CN114176616A - Venous thrombosis detection method, electronic device and storage medium - Google Patents
Venous thrombosis detection method, electronic device and storage medium Download PDFInfo
- Publication number
- CN114176616A CN114176616A CN202111444381.9A CN202111444381A CN114176616A CN 114176616 A CN114176616 A CN 114176616A CN 202111444381 A CN202111444381 A CN 202111444381A CN 114176616 A CN114176616 A CN 114176616A
- Authority
- CN
- China
- Prior art keywords
- image
- blood vessel
- thrombus
- vein
- block
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 206010047249 Venous thrombosis Diseases 0.000 title claims abstract description 50
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 108
- 208000007536 Thrombosis Diseases 0.000 claims abstract description 104
- 210000003462 vein Anatomy 0.000 claims abstract description 85
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims description 34
- 210000003141 lower extremity Anatomy 0.000 claims description 33
- 238000003709 image segmentation Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 13
- 230000008569 process Effects 0.000 abstract description 9
- 230000000694 effects Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 210000003414 extremity Anatomy 0.000 description 4
- 239000007789 gas Substances 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 210000001367 artery Anatomy 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000017531 blood circulation Effects 0.000 description 2
- 210000003191 femoral vein Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000003111 iliac vein Anatomy 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010008479 Chest Pain Diseases 0.000 description 1
- 208000000616 Hemoptysis Diseases 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 208000010378 Pulmonary Embolism Diseases 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000003513 popliteal vein Anatomy 0.000 description 1
- 210000001147 pulmonary artery Anatomy 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
- 210000001631 vena cava inferior Anatomy 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/504—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of blood vessels, e.g. by angiography
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- High Energy & Nuclear Physics (AREA)
- Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Vascular Medicine (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Pulmonology (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a venous thrombosis detection method, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring an original enhancement image of a vein vessel of a current patient; segmenting to obtain a blood vessel image corresponding to the vein in the original enhanced image; comparing the blood vessel image with a standard map matched with the current patient to obtain a comparison result; and determining a thrombus detection result corresponding to the vein of the current patient based on the comparison result. The detection scheme of the invention can achieve the effect of quickly and accurately determining the venous thrombosis, greatly simplifies the existing detection process of the venous thrombosis, effectively reduces the diagnosis time of doctor investment and reduces the manual input cost; in addition, the thrombus detection result which is rapidly output synchronously improves the overall diagnosis experience of doctors and patients.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method for detecting venous thrombosis, an electronic device, and a storage medium.
Background
With the development of medical imaging equipment, doctors can perform disease screening and diagnosis through medical images, such as the localization and grading diagnosis of vascular diseases through cardiovascular electronic Tomography (CT). Among them, observation of the veins of the lower limbs using CT images is a common item. The lower limb veins refer to the venous blood vessels of the lower limbs of the human body and are divided into a deep vein and a shallow vein, wherein the deep vein of the lower limbs is accompanied by the artery. Under the influence of related causes, thrombus is formed in deep veins of lower limbs, if the affected limbs are mild, the affected limbs are painful and swollen, and if the affected limbs are severe, the thrombus moves to pulmonary vessels along with the blood circulation of a human body and causes pulmonary embolism, so that the current patients have difficulty in breathing, chest pain, hemoptysis, oxygen deficiency and even endanger life.
Considering that the centrifugal end of a lower limb blood vessel is longer, and the blood flow of a vein blood vessel of an affected limb is slow and even stagnated, when a patient scans the lower limb CT currently, the vein blood vessel is strengthened weakly, and is difficult to form strong contrast with surrounding tissues in density distribution, so that the observation is inconvenient, an experienced doctor needs to repeatedly look over and compare the density value of a suspected thrombus block to draw a conclusion, and generally the CT thin-layer data of the lower limb of the patient currently exceeds 1000 layers; that is, currently, due to the fact that the number of CT scanning layers of the whole lower limb is large, the distal end of the deep vein vessel of the lower limb is poor, and the like, in order to avoid the observation omission, a doctor in an imaging department needs to spend a lot of time to diagnose the current vascular condition of the patient more accurately.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of long time consumption, low detection efficiency and accuracy, high labor cost investment and the like in the prior art of diagnosing the venous thrombosis condition of a patient by repeatedly observing a venous thrombosis image based on a doctor manual mode, and the invention aims to provide a venous thrombosis detection method, electronic equipment and a storage medium.
The invention solves the technical problems through the following technical scheme:
the invention provides a method for detecting venous thrombosis, which comprises the following steps:
acquiring an original enhancement image of a vein vessel of a current patient;
segmenting to obtain a blood vessel image corresponding to the vein in the original enhanced image;
comparing the blood vessel image with a standard map matched with the current patient to obtain a comparison result;
and determining a thrombus detection result corresponding to the vein of the current patient based on the comparison result.
Preferably, the comparing the blood vessel image with the standard atlas matched with the current patient to obtain the comparison result further includes:
carrying out registration processing on the blood vessel image and the standard atlas to obtain a first blood vessel image after registration processing;
the step of comparing the blood vessel image with a standard map matched with a current patient to obtain a comparison result comprises the following steps:
and comparing the first blood vessel image after the registration processing with the standard atlas matched with the current patient to obtain the comparison result.
