CN113592857A - Method for identifying, extracting and labeling graphic elements in medical image - Google Patents
Method for identifying, extracting and labeling graphic elements in medical image Download PDFInfo
- Publication number
- CN113592857A CN113592857A CN202110978633.XA CN202110978633A CN113592857A CN 113592857 A CN113592857 A CN 113592857A CN 202110978633 A CN202110978633 A CN 202110978633A CN 113592857 A CN113592857 A CN 113592857A
- Authority
- CN
- China
- Prior art keywords
- medical image
- graphic
- computer
- group
- medical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000002372 labelling Methods 0.000 title claims abstract description 16
- 230000036285 pathological change Effects 0.000 claims abstract description 8
- 231100000915 pathological change Toxicity 0.000 claims abstract description 8
- 239000000284 extract Substances 0.000 claims abstract description 6
- 210000000056 organ Anatomy 0.000 claims description 39
- 201000010099 disease Diseases 0.000 claims description 20
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 12
- 238000005481 NMR spectroscopy Methods 0.000 claims description 8
- 230000001575 pathological effect Effects 0.000 claims description 8
- 239000012634 fragment Substances 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 230000005477 standard model Effects 0.000 claims description 5
- 208000024891 symptom Diseases 0.000 claims description 5
- 238000002583 angiography Methods 0.000 claims description 4
- 238000002555 auscultation Methods 0.000 claims description 4
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 230000002969 morbid Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 238000000605 extraction Methods 0.000 abstract description 2
- 210000004072 lung Anatomy 0.000 description 61
- 210000000621 bronchi Anatomy 0.000 description 22
- 230000002685 pulmonary effect Effects 0.000 description 16
- 230000002787 reinforcement Effects 0.000 description 10
- 238000012512 characterization method Methods 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 7
- 210000003492 pulmonary vein Anatomy 0.000 description 7
- 208000004434 Calcinosis Diseases 0.000 description 6
- 206010028980 Neoplasm Diseases 0.000 description 6
- 230000003902 lesion Effects 0.000 description 6
- 230000002308 calcification Effects 0.000 description 5
- 210000001147 pulmonary artery Anatomy 0.000 description 4
- 238000012552 review Methods 0.000 description 4
- 238000005728 strengthening Methods 0.000 description 4
- 230000001839 systemic circulation Effects 0.000 description 4
- 210000004204 blood vessel Anatomy 0.000 description 3
- 238000002059 diagnostic imaging Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 210000003437 trachea Anatomy 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 206010003226 Arteriovenous fistula Diseases 0.000 description 2
- 206010010904 Convulsion Diseases 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 2
- 206010036790 Productive cough Diseases 0.000 description 2
- 208000032023 Signs and Symptoms Diseases 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 230000036770 blood supply Effects 0.000 description 2
- 230000036461 convulsion Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000002401 inhibitory effect Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 210000004379 membrane Anatomy 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 230000027939 micturition Effects 0.000 description 2
- 210000004224 pleura Anatomy 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000010186 staining Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 210000003462 vein Anatomy 0.000 description 2
- 208000004998 Abdominal Pain Diseases 0.000 description 1
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 201000003126 Anuria Diseases 0.000 description 1
- 208000006820 Arthralgia Diseases 0.000 description 1
- 206010003694 Atrophy Diseases 0.000 description 1
- 208000008035 Back Pain Diseases 0.000 description 1
- 101100452236 Caenorhabditis elegans inf-1 gene Proteins 0.000 description 1
- 206010008479 Chest Pain Diseases 0.000 description 1
- 206010010774 Constipation Diseases 0.000 description 1
- 206010011703 Cyanosis Diseases 0.000 description 1
- 206010012735 Diarrhoea Diseases 0.000 description 1
- 208000000059 Dyspnea Diseases 0.000 description 1
- 206010013975 Dyspnoeas Diseases 0.000 description 1
- 206010016717 Fistula Diseases 0.000 description 1
- 208000012671 Gastrointestinal haemorrhages Diseases 0.000 description 1
- 208000034507 Haematemesis Diseases 0.000 description 1
- 206010019233 Headaches Diseases 0.000 description 1
- 208000000616 Hemoptysis Diseases 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 101000786631 Homo sapiens Protein SYS1 homolog Proteins 0.000 description 1
- 206010023126 Jaundice Diseases 0.000 description 1
- 208000008930 Low Back Pain Diseases 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- 206010030302 Oliguria Diseases 0.000 description 1
- 206010033557 Palpitations Diseases 0.000 description 1
- 240000007711 Peperomia pellucida Species 0.000 description 1
- 206010035664 Pneumonia Diseases 0.000 description 1
- 208000004880 Polyuria Diseases 0.000 description 1
- 102100025575 Protein SYS1 homolog Human genes 0.000 description 1
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 206010053648 Vascular occlusion Diseases 0.000 description 1
- 208000012886 Vertigo Diseases 0.000 description 1
- 206010047700 Vomiting Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000010425 asbestos Substances 0.000 description 1
- 230000037444 atrophy Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 101150053549 cni gene Proteins 0.000 description 1
- 238000003851 corona treatment Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 230000003890 fistula Effects 0.000 description 1
