CN112801957A - Pneumothorax automatic check out system based on ultrasonic strain formation of image - Google Patents
Pneumothorax automatic check out system based on ultrasonic strain formation of image Download PDFInfo
- Publication number
- CN112801957A CN112801957A CN202110061483.6A CN202110061483A CN112801957A CN 112801957 A CN112801957 A CN 112801957A CN 202110061483 A CN202110061483 A CN 202110061483A CN 112801957 A CN112801957 A CN 112801957A
- Authority
- CN
- China
- Prior art keywords
- module
- pleural
- pneumothorax
- strain
- electric connection
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
Abstract
The invention provides an automatic pneumothorax detection system based on ultrasonic strain imaging, which comprises an image input module, an automatic pneumothorax detection module, a data transmission module and a display terminal module. The image input module comprises an ultrasonic probe, and the output end of the ultrasonic probe is in one-way electric connection with the input end of the pneumothorax automatic detection module; the output end of the pneumothorax automatic detection module is in one-way electric connection with the input end of the data transmission module; the output end of the data transmission module is in one-way electric connection with the input end of the display terminal module. The pneumothorax automatic detection system based on the ultrasonic strain imaging comprises a rapid pneumothorax ultrasonic detection algorithm based on strain calculation, can be integrated into handheld ultrasonic equipment, greatly enhances the portability and the flexibility, reduces the requirements of pneumothorax ultrasonic diagnosis on the experience and skill of doctors, and can be applied to more scenes, such as emergency treatment, ICU, emergency treatment sites, battlefields and the like.
Description
Technical Field
The invention belongs to the field of medical instruments, and particularly relates to an automatic pneumothorax detection system based on ultrasonic strain imaging.
Background
Pneumothorax (pneumothorax) refers to the condition of air accumulation caused by air entering into pleural cavity, and air in lung and bronchus escapes into pleural cavity due to rupture of lung tissues and visceral pleura or rupture of tiny air bubbles near the surface of lung caused by lung diseases or external force. Those caused by chest wall or lung trauma are called traumatic pneumothorax; spontaneous pneumothorax is called as the one caused by the self-rupture of lung tissue due to diseases; the artificial pneumothorax is called as artificial pneumothorax by injecting air into the pleural cavity artificially for treatment or diagnosis. Pneumothorax can be divided into closed pneumothorax, open pneumothorax and tension pneumothorax. Spontaneous pneumothorax is often seen in young and strong males or in patients with chronic bronchitis, emphysema and pulmonary tuberculosis. The disease belongs to one of the emergency diseases of the pneumology department, serious patients can endanger life, and the patient can be treated in time and cured.
At present, the imaging means of pneumothorax diagnosis mainly comprises X-ray chest film and CT. Wherein, the chest radiography is projection imaging, which is easy to cause missed diagnosis; CT is the gold standard for pneumothorax diagnosis, and is particularly sensitive and accurate to identification of small pneumothorax, localized pneumothorax, and bullous lung versus pneumothorax over X-ray chest radiographs. Basic CT of pneumothorax is manifested by the appearance of extremely low density gas shadows within the pleural cavity, with varying degrees of compressive collapse changes in lung tissue. However, CT has strong radioactivity, long diagnosis time and large volume, and cannot be widely used in a large scale.
In recent years, ultrasound has been used for pneumothorax diagnosis, and a good effect has been obtained. According to the Blue procedure, pneumothorax can be diagnosed by observing signs such as pleural slip, B-line, lung spots, etc., as shown in fig. 1. However, since pneumothorax diagnosis is mostly performed in emergency departments, emergency department doctors often lack basic knowledge and skills for ultrasound image interpretation, resulting in low pneumothorax ultrasound diagnosis rate. Therefore, the development of an automatic intelligent algorithm can effectively reduce the requirements of the ultrasonic wave on the experience and skill of a doctor and improve the pneumothorax diagnosis rate.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the present invention aims to provide an automatic pneumothorax detection system based on ultrasonic strain imaging, which includes a fast pneumothorax ultrasonic detection algorithm based on strain calculation, can be integrated into a handheld ultrasonic device, greatly enhances portability and flexibility, reduces the requirements of pneumothorax ultrasonic diagnosis on the experience and skill of doctors, and can be applied to more scenes, such as emergency treatment, ICU, emergency scene, battlefield, etc.
In order to achieve the purpose, the invention provides an automatic pneumothorax detection system based on ultrasonic strain imaging, which comprises an image input module, an automatic pneumothorax detection module, a data transmission module and a display terminal module.
