CN113421634A - Aorta labeling method, system and computer readable storage medium - Google Patents
Aorta labeling method, system and computer readable storage medium Download PDFInfo
- Publication number
- CN113421634A CN113421634A CN202010139894.8A CN202010139894A CN113421634A CN 113421634 A CN113421634 A CN 113421634A CN 202010139894 A CN202010139894 A CN 202010139894A CN 113421634 A CN113421634 A CN 113421634A
- Authority
- CN
- China
- Prior art keywords
- artery
- labeling
- aorta
- image sequence
- target image
- 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
- 238000002372 labelling Methods 0.000 title claims abstract description 237
- 210000000709 aorta Anatomy 0.000 title claims abstract description 138
- 210000001367 artery Anatomy 0.000 claims abstract description 113
- 210000003090 iliac artery Anatomy 0.000 claims abstract description 76
- 210000002376 aorta thoracic Anatomy 0.000 claims abstract description 65
- 210000000702 aorta abdominal Anatomy 0.000 claims abstract description 57
- 210000001105 femoral artery Anatomy 0.000 claims abstract description 39
- 230000001174 ascending effect Effects 0.000 claims abstract description 15
- 230000004087 circulation Effects 0.000 claims abstract description 12
- 230000008859 change Effects 0.000 claims abstract description 9
- 210000002465 tibial artery Anatomy 0.000 claims description 42
- 210000001168 carotid artery common Anatomy 0.000 claims description 35
- 210000003270 subclavian artery Anatomy 0.000 claims description 35
- 210000001363 mesenteric artery superior Anatomy 0.000 claims description 34
- 238000000034 method Methods 0.000 claims description 33
- 210000002254 renal artery Anatomy 0.000 claims description 28
- 210000001715 carotid artery Anatomy 0.000 claims description 16
- 230000003187 abdominal effect Effects 0.000 claims description 14
- 210000003137 popliteal artery Anatomy 0.000 claims description 12
- 210000002168 brachiocephalic trunk Anatomy 0.000 claims description 11
- 210000000245 forearm Anatomy 0.000 claims description 9
- 230000002496 gastric effect Effects 0.000 claims description 6
- 210000000496 pancreas Anatomy 0.000 claims description 6
- 210000000952 spleen Anatomy 0.000 claims description 6
- 210000003109 clavicle Anatomy 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 210000000115 thoracic cavity Anatomy 0.000 claims description 2
- 244000309466 calf Species 0.000 claims 1
- 238000002059 diagnostic imaging Methods 0.000 abstract description 3
- 238000010968 computed tomography angiography Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 210000002414 leg Anatomy 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 208000024172 Cardiovascular disease Diseases 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 3
- 239000002872 contrast media Substances 0.000 description 3
- 230000002526 effect on cardiovascular system Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 210000001699 lower leg Anatomy 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 210000003484 anatomy Anatomy 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000002767 hepatic artery Anatomy 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 210000004373 mandible Anatomy 0.000 description 2
- 210000001370 mediastinum Anatomy 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 210000000689 upper leg Anatomy 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 208000018262 Peripheral vascular disease Diseases 0.000 description 1
- 210000000683 abdominal cavity Anatomy 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 208000015114 central nervous system disease Diseases 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004195 computer-aided diagnosis Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011038 discontinuous diafiltration by volume reduction Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000004392 genitalia Anatomy 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000005240 left ventricle Anatomy 0.000 description 1
- 210000003141 lower extremity Anatomy 0.000 description 1
- 210000003975 mesenteric artery Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 210000001698 popliteal fossa Anatomy 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000001839 systemic circulation Effects 0.000 description 1
- 210000004291 uterus Anatomy 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides an aorta labeling method, an aorta labeling system and a computer readable storage medium, when the aorta labeling is carried out, the most obvious and thickest thoracic and abdominal aorta is preferentially labeled by considering the body circulation direction and/or the thickness change direction of the aorta, then the iliac artery and the femoral artery are labeled by descending of the abdominal aorta, and the neck artery is labeled by ascending of the thoracic aorta, based on the standardized artery labeling flow, the complete aorta can be rapidly labeled, the labeling accuracy is high, and the requirement on the medical imaging knowledge background of a labeling person is low.
Description
Technical Field
The present invention relates to the field of medical technology, and in particular, to a method and system for aorta annotation and a computer-readable storage medium.
Background
CT angiography scanning has the characteristics of thin layer thickness, large range and fast scanning, and is widely applied to clinical diagnosis, preoperative planning and academic research of tumors, central nervous system diseases, cardiovascular diseases and peripheral vascular diseases, however, the problems of large patient data volume, high doctor workload, long labeling time consumption and the like are generated, and the problems become research difficulties and pain points of the medical image auxiliary diagnosis technology at the present stage. In general, researchers have devised a new medical image-assisted diagnosis technique or method that requires training or evaluation using data that accurately labels the targeted organ. Therefore, accurate labeling of the target organ becomes a gold standard for many important evaluation indexes, such as Precision, Recall, F-score (a combination operation of Precision and Recall, which represents a commonly used classification evaluation index), Dice coefficient, IoU standard (interaction over Union), and the like.
However, due to the rapid development of modern large-scale medical instruments, such as CT, CTA (CT angiography) data of a patient has the characteristics of thin layer thickness and wide range, such as a layer thickness of 0.5mm, which can be continuous from the neck to the lower leg, and the data volume of only one patient can be as high as 1000-2000 dicom (digital Imaging and Communications in medicine) images.
Disclosure of Invention
The invention aims to provide an aorta labeling method, an aorta labeling system and a computer-readable storage medium, so as to standardize an aorta labeling process and improve the speed and accuracy of aorta labeling.
In order to solve the above technical problem, the present invention provides an aorta labeling method, including:
acquiring a target image sequence to be subjected to aorta annotation;
marking the thoracic aorta and the abdominal aorta from the target image sequence according to the body circulation direction and/or the artery thickness change direction;
labeling iliac and femoral arteries from the target image sequence descending the abdominal aorta;
the carotid artery is marked from the target image sequence by ascending the thoracic aorta.
Optionally, in the aorta labeling method, labeling the thoracic aorta includes labeling an ascending aorta, an aortic arch, and a descending aorta;
wherein a cut-off outlet of the starting end of the ascending aorta is set at the ascending aortic bulb.