Preferably, the comparing the first blood vessel image after the registration processing with the standard atlas matched with the current patient to obtain a comparison result includes:
calculating to obtain a difference image between the first blood vessel image subjected to registration processing and the standard atlas, and taking the difference image as the comparison result;
the difference image comprises a plurality of image blocks, and the image blocks are parts which are not intersected with the standard atlas in the first blood vessel image after registration processing.
Preferably, the determining the thrombus detection result corresponding to the vein of the current patient based on the comparison result comprises:
acquiring a vessel central line corresponding to a vein vessel in the first vessel image after registration processing;
extracting a first image block distributed on the center line of the blood vessel, determining that the position of the first image block corresponds to a true thrombus block, and deleting other image blocks except the first image block in the difference image;
or extracting a second image block which is not distributed on the center line of the blood vessel, determining the position of the second image block corresponding to the false thrombus block, and deleting the second image block in the difference image.
Preferably, the extracting a first image block distributed on the centerline of the blood vessel and determining that the first image block is located at a position corresponding to a true thrombus block includes:
registering the original enhanced image with the standard atlas to obtain a first enhanced image after registration processing;
when the first image block is determined to be distributed on the blood vessel central line, acquiring position information of the first image block;
acquiring a density parameter value of the first image block at a corresponding position in the first enhanced image after registration processing based on the position information;
and when the density parameter value is smaller than a set threshold value, determining that the first image block corresponds to a true thrombus block.
Preferably, the determining that the first image block corresponds to a true thrombus block further comprises:
acquiring thrombus information corresponding to each true thrombus block;
generating a thrombus detection report for a venous vessel of a current patient based on the thrombus information.
Preferably, the segmenting to obtain a blood vessel image corresponding to a vein blood vessel in the original enhanced image includes:
segmenting the original enhanced image to obtain a blood vessel image corresponding to a vein by adopting a pre-constructed image segmentation model;
wherein the step of constructing the image segmentation model comprises:
acquiring a plurality of historical enhancement images corresponding to different patients with venous thrombosis;
preprocessing the historical enhanced image to obtain the preprocessed historical enhanced image;
marking out historical vein images in each historical enhanced image;
and training to obtain the image segmentation model by taking the preprocessed historical enhanced image as input and the corresponding historical vein image as output.
Preferably, the step of constructing the standard map comprises:
personnel parameter information of different healthy personnel and historical enhanced images of venous vessels;
classifying the personnel parameter information to obtain different grouped crowds;
constructing the standard maps corresponding to different grouped people based on the grouped people, the personnel parameter information of each healthy person in the grouped people and the historical enhanced images;
and/or the presence of a gas in the gas,
the step of obtaining a standard atlas matching the current patient includes:
acquiring patient parameter information of a current patient;
obtaining a grouping population to which the current patient belongs based on the patient parameter information matching;
obtaining a standard atlas matched with the current patient based on the grouped population matching;
and/or the presence of a gas in the gas,
the venous vessels include lower extremity venous vessels.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the venous thrombosis detection method.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of detecting venous thrombosis described above.
On the basis of the common knowledge in the field, the preferred conditions can be combined randomly to obtain the preferred embodiments of the invention.
The positive progress effects of the invention are as follows:
according to the method, the original enhanced image of the venous vessel of the patient is segmented to obtain a corresponding vessel image, the segmented vessel image is compared with a standard map which is constructed in advance and matched with the characteristics of the current patient, and the distribution condition of thrombus in the venous vessel of the current patient is obtained through analysis based on the comparison result, so that the effect of rapidly and accurately determining the venous thrombus is achieved, the existing detection process of the venous thrombus is greatly simplified, the diagnosis time of doctor investment is effectively reduced, and the labor input cost is reduced; in addition, the thrombus detection result which is rapidly output synchronously improves the overall diagnosis experience of doctors and patients.
Drawings
FIG. 1 is a flowchart of a method for detecting venous thrombosis according to example 1 of the present invention.
FIG. 2 is a first flowchart of a venous thrombosis detection method according to embodiment 2 of the present invention.
FIG. 3 is a second flowchart of the venous thrombosis detection method in embodiment 2 of the present invention.
FIG. 4 is a third flowchart of the method for detecting venous thrombosis according to embodiment 2 of the present invention.
FIG. 5 is a fourth flowchart of the venous thrombosis detection method according to embodiment 2 of the present invention.
Fig. 6a is a schematic diagram of a blood vessel image after segmentation processing in embodiment 2 of the present invention.
Fig. 6b is a schematic diagram of a stereo standard atlas matched with a blood vessel image in embodiment 2 of the present invention.
Fig. 6c is a schematic diagram of the blood vessel image after registration in embodiment 2 of the present invention.
Fig. 6d is a schematic diagram of the difference image after comparison in embodiment 2 of the present invention.
Fig. 6e is a first schematic diagram of a blood vessel centerline in a blood vessel image according to embodiment 2 of the present invention.
Fig. 6f is a second schematic diagram of the center line of the blood vessel in the blood vessel image according to embodiment 2 of the present invention.
Fig. 6g is a schematic diagram of the difference image after the screening process in embodiment 2 of the present invention.
FIG. 6h is a schematic view of the whole true thrombus mass in example 2 of the present invention.
Fig. 7 is a block diagram schematically showing a system for detecting venous thrombosis according to embodiment 3 of the present invention.