Furthermore, the image input module comprises an ultrasonic probe, and the output end of the ultrasonic probe is in one-way electric connection with the input end of the pneumothorax automatic detection module; the output end of the pneumothorax automatic detection module is in one-way electric connection with the input end of the data transmission module; the output end of the data transmission module is in one-way electric connection with the input end of the display terminal module.
Furthermore, the pneumothorax automatic detection module comprises a database reference module, a strain analysis module, an AI classification module, a result output module and a data storage module.
Furthermore, the output end of the ultrasonic probe of the image input module is in one-way electric connection with the input end of the strain analysis module; the output end of the database reference module is in one-way electric connection with the input end of the strain analysis module; the output end of the strain analysis module is in one-way electric connection with the input end of the AI classification module; the output end of the AI classification module is in one-way electric connection with the input end of the result output module; the output end of the result output module is in one-way electric connection with the input end of the data storage module; the output end of the result output module is in one-way electric connection with the input end of the data transmission module.
Further, the database reference module includes a plurality of ultrasound images of the pleural region, which may be derived from the ultrasound image database of one or more hospitals, and is classified by an experienced physician according to whether the pleura sliding sign, the pleura sliding disappearance sign, and the lung point sign appear in the images, so as to assist the AI classification module in machine learning. Preferably, more than 100 ultrasound images are in the database reference module. More preferably, more than 500 ultrasound images are in the database reference module.
Further, the strain analysis module comprises a pleural slip determination module, a pleural slip disappearance determination module and a lung point determination module, and is applied to the lung ultrasonic image by using a strain imaging technology in image processing, so that the local displacement caused by the pleural slip can be identified, the pleural slip and the pleural slip disappearance can be effectively identified, and meanwhile, the lung point can also be identified.
Further, the strain analysis module performs strain calculation for the pleural region in two consecutive ultrasound images, and the main principle is as follows: under normal conditions, pleural slippage can produce local strain; in pneumothorax, however, the pleural effusions disappeared and the entire image was free of local strain. Normally, in an ultrasound image, especially a chest wall part above a pleural line, the change of an ultrasound signal of the region in a time dimension is small, for example, in the case that the position of an ultrasound probe is kept unchanged, some structures of the chest wall such as muscles and the like also keep the position unchanged, and the change of pixel values of fixed positions in the region in the time dimension is small. However, in the case of pneumothorax, since the pleura does not slide, the area below the pleural line is a gas, and in this case, the area below the pleural line on the ultrasound image is often a mirror image of the area above the pleural line (to the surface of the chest wall, i.e., the surface of the ultrasound probe), and the pixel value at a fixed position in this area is constant in the time dimension, and the strain is approximately zero. Therefore, the pleura sliding can be effectively judged and lung points can be identified by utilizing whether the pleura slides or not and whether the pleural region in the ultrasonic image has local strain or not.
Further, the strain analysis module firstly locates the position of a pleural line in the ultrasonic image, and then identifies a pleural region, and then the pleural sliding determination module, the pleural sliding disappearance determination module and the lung point determination module respectively determine whether pleural sliding signs, pleural sliding disappearance signs and lung point signs exist.
Further, the judgment rule of the pleural effusion slide sign is as follows: in the pleural region, the change of the pixel value of the fixed position in the area above the pleural line along the time dimension is small, namely less than a certain threshold value; whereas the pixel values of the fixed positions in the area below the pleural line vary more in the time dimension, i.e. above a certain threshold.
Further, the judgment rule of the pleural-sliding disappearance sign is as follows: in the pleural region, the change of the pixel values of the fixed positions of the regions above the pleural line and the regions below the pleural line along the time dimension is small, namely smaller than a certain threshold value; and the area below the pleural line is approximately a mirror mapping of the area above the pleural line.
Further, the lung landmark judgment rule is as follows: in the pleural region, there are both a pleura glide feature and a pleura glide loss feature.
Further, the AI classification module may perform machine learning and training according to a large number of ultrasound images provided by the database reference module and processed by the strain analysis module, and in combination with classification results of the ultrasound images by experienced doctors, continuously improve and adjust the thresholds for determining pleural sliding signs, pleural sliding disappearance signs and lung point signs, and then may intelligently classify the ultrasound images processed by the strain analysis module, and transmit the classification results to the result output module.
Further, the result output module transmits the ultrasound image and the classification result thereof to the data storage module for storage.