Optionally, in the aorta labeling method, labeling the thoracic aorta includes sequentially labeling the ascending aorta, the aortic arch, and the descending aorta.
Optionally, in the aorta labeling method, labeling the abdominal aorta includes labeling an abdominal aorta, a celiac trunk, an superior mesenteric artery, and a renal artery;
wherein, the cut-off outlet of the starting end of the abdominal trunk is set in the thick short artery trunk from the front arm of the abdominal aorta, and the cut-off outlet of the ending end is set in front of the inlets of the total artery trunk, the left gastric artery and the spleen artery;
a cut-off outlet of the starting end of the superior mesenteric artery is arranged at the forearm below the starting point of the abdominal trunk, and a cut-off outlet of the ending end of the superior mesenteric artery is arranged at the bifurcation of the superior mesenteric artery behind the pancreas;
the renal artery is approximately at the same level as the superior mesenteric artery, and a cut-off outlet at the end of the renal artery is set before the renal artery has a bifurcated artery vessel.
Optionally, in the aorta labeling method, labeling the abdominal aorta includes sequentially labeling the abdominal aorta, the celiac trunk, the superior mesenteric artery, and the renal artery.
Optionally, in the aorta labeling method, labeling the iliac artery includes labeling a common iliac artery, an internal iliac artery and an external iliac artery;
wherein a cut-off outlet of the ending end of the internal iliac artery is set immediately before the horizontal end of the sacrum, the superior gluteal artery and the bifurcation end of each internal iliac artery.
Optionally, in the aorta labeling method, labeling the iliac artery includes sequentially labeling the common iliac artery, the internal iliac artery, and the external iliac artery.
Optionally, in the aorta labeling method, labeling the femoral artery includes labeling a femoral artery, a popliteal artery, an anterior tibial artery and a posterior tibial artery;
wherein a cut-off outlet of the ending end of the anterior tibial artery is set in front of a foot artery or at the tail end of the target image sequence;
the cut-off outlet of the ending end of the posterior tibial artery is set in front of the traffic branch or bifurcation branch of the posterior tibial artery.
Optionally, in the aorta labeling method, labeling the femoral artery includes sequentially labeling the femoral artery, the popliteal artery, the anterior tibial artery, and the posterior tibial artery.
Optionally, in the aorta labeling method, labeling the carotid artery includes labeling a left subclavian artery, a left common carotid artery, a brachiocephalic trunk, a right common carotid artery, and a right subclavian artery;
wherein, the cut-off outlets of the ending ends of the left common carotid artery and the right common carotid artery are set at the horizontal end of the lower jaw teeth of the human body or the starting end of the target image sequence;
the cut-off outlets of the ending ends of the left subclavian artery and the right subclavian artery are respectively arranged at the inner sides of the left and right clavicles.
Optionally, in the aorta labeling method, labeling the carotid artery includes sequentially labeling the left subclavian artery, the left common carotid artery, the brachiocephalic trunk, the right common carotid artery, and the right subclavian artery.
Optionally, in the aorta annotation method, the step of obtaining a target image sequence to be subjected to aorta annotation includes:
an intermediate image sequence within a predetermined range is obtained from a DICOM image sequence obtained through a CTA scanning as the target image sequence.
Optionally, in the aorta labeling method, the predetermined range is from a human neck artery to a position in front of a leg foot artery.
Optionally, in the aorta labeling method, the method further includes:
if the layer thickness of the intermediate image sequence is lower than a predetermined layer thickness, the layer thickness of the intermediate image sequence is transformed into the predetermined layer thickness, and the transformed intermediate image sequence is taken as the target image sequence.
Optionally, in the aorta labeling method, the method further includes:
if the window width window level of the intermediate image sequence does not meet the preset window width window level, the window width window levels of the intermediate image sequence are uniformly adjusted to the preset window width window level, and the adjusted intermediate image sequence is used as the target image sequence.
Based on the same inventive concept, the invention also provides an aorta labeling system, comprising:
the image sequence acquisition module is used for acquiring a target image sequence to be subjected to aorta labeling;
the thoracic and abdominal artery labeling module is used for labeling a thoracic aorta and an abdominal aorta from the target image sequence according to the body circulation direction and/or the thickness change direction of the arteries;
the iliac-femoral artery labeling module is used for descending from the abdominal aorta and labeling iliac arteries and femoral arteries from the target image sequence;
and the neck artery labeling module is used for ascending from the thoracic aorta and labeling the neck artery from the target image sequence.
Optionally, in the aorta labeling system, the thoracic-abdominal aorta labeling module is configured to label an ascending aorta, an aortic arch and a descending aorta to mark the thoracic aorta;
wherein a cut-off outlet of the starting end of the ascending aorta is set at the ascending aortic bulb.
Optionally, in the aorta labeling system, the thoracic-abdominal aorta labeling module is configured to label the ascending aorta, the aortic arch, and the descending aorta in sequence to mark the thoracic aorta.
Optionally, in the aorta labeling system, the thoracic and abdominal aorta labeling module is configured to label an abdominal aorta, a trunk of the abdominal cavity, an superior mesenteric artery and a renal artery to mark the abdominal aorta;
wherein, the cut-off outlet of the starting end of the abdominal trunk is set in the thick short artery trunk from the front arm of the abdominal aorta, and the cut-off outlet of the ending end is set in front of the inlets of the total artery trunk, the left gastric artery and the spleen artery;
a cut-off outlet of the starting end of the superior mesenteric artery is arranged at the forearm below the starting point of the abdominal trunk, and a cut-off outlet of the ending end of the superior mesenteric artery is arranged at the bifurcation of the superior mesenteric artery behind the pancreas;
the renal artery is approximately at the same level as the superior mesenteric artery, and a cut-off outlet at the end of the renal artery is set before the renal artery has a bifurcated artery vessel.
Optionally, in the aorta labeling system, the thoracic-abdominal aorta labeling module is configured to label the abdominal aorta, the celiac trunk, the superior mesenteric artery, and the renal artery in sequence to mark the abdominal aorta.
Optionally, in the aorta labeling system, the iliofemoral artery labeling module is used for labeling the common iliac artery, the internal iliac artery and the external iliac artery so as to label the iliac artery;
wherein a cut-off outlet of the ending end of the internal iliac artery is set immediately before the horizontal end of the sacrum, the superior gluteal artery and the bifurcation end of each internal iliac artery.