Fig. 8 is a schematic structural diagram of an electronic device that implements a method for detecting a venous thrombus according to embodiment 4 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
The method for detecting venous thrombosis of the embodiment is suitable for a detection scene of venous thrombosis in a set venous blood vessel, wherein the set venous blood vessel comprises but is not limited to a lower limb venous blood vessel.
As shown in fig. 1, the method for detecting venous thrombosis of the present embodiment includes:
s101, obtaining an original enhancement image of a vein of a current patient;
the original enhanced image includes, but is not limited to, a CT enhanced image and a magnetic resonance enhanced image.
Specifically, the original enhanced image may be directly acquired from a storage device of the machine, or a corresponding image may be acquired after an image acquisition request is sent to the cloud server; of course, other acquisition methods may be used to obtain the original enhanced image. The specific acquisition mode can be determined and adjusted according to the actual situation.
S102, segmenting to obtain a blood vessel image corresponding to a vein in the original enhanced image;
the vein blood vessels are directly extracted, and the vein blood vessels are used as a subsequent comparison basis, so that the overall detection process is simplified, and the detection efficiency and the detection precision are ensured. Preferably, an image segmentation model obtained based on neural network training is adopted for image segmentation.
The shapes of venous thrombi of lower limbs are different, and experience doctors are needed to adaptively adjust the window width and the window position to observe in the prior art, so that the difficulty in directly dividing the thrombi is high (for example, the venous blood vessels are weakly enhanced, the density distribution is difficult to form strong contrast with surrounding tissues, the observation is inconvenient, and the like). In the embodiment, the characteristic that the lower limb deep vein blood vessels accompany the lower limb artery blood vessels is utilized, the model performance of segmenting the deep vein blood vessels by utilizing a deep learning method is ensured, and the accuracy of the image segmentation result is ensured.
Specifically, in an implementation scenario, step S102 includes:
adopting a pre-constructed image segmentation model to segment from the original enhanced image to obtain a blood vessel image corresponding to the vein;
the image segmentation model construction method comprises the following steps of:
acquiring a plurality of historical enhancement images corresponding to different patients with venous thrombosis;
preprocessing the historical enhanced image to obtain a preprocessed historical enhanced image;
marking out historical vein images in each historical enhanced image;
and taking the preprocessed historical enhanced image as an input and the corresponding historical vein image as an output, and training to obtain an image segmentation model.
The image segmentation model is obtained based on artificial intelligence technology training, so that the lower limb venous vessel image of the patient is obtained through accurate segmentation, and the detection accuracy of venous thrombosis is effectively guaranteed.
The set deep learning network structure training and test image segmentation model can be adopted, including but not limited to V-Net and U-Net (V-Net and U-Net are respectively a deep learning algorithm).
Specifically, a plurality of CT enhanced images of patients with thrombus in the deep veins of the lower limbs are collected, the deep veins of the lower limbs in the CT enhanced images are labeled, and the labeling range comprises: the cut-off positions are marked as: the common iliac vein reaches 5cm above the inferior vena cava, and passes through the external iliac vein, the deep femoral vein, the popliteal vein, the tibial vein, and down to the distal end of the peroneal vein.
In order to ensure the model training precision, the historical enhanced image needs to be preprocessed, specifically including window width and window level adjustment, gray value normalization, image enhancement and other adjustment operations on the patient CT enhanced image, and resampling processing is performed after unifying the CT enhanced image to the same resolution through a series of adjustment operations, for example, the CT enhanced image is fixed as spacing [0.7,0.7,0.7 ]; finally, cutting a fixed-size segmented region in the Z-axis direction of the CT enhanced image (certainly, cutting may also be performed along other directions, specifically, determining and adjusting according to actual requirements) and performing convolutional neural network training to obtain a corresponding image segmentation model.
S103, comparing the blood vessel image with a standard map matched with the current patient to obtain a comparison result;
the standard map corresponds to the vein blood vessel of patients with different characteristics (different ages, sexes and the like) in a normal healthy state, namely a blood vessel reference map corresponding to the condition without thrombus. The standard maps corresponding to the patients with different characteristics are constructed in advance, so that thrombus detection is carried out by adopting the standard maps matched with different patients aiming at different patients during actual thrombus detection.
Wherein, the standard map comprises a three-dimensional map and a planar map of vein and blood vessel of lower limb; preferably, a lower limb venous blood vessel three-dimensional map is constructed, compared with a planar map, a comparison result with higher precision can be guaranteed, and the final venous thrombosis detection precision is further guaranteed; that is, the three-dimensional atlas of vein vessels of lower limbs of this embodiment is derived from multi-level data sources, and this classification mechanism according to age and gender effectively avoids the problem that there is a large difference between CT images and atlas templates of different patients.
In one embodiment, the step of constructing a standard map comprises:
personnel parameter information of different healthy personnel and historical enhanced images of venous vessels;
wherein, the personnel parameter information includes but is not limited to age and gender.
Classifying the personnel parameter information to obtain different grouped crowds;
and constructing standard maps corresponding to different grouped people based on the grouped people, the personnel parameter information of each healthy person in the grouped people and the historical enhanced images.