Furthermore, the output end of the data storage module can be in one-way electric connection with the input end of the database reference module, so that the new ultrasonic image input by the image input module and the classification result thereof can be transmitted to the database reference module to expand the data volume thereof, thereby providing more data for machine learning of the AI classification module, and improving and perfecting the intelligent classification capability thereof.
Further, the data transmission module can transmit the data of the result output module to the display terminal module in a wired or wireless mode. The wireless mode is selected from one of bluetooth, WiFi, Zigbee, and cellular network communication (e.g., 3G, 4G, and 5G).
Further, the display terminal module includes a display.
Compared with the prior art, the invention has the beneficial effects that:
1. the imaging diagnosis of pneumothorax in the prior art is often based on the assumption that the brightness is constant, i.e. the brightness of the same point does not change with time. However, for ultrasound images, this assumption is difficult to satisfy completely due to the effect of speckle noise. This assumption requires small movements, i.e. the change in time does not cause a drastic change in position, however, pleural sliding may cause a large displacement of pixels at the pleural position, resulting in the prior art being time-consuming in calculation, poor in real-time and practicability, and not suitable for portable terminal devices with limited computing resources such as mobile ultrasound. In contrast, the rapid pneumothorax ultrasonic detection method based on strain calculation is adopted, the calculation amount is small, and the rapid pneumothorax ultrasonic detection method can be integrated into equipment with limited calculation resources such as handheld ultrasound and the like; and the calculation is carried out on the whole image data, and the obtained result is more stable.
The pneumothorax automatic detection system based on ultrasonic strain imaging adopts a strain imaging technology and combines machine learning, so that an AI classification module can intelligently identify local displacement generated by pleural sliding, effectively identify pleural sliding and pleural sliding disappearance, and can identify lung points at the same time, thereby reducing the requirements of pneumothorax ultrasonic diagnosis on the experience and the skill of doctors, and further being applied to more scenes, such as emergency treatment, ICU, emergency treatment sites, battlefields and the like.
Drawings
FIG. 1 is a schematic flow chart of pneumothorax diagnostic Blue of the prior art;
FIG. 2 is a schematic structural diagram of an automatic pneumothorax detection system based on ultrasonic strain imaging according to a preferred embodiment of the present invention;
FIG. 3 is a schematic ultrasound image showing the presence of pleura slide feature, pleura slide loss feature and lung spot feature according to a preferred embodiment of the present invention.
Detailed Description
The following examples are given to illustrate the present invention in detail, and the following examples are given to illustrate the detailed embodiments and specific procedures of the present invention, but the scope of the present invention is not limited to the following examples.
As shown in fig. 2-3, in a preferred embodiment, the system for automatic pneumothorax detection based on ultrasonic strain imaging of the present invention comprises an image input module 1, an automatic pneumothorax detection module 2, a data transmission module 3 and a display terminal module 4. The image input module 1 comprises an ultrasonic probe, and the output end of the ultrasonic probe is in one-way electric connection with the input end of the pneumothorax automatic detection module 2; the output end of the pneumothorax automatic detection module 2 is in one-way electric connection with the input end of the data transmission module 3; the output end of the data transmission module 3 is in one-way electric connection with the input end of the display terminal module 4.
The pneumothorax automatic detection module 2 further comprises a database reference module 21, a strain analysis module 22, an AI classification module 23, a result output module 24 and a data storage module 25. Wherein, the output end of the ultrasonic probe of the image input module 1 is in one-way electric connection with the input end of the strain analysis module 22; the output end of the database reference module 21 is in one-way electric connection with the input end of the strain analysis module 22; the output end of the strain analysis module 22 is in one-way electrical connection with the input end of the AI classification module 23; the output end of the AI classification module 23 is in one-way electric connection with the input end of the result output 24 module; the output end of the result output module 24 is in one-way electric connection with the input end of the data storage module 25; the output end of the result output module 24 is in one-way electric connection with the input end of the data transmission module 3.
The database reference module 21 includes a large number (e.g., more than 500) of ultrasound images of the pleural region, which may be derived from an ultrasound image database of one or more hospitals, and is classified by an experienced physician according to whether or not a pleura sliding feature, a pleura sliding disappearance feature, and a lung point feature appear in the images, so as to assist the AI classification module 23 in machine learning.