- 210000000232 gallbladder Anatomy 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 231100000869 headache Toxicity 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 208000035861 hematochezia Diseases 0.000 description 1
- 208000006750 hematuria Diseases 0.000 description 1
- 101150002826 inf2 gene Proteins 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 206010022000 influenza Diseases 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 230000002197 limbic effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 210000001165 lymph node Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004877 mucosa Anatomy 0.000 description 1
- 206010029410 night sweats Diseases 0.000 description 1
- 230000036565 night sweats Effects 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 208000008128 pulmonary tuberculosis Diseases 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 229910052895 riebeckite Inorganic materials 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 206010042772 syncope Diseases 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 201000008827 tuberculosis Diseases 0.000 description 1
- 210000001113 umbilicus Anatomy 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 208000021331 vascular occlusion disease Diseases 0.000 description 1
- 231100000889 vertigo Toxicity 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention provides a method for identifying, extracting and labeling graphic elements in medical images. The method further identifies, extracts and labels the graphic elements in the medical image, outputs and analyzes the obtained information, avoids outputting single graphic information of the medical image for a doctor to judge, and solves the technical problem of identifying, extracting and labeling the graphic elements in the medical image. The invention avoids the influence of personal factors or errors on the manual reading of the medical image, improves the output speed of the medical image, can be suitable for the identification, extraction and marking of graphic elements in the medical image of the AI, utilizes the image characteristics of basic pathological changes to assist the result output of the medical image and obtains more accurate and comprehensive medical information. The method is suitable for recognizing, extracting and labeling the graphic elements in the medical images.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method for identifying, extracting and labeling graphic elements in AI medical images.
Background
Medical imaging refers to the technique and process of obtaining images of internal tissues of a human body or a part of the human body in a non-invasive manner for medical treatment or medical research. It contains the following two relatively independent directions of study: medical imaging systems (medical imaging systems) and medical image processing (medical image processing). The former refers to the process of image formation, including the research on the problems of imaging mechanism, imaging equipment, imaging system analysis and the like; the latter refers to further processing of the acquired images, either to restore the original less sharp image, to highlight some feature information in the image, to classify the pattern of the image, or the like.
Taking the CT image as an example, the CT image is formed by arranging a certain number of pixels with different gray scales from black to white in a matrix. These pixels reflect the X-ray absorption coefficients of the corresponding voxels. The size and number of pixels in the images obtained by different CT devices are different. The size can be 1.0 multiplied by 1.0 mm, 0.5 multiplied by 0.5 mm; the number may be 256 × 256, i.e. 65536, or 512 × 512, i.e. 262144, unequal. Obviously, the information recording capacity of a single medical image is very large, the number of medical images of each patient part is usually more than 1, and if the medical images are still marked and manually interpreted by adopting a traditional method, omission and errors exist in diagnosis results, reading and distinguishing of the medical images are usually affected by experience and subjective judgment of image doctors, and when the experience of the image doctors is insufficient or the image doctors insist on the patient, errors are easily generated, so that the judgment of the doctors on the information of the patients is affected.
Moreover, the number of disease types is tens of thousands, the number of corresponding human organs is limited, some disease types are highly similar in the early stage or characterization, only individual parts are different, or some disease types are overlapped in a cross mode, and accurate information cannot be obtained if the information is fed back from a single part, so that the medical image assistance can be used as a basis for judging the disease, the information of the medical image is more accurate, and a doctor can be helped to assist in judging the state of the disease of the patient.
Some diseases cannot be accurately judged by the medical image of a certain organ or system, for example, the symptoms of cough, expectoration, night sweat and fatigue are generally suspected to be respiratory diseases, the diseases can be judged to be various diseases such as cold, influenza, pneumonia, tuberculosis and the like in the early stage of disease onset of a patient, different diseases have different treatment schemes, if the optimal treatment time is delayed, the disease deterioration is possibly caused, the medical image is assisted to judge the disease condition of the patient, and the identification and extraction accuracy of the graphic elements of the medical image is particularly important.
