技有限公司 | A kind of method and device of image procossing |
| CN107392897A (en) * | 2017-07-17 | 2017-11-24 | 上海联影医疗科技有限公司 | Organ contours acquisition methods, image documentation equipment, radiotherapy planning system and storage medium |
| CN107358053A (en) * | 2017-07-19 | 2017-11-17 | 上海联影医疗科技有限公司 | A kind of image processing method and device |
| CN109461161A (en) * | 2018-10-22 | 2019-03-12 | 北京连心医疗科技有限公司 | A method of human organ in medical image is split based on neural network |
| CN109615642A (en) * | 2018-11-05 | 2019-04-12 | 北京全域医疗技术有限公司 | Jeopardize the automatic delineation method of organ and device in a kind of radiotherapy planning |
| CN109727235A (en) * | 2018-12-26 | 2019-05-07 | 苏州雷泰医疗科技有限公司 | A kind of automatic delineation algorithms of organ based on deep learning |
| CN109785306A (en) * | 2019-01-09 | 2019-05-21 | 上海联影医疗科技有限公司 | Organ delineation method, device, computer equipment and storage medium |
| CN110739049A (en) * | 2019-10-10 | 2020-01-31 | 上海联影智能医疗科技有限公司 | Image sketching method and device, storage medium and computer equipment |
| WO2021115313A1 (en) * | 2019-12-10 | 2021-06-17 | 广州柏视医疗科技有限公司 | System for automatically sketching contour line of normal organ in medical image |
| CN112116989A (en) * | 2020-09-11 | 2020-12-22 | 海创时代(深圳)医疗科技有限公司 | Multi-organ sketching method and device |
| CN113034528A (en) * | 2021-04-01 | 2021-06-25 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Target area and organ-at-risk delineation contour accuracy testing method based on image omics |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023001193A1 (en) * | 2021-07-20 | 2023-01-26 | United Imaging Research Institute of Innovative Medical Equipment | Systems and methods for image segmentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11455732B2 (en) | Knowledge-based automatic image segmentation | |
| CN109074500B (en) | System and method for segmenting medical images of the same patient | |
| US7817836B2 (en) | Methods for volumetric contouring with expert guidance | |
| CN112001925B (en) | Image segmentation method, radiation therapy system, computer device and storage medium | |
| Reed et al. | Automatic segmentation of whole breast using atlas approach and deformable image registration | |
| CN107392897B (en) | Organ contour acquisition method, imaging apparatus, radiotherapy planning system, and storage medium | |
| US9646229B2 (en) | Method and system for bone segmentation and landmark detection for joint replacement surgery | |
| US9727975B2 (en) | Knowledge-based automatic image segmentation | |
| EP3457356B1 (en) | Method and apparatus for fully automated segmentation of joint using patient-specific optimal thresholding and watershed algorithm | |
| CN109615642A (en) | Jeopardize the automatic delineation method of organ and device in a kind of radiotherapy planning | |
| EP3268931A1 (en) | Method and apparatus for assessing image registration | |
| CN111862021B (en) | Deep learning-based automatic head and neck lymph node and drainage area delineation method | |
| CN110739049A (en) | Image sketching method and device, storage medium and computer equipment | |
| CN110751187A (en) | Training method of abnormal area image generation network and related product | |
| Wittenstein et al. | Automatic image segmentation based on synthetic tissue model for delineating organs at risk in spinal metastasis treatment planning | |
| CN113536575A (en) | Organ contour delineation method, medical imaging system and storage medium | |
| Vaassen et al. | Real-world analysis of manual editing of deep learning contouring in the thorax region | |
| Rigaud et al. | Modeling complex deformations of the sigmoid colon between external beam radiation therapy and brachytherapy images of cervical cancer | |
| Zahel et al. | Rapid assessment of liver volumetry by a novel automated segmentation algorithm | |
| Rong et al. | NRG Oncology Assessment of Artificial Intelligence Deep Learning–Based Auto-segmentation for Radiation Therapy: Current Developments, Clinical Considerations, and Future Directions | |
| WO2023001193A1 (en) | Systems and methods for image segmentation | |
| WO2023057281A1 (en) | A system and method for quality assurance of medical image segmentation | |
| Lüddemann | Interactive graph-based segmentation of the rectosigmoid colon in MRI data for image guided gynecological brachytherapy | |
| Wittenstein et al. | Auf einem Gewebemodell basierende automatische Bildsegmentierung zur Konturierung von Risikoorganen in der Behandlungsplanung für spinale Metastasierung | |
| GB2611602A (en) | A System and Method for quality assurance of medical image segmentation |
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 |