The strain analysis module 22 comprises a pleural slip determination module, a pleural slip disappearance determination module and a lung point determination module, and is applied to a lung ultrasound image by using a strain imaging technology in image processing, so that local displacement caused by pleural slip can be identified, pleural slip and pleural slip disappearance can be effectively identified, and lung points can also be identified.
The strain analysis module 22 performs strain calculation for the pleural region in two consecutive ultrasound images, and the main principle is as follows: under normal conditions, pleural slippage can produce local strain; in pneumothorax, however, the pleural effusions disappeared and the entire image was free of local strain. Normally, in an ultrasound image, especially a chest wall part above a pleural line, the change of an ultrasound signal of the region in a time dimension is small, for example, in the case that the position of an ultrasound probe is kept unchanged, some structures of the chest wall such as muscles and the like also keep the position unchanged, and the change of pixel values of fixed positions in the region in the time dimension is small, as shown in fig. 3 (a). However, in the case of pneumothorax, since the pleura does not slide, the area below the pleural line is a gas, and in this case, the area below the pleural line on the ultrasound image is often a mirror image of the area above the pleural line (to the surface of the chest wall, i.e., the surface of the ultrasound probe), and the pixel value at the fixed position in this area is constant along the time dimension, and the strain is approximately zero, as shown in fig. 3 (b). Therefore, the pleura sliding can be effectively judged and lung points can be identified by utilizing whether the pleura slides or not and whether the pleural region in the ultrasonic image has local strain or not.
The strain analysis module 22 first locates the position of the pleural line in the ultrasound image, and then identifies the pleural region, and then determines whether the pleural sliding sign, the pleural sliding disappearance sign, and the lung point sign exist by the pleural sliding determination module, the pleural sliding disappearance determination module, and the lung point determination module, respectively.
As shown in fig. 3(a), the judgment rule of the pleural effusion slide sign is: in the pleural region, the change of the pixel value of the fixed position in the area above the pleural line along the time dimension is small, namely less than a certain threshold value; whereas the pixel values of the fixed positions in the area below the pleural line vary more in the time dimension, i.e. above a certain threshold. The ultrasound image indicates that the subject is normal, not pneumothorax.
As shown in fig. 3(b), the judgment rule of the pleural-sliding disappearance sign is: in the pleural region, the change of the pixel values of the fixed positions of the regions above the pleural line and the regions below the pleural line along the time dimension is small, namely smaller than a certain threshold value; and the area below the pleural line is approximately a mirror mapping of the area above the pleural line. The ultrasound image indicates that the subject may have a pneumothorax.
As shown in fig. 3(c), the lung spot characteristic determination rule is: in the pleural region, there are both a pleura glide feature and a pleura glide loss feature. The ultrasound image indicates that the subject has a pneumothorax.
The AI classification module 23 may perform machine learning and training according to a large number of ultrasound images provided by the database reference module 21 and processed by the strain analysis module 22, and combine classification results of the ultrasound images with experienced doctors, continuously improve and adjust the thresholds for determining pleural sliding signs, pleural sliding disappearance signs, and lung point signs, and further may perform automatic intelligent classification on the ultrasound images processed by the strain analysis module 22, and transmit the classification results to the result output module 24.
The result output module 24 transmits the ultrasound image and the classification result thereof to the data storage module 25 for storage.
The output end of the data storage module 25 can be electrically connected to the input end of the database reference module 21 in a unidirectional manner, so that the new ultrasound image and the classification result thereof input by the image input module 1 can be transmitted to the database reference module 21 to expand the data volume thereof, thereby providing more data for machine learning of the AI classification module 23, improving and perfecting the intelligent classification capability thereof.
The data transmission module 3 may transmit the data of the result output module 24 to the display terminal module 4 in a wired or wireless manner. The wireless mode is selected from one of bluetooth, WiFi, Zigbee, and cellular network communication (e.g., 3G, 4G, and 5G).
The display terminal module 4 includes a display.
The working principle of the invention is as follows: strain (strain) belongs to the concept of physics, which is defined as the deformation of an object under the action of an external force, and the degree of deformation is called strain. The strain includes positive strain (linear strain), shear strain (angular strain), and bulk strain. The positive strain formula is
Where L is the pre-deformation length and Δ L is the post-deformation elongation.