Specifically, each decade of life is taken as a grade, male and female gender is distinguished, so that a plurality of groups of people are constructed, and then a standard map corresponding to each group of people is constructed. For example, the male in the age of 30-40 is selected as the group M-A, the male in the age of 40-50 is selected as the group M-B, and the male in the age of 50-60 is selected as the group M-C … …; the group of 30-40 years old women is F-A, the group of 40-50 years old women is F-B, the group of 50-60 years old women is F-C … …, and so on.
Collecting a plurality of examples of lower limb deep vein CT enhanced image data of healthy people in each grouped population, and generating a standard map corresponding to each grouped population by adopting a preset mode based on each grouped population, the personnel parameter information of each healthy person in the grouped population and the CT enhanced image, wherein the preset mode comprises but is not limited to Mean Shape model.
In one embodiment, the step of obtaining a standard atlas that matches the current patient includes:
acquiring patient parameter information of a current patient; the patient parameter information includes age, sex, and the like.
Obtaining a grouping population to which the current patient belongs based on patient parameter information matching;
and obtaining a standard atlas matched with the current patient based on grouping crowd matching.
According to the age, the sex and the like of the current patient, the corresponding standard atlas is automatically matched and called, and the whole process does not need to be operated manually, so that the whole detection process is simplified, the manual input cost is reduced, the matching accuracy is ensured, meanwhile, the conditions of standard atlas matching errors and the like caused by manual intervention operation are avoided, and the final venous thrombosis detection precision is further ensured.
And S104, determining a thrombus detection result corresponding to the vein of the current patient based on the comparison result.
Specifically, the comparison result represents the difference between the actual venous vessel of the current patient and the standard venous vessel corresponding to the actual venous vessel in the healthy state, and if the difference is not obtained, the difference indicates that no thrombus block exists in the venous vessel of the current patient; if there is a difference, the specific case of the difference indicates the distribution of the thrombus in the vein of the patient at present.
In the embodiment, the original enhanced image of the vein of the patient is segmented to obtain a corresponding blood vessel image, the segmented blood vessel image is compared with a standard map which is constructed in advance and matched with the characteristics of the current patient, and the distribution condition of thrombus in the vein of the current patient is obtained based on the comparison result analysis, so that the effect of quickly and accurately determining the vein thrombus is achieved, the existing detection flow of the vein thrombus is greatly simplified, the diagnosis time of doctor investment is effectively reduced, and the labor input cost is reduced; in addition, the thrombus detection result which is rapidly output synchronously improves the overall diagnosis experience of doctors and patients.
Example 2
The method for detecting venous thrombosis of the embodiment is a further improvement of the embodiment 1, and specifically comprises the following steps:
in an implementation scenario, as shown in fig. 2, step S103 includes, before:
s10301, carrying out registration processing on the blood vessel image and the standard atlas to obtain a first blood vessel image after the registration processing;
the image registration algorithm adopted in the registration processing process includes, but is not limited to, rigid registration, deformation registration, and rigid deformation registration, and specifically, which kind of registration algorithm is adopted can be determined according to actual requirements. The image registration algorithms described below in relation to the registration processing operations are similar and will not be described in detail.
Step S103 includes:
and S1031, comparing the first blood vessel image after the registration processing with the standard atlas matched with the current patient, and obtaining a comparison result.
In an implementation scenario, as shown in fig. 3, step S1031 includes:
s10311, calculating to obtain a difference image between the first blood vessel image subjected to registration processing and the standard map, and taking the difference image as a comparison result;
the difference image comprises a plurality of image blocks, and the image blocks are parts which are not intersected with the standard atlas in the first blood vessel image after registration processing. Each image block corresponds to a place where the vein vessel of the current patient is different from the standard map of the matched healthy population, so that the possibility of vein thrombosis exists.
Step S104 includes:
s1041, obtaining a blood vessel center line corresponding to a vein in the first blood vessel image after registration processing;
how to obtain the vessel centerline corresponding to the vein vessel belongs to the mature technology in the field, and therefore, the description thereof is omitted here.
S1042, extracting first image blocks distributed on the center line of the blood vessel, determining the position of the first image block to correspond to the true thrombus block, and deleting other image blocks except the first image block in the difference image;
or extracting a second image block which is not distributed on the center line of the blood vessel, determining the position of the second image block corresponding to the false thrombus block, and deleting the second image block in the difference image.
In consideration of the actual situation that the venous thrombus exists in the middle of the venous blood vessel, whether each first image block in the difference image corresponds to a true thrombus block can be accurately determined by judging whether the blood vessel center line corresponding to the venous blood vessel passes through the first image block in the difference image or judging whether the blood vessel center line corresponding to the venous blood vessel overlaps with the first image block in the difference image. Specifically, for the image block that the center line of the blood vessel does not pass through, that is, the corresponding image block exists on the side of the vein blood vessel, it can be directly determined that the image block is not a thrombus and belongs to a false thrombus block. For an image block where the vessel centerline passes through, it can be directly determined that it belongs to a true thrombus block.
In order to avoid the situation that the image block passed by the central line of the blood vessel is too rough and is not true thrombus still exists, the image block passed by the central line of the blood vessel can be further screened so as to further ensure the thrombus detection precision.