Optionally, in the aorta labeling system, the iliac-femoral artery labeling module is configured to label the common iliac artery, the internal iliac artery and the external iliac artery in sequence to label the iliac artery.
Optionally, in the aorta labeling system, the iliac-femoral artery labeling module is configured to label a femoral artery, a popliteal artery, an anterior tibial artery and a posterior tibial artery to label the femoral artery;
wherein a cut-off outlet of the ending end of the anterior tibial artery is set in front of a foot artery or at the tail end of the target image sequence;
the cut-off outlet of the ending end of the posterior tibial artery is set in front of the traffic branch or bifurcation branch of the posterior tibial artery.
Optionally, in the aorta labeling system, the iliac femoral artery labeling module is used for sequentially labeling the femoral artery, the popliteal artery, the anterior tibial artery and the posterior tibial artery to mark out the femoral artery.
Optionally, in the aorta labeling system, the carotid artery labeling module is configured to label a left subclavian artery, a left common carotid artery, a brachiocephalic trunk, a right common carotid artery, and a right subclavian artery to label the carotid artery;
the cut-off outlets of the ending ends of the left common carotid artery and the right common carotid artery are set at the horizontal end of the mandible teeth of the human body or the starting end of the target image sequence, and the cut-off outlets of the ending ends of the left subclavian artery and the right subclavian artery are respectively set at the inner sides of the left and right clavicles.
Optionally, in the aorta labeling system, the carotid artery labeling module is configured to sequentially label the left subclavian artery, the left common carotid artery, the brachiocephalic trunk, the right common carotid artery, and the right subclavian artery, so as to label the carotid artery.
Optionally, in the aorta annotation system, the image sequence acquisition module acquires a target image sequence to be subjected to aorta annotation, specifically:
an intermediate image sequence within a predetermined range is obtained from a DICOM image sequence obtained through a CTA scanning as the target image sequence.
Optionally, in the aorta labeling system, the predetermined range is from a human neck artery to a position in front of a leg foot artery.
Optionally, in the aorta annotation system, the image sequence acquisition module is further configured to:
if the layer thickness of the intermediate image sequence is lower than a predetermined layer thickness, the layer thickness of the intermediate image sequence is transformed into the predetermined layer thickness, and the transformed intermediate image sequence is taken as the target image sequence.
Optionally, in the aorta annotation system, the image sequence acquisition module is further configured to:
if the window width window level of the intermediate image sequence does not meet the preset window width window level, the window width window levels of the intermediate image sequence are uniformly adjusted to the preset window width window level, and the adjusted intermediate image sequence is used as the target image sequence.
Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements any of the aorta annotation methods described above.
According to the aorta labeling method, the aorta labeling system and the computer readable storage medium provided by the invention, for a target image sequence to be subjected to aorta labeling, firstly, according to the body circulation direction and/or the artery thickness change direction, a thoracic aorta and an abdominal aorta are labeled from the target image sequence, then, the abdominal aorta descends, an iliac artery and a femoral artery are labeled from the target image sequence, the thoracic aorta ascends, and a neck artery is labeled from the target image sequence. Therefore, when the aorta labeling is carried out, the most obvious and thickest thoraco-abdominal aorta is preferentially labeled by considering the body circulation direction and/or the thickness degree of the aorta, then the iliac artery and the femoral artery are labeled by descending of the abdominal aorta, and the neck artery is labeled by ascending of the thoracic aorta.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of an aorta annotation method according to an embodiment of the present invention;
FIG. 2a is a schematic illustration of the labeling results of the thoracic aorta;
FIG. 2b is a schematic illustration of the labeling results for the abdominal aorta;
FIG. 2c is a schematic illustration of the labeling results for the iliac artery;
FIG. 2d is a schematic illustration of the labeling result of the femoral artery;
FIG. 2e is a schematic illustration of the labeling result of the carotid artery;
FIG. 3a is an elevation view of the entire arterial annotation result;
FIG. 3b is a side view of the entire arterial annotation result;
fig. 4 is a schematic structural diagram of an aorta annotation system according to an embodiment of the invention.
The reference numerals in fig. 2 a-2 e are as follows:
11-ascending aorta; 12-aortic arch; 13-descending aorta;
21-abdominal aorta; 22-abdominal trunk; 23-superior mesenteric artery; 24-left and right renal arteries;
31-common iliac artery; 32-internal iliac artery; 33-external iliac artery;
41-femoral, popliteal artery; 42-anterior tibial artery; 43-posterior tibial artery;
51-left subclavian artery; 52-left common carotid artery; 53-brachiocephalic trunk (right common carotid artery, right subclavian artery).
Detailed Description
The aorta labeling method, the aorta labeling system and the computer-readable storage medium according to the present invention will be described in further detail with reference to the accompanying drawings and embodiments. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are all used in a non-precise scale for the purpose of facilitating and distinctly aiding in the description of the embodiments of the present invention. To make the objects, features and advantages of the present invention comprehensible, reference is made to the accompanying drawings. It should be understood that the structures, ratios, sizes, and the like shown in the drawings and described in the specification are only used for matching with the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the implementation conditions of the present invention, so that the present invention has no technical significance, and any structural modification, ratio relationship change or size adjustment should still fall within the scope of the present invention without affecting the efficacy and the achievable purpose of the present invention.
The core idea of the invention is to provide a method, a system and a computer readable storage medium for aorta labeling, which can improve the speed and accuracy of aorta labeling and reduce the requirements on the medical imaging knowledge background of the labeling personnel through specialized labeling standards. The method optimizes the detailed flow in the aorta labeling process to obtain the normalized aorta labeling flow, and can shorten the labeling time as much as possible by means of advanced and convenient labeling tools, thereby achieving the aims of greatly shortening the aorta labeling time and accelerating the labeling efficiency. In addition, the aorta golden standard marked by the marking specification and the optimization process is not only suitable for traditional machine learning training and evaluation, but also can be applied to large data volume marking required by deep learning training.
Referring to fig. 1, fig. 1 schematically shows a flow chart of an aorta labeling method according to an embodiment of the present invention, as shown in fig. 1, the aorta labeling method includes the following steps:
and S101, acquiring a target image sequence to be subjected to aorta annotation.
In this step, the target image sequence may be a DICOM image sequence obtained after CTA scanning of the patient, or may be another type of image sequence, which is not limited in the present invention.