The method applies the thought to image processing, and can calculate the strain generated by local pixel movement in the image, namely strain imaging (strain imaging). As shown in fig. 3, when the strain imaging technique is applied to the lung ultrasound image, the local displacement caused by the pleural slip can be identified, the pleural slip and the disappearance of the pleural slip can be effectively identified, and the lung point can also be identified.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. An automatic pneumothorax detection system based on ultrasonic strain imaging is characterized by comprising an image input module, an automatic pneumothorax detection module, a data transmission module and a display terminal module; wherein the content of the first and second substances,
the image input module comprises an ultrasonic probe, and the output end of the ultrasonic probe is in one-way electric connection with the input end of the pneumothorax automatic detection module; the output end of the pneumothorax automatic detection module is in one-way electric connection with the input end of the data transmission module; the output end of the data transmission module is in one-way electric connection with the input end of the display terminal module.
2. The system of claim 1, wherein the pneumothorax automatic detection module comprises a database reference module, a strain analysis module, an AI classification module, a result output module, and a data storage module.
3. The system of claim 2, wherein the output end of the ultrasonic probe of the image input module is in one-way electrical connection with the input end of the strain analysis module; the output end of the database reference module is in one-way electric connection with the input end of the strain analysis module; the output end of the strain analysis module is in one-way electric connection with the input end of the AI classification module; the output end of the AI classification module is in one-way electric connection with the input end of the result output module; the output end of the result output module is in one-way electric connection with the input end of the data storage module; the output end of the result output module is in one-way electric connection with the input end of the data transmission module.
4. The automated sonostrain imaging-based pneumothorax detection system of claim 3, wherein the database reference module includes more than 100 ultrasound images of the pleural region, the ultrasound images being classified according to whether a pleura slide feature, a pleura slide disappearance feature, and a lung point feature are present to facilitate machine learning by the AI classification module.
5. The automated sonostrain imaging-based pneumothorax detection system of claim 4, wherein the strain analysis module includes a pleural slip determination module, a pleural slip effacement determination module, and a lung point determination module; and the strain analysis module performs strain calculation aiming at the pleural region in the two continuous ultrasonic images.
6. The automated sonostrain imaging-based pneumothorax detection system of claim 5, wherein the strain analysis module first locates a pleural line position in the ultrasound image, thereby identifying a pleural region, and then determines whether a pleural slip sign, a pleural slip disappearance sign, and a lung point sign are present by the pleural slip determination module, the pleural slip disappearance determination module, and the lung point determination module, respectively.
7. The system of claim 6, wherein the pleural effusions are determined by the following rules: in the pleural region, the change of the pixel value of the fixed position of the region above the pleural line along the time dimension is less than a certain threshold; and the variation of the pixel values of the fixed position in the area below the pleural line along the time dimension is larger than the threshold value;
the judgment rule of the pleural effusion disappearance sign is as follows: in the pleural region, the change of the pixel values of the fixed positions in the above pleural line region and the below pleural line region along the time dimension is less than the threshold value; and the area below the pleural line is substantially a mirror mapping of the area above the pleural line;
the judgment rule of the lung point sign is as follows: in the pleural region, the pleuropneumonia feature and the pleuropneumonia disappearance feature are present simultaneously.
8. The system of claim 7, wherein the result output module transmits the ultrasound image and the classification result thereof to the data storage module for storage.
9. The automated sonography-based pneumothorax detection system of claim 8, wherein an output of said data storage module is electrically connectable in a unidirectional manner to an input of said database reference module.