In an implementable scenario, as shown in fig. 4, the step S1042 of extracting a first image block distributed on a centerline of the blood vessel and determining a position of the first image block to correspond to a true thrombus block specifically includes:
s10421, registering the original enhanced image with the standard map to obtain a first enhanced image after registration processing;
s10422, when the first image block is determined to be distributed on the center line of the blood vessel, obtaining position information of the first image block;
s10423, acquiring a density parameter value of the first image block at a corresponding position in the first enhanced image after the registration processing based on the position information;
wherein, the density parameter value corresponds to the CT density value, the density value corresponding to the nuclear magnetic resonance enhanced image, and the like.
Specifically, a corresponding region in the first enhanced image after the registration processing is determined, and then an average CT density value of the corresponding region is calculated to be a CT density value corresponding to the current first image block. Of course, other calculation methods may be adopted to calculate the corresponding density parameter value, which is not described herein again.
S10424, when the density parameter value is smaller than the set threshold, determining that the first image block corresponds to a true thrombus block;
when the density parameter value is larger than or equal to the set threshold value, determining that the first image block corresponds to a false thrombus block, and determining that the segmented blood vessel image does not meet the set condition; that is, the segmented blood vessel image is not effectively segmented into the vein blood vessel, so that an under-segmented image block exists in the blood vessel image, which causes the case that the blood vessel image is mistaken for the thrombus, and the blood vessel image is directly determined as a false thrombus and is not considered.
In the embodiment, the overall distribution of the thrombus blocks in the vein of the current patient is obtained according to each first image block determined as the true thrombus block.
The difference image is obtained based on the comparison between the blood vessel image and the standard map, so that whether the image block in the difference image is a true thrombus block or a false thrombus block is determined, and finally all the true thrombus blocks in the difference image are reserved as the thrombus blocks in the vein of the current patient, so that the efficiency and the precision of the whole vein thrombus detection are ensured.
Of course, the distribution of the thrombus mass in the venous blood vessel obtained in step S10425 may also be determined or updated according to actual conditions and other more factors, for example, based on the current historical condition record information of the patient, the doctor' S opinion on the analysis of the CT enhanced image, and the like. More influencing factors are considered more comprehensively to further improve the detection precision of the venous thrombosis and improve the rationality and flexibility of the detection process.
In an implementation scenario, as shown in fig. 5, determining the corresponding true thrombus block at the first image block in step S1042 further includes:
s105, obtaining thrombus information corresponding to each true thrombus block;
the thrombus information includes, but is not limited to, thrombus position information, thrombus size information (such as long and short diameters, volume, etc.). Specifically, the thrombus is reported to be located in a specific section of the deep vein of the patient based on the upper and lower positions of the thrombus mass, for example, a certain thrombus mass is located at the deep femoral vein, and has a length of 80mm and a width of 15 mm.
And S106, generating a thrombus detection report of the vein vessel of the current patient based on the thrombus information.
The corresponding thrombus detection report is automatically generated based on the thrombus information corresponding to the real thrombus block obtained by detection and automatically reported, so that doctors and patients can timely know the corresponding thrombus distribution condition, and the overall diagnosis experience of the doctors and the patients is effectively improved.
The following will specifically explain the implementation principle of the venous thrombosis detection method of the present embodiment with reference to the examples:
(1) acquiring an original CT enhanced image of a patient A;
(2) performing segmentation processing on the original CT enhanced image by using the constructed image segmentation model to obtain a corresponding blood vessel image, which is shown in FIG. 6 a;
(3) according to the age, sex and other parameter information of the patient A, automatically matching to obtain a lower limb vein three-dimensional atlas matched with the patient A, and referring to fig. 6 b;
(4) registering the blood vessel image based on the lower limb vein three-dimensional atlas corresponding to the patient A to obtain a registered blood vessel image 6 c;
(5) comparing the registered blood vessel image of the patient a with the corresponding lower limb venous blood vessel stereogram to obtain a corresponding difference image, see fig. 6 d; wherein, each image block (corresponding to the sporadic distribution part in the image) in the difference image is a part where the blood vessel image and the stereo map are not intersected (i.e. are not overlapped);
(6) automatically acquiring a vessel centerline corresponding to a vein in the registered vessel image, see fig. 6e (corresponding to the centerline) and fig. 6f (corresponding to the vessel and the centerline);
(7) screening image blocks with the center lines of the blood vessels passing through, and deleting image blocks with the center lines of the blood vessels not passing through, referring to fig. 6g (in the figure, P corresponds to the image blocks with the center lines of the blood vessels not passing through);
(8) registering the original enhanced image and the standard atlas to obtain a first enhanced image;
(9) determining the position of a corresponding area of an image block passed by the central line of the blood vessel in the first enhanced image after registration; calculating to obtain an average CT density value corresponding to the region position, and determining the image block penetrated by the current blood vessel central line as a true thrombus block when the average CT density value is smaller than a set value; otherwise, determining that the blood vessel image is a false thrombus block, and simultaneously determining that the false thrombus block appears because the segmented blood vessel image is not effectively segmented on the vein blood vessel, so that an under-segmented image block exists in the blood vessel image;
(10) all true thrombus blocks are obtained, see fig. 6h (all image blocks in the figure are true thrombus blocks); and acquiring information such as corresponding thrombus position information and thrombus size information, automatically generating a thrombus detection report of the corresponding vein vessel, and automatically reporting to related personnel such as doctors, patients A, family members of the patients A and the like.