Based on this, there is a need for a method for identifying, extracting and labeling graphic elements in medical images suitable for AI, which uses the image characteristics of basic lesions to assist the result output of the medical images and obtain more accurate and comprehensive medical information.
Disclosure of Invention
The invention provides a method for identifying, extracting and labeling graphic elements in a medical image, which aims to identify, extract and label the graphic elements in the medical image. The method further identifies, extracts and labels the graphic elements in the medical image, outputs and analyzes the obtained information, avoids outputting single graphic information of the medical image for a doctor to judge, and solves the technical problem of identifying, extracting and labeling the graphic elements in the medical image.
The technical scheme adopted by the invention for solving the technical problems is as follows:
firstly, according to the medical images of different organs or systems of a patient, splitting the medical images of each organ or system according to the positions, distribution, number, edges, density, form, peripheral change, organ function change enhancement, angiography change, nuclear magnetic resonance sequence, related examination result, morbid size, dynamic observation, general condition, symptom sign, special condition, inspection condition, auscultation condition, excision condition, laboratory examination result, pathological result and the like, establishing a graphic element identification frame group, performing graphic element coding according to the medical images of each organ or system, establishing a unique medical image code of each organ or system, and establishing an identification element group according to the grouping of the medical image codes.
Secondly, inputting a medical image of a normal organ or system as a judgment standard, labeling and dividing the medical image of the normal organ or system according to an identification element group by using a 3D slicer drawing tool, processing the whole medical image into fragment type computer-recognizable information according to the identification element group, grouping the medical image of the normal organ or system according to the identification element group, and establishing a graphic element computer-recognizable standard model for the graphic element group subjected to computer informatization processing.
Thirdly, inputting pathological medical images related to pathological changes or disease representations of each organ or system, labeling and dividing the medical images of the abnormal organs or systems according to the identification element groups by using a 3D slicer drawing tool, processing the whole medical image into fragment type computer recognizable information according to the identification element groups, grouping the medical images of the abnormal organs or systems according to the identification element groups, and establishing a computer recognizable comparison model for the graphic element groups subjected to computer informatization processing.
Finally, the medical image of the acquired patient is input into a computer by taking a data packet NAME + ID as a unit, the computer automatically extracts, divides and labels the graphic elements of the medical image of the patient according to the established graphic element group, divides the medical image into fragment-type graphic elements and records the fragment-type graphic elements as a judgment group, the judgment group is respectively matched and compared with a computer recognizable reference model and a computer recognizable comparison identification model, and when the judgment group graphic element codes are completely matched with the computer recognizable reference model, the output result is only position codes + nor (normal);
when the judgment group graphic element codes are matched with the graphic element codes in the comparison model which can be identified by the computer, the specific graphic codes of the matching group are output, abnormal graphic codes are output to the judgment group, the abnormality is displayed, and the marks are displayed on an operation interface in a red warning symbol mode.
The method has the advantages that the medical image is divided into the chip type computer identifiable information according to the graphic code, the computer identifiable reference model and the computer identifiable comparison model are established, the judgment group is compared with the basic model and the comparison model, the comparison result is output to the judgment group, and the operation interface is marked with the red warning symbol, the method processes the simple image information into the chip type computer identifiable information, so that the computer automatically judges whether the medical image is abnormal, the comprehensive information comparison of the NAME + ID packet can be realized by single input, the repeated input and comparison of different departments are not needed, the influence of personal factors or errors on the manual reading of the medical image is avoided, the output speed of the medical image identification result is improved, a large amount of time is saved, and the method has the advantages of accurate medical image identification result, complete information and high identification speed, the method can be suitable for AI identification of medical images. The method is suitable for recognizing, extracting and labeling the graphic elements in the medical images.