In this embodiment, the acquiring of the target image sequence to be subjected to aorta labeling may specifically be: an intermediate image sequence within a predetermined range is obtained from a DICOM image sequence obtained through a CTA scanning as the target image sequence. The preset range can be set according to actual conditions, and preferably, the preset range is from the neck artery to the front of the leg foot artery of the human body.
It can be understood that in the CTA scanning, the DICOM image sequence of each patient covers a wide range of human bodies with large differences, and the imaging range is different from the neck of the human body to the root of the lower leg. In this embodiment, the labeling range is set from the beginning of the neck artery to the ending of the proximal crus artery, and the purpose is that the labeling of the artery vessels of the human body including the vessels below three levels covered in the range is the focus of attention of doctors in clinical application such as cardiovascular disease preoperative planning, interventional operation and postoperative healing, and can also satisfy the application of computer-aided diagnosis technology, such as machine learning, deep convolutional neural network, and the like.
Further, before the intermediate image sequence is taken as the target image sequence, it may be determined whether a layer thickness of the intermediate image sequence is lower than a predetermined layer thickness, and if so, the layer thickness of the intermediate image sequence is converted into the predetermined layer thickness, and the converted intermediate image sequence is taken as the target image sequence. In particular, the DICOM image sequence of the low layer thickness can be transformed to the high layer thickness by using an interpolation algorithm in a unified manner. It will be appreciated that in a CTA scan, the low slice thickness is usually chosen for scanning in order to keep the artery condition of the patient as far as possible, and therefore the number of DICOM image sequences per patient is enormous. In the embodiment, the image sequence with the low layer thickness is interpolated to obtain the image sequence with the high layer thickness, so that the cardiovascular labeling process can be accelerated and unified on the premise of not reducing the accuracy, and the number of the images to be labeled is greatly reduced. For example, the layer thickness of the intermediate image sequence is 0.5mm, which may include up to 1000-2000 images, and the predetermined layer thickness is 1mm, after the intermediate image sequence is transformed into the predetermined layer thickness, the number of images included in the transformed intermediate image sequence may be reduced by half to 500-1000 images, so as to greatly reduce the number of images to be labeled.
Wherein the predetermined layer thicknesses include, but are not limited to, 1mm layer thicknesses, and interpolation algorithms to transform low layer thicknesses to high layer thicknesses include, but are not limited to, nearest neighbor, linear, cubic spline interpolation, and the like. In this embodiment, the image sequence is converted from the low layer thickness to the high layer thickness, and the interpolation operation is applied to complete image volume reduction, so that the overall labeling quantity can be reduced, and the labeling efficiency can be improved.
Further, before the intermediate image sequence is used as the target image sequence, it may be determined whether a window width level of the intermediate image sequence satisfies a predetermined window width level, and if not, the window width levels of the intermediate image sequence are uniformly adjusted to the predetermined window width level, and the adjusted intermediate image sequence is used as the target image sequence. This is because the range of CT values in the CT image scanned by CTA [ -1024HU, 1024HU ], adjusting to the predetermined window width window level can enhance the contrast of the contrast agent and other tissues and organs, so as to better observe the variation difference between the contrast agent in the artery and the surrounding tissues, thereby facilitating the labeling of the artery vessels. The DICOM image sequence is uniformly adjusted to a predetermined window width level, for example, the predetermined window width level may set the window width levels of longitudinally spaced windows in the medical image to 700HU and 50HU, respectively. Wherein the predetermined window width window level includes, but is not limited to, a mediastinum window width 700HU, and a window level 50 HU. The window width refers to the range of CT values included in the CT image, the window level refers to the average value of the upper and lower limits of the window width, for example, the window width of the mediastinum window is 700HU, the window level is 50HU, the lower limit of the display range of the CT value representing the current CT image is-300 HU, and the upper limit is 400 HU.
And S102, marking the thoracic aorta and the abdominal aorta from the target image sequence according to the body circulation direction and/or the thickness change direction of the artery.
And S103, descending from the abdominal aorta, and marking an iliac artery and a femoral artery from the target image sequence.
And S104, ascending the thoracic aorta, and marking a neck artery from the target image sequence.
In steps S102 to S104, the artery labeling may be performed by using ITK-SNAP medical image processing software, and in the cross-sectional direction, the aorta in the contrast agent highlight region may be automatically filled by a three-dimensional adaptive algorithm in a brush mode, so as to accelerate the artery labeling. The brush mode refers to a brush marking tool provided by ITK-SNAP software, and the selectable parameters of the brush comprise brush size, 2D/3D mode and homogeneity. The three-dimensional adaptive algorithm refers to an adaptive segmentation algorithm provided by ITK-SNAP software in a 3D mode, and the selectable parameters of the algorithm comprise granularity and smoothness. In the embodiment, the rapid labeling operation of a small range and multiple images can be realized by adopting the ITK-SNAP auxiliary labeling tool, so that the overall labeling efficiency is improved. In other embodiments, other auxiliary labeling tools may be used to label the artery, and the invention is not limited thereto.
The labeling methods of the thoracic aorta, abdominal aorta, iliac arteries, femoral arteries, and cervical arteries are described below.
First, the most prominent, thickest thoracic aorta and abdominal aorta can be preferentially labeled, taking into account the direction of the systemic circulation and/or the direction of the change in thickness of the arteries.
The aorta is the largest artery in the human body and is the region with the highest incidence of cardiovascular disease. The thoracic aorta comprises an ascending aorta, an aortic arch and a descending aorta, wherein the ascending aorta is arranged in the left ventricle, ascends first, then bends leftwards and then downwards to form the aortic arch, and then descends to form the descending aorta. Accordingly, labeling the thoracic aorta includes labeling the ascending aorta, the aortic arch, and the descending aorta. Wherein a cut-off outlet of the starting end of the ascending aorta is set at the ascending aortic bulb.
In an embodiment, the target image sequence may be sequentially labeled according to the body circulation direction according to the ascending aorta, the aortic arch and the descending aorta, and the labeling result of the thoracic aorta is obtained as shown in fig. 2a, and for inexperienced labeling personnel or non-medical practitioners, the labeling is performed according to the labeling sequence shown in fig. 2a, so that the effect of rapidly and accurately labeling the thoracic aorta can be achieved.