In the embodiment, the original enhanced image of the vein of the patient is segmented to obtain a corresponding blood vessel image, the segmented blood vessel image is compared with a standard map which is constructed in advance and matched with the characteristics of the current patient, and the distribution condition of thrombus in the vein of the current patient is obtained based on the comparison result analysis, so that the effect of quickly and accurately determining the vein thrombus is achieved, the existing detection flow of the vein thrombus is greatly simplified, the diagnosis time of doctor investment is effectively reduced, and the labor input cost is reduced; in addition, the thrombus detection result which is rapidly output synchronously improves the overall diagnosis experience of doctors and patients.
Example 3
The venous thrombosis detection system of the embodiment is suitable for setting a detection scene of venous thrombosis in a venous blood vessel, wherein the venous blood vessel includes but is not limited to a lower limb venous blood vessel.
As shown in fig. 7, the detection system of venous thrombosis of the present embodiment includes:
the original enhanced image module 1 is used for acquiring an original enhanced image of a vein of a current patient;
the original enhanced image includes, but is not limited to, a CT enhanced image and a magnetic resonance enhanced image.
Specifically, the original enhanced image may be directly acquired from a storage device of the machine, or a corresponding image may be acquired after an image acquisition request is sent to the cloud server; of course, other acquisition methods may be used to obtain the original enhanced image. The specific acquisition mode can be determined and adjusted according to the actual situation.
The blood vessel image acquisition module 2 is used for obtaining a blood vessel image corresponding to the vein in the original enhanced image by segmentation;
the vein blood vessels are directly extracted, and the vein blood vessels are used as a subsequent comparison basis, so that the overall detection process is simplified, and the detection efficiency and the detection precision are ensured. Preferably, an image segmentation model obtained based on neural network training is adopted for image segmentation.
The shapes of venous thrombi of lower limbs are different, and experience doctors are needed to adaptively adjust the window width and the window position to observe in the prior art, so that the difficulty in directly dividing the thrombi is high (for example, the venous blood vessels are weakly enhanced, the density distribution is difficult to form strong contrast with surrounding tissues, the observation is inconvenient, and the like). In the embodiment, the characteristic that the lower limb deep vein blood vessels accompany the lower limb artery blood vessels is utilized, the model performance of segmenting the deep vein blood vessels by utilizing a deep learning method is ensured, and the accuracy of the image segmentation result is ensured.
The comparison result acquisition module 3 is used for comparing the blood vessel image with a standard map matched with the current patient to acquire a comparison result;
the standard map corresponds to the vein blood vessel of patients with different characteristics (different ages, sexes and the like) in a normal healthy state, namely a blood vessel reference map corresponding to the condition without thrombus. The standard maps corresponding to the patients with different characteristics are constructed in advance, so that thrombus detection is carried out by adopting the standard maps matched with different patients aiming at different patients during actual thrombus detection.
Wherein, the standard map comprises a three-dimensional map and a planar map of vein and blood vessel of lower limb; preferably, a lower limb venous blood vessel three-dimensional map is constructed, compared with a planar map, a comparison result with higher precision can be guaranteed, and the final venous thrombosis detection precision is further guaranteed; that is, the three-dimensional atlas of vein vessels of lower limbs of this embodiment is derived from multi-level data sources, and this classification mechanism according to age and gender effectively avoids the problem that there is a large difference between CT images and atlas templates of different patients.
And the thrombus detection result determining module 4 is used for determining a thrombus detection result corresponding to the vein of the current patient based on the comparison result.
Specifically, the comparison result represents the difference between the actual venous vessel of the current patient and the standard venous vessel corresponding to the actual venous vessel in the healthy state, and if the difference is not obtained, the difference indicates that no thrombus block exists in the venous vessel of the current patient; if there is a difference, the specific case of the difference indicates the distribution of the thrombus in the vein of the patient at present.
It should be noted that the implementation principle of the detection system for venous thrombosis of the present embodiment is similar to that of the detection method for venous thrombosis in embodiment 1 or 2, and therefore, the description thereof is omitted here.
In the embodiment, the original enhanced image of the vein of the patient is segmented to obtain a corresponding blood vessel image, the segmented blood vessel image is compared with a standard map which is constructed in advance and matched with the characteristics of the current patient, and the distribution condition of thrombus in the vein of the current patient is obtained based on the comparison result analysis, so that the effect of quickly and accurately determining the vein thrombus is achieved, the existing detection flow of the vein thrombus is greatly simplified, the diagnosis time of doctor investment is effectively reduced, and the labor input cost is reduced; in addition, the thrombus detection result which is rapidly output synchronously improves the overall diagnosis experience of doctors and patients.
Example 4
Fig. 8 is a schematic structural diagram of an electronic device according to embodiment 4 of the present invention. The electronic device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the method for detecting venous thrombosis in any one of embodiments 1 or 2. The electronic device 30 shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in FIG. 8, electronic device 30 may take the form of a general purpose computing device, which may be a server device, for example. The components of the electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, and a bus 33 connecting the various system components (including the memory 32 and the processor 31).
The bus 33 includes a data bus, an address bus, and a control bus.