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Firstly, according to the medical images of different organs or systems of a patient, according to the position, distribution, number, edge, density, form, peripheral change, organ function change enhancement, angiography change, nuclear magnetic resonance sequence, related examination result, morbid size, dynamic observation, general condition, symptom sign, special condition, inspection condition, auscultation condition, excision condition, laboratory examination result, pathological result and the like, the medical image of each organ or system is split, graph element identification frame group establishment is carried out, graph element coding is carried out according to the medical images of each organ or system, the unique code of the medical image of each organ or system is established, and the medical image coding is established into identification element groups according to the grouping,
pattern recognition element group code (lung for example)
Position one, Sowh
1) Lung LU: 11. the right superior pulmonary lobe section; 12. the anterior segment of the right superior lobe; 13. the posterior segment of the right superior pulmonary lobe; 14. the medial section of the right lobe of the middle lung; 15. the right lateral segment of the middle lobe of the lung; 16. the lower lobe dorsal segment of the right lung; 17. the basal section of the inner side of the right inferior lobe of the lung; 18. the anterior basal segment of the right inferior lobe of the lung; 19. the basal segment outside the right inferior lobe of the lung; 110. the posterior basal segment of the right inferior lobe of the lung; 111. the right lung; 112. the upper right lung lobe; 113. the right middle lung lobe; 114. the right inferior pulmonary lobe; 115. the posterior segment of the superior lobe tip of the left lung; 116. the anterior segment of the upper lobe of the left lung; 117. the upper lingual segment of the upper lobe of the left lung; 118. the upper lobe and lower tongue of the left lung; 119. the left lung inferior lobe dorsal segment; 120. the anterior-medial basal segment of the inferior lobe of the left lung; 121. the left lung inferior lobe outer basal section; 122. the posterior basal segment of the inferior lobe of the left lung; 123. the left lung; 124. the upper lobe of the left lung; 125. the inferior lobe of the left lung; 126. the right lung portal; 127. the left pulmonary portal; 128. the lobule of the lung; 129. spacing the leaflets; 130. a leaflet center; 131. under the chest membrane; 132. right oblique fracture; 133. horizontally splitting; 34. oblique fissure of left lung … …
2) Tracheal Trachea: 21. the upper end of the air pipe; 22. the lower end of the air pipe; 23. a trachea fork;
3) bronchus Bronchi; 31. a left main bronchus; 32. a right main bronchus; 33. the posterior apical left bronchi; 34. right anterior segmental bronchi; 35. the upper bronchus of the left lung; 36. upper left lingual segmental bronchi; 37. left inferior lingual segmental bronchi; 38. the left lung inferior lobe bronchus; 39. a left anterior base segment bronchus; 310. left lateral segmental bronchi; 311. a left posterior fundus bronchi; 312. the left apical (upper) bronchial tract; 313. the right upper lung lobe bronchus; 314. right brachial apices; 315. right posterior segmental bronchi; 316. right anterior segmental bronchi; 317. right lung middle lobe bronchus; 318. right lateral segmental bronchi; 319. right medial segmental bronchi; 320. right apical (upper) bronchial; 321. the right inferior pulmonary lobe bronchus; 322. right pulmonary posterior fundus bronchi; 323. right anterior base segment bronchi; 324. right medial (cardiac) fundus bronchi; 325. right lateral base bronchial tube … …
4) Art in pulmonary artery pul: 41. the left pulmonary trunk; 42. the left pulmonary artery from; 43. the right pulmonary trunk; 44. right pulmonary artery slave … …
5) Pulmonary vein pul. hyp: 51. the right superior pulmonary vein; 52. the right inferior pulmonary vein; 53. the left superior pulmonary vein; 54. left pulmonary veins … …
6) Intrapulmonary lymph node lym. pup: 51. the right superior pulmonary lobe section; 52. the anterior segment of the right superior lobe; 53. the posterior segment of the right superior pulmonary lobe; 54. the medial section of the right lobe of the middle lung; 55. the right lateral segment of the middle lobe of the lung; 56. the lower lobe dorsal segment of the right lung; 57. the basal section of the inner side of the right inferior lobe of the lung; 58. the anterior basal segment of the right inferior lobe of the lung; 59. the basal segment outside the right inferior lobe of the lung; 510. the posterior basal segment of the right inferior lobe of the lung; 511. the right lung; 512. the upper right lung lobe; 513. the right middle lung lobe; 514. the right inferior pulmonary lobe; 515. the posterior segment of the superior lobe tip of the left lung; 516. the anterior segment of the upper lobe of the left lung; 517. the upper lingual segment of the upper lobe of the left lung; 518. the upper lobe and lower tongue of the left lung; 519. the left lung inferior lobe dorsal segment; 520. the anterior-medial basal segment of the inferior lobe of the left lung; 521. the left lung inferior lobe outer basal section; 522. the posterior basal segment of the inferior lobe of the left lung; 523. the left lung; 524. the upper lobe of the left lung; 525. the inferior lobe of the left lung; 526. the right lung portal; 527. the left pulmonary portal; 528. the lobule of the lung; 529. spacing the leaflets; 530. a leaflet center; 531. under the chest membrane; 532. right oblique fracture; 533. horizontally splitting; 534. oblique fissure of left lung … …