The descending aorta continues downwards to pass through the septum to reach the abdominal aorta, and then the abdominal aorta sequentially passes through the celiac trunk of the forearm of the abdominal aorta, the superior mesenteric artery and the left and right renal arteries horizontally and outwards, so that the abdominal aorta is marked by including the abdominal aorta, the celiac trunk, the superior mesenteric artery and the renal arteries. Wherein, a cut-off outlet of the starting end of the abdominal trunk is set in the thick short artery trunk from the front arm of the abdominal aorta, and a cut-off outlet of the ending end is set in front of inlets of the total hepatic artery, the left gastric artery and the spleen artery; a cut-off outlet at the starting end of the superior mesenteric artery is arranged on the forearm below the starting point of the abdominal trunk, and a cut-off outlet at the ending end of the superior mesenteric artery is arranged on the bifurcation of the superior mesenteric artery behind the pancreas; the left and right renal arteries are almost at the same level as the superior mesenteric artery, and the cut-off outlet at the end is set before the renal arteries branch off into arterial vessels.
In an embodiment, the abdominal aorta, the celiac trunk, the superior mesenteric artery and the renal artery may be sequentially labeled in the target image sequence, and the labeling result of the abdominal aorta is shown in fig. 2b, and similarly, for inexperienced labeling personnel or non-medical practitioners, labeling according to the labeling sequence shown in fig. 2b may achieve the effect of rapidly and accurately labeling the abdominal aorta.
The above completes the labeling of the thoracic aorta and abdominal aorta. After the aorta labeling is completed, the distal end of the abdominal aorta is bifurcated into the left and right common iliac arteries, and the descending common iliac artery is bifurcated into the external iliac artery and the internal iliac artery. Since the internal iliac arteries are short-stem and distributed in the bladder, uterus and the internal side of the external genitalia, thigh, while the external iliac arteries migrate as the main artery of the lower extremities, femoral arteries, the labeling of the internal iliac arteries includes labeling of the common iliac arteries, internal iliac arteries and external iliac arteries. Wherein a cut-off outlet of the ending end of the internal iliac artery is set immediately before the horizontal end of the sacrum, the superior gluteal artery and the bifurcation end of each internal iliac artery.
In an embodiment, the common iliac artery, the internal iliac artery and the external iliac artery can be labeled in sequence from the target image sequence, and the labeling result of the iliac artery is shown in fig. 2c, and similarly, for inexperienced labeling personnel or non-medical practitioners, labeling is performed according to the labeling sequence shown in fig. 2c, so that the function of rapidly and accurately labeling the iliac artery can be achieved.
The external iliac artery runs downward to the femoral artery, also called superficial femoral artery, runs through the medial aspect of the thigh, runs to the popliteal fossa to move to the popliteal artery, and continues to vertically descend to branch into the anterior tibial artery and the posterior tibial artery. Thus, labeling the femoral artery includes labeling the femoral artery, the popliteal artery, the anterior tibial artery, and the posterior tibial artery, wherein the cut-off outlet of the terminating end of the anterior tibial artery is set anterior to the foot artery or the end of the target image sequence (i.e., the CTA data provided) and the cut-off outlet of the terminating end of the posterior tibial artery is set anterior to the traffic branch or bifurcation branch of the posterior tibial artery.
In an embodiment, labeling may be performed in the target image sequence from a main trunk to a branch, and sequentially from top to bottom according to the order of the femoral artery, the popliteal artery, the anterior tibial artery, and the posterior tibial artery, and the labeling result of the femoral artery is obtained as shown in fig. 2d, and similarly, labeling may be performed for an inexperienced labeling person or a non-medical practitioner according to the labeling order shown in fig. 2d, so as to achieve the effect of rapidly and accurately labeling the femoral artery.
And finishing the descending labeling of the artery of the human anatomical structure. The up-going labeling of the arteries of the human anatomy will be performed below. Observing the superior thoracic aorta behavioral cervical artery of fig. 2a from a human coronary angle, the ascending aorta in the thoracic aorta is respectively left subclavian artery, left common carotid artery and brachiocephalic trunk, and the brachiocephalic trunk comprises right common carotid artery and right subclavian artery, so labeling the cervical artery comprises labeling left subclavian artery, left common carotid artery, brachiocephalic trunk, right common carotid artery and right subclavian artery, wherein the cut-off outlets of the ending ends of the left common carotid artery and the right common carotid artery are set at the level end of the teeth of the lower jaw of the human body or the starting end of the target image sequence (i.e., the provided CTA data), and the cut-off outlets of the ending ends of the left subclavian artery and the right subclavian artery are set inside the left and right subclavian bones, respectively.
In an embodiment, a left subclavian artery may be labeled first, then a left common carotid artery may be labeled, and finally a head-arm trunk may be labeled, the head-arm trunk branches upward to form a right common carotid artery and a right subclavian artery, and labeling may be performed sequentially from the target image sequence according to the sequence, so as to obtain a labeling result of the neck artery as shown in fig. 2e, and similarly, for an inexperienced labeling person or a non-medical practitioner, labeling may be performed according to the labeling sequence shown in fig. 2e, so that an effect of rapidly and accurately labeling the neck artery may be achieved.
So far, the labeling of the cardiovascular artery concerned by the doctor in the cardiovascular interventional operation is completed. The whole artery labeling result is shown in fig. 3a and 3b, wherein fig. 3a is a front view of the artery, and fig. 3b is a side view of the artery. The cut-off outlets of the global artery labels shown in fig. 3a and 3b include the following 9 positions:
1) the cut-off outlet of the starting end of the ascending aorta is arranged at the ascending aortic bulb part;
2) the starting end of the celiac trunk is set at the thick short arterial trunk from the abdominal aorta forearm, and the ending end is set in front of the entrance of the total hepatic artery, the left gastric artery and the spleen artery;
3) the starting end of the superior mesenteric artery is arranged at the lower forearm of the starting point of the abdominal trunk, and the ending end is arranged at the superior mesenteric artery bifurcation behind the pancreas;
4) the left and right renal arteries are almost at the same level with the superior mesenteric artery, and a cut-off outlet at the end is set before the renal artery has a bifurcated artery;
5) a cut-off outlet at the end of the internal iliac artery is arranged at the horizontal end close to the sacrum, the superior gluteal artery and the front of the bifurcation end of each internal iliac artery;
6) the cut-off outlet of the end of the anterior tibial artery is set at the end of the CTA data provided in front of or at the foot artery;
7) a cut-off outlet at the end of the posterior tibial artery is set in front of a traffic branch or a bifurcation branch of the posterior tibial artery;
8) the cut-off outlets of the end ends of the left and right common carotid arteries are set at the horizontal end of the mandible teeth of the human body or the start end of the supplied CTA data;
9) the stop outlets at the ending ends of the left and right subclavian arteries are arranged at the inner sides of the left and right clavicles.
The cut-off exit of the above 9 artery labeling includes the artery labeling range of the important attention of the doctor, and the cut-off exit is set, so that the following advantages are provided: 1. the cut-off outlets stop at 1-3 levels of thick arterial vascular orifices, so that the attention of a doctor to the arterial range is emphasized, and whether blockage and pathological changes exist or not is observed; 2. redundant artery extension areas are prevented from being excessively marked by a marking person, workload is reduced, and artery marking efficiency is accelerated; 3. the method is beneficial to distinguishing whether the results of other artery researches exist or not or are partially identified by using the labeling process and the labeling data of the invention, because the results of related researches made by using the data labeled by the process of the invention are shown near the cut-off outlet and show the position approximation of the cut-off outlet.
It should be noted that horizontal lines and vertical lines in fig. 3a and 3b are spatial reference lines when software 3D displays, the vertical lines represent a Z axis in a vertical direction (also shown in fig. 2a to 2 e), one of the horizontal lines represents an X axis in a horizontal direction, and the other represents a Y axis in a horizontal direction (which is a direction from the outside of the screen to the inside of the image), and these three lines can determine the entire spatial direction. In fig. 3a, two transverse lines (i.e., x-axis and Y-axis) are shown, which overlap and are indistinguishable, while in fig. 3b, two nearly overlapping transverse lines are visible in the horizontal direction.
In summary, when the aorta labeling is performed, the aorta labeling method provided by the embodiment of the invention firstly considers the body circulation direction and/or the artery thickness variation direction to preferentially label the most obvious and thickest thoracic and abdominal aorta, then labels the iliac artery and the femoral artery from the abdominal aorta in a descending manner, and labels the neck artery from the thoracic aorta in an ascending manner, based on the normalized artery labeling process, the complete aorta can be rapidly labeled, the labeling accuracy is high, and the requirement on the medical imaging knowledge background of the labeling personnel is low.
Based on similar inventive concepts, the present invention further provides an aorta labeling system, which can realize automatic labeling of an aorta, please refer to fig. 4, fig. 4 schematically shows a flow diagram of the aorta labeling system according to an embodiment of the present invention, as shown in fig. 4, the aorta labeling system includes: an image sequence acquisition module 201, a thoraco-abdominal artery labeling module 202, an iliofemoral artery labeling module 203, and a neck artery labeling module 204, wherein,
the image sequence acquiring module 201 is configured to acquire a target image sequence to be subjected to aorta labeling;
the thoracic and abdominal aorta labeling module 202 is configured to label a thoracic aorta and an abdominal aorta from the target image sequence according to a body circulation direction and/or an artery thickness variation direction;
the iliac-femoral artery labeling module 203 is used for descending from the abdominal aorta and labeling iliac arteries and femoral arteries from the target image sequence;
the neck artery labeling module 204 is configured to ascend from the thoracic aorta and label a neck artery from the target image sequence.
Optionally, in the aorta labeling system, the thoracic-abdominal aorta labeling module 202 is configured to label the ascending aorta, the aortic arch and the descending aorta to mark the thoracic aorta;
wherein a cut-off outlet of the starting end of the ascending aorta is set at the ascending aortic bulb.
Optionally, in the aorta labeling system, the thoracic-abdominal aorta labeling module 202 is configured to label the ascending aorta, the aortic arch and the descending aorta in sequence to mark out the thoracic aorta.
Optionally, in the aorta labeling system, the thoracic-abdominal aorta labeling module 202 is configured to label an abdominal aorta, a celiac trunk, an superior mesenteric artery and a renal artery to mark the abdominal aorta;
wherein, the cut-off outlet of the starting end of the abdominal trunk is set in the thick short artery trunk from the front arm of the abdominal aorta, and the cut-off outlet of the ending end is set in front of the inlets of the total artery trunk, the left gastric artery and the spleen artery;
a cut-off outlet of the starting end of the superior mesenteric artery is arranged at the forearm below the starting point of the abdominal trunk, and a cut-off outlet of the ending end of the superior mesenteric artery is arranged at the bifurcation of the superior mesenteric artery behind the pancreas;
the renal artery is approximately at the same level as the superior mesenteric artery, and a cut-off outlet at the end of the renal artery is set before the renal artery has a bifurcated artery vessel.
Optionally, in the aorta labeling system, the thoracic-abdominal aorta labeling module 202 is configured to label the abdominal aorta, the celiac trunk, the superior mesenteric artery, and the renal artery in sequence to label the abdominal aorta.
Optionally, in the aorta labeling system, the iliofemoral artery labeling module 203 is configured to label the common iliac artery, the internal iliac artery and the external iliac artery to mark the iliac artery;
wherein a cut-off outlet of the ending end of the internal iliac artery is set immediately before the horizontal end of the sacrum, the superior gluteal artery and the bifurcation end of each internal iliac artery.
Optionally, in the aorta labeling system, the iliac-femoral artery labeling module 203 is configured to label the common iliac artery, the internal iliac artery, and the external iliac artery in sequence to label the iliac artery.
Optionally, in the aorta labeling system, the iliac-femoral artery labeling module 203 is configured to label the femoral artery, the popliteal artery, the anterior tibial artery and the posterior tibial artery to label the femoral artery;
wherein a cut-off outlet of the ending end of the anterior tibial artery is set in front of a foot artery or at the tail end of the target image sequence;
the cut-off outlet of the ending end of the posterior tibial artery is set in front of the traffic branch or bifurcation branch of the posterior tibial artery.
Optionally, in the aorta labeling system, the iliac femoral artery labeling module 203 is configured to label the femoral artery, the popliteal artery, the anterior tibial artery and the posterior tibial artery in sequence to mark the femoral artery.