The memory 32 may include volatile memory, such as Random Access Memory (RAM)321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
The processor 31 executes a computer program stored in the memory 32 to execute various functional applications and data processing, such as a method for detecting venous thrombosis in any one of the embodiments 1 or 2 of the present invention.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through input/output (I/O) interfaces 35. Also, model-generating device 30 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via network adapter 36. As shown in FIG. 8, network adapter 36 communicates with the other modules of model-generating device 30 via bus 33. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the model-generating device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 5
The present embodiment provides a computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the steps in the method for detecting venous thrombosis in any one of embodiments 1 or 2.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation, the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps of implementing the method for detecting venous thrombosis in any of embodiments 1 or 2, when the program product is run on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (10)
1. A method for detecting venous thrombosis, the method comprising:
acquiring an original enhancement image of a vein vessel of a current patient;
segmenting to obtain a blood vessel image corresponding to the vein in the original enhanced image;
comparing the blood vessel image with a standard map matched with the current patient to obtain a comparison result;
and determining a thrombus detection result corresponding to the vein of the current patient based on the comparison result.
2. The method for detecting venous thrombosis according to claim 1, wherein the comparing the blood vessel image with the standard atlas matched with the current patient to obtain the comparison result further comprises:
carrying out registration processing on the blood vessel image and the standard atlas to obtain a first blood vessel image after registration processing;
the step of comparing the blood vessel image with a standard map matched with a current patient to obtain a comparison result comprises the following steps:
and comparing the first blood vessel image after the registration processing with the standard atlas matched with the current patient to obtain the comparison result.
3. The venous thrombosis detection method as claimed in claim 2, wherein the comparing the first blood vessel image after the registration processing with the standard atlas matched with the current patient to obtain the comparison result comprises:
calculating to obtain a difference image between the first blood vessel image subjected to registration processing and the standard atlas, and taking the difference image as the comparison result;
the difference image comprises a plurality of image blocks, and the image blocks are parts which are not intersected with the standard atlas in the first blood vessel image after registration processing.
4. The method for detecting venous thrombosis according to claim 3, wherein the step of determining the thrombosis detection result corresponding to the venous blood vessel of the current patient based on the comparison result comprises the following steps:
acquiring a vessel central line corresponding to a vein vessel in the first vessel image after registration processing;
extracting a first image block distributed on the center line of the blood vessel, determining that the position of the first image block corresponds to a true thrombus block, and deleting other image blocks except the first image block in the difference image;
or extracting a second image block which is not distributed on the center line of the blood vessel, determining the position of the second image block corresponding to the false thrombus block, and deleting the second image block in the difference image.
5. The method for detecting venous thrombosis according to claim 4, wherein said extracting a first image block distributed on the center line of said blood vessel and determining the position of said first image block corresponding to the true thrombus block comprises:
registering the original enhanced image with the standard atlas to obtain a first enhanced image after registration processing;
when the first image block is determined to be distributed on the blood vessel central line, acquiring position information of the first image block;
acquiring a density parameter value of the first image block at a corresponding position in the first enhanced image after registration processing based on the position information;
and when the density parameter value is smaller than a set threshold value, determining that the first image block corresponds to a true thrombus block.
6. The method according to claim 4 or 5, wherein the determining of the corresponding true thrombus block at the first image block further comprises:
acquiring thrombus information corresponding to each true thrombus block;
generating a thrombus detection report for a venous vessel of a current patient based on the thrombus information.
7. The method for detecting venous thrombosis according to claim 2 or 3, wherein the step of segmenting to obtain the blood vessel image corresponding to the venous blood vessel in the original enhanced image comprises the steps of:
segmenting the original enhanced image to obtain a blood vessel image corresponding to a vein by adopting a pre-constructed image segmentation model;
wherein the step of constructing the image segmentation model comprises:
acquiring a plurality of historical enhancement images corresponding to different patients with venous thrombosis;
preprocessing the historical enhanced image to obtain the preprocessed historical enhanced image;
marking out historical vein images in each historical enhanced image;
and training to obtain the image segmentation model by taking the preprocessed historical enhanced image as input and the corresponding historical vein image as output.