Two, distribution and number Dist/Num
1) Distribution Dist: D1. dispersing; D2. diffuse distribution; D3. the materials are distributed in a centripetal manner; D4. centrifugal distribution; D5. blood seeding distribution; D6. distributed along the air passage; D7. pulmonary limbic (sub-pleural) distribution; D8. no distribution at the lung margin (under pleura); D9. localized distribution … …
2) The number Num: DN1. Single shot; dn2. multiple;
third, Edge
1) Edge: E1. the edge is clear and sharp; E2. the edges are cleaner; E3. blurring edges; E4. burr characterization; E5. rabbit ear signs; E6. performing halo characterization; E7. performing anti-corona treatment; E8. conducting the trachea; E9. sinus and fistula tracts; E10. collecting blood vessels; E11. unclear with pleura; E12.… … unclear with great vessels
Fourthly, density Den
1) Density: den1. high density; den2. slightly higher density; den3. equal density; den4. Low Density; den5. lower density; den6. hybrid density; den7, liquid-gas leveling inside the focus; den8. uneven density inside the lesion; den9. separation of the density inside the lesion; den10. density and liquid level in the focus; den11. soft tissue density; den12. calcification; den13. plaque-like calcification; den14. clustered microcalcifications; den15. Sand-like calcification; den16 egg shell-like calcification; den17, grinding the glass density; den18. water sample density; den19. fat density; den20. gas density; den21. hardening … …
Form
1) Form: form1. linear; form2. bar; form3. circular; form4. round-like; form5. irregular shape; form6. dot-like; form7. plaque-like; form8. pellet-like; form9. leaf separation; form10. tree bud; form11. umbilicus sign; form12. inverse parabola sign; form13. reverse S sign; form14. mosaic sample; form15. mesh; form16. honeycomb; form17. beaded … …
Sixth, peripheral Change SurC
1) Change around surrouding change: (iii) SurC1. atrophy; (iii) SurC2. swelling; infiltrating in SurC 3; (iii) SurC4. invasion; drawing by SurC 5; SurC6. push … …
Seventhly, the OFCE is enhanced by changing the organ functions
1) Organ function alterations enhance organic function changes and enhancements: ofce1. pulmonary arterial phase; ofce2. pulmonary venous phase; ofce3. fortification; ofce4. significant strengthening; ofce5. weak reinforcement; ofce6. no reinforcement; OFCE7. fast forward and fast out enhancement; ofce8. progressive reinforcement; ofce9. continuous reinforcement; OFCE10. slow-in slow-out intensification; ofce11. vascular occlusion; ofce12. filling defect; ofce13. tumor blood vessels; ofce14. tumor staining; ofce15. tumor lake; ofce16. early vein appearance; ofce17, arteriovenous fistula; ofce18. vasovagal; ofce19. systemic circulation blood supply; ofce20. pulmonary vein into systemic circulation; OFCE21. floral Ring Reinforcement … …
Eight, angiographic alteration ANg
1) Angiography alters angiographics: ang1. pulmonary artery phase; ang2. pulmonary venous phase; ang3. strengthening; ang4. obvious strengthening; ang5. weak strengthening; ang6. no reinforcement; ang7. fast forward and fast out enhancement; ang8. progressive reinforcement; ang9. continuous reinforcement; ang10. slow-in slow-out reinforcement; angiectasis; ang12. filling the defect; tumor blood vessels, ang 13; ang14. tumor staining; ang15. tumor lake; ang16 vein early appearance; angi 17, arteriovenous fistula; angiectasis, Ang18; ang19. systemic circulation blood supply; ang20 pulmonary vein into systemic circulation; ang21. floral ring reinforcement … …
Nine, nuclear magnetic resonance sequence NMR
1) Nuclear magnetic resonance Sequence NMR Sequence: nmr1.t 1; nmr2.t 2; nmr3. proton density; nmr4. lipid-inhibitory sequence; nmr5. water-inhibiting sequence; NMR6. fat and water inhibiting sequence; nmr7. in phase; nmr8, anti-phase; nmr9.lava sequence; nmr10.t2 sequence; nmr11. heavy T2 sequence; nmr12. magnetic sensitive imaging; nmr13. pop imaging; nmr14.dwi imaging; nmr15.adc map … …
Ten, related examination results ABo
1) X.X-ray; CT; MRI, MRI; PET-CT.PET-CT; PET-MR; OCT; endos7. endoscopic optics; multimodality; molecular imaging, mole.ima 9; gene10. Gene information … …
Eleven, size of disease Ms
1) Ms. size of measurement: x y zmm … …
Wherein x = lesion length, y = lesion width, z = lesion height, x, y, z may all be equal to 0, and count as 2 digits after the decimal point;
twelve, dynamic observation Dyno
1) Dyno1. lateral lung; dyno2. transpulmonary lobe; dyno3. a lung lobe; dyno4. lung segment; dyno5. across the lung segment; dyno6. increase in review volume or area; dyno7. reduction in review volume or area; dyno8. the review volume or area was unchanged; dyno9. the recheck density increased; dyno10. the rechecking density is reduced, and Dyno11. the rechecking density is unchanged; dyno12. review newly added … …