Optionally, in the aorta labeling system, the carotid artery labeling module 204 is configured to label a left subclavian artery, a left common carotid artery, a brachiocephalic trunk, a right common carotid artery, and a right subclavian artery to label the carotid artery;
wherein, the cut-off outlets of the ending ends of the left common carotid artery and the right common carotid artery are set at the horizontal end of the lower jaw teeth of the human body or the starting end of the target image sequence;
the cut-off outlets of the ending ends of the left subclavian artery and the right subclavian artery are respectively arranged at the inner sides of the left and right clavicles.
Optionally, in the aorta labeling system, the carotid artery labeling module 204 is configured to label the left subclavian artery, the left common carotid artery, the brachiocephalic trunk, the right common carotid artery, and the right subclavian artery in sequence to label the carotid artery.
Optionally, in the aorta annotation system, the image sequence obtaining module 201 obtains a target image sequence to be subjected to aorta annotation, specifically:
an intermediate image sequence within a predetermined range is obtained from a DICOM image sequence obtained through a CTA scanning as the target image sequence.
Optionally, in the aorta labeling system, the predetermined range is from a human neck artery to a position in front of a leg foot artery.
Optionally, in the aorta annotation system, the image sequence obtaining module 201 is further configured to:
if the layer thickness of the intermediate image sequence is lower than a predetermined layer thickness, the layer thickness of the intermediate image sequence is transformed into the predetermined layer thickness, and the transformed intermediate image sequence is taken as the target image sequence.
Optionally, in the aorta annotation system, the image sequence obtaining module 201 is further configured to:
if the window width window level of the intermediate image sequence does not meet the preset window width window level, the window width window levels of the intermediate image sequence are uniformly adjusted to the preset window width window level, and the adjusted intermediate image sequence is used as the target image sequence.
In summary, when the aorta labeling is performed by the aorta labeling system provided in the embodiment of the present invention, the most obvious and thickest thoraco-abdominal aorta is preferentially labeled by considering the body circulation direction and/or the artery thickness variation direction, the iliac artery and the femoral artery are labeled by descending the abdominal aorta, and the neck artery is labeled by ascending the thoracic aorta.
Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the aorta annotation method according to the embodiment shown in fig. 1.
It should be noted that, in the present specification, all the embodiments are described in a related manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system and the computer-readable storage medium are substantially similar to the method embodiments, so that the description is simple, and the relevant points can be referred to partial description of the method embodiments.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (17)
1. An aorta annotation method, comprising:
acquiring a target image sequence to be subjected to aorta annotation;
marking the thoracic aorta and the abdominal aorta from the target image sequence according to the body circulation direction and/or the artery thickness change direction;
labeling iliac and femoral arteries from the target image sequence descending the abdominal aorta;
the carotid artery is marked from the target image sequence by ascending the thoracic aorta.
2. The aorta labeling method according to claim 1, wherein labeling the thoracic aorta comprises labeling an ascending aorta, an aortic arch, and a descending aorta;
wherein a cut-off outlet of the starting end of the ascending aorta is set at the ascending aortic bulb.
3. The aortic labeling method of claim 2 wherein labeling the thoracic aorta comprises labeling the ascending aorta, the aortic arch, and the descending aorta in that order.
4. The aorta annotation method of claim 1, wherein annotating the abdominal aorta comprises annotating the abdominal aorta, the celiac trunk, the superior mesenteric artery, and the renal arteries;
wherein a cut-off outlet of the starting end of the abdominal trunk is set in the thick short artery trunk from the forearm of the abdominal aorta, and a cut-off outlet of the ending end of the abdominal trunk is set in front of inlets of the main artery, the left gastric artery and the spleen artery;
a cut-off outlet of the starting end of the superior mesenteric artery is arranged at the forearm below the starting point of the abdominal trunk, and a cut-off outlet of the ending end of the superior mesenteric artery is arranged at the bifurcation of the superior mesenteric artery behind the pancreas;
the renal artery is approximately at the same level as the superior mesenteric artery, and a cut-off outlet at the end of the renal artery is set before the renal artery has a bifurcated artery vessel.
5. The aorta labeling method according to claim 4, wherein labeling the abdominal aorta comprises labeling the abdominal aorta, the celiac trunk, the superior mesenteric artery, and the renal artery in that order.
6. The aorta annotation method of claim 1, wherein annotating the iliac arteries comprises annotating common iliac arteries, internal iliac arteries, and external iliac arteries;
wherein a cut-off outlet of the ending end of the internal iliac artery is set immediately before the horizontal end of the sacrum, the superior gluteal artery and the bifurcation end of each internal iliac artery.
7. The aorta labeling method according to claim 6, wherein labeling the iliac artery comprises labeling the common iliac artery, the internal iliac artery, and the external iliac artery in that order.
8. The aortic labeling method of claim 1 wherein labeling the femoral artery comprises labeling the femoral artery, the popliteal artery, the anterior tibial artery, and the posterior tibial artery;
wherein a cut-off outlet of the ending end of the anterior tibial artery is set in front of a foot artery or at the tail end of the target image sequence;
the cut-off outlet of the ending end of the posterior tibial artery is set in front of the traffic branch or bifurcation branch of the posterior tibial artery.
9. The aortic labeling method of claim 8 wherein labeling the femoral artery comprises labeling the femoral artery, the popliteal artery, the anterior tibial artery, and the posterior tibial artery in that order.
10. The aortic labeling method of claim 1 wherein labeling the carotid artery comprises labeling a left subclavian artery, a left common carotid artery, a brachiocephalic trunk, a right common carotid artery, and a right subclavian artery;
wherein, the cut-off outlets of the ending ends of the left common carotid artery and the right common carotid artery are set at the horizontal end of the lower jaw teeth of the human body or the starting end of the target image sequence;
the cut-off outlets of the ending ends of the left subclavian artery and the right subclavian artery are respectively arranged at the inner sides of the left and right clavicles.
11. The aortic labeling method of claim 10 wherein labeling the carotid artery comprises labeling the left subclavian artery, the left common carotid artery, the brachiocephalic trunk, the right common carotid artery, and the right subclavian artery in that order.
12. The aorta annotation method according to claim 1, wherein the step of obtaining the target image sequence to be subjected to aorta annotation comprises:
an intermediate image sequence within a predetermined range is obtained from a DICOM image sequence obtained through a CTA scanning as the target image sequence.
13. The aorta annotation method according to claim 12, wherein the predetermined range is from a human carotid artery to a region anterior to a calf foot artery.