8. The method for detecting venous thrombosis of claim 1 wherein said step of constructing said standard profile comprises:
personnel parameter information of different healthy personnel and historical enhanced images of venous vessels;
classifying the personnel parameter information to obtain different grouped crowds;
constructing the standard maps corresponding to different grouped people based on the grouped people, the personnel parameter information of each healthy person in the grouped people and the historical enhanced images;
and/or the presence of a gas in the gas,
the step of obtaining a standard atlas matching the current patient includes:
acquiring patient parameter information of a current patient;
obtaining a grouping population to which the current patient belongs based on the patient parameter information matching;
obtaining a standard atlas matched with the current patient based on the grouped population matching;
and/or the presence of a gas in the gas,
the venous vessels include lower extremity venous vessels.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of detecting venous thrombosis of any one of claims 1-8 when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of detecting venous thrombosis of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111444381.9A CN114176616A (en) | 2021-11-30 | 2021-11-30 | Venous thrombosis detection method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111444381.9A CN114176616A (en) | 2021-11-30 | 2021-11-30 | Venous thrombosis detection method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114176616A true CN114176616A (en) | 2022-03-15 |
Family
ID=80603102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111444381.9A Pending CN114176616A (en) | 2021-11-30 | 2021-11-30 | Venous thrombosis detection method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114176616A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117133443A (en) * | 2023-08-29 | 2023-11-28 | 山东大学 | Lower limb venous thrombosis ultrasonic auxiliary diagnosis system based on video dynamic operator |
| CN117898766A (en) * | 2024-03-20 | 2024-04-19 | 柔脉医疗(深圳)有限公司 | Vascular imaging method, vascular imaging device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1785132A (en) * | 2004-12-08 | 2006-06-14 | 西门子公司 | Method for implementing imaging inspection method |
| CN110223280A (en) * | 2019-06-03 | 2019-09-10 | Oppo广东移动通信有限公司 | Phlebothrombosis detection method and phlebothrombosis detection device |
| CN110522449A (en) * | 2019-10-29 | 2019-12-03 | 南京景三医疗科技有限公司 | A kind of patch classifying method, device, electronic equipment and readable storage medium storing program for executing |
| CN111325266A (en) * | 2020-02-18 | 2020-06-23 | 慧影医疗科技（北京）有限公司 | Method and device for detecting micro-calcified clusters in breast molybdenum target image and electronic equipment |
| CN111968070A (en) * | 2020-04-22 | 2020-11-20 | 深圳睿心智能医疗科技有限公司 | Blood vessel detection method and device based on three-dimensional modeling |
-
2021
- 2021-11-30 CN CN202111444381.9A patent/CN114176616A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1785132A (en) * | 2004-12-08 | 2006-06-14 | 西门子公司 | Method for implementing imaging inspection method |
| CN110223280A (en) * | 2019-06-03 | 2019-09-10 | Oppo广东移动通信有限公司 | Phlebothrombosis detection method and phlebothrombosis detection device |
| CN110522449A (en) * | 2019-10-29 | 2019-12-03 | 南京景三医疗科技有限公司 | A kind of patch classifying method, device, electronic equipment and readable storage medium storing program for executing |
| CN111325266A (en) * | 2020-02-18 | 2020-06-23 | 慧影医疗科技（北京）有限公司 | Method and device for detecting micro-calcified clusters in breast molybdenum target image and electronic equipment |
| CN111968070A (en) * | 2020-04-22 | 2020-11-20 | 深圳睿心智能医疗科技有限公司 | Blood vessel detection method and device based on three-dimensional modeling |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117133443A (en) * | 2023-08-29 | 2023-11-28 | 山东大学 | Lower limb venous thrombosis ultrasonic auxiliary diagnosis system based on video dynamic operator |
| CN117133443B (en) * | 2023-08-29 | 2024-03-12 | 山东大学 | Lower limb venous thrombosis ultrasonic auxiliary diagnosis system based on video dynamic operator |
| CN117898766A (en) * | 2024-03-20 | 2024-04-19 | 柔脉医疗(深圳)有限公司 | Vascular imaging method, vascular imaging device, electronic equipment and storage medium |
| CN117898766B (en) * | 2024-03-20 | 2024-06-07 | 柔脉医疗(深圳)有限公司 | Vascular imaging method, vascular imaging device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886933B (en) | Medical image recognition method and device and storage medium | |
| CN113506334B (en) | Multi-mode medical image fusion method and system based on deep learning | |
| CN112508965B (en) | Automatic outline sketching system for normal organs in medical image | |
| US10854339B2 (en) | Systems and methods for associating medical images with a patient | |
| CN107368671A (en) | System and method are supported in benign gastritis pathological diagnosis based on big data deep learning | |
| CN109480780A (en) | A kind of cerebral apoplexy early warning system and method | |
| CN108618749B (en) | Retina blood vessel three-dimensional reconstruction method based on portable digital fundus camera | |
| CN111951219B (en) | Thyroid eye disease screening method, system and equipment based on orbit CT image | |
| CN114176616A (en) | Venous thrombosis detection method, electronic device and storage medium | |
| CN109166104A (en) | A kind of lesion detection method, device and equipment | |
| CN110189324B (en) | Medical image processing method and processing device | |
| US11475568B2 (en) | Method for controlling display of abnormality in chest x-ray image, storage medium, abnormality display control apparatus, and server apparatus | |
| CN109255354A (en) | medical CT-oriented computer image processing method and device | |
| CN111178420A (en) | Coronary segment labeling method and system on two-dimensional contrast image | |
| US11200671B2 (en) | Reference image guided object detection in medical image processing | |
| CN109034259A (en) | Image control system, method, terminal, the storage medium of carcinoma intervention device | |
| CN110503636B (en) | Parameter adjustment method, focus prediction method, parameter adjustment device and electronic equipment | |
| Xu et al. | RUnT: A network combining residual U-Net and transformer for vertebral edge feature fusion constrained spine CT image segmentation | |
| Li et al. | Towards enabling cardiac digital twins of myocardial infarction using deep computational models for inverse inference | |
| CN113256638A (en) | Eyeball cornea nerve segmentation method and device based on convolutional neural network model | |
| CN114266848A (en) | Medical image three-dimensional reconstruction method and device | |
| Malinda et al. | Lumbar vertebrae synthetic segmentation in computed tomography images using hybrid deep generative adversarial networks | |
| CN115797308A (en) | DCE-MRI-based breast tumor segmentation method | |
| CN113570600A (en) | Method, system and equipment for detecting stent inner leakage based on AI technology | |
| Li et al. | [Retracted] Nursing Analysis Based on Medical Imaging Technology before and after Coronary Angiography in Cardiovascular Medicine |
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 |