The method comprises the steps of automatically acquiring last medical image information of an NAME + ID package through dynamic observation, comparing a latest acquired medical image graphic identification element with a last medical image graphic identification element, judging that the volume or the area of a focus is increased when Dyno6= n & gt x (x = the size of the focus corresponding to the last medical image graphic element, and n is the size of the focus corresponding to the latest medical image graphic element), indicating that the volume or the area of the focus is reduced when Dyno7= n & lt x, judging that the original focus is not seen when Dyno7= -x, and judging that the volume or the area of the focus is not changed when Dyno8= x;
thirteen, general case Inf
1) Age, inf 1; inf2. sex; inf3. occupational history; inf4. history of contact; inf5. area of living; inf6. history of fertility; inf7. time of onset; history of silicon dust, inf 8; inf9. history of other dusts; history of asbestos; inf11. history of radiation exposure; inf12. history of epidemic areas; inf13. history of endemic regions; inf14. pasture history … …
Fourteen, symptomatic signs Symptoms and signs
SYS1. heating; sys2. bleeding of skin mucosa; sys3. edema; sys4, cough and expectoration; SYS5 hemoptysis; sys6. chest pain; sys7. cyanosis; sys8. dyspnea; sys9. palpitations; sys10. nausea and vomiting; sys11, hematemesis; sys12. hematochezia; sys13. abdominal pain; sys14. diarrhea; sys15 constipation; SYS16. jaundice; sys17. low back pain; sys18. arthralgia; sys19. hematuria; SYS20. frequent micturition, urgent micturition and odynuria; SYS21. anuria and polyuria due to oliguria; sys22. headache; SYS23. vertigo; SYS24. syncope; sys25. convulsions and convulsions; sys26. disturbance of consciousness; SYS27. associated symptoms … …
Fifteen Special cases Spec
Spec. detailed description of symptoms and signs: … … are provided.
Sixteen inspection cases CNIs
CNIns1. inspection of tongue; cnins2. inspection of qi.
Seventeen, the auscultation condition CNSme
Cnsme.
Eighteen, cutting and diagnosing CNPal
Cutting diagnosis at CNPal.
Nineteen, laboratory examination result Labor
Cbc, blood routine; RT urine routine … …
Twenty, pathological examination result pat
Ex. pathological outcome.
After the coding is finished, inputting a medical image of a normal organ or system according to the coding graphic element group, inputting the medical image of the normal organ or system as a judgment standard, marking and dividing the medical image of the normal organ or system according to the identification element group by using a 3D slicer drawing tool, processing the whole medical image into fragment type computer recognizable information according to the identification element group, grouping the medical image of the normal organ or system according to the identification element group, and establishing a graphic element computer recognizable standard model for the graphic element group subjected to computer informatization;
thirdly, inputting pathological medical images related to pathological changes or disease representation of each organ or system, labeling and dividing the medical images of abnormal organs or systems according to the identification element groups by using a 3D slicer drawing tool, processing the whole medical image into fragment type computer identifiable information according to the identification element groups, grouping the medical images of the abnormal organs or systems according to the identification element groups, and establishing a computer identifiable comparison model for the graphic element groups subjected to computer informatization;
finally, the medical image of the acquired patient is input into a computer by taking a data packet NAME + ID as a unit, the computer automatically extracts, divides and labels the graphic elements of the medical image of the patient according to the established graphic element group, the medical image is divided into fragment-type graphic elements which are recorded as a judgment group, the judgment group is respectively matched and compared with a computer recognizable standard model and a computer recognizable comparison identification model, when the judgment group graphic element code is completely matched with the computer recognizable standard model, the output result is only position code + nor (normal), and no specific small code is output, such as: LU + Nor;
when the graphic element codes of the group are judged to be matched with the graphic element codes in the computer recognizable comparison model, outputting specific graphic codes of the matched group, such as: d2.DN1.Den12.E3.Den4.Form5.SurC4, output the abnormal figure code to the judgement group package, match with pathological change and disease characterization according to the output figure code, the above-mentioned output result is: the upper right lung lobe segment + diffuse distribution + edge blurring + low density + calcification + irregular shape + (toward the periphery) infiltration, because the computer can identify the comparison model as the pathological changes or disease characterization graphic elements of each organ or system, when the group graphic element codes are judged to correspond to the codes in the computer-identifiable comparison model, the corresponding codes can be judged as the corresponding pathological changes or disease characterization without repeatedly reading the medical image for judgment and naming, and the comparison between the graphic codes and the corresponding pathological changes or disease characterization can be output as follows: and when the pulmonary tuberculosis is abnormal, the mark is displayed on an operation interface in a red warning sign form for interpretation, and a reader can quickly and accurately obtain the information condition of the abnormal part.