14. The aortic labeling method of claim 12 further comprising:
if the layer thickness of the intermediate image sequence is lower than a predetermined layer thickness, the layer thickness of the intermediate image sequence is transformed into the predetermined layer thickness, and the transformed intermediate image sequence is taken as the target image sequence.
15. The aortic labeling method of claim 12 further comprising:
if the window width window level of the intermediate image sequence does not meet the preset window width window level, the window width window levels of the intermediate image sequence are uniformly adjusted to the preset window width window level, and the adjusted intermediate image sequence is used as the target image sequence.
16. An aortic labeling system comprising:
the image sequence acquisition module is used for acquiring a target image sequence to be subjected to aorta labeling;
the thoracic and abdominal artery labeling module is used for labeling a thoracic aorta and an abdominal aorta from the target image sequence according to the body circulation direction and/or the thickness change direction of the arteries;
the iliac-femoral artery labeling module is used for descending from the abdominal aorta and labeling iliac arteries and femoral arteries from the target image sequence;
and the neck artery labeling module is used for ascending from the thoracic aorta and labeling the neck artery from the target image sequence.
17. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the aorta annotation method according to any one of claims 1 to 15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139894.8A CN113421634A (en) | 2020-03-03 | 2020-03-03 | Aorta labeling method, system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139894.8A CN113421634A (en) | 2020-03-03 | 2020-03-03 | Aorta labeling method, system and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113421634A true CN113421634A (en) | 2021-09-21 |
Family
ID=77711625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010139894.8A Pending CN113421634A (en) | 2020-03-03 | 2020-03-03 | Aorta labeling method, system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113421634A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103700068A (en) * | 2012-01-17 | 2014-04-02 | 浙江大学 | Method for simultaneously segmenting liver and blood vessel in CTA (computed tomography angiography) image |
| CN106650272A (en) * | 2016-12-28 | 2017-05-10 | 北京昆仑医云科技有限公司 | Individual specificity based cardiovascular model generation method and application thereof |
| CN108171698A (en) * | 2018-02-12 | 2018-06-15 | 数坤（北京）网络科技有限公司 | A kind of method of automatic detection human heart Coronary Calcification patch |
| CN108765363A (en) * | 2018-03-24 | 2018-11-06 | 语坤（北京）网络科技有限公司 | A kind of automatic after-treatment systems of coronary artery CTA based on artificial intelligence |
| CN110310281A (en) * | 2019-07-10 | 2019-10-08 | 重庆邮电大学 | Lung neoplasm detection and dividing method in a kind of Virtual Medical based on Mask-RCNN deep learning |
-
2020
- 2020-03-03 CN CN202010139894.8A patent/CN113421634A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103700068A (en) * | 2012-01-17 | 2014-04-02 | 浙江大学 | Method for simultaneously segmenting liver and blood vessel in CTA (computed tomography angiography) image |
| CN106650272A (en) * | 2016-12-28 | 2017-05-10 | 北京昆仑医云科技有限公司 | Individual specificity based cardiovascular model generation method and application thereof |
| CN108171698A (en) * | 2018-02-12 | 2018-06-15 | 数坤（北京）网络科技有限公司 | A kind of method of automatic detection human heart Coronary Calcification patch |
| CN108765363A (en) * | 2018-03-24 | 2018-11-06 | 语坤（北京）网络科技有限公司 | A kind of automatic after-treatment systems of coronary artery CTA based on artificial intelligence |
| CN110310281A (en) * | 2019-07-10 | 2019-10-08 | 重庆邮电大学 | Lung neoplasm detection and dividing method in a kind of Virtual Medical based on Mask-RCNN deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 葛阳阳: ""B型主动脉夹层301分型与主动脉人工智能云平台建立"", 《中国博士学位论文全文数据库 医药卫生科技辑》, no. 09, pages 062 - 60 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fuessinger et al. | Planning of skull reconstruction based on a statistical shape model combined with geometric morphometrics | |
| Dean et al. | Computer aided design of large-format prefabricated cranial plates | |
| CN106485704B (en) | Method for extracting center line of blood vessel | |
| Arias et al. | Virtual surgical planning and three-dimensional printed guide for soft tissue correction in facial asymmetry | |
| CN110517238B (en) | AI three-dimensional reconstruction and human-computer interaction visualization network system for CT medical image | |
| CN105943113B (en) | A kind of preparation method of mandibular angle bone cutting navigation template | |
| Nagi et al. | Digitization in forensic odontology: A paradigm shift in forensic investigations | |
| Liberton et al. | Development and validation of novel three-dimensional craniofacial landmarks on cone-beam computed tomography scans | |
| Tokgöz et al. | Cosmetic and reconstructive facial plastic surgery related simulation and optimization efforts | |
| Cevik et al. | Three-dimensional printing technologies in the fabrication of maxillofacial prosthesis: A case report | |
| CN113326588A (en) | Porous bone implant structure design method for simulating biological bone rigidity | |
| Egger et al. | Computer-aided position planning of miniplates to treat facial bone defects | |
| Fawzy et al. | Evaluation of virtual surgical plan applicability in 3D simulation-guided two-jaw surgery | |
| Lee et al. | Computer-Aided Design and Rapid Prototyping–Assisted Contouring of Costal Cartilage Graft for Facial Reconstructive Surgery | |
| Navic et al. | The development and testing of Thai facial soft tissue thickness data in three-dimensional computerized forensic facial reconstruction | |
| Zhao et al. | Lip morphology estimation models based on three-dimensional images in a modern adult population from China | |
| Chen et al. | Visualization of penile suspensory ligamentous system based on visible human data sets | |
| CN111627023B (en) | Method and device for generating coronary artery projection image and computer readable medium | |
| CN113421634A (en) | Aorta labeling method, system and computer readable storage medium | |
| Huang et al. | Patient‐Specific Coronary Artery 3D Printing Based on Intravascular Optical Coherence Tomography and Coronary Angiography | |
| Spampinato | Skeletal bone age assessment | |
| Ko et al. | Machine learning in dentistry | |
| Beebe et al. | Computed tomography scanning for endograft planning: evolving toward three-dimensional, single source imaging | |
| Pucciarelli et al. | Stereophotogrammetric evaluation of labial symmetry after surgical treatment of a lymphatic malformation | |
| Chabanas et al. | Evaluating soft tissue simulation in maxillofacial surgery using preoperative and postoperative CT scans |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210921 |