10. The system for automatically detecting pneumothorax based on ultrasonic strain imaging of any one of claims 1-9, wherein the data transmission module transmits the data of the result output module to the display terminal module in a wired or wireless manner; the wireless mode is selected from one of Bluetooth, WiFi, Zigbee and cellular network communication; the display terminal module comprises a display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110061483.6A CN112801957A (en) | 2021-01-18 | 2021-01-18 | Pneumothorax automatic check out system based on ultrasonic strain formation of image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110061483.6A CN112801957A (en) | 2021-01-18 | 2021-01-18 | Pneumothorax automatic check out system based on ultrasonic strain formation of image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112801957A true CN112801957A (en) | 2021-05-14 |
Family
ID=75810023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110061483.6A Pending CN112801957A (en) | 2021-01-18 | 2021-01-18 | Pneumothorax automatic check out system based on ultrasonic strain formation of image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801957A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114533128A (en) * | 2022-02-24 | 2022-05-27 | 中国人民解放军海军军医大学 | Pneumothorax auxiliary diagnosis device, medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934228A (en) * | 2017-03-06 | 2017-07-07 | 杭州健培科技有限公司 | Lung's pneumothorax CT image classification diagnostic methods based on machine learning |
| CN107072637A (en) * | 2014-09-25 | 2017-08-18 | 皇家飞利浦有限公司 | The apparatus and method detected for automatic pneumothorax |
| CN109310398A (en) * | 2016-03-24 | 2019-02-05 | 皇家飞利浦有限公司 | For detecting the ultrasonic system and method for lung's sliding |
| CN111528907A (en) * | 2020-05-07 | 2020-08-14 | 万东百胜(苏州)医疗科技有限公司 | Ultrasonic image pneumonia auxiliary diagnosis method and system |
| CN112085729A (en) * | 2020-09-18 | 2020-12-15 | 无锡祥生医疗科技股份有限公司 | Pleural line region extraction method, storage medium, and ultrasound diagnostic apparatus |
-
2021
- 2021-01-18 CN CN202110061483.6A patent/CN112801957A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107072637A (en) * | 2014-09-25 | 2017-08-18 | 皇家飞利浦有限公司 | The apparatus and method detected for automatic pneumothorax |
| CN109310398A (en) * | 2016-03-24 | 2019-02-05 | 皇家飞利浦有限公司 | For detecting the ultrasonic system and method for lung's sliding |
| CN106934228A (en) * | 2017-03-06 | 2017-07-07 | 杭州健培科技有限公司 | Lung's pneumothorax CT image classification diagnostic methods based on machine learning |
| CN111528907A (en) * | 2020-05-07 | 2020-08-14 | 万东百胜(苏州)医疗科技有限公司 | Ultrasonic image pneumonia auxiliary diagnosis method and system |
| CN112085729A (en) * | 2020-09-18 | 2020-12-15 | 无锡祥生医疗科技股份有限公司 | Pleural line region extraction method, storage medium, and ultrasound diagnostic apparatus |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114533128A (en) * | 2022-02-24 | 2022-05-27 | 中国人民解放军海军军医大学 | Pneumothorax auxiliary diagnosis device, medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108024791B (en) | Differentiating pulmonary sliding from external motion | |
| CN107569257A (en) | Ultrasonoscopy processing method and system, ultrasonic diagnostic equipment | |
| US8515141B2 (en) | Medical image processing apparatus and method for detecting locally protruding lesion | |
| US10178941B2 (en) | Image processing apparatus, image processing method, and computer-readable recording device | |
| KR102209086B1 (en) | Urinary Stones Information Providing Method, Apparatus and Computer-Readable Medium | |
| CN111863209B (en) | Colonoscopy quality assessment workstation based on image recognition | |
| CN116503392B (en) | Follicular region segmentation method for ovarian tissue analysis | |
| JPWO2008136098A1 (en) | Medical image processing apparatus and medical image processing method | |
| CN112384146A (en) | Identifying an optimal image from a plurality of ultrasound images | |
| Isaiah et al. | Ultrasonographic detection of airway obstruction in a model of obstructive sleep apnea | |
| CN110910404B (en) | Anti-noise data breast ultrasonic nodule segmentation method | |
| CN112801957A (en) | Pneumothorax automatic check out system based on ultrasonic strain formation of image | |
| CN113786239B (en) | Method and system for tracking and real-time early warning of surgical instruments under stomach and digestive tract | |
| CN116542883B (en) | Magnetic control capsule gastroscope image focus mucosa enhancement system | |
| US20170319107A1 (en) | Image-based detection and diagnosis of diastasis recti | |
| CN116934683A (en) | Method for assisting ultrasonic diagnosis of spleen wound by artificial intelligence | |
| US11941806B2 (en) | Methods and systems for automatic assessment of fractional limb volume and fat lean mass from fetal ultrasound scans | |
| US11120554B2 (en) | Image diagnosis apparatus, image diagnosis method, and program | |
| US9014440B2 (en) | Dental cysts detector | |
| CN110648333B (en) | Real-time segmentation system of mammary gland ultrasonic video image based on middle-intelligence theory | |
| CN113409312B (en) | Image processing method and device for biomedical images | |
| US11881301B2 (en) | Methods and systems for utilizing histogram views for improved visualization of three-dimensional (3D) medical images | |
| CN115661096B (en) | Image judging method for invasion length of lower esophageal segment of gastroesophageal junction cancer | |
| KR20180114596A (en) | Apparatus, and method for examining pulmonary function using face image, and computer readable recording medium for recoring the same | |
| Hu et al. | Automatic tracking algorithm in coaxial near-infrared laser ablation endoscope for fetus surgery |
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 |