The medical images comprise X-ray, CT, ultrasonic scanning and nuclear magnetic resonance images of the lung, the liver, the brain, the chest, the head and the gallbladder, the images can be used for extracting, dividing and marking graphic elements according to the method of the invention, the adopted method and the obtained effect are the same as the invention, and other parts are not repeated.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (4)
1. The method for identifying, extracting and labeling the graphic elements in the medical image is characterized by comprising the following steps of: firstly, according to the medical images of different organs or systems of a patient, splitting the medical images of each organ or system according to the positions, distribution, number, edges, density, form, peripheral change, organ function change enhancement, angiography change, nuclear magnetic resonance sequence, related examination result, morbid size, dynamic observation, general condition, symptom sign, special condition, inspection condition, auscultation condition, excision condition, laboratory examination result, pathological result and the like, establishing a graphic element identification frame group, performing graphic element coding according to the medical images of each organ or system, establishing a unique medical image code of each organ or system, and establishing an identification element group according to the grouping of the medical image codes.
2. The method of claim 1, wherein the method comprises the steps of:
secondly, inputting a medical image of a normal organ or system as a judgment standard, labeling and dividing the medical image of the normal organ or system according to an identification element group by using a 3D slicer drawing tool, processing the whole medical image into fragment type computer-recognizable information according to the identification element group, grouping the medical image of the normal organ or system according to the identification element group, and establishing a graphic element computer-recognizable standard model for the graphic element group subjected to computer informatization processing.
3. The method as claimed in claim 2, wherein the method comprises the steps of:
thirdly, inputting pathological medical images related to pathological changes or disease representations of each organ or system, labeling and dividing the medical images of the abnormal organs or systems according to the identification element groups by using a 3D slicer drawing tool, processing the whole medical image into fragment type computer recognizable information according to the identification element groups, grouping the medical images of the abnormal organs or systems according to the identification element groups, and establishing a computer recognizable comparison model for the graphic element groups subjected to computer informatization processing.
4. The method as claimed in claim 3, wherein the method comprises the steps of:
finally, the medical image of the acquired patient is input into a computer by taking a data packet NAME + ID as a unit, the computer automatically extracts, divides and labels the graphic elements of the medical image of the patient according to the established graphic element group, divides the medical image into fragment-type graphic elements and records the fragment-type graphic elements as a judgment group, the judgment group is respectively matched and compared with a computer recognizable reference model and a computer recognizable comparison identification model, and when the judgment group graphic element codes are completely matched with the computer recognizable reference model, the output result is only position codes + nor (normal);
when the judgment group graphic element codes are matched with the graphic element codes in the comparison model which can be identified by the computer, the specific graphic codes of the matching group are output, abnormal graphic codes are output to the judgment group, the abnormality is displayed, and the marks are displayed on an operation interface in a red warning symbol mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110978633.XA CN113592857B (en) | 2021-08-25 | Method for identifying, extracting and labeling graphic elements in medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110978633.XA CN113592857B (en) | 2021-08-25 | Method for identifying, extracting and labeling graphic elements in medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113592857A true CN113592857A (en) | 2021-11-02 |
| CN113592857B CN113592857B (en) | 2024-11-15 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663512A (en) * | 2022-04-02 | 2022-06-24 | 广西科学院 | Medical image accurate positioning method and system based on organ coding |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018120942A1 (en) * | 2016-12-31 | 2018-07-05 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image by means of multi-model fusion |
| CN109583440A (en) * | 2017-09-28 | 2019-04-05 | 北京西格码列顿信息技术有限公司 | It is identified in conjunction with image and reports the medical image aided diagnosis method edited and system |
| CN110543894A (en) * | 2019-07-28 | 2019-12-06 | 聊城市光明医院 | Medical image processing method |
| CN111739615A (en) * | 2020-07-03 | 2020-10-02 | 桓光健 | AI medical diagnosis image picture computer input method |
| CN113269868A (en) * | 2021-04-30 | 2021-08-17 | 哈雷医用(广州)智能技术有限公司 | Method and device for establishing three-dimensional virtual model of human tumor |
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018120942A1 (en) * | 2016-12-31 | 2018-07-05 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image by means of multi-model fusion |
| CN109583440A (en) * | 2017-09-28 | 2019-04-05 | 北京西格码列顿信息技术有限公司 | It is identified in conjunction with image and reports the medical image aided diagnosis method edited and system |
| CN110543894A (en) * | 2019-07-28 | 2019-12-06 | 聊城市光明医院 | Medical image processing method |
| CN111739615A (en) * | 2020-07-03 | 2020-10-02 | 桓光健 | AI medical diagnosis image picture computer input method |
| CN113269868A (en) * | 2021-04-30 | 2021-08-17 | 哈雷医用(广州)智能技术有限公司 | Method and device for establishing three-dimensional virtual model of human tumor |
Non-Patent Citations (1)
| Title |
|---|
| 李越: "计算机图像处理技术在医学影像中的进展与应用", 《电脑知识与技术》, vol. 12, no. 30, 31 October 2016 (2016-10-31), pages 238 - 240 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663512A (en) * | 2022-04-02 | 2022-06-24 | 广西科学院 | Medical image accurate positioning method and system based on organ coding |
| CN114663512B (en) * | 2022-04-02 | 2023-04-07 | 广西科学院 | Medical image accurate positioning method and system based on organ coding |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kuijf et al. | Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge | |
| CN110969622B (en) | Image processing method and system for assisting pneumonia diagnosis | |
| JP6220310B2 (en) | Medical image information system, medical image information processing method, and program | |
| CN109493325B (en) | Tumor heterogeneity analysis system based on CT images | |
| US8630467B2 (en) | Diagnosis assisting system using three dimensional image data, computer readable recording medium having a related diagnosis assisting program recorded thereon, and related diagnosis assisting method | |
| CN111243042A (en) | Ultrasonic thyroid nodule benign and malignant characteristic visualization method based on deep learning | |
| CN102113016B (en) | The method that selective interactive process is carried out to data set | |
| US20060239524A1 (en) | Dedicated display for processing and analyzing multi-modality cardiac data | |
| CN106659424A (en) | Medical image display processing method, medical image display processing device, and program | |
| BRPI0618949A2 (en) | method and system for analyzing a plurality of medical imaging data from one region in an anatomy, method for acquiring and analyzing mrs medical imaging data from a region in an anatomy and system for analyzing medical imaging data from a region in an anatomy | |
| CN107945169B (en) | Coronary artery image analysis method | |
| JP5676269B2 (en) | Image analysis of brain image data | |
| CN107789056B (en) | Medical image matching and fusing method | |
| Hsieh et al. | Combining VGG16, Mask R-CNN and Inception V3 to identify the benign and malignant of breast microcalcification clusters | |
| Karimi et al. | Automatic lung infection segmentation of covid-19 in CT scan images | |
| Cheng et al. | Segmentation of the airway tree from chest CT using tiny atrous convolutional network | |
| Munhoz et al. | The value of the apparent diffusion coefficient calculated from diffusion-weighted magnetic resonance imaging scans in the differentiation of maxillary sinus inflammatory diseases | |
| CN113470060B (en) | Coronary artery multi-angle curved surface reconstruction visualization method based on CT image | |
| Chen et al. | Automatic and visualized grading of dental caries using deep learning on panoramic radiographs | |
| CN113592857A (en) | Method for identifying, extracting and labeling graphic elements in medical image | |
| CN113592857B (en) | Method for identifying, extracting and labeling graphic elements in medical image | |
| CN110858412B (en) | Heart coronary artery CTA model building method based on image registration | |
| CN115115735B (en) | Rapid calculation system of endothelial dynamic strain based on multi-phase coronary CT contrast | |
| CN202179552U (en) | Assistant pulmonary nodule diagnosis system for roentgenologists | |
| Zhao et al. | An artificial intelligence grading system of apical periodontitis in cone-beam computed tomography data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |