CN113610785A - Pneumoconiosis early warning method and device based on intelligent image and storage medium - Google Patents
Pneumoconiosis early warning method and device based on intelligent image and storage medium Download PDFInfo
- Publication number
- CN113610785A CN113610785A CN202110843831.5A CN202110843831A CN113610785A CN 113610785 A CN113610785 A CN 113610785A CN 202110843831 A CN202110843831 A CN 202110843831A CN 113610785 A CN113610785 A CN 113610785A
- Authority
- CN
- China
- Prior art keywords
- pneumoconiosis
- image
- result
- segmentation result
- images
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
-
- 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
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a pneumoconiosis early warning method, a pneumoconiosis early warning device and a storage medium based on intelligent images, wherein the method comprises the following steps: preprocessing the received CT image; carrying out rough segmentation and fine segmentation on the preprocessed pneumoconiosis CT image in sequence based on the recognition model to obtain a rough segmentation result and a fine segmentation result; performing fusion processing on the rough segmentation result and the fine segmentation result to obtain a fusion result; and performing pneumoconiosis early warning based on the fusion result, clinical occupational history data of relevant industrial personnel and hematological indexes. Presetting a training sample set, wherein the training sample set comprises a plurality of frames of CT images; the identification model identifies the CT images in the training sample set to sequentially obtain a rough segmentation result, a fine segmentation result and a fusion result; the identification model compares the rough segmentation result, the fine segmentation result and the fusion result with the pneumoconiosis information and/or the standard information to update the parameter gradient of the identification model. The invention can effectively identify early lung lesions and carry out early warning on high risk groups with potential pneumoconiosis according to the identification result.
Description
Technical Field
The invention relates to the technical field of pneumoconiosis identification, in particular to a pneumoconiosis early warning method and device based on intelligent images and a storage medium.
Background
Pneumoconiosis is a systemic disease mainly characterized by diffuse fibrosis of lung tissue due to prolonged inhalation of productive dust during professional activities and retention in the lung. According to the occupational disease onset conditions which are reported in recent years in China, the pneumoconiosis is still the first occupational disease.
According to the national pneumoconiosis diagnosis standard, the pneumoconiosis is classified into four types according to grades: the grade of the pneumoconiosis is mainly identified by chest pictures shot by X-rays, the traditional X-ray imaging is to project X-rays penetrating through a human body on a film clamped between two intensifying screens at two sides, the image is an analog signal, the image information can only be recorded on the film, and the image is real and cannot be modified. With the development of modern science and technology, images of modern X-ray imaging technologies such as CR, DR and CT are digitized. The shooting result can be input into a computer for processing imaging.
When a first-stage pneumoconiosis CT image is identified, a plurality of small lung lesions cannot be accurately identified, and therefore, misjudgment can occur during early stage lung lesion identification.
Disclosure of Invention
The embodiment of the invention provides a pneumoconiosis early warning method, a pneumoconiosis early warning device and a storage medium based on intelligent images, which can effectively identify early lung lesions and carry out pneumoconiosis early warning according to an identification result.
In a first aspect of the embodiments of the present invention, an intelligent image-based pneumoconiosis early warning method is provided, including:
preprocessing the received CT image;
carrying out rough segmentation and fine segmentation on the preprocessed pneumoconiosis CT image in sequence based on the recognition model to obtain a rough segmentation result and a fine segmentation result;
performing fusion processing on the rough segmentation result and the fine segmentation result to obtain a fusion result;
and carrying out pneumoconiosis early warning based on the fusion result.
Optionally, in a possible implementation manner of the first aspect, the training of the recognition model includes:
presetting a training sample set, wherein the training sample set comprises a plurality of frames of CT images, and each frame of CT image respectively has pneumoconiosis information and/or standard information;
the identification model identifies the CT images in the training sample set to sequentially obtain a rough segmentation result, a fine segmentation result and a fusion result;
the identification model compares the rough segmentation result, the fine segmentation result and the fusion result with the pneumoconiosis information and/or the standard information to update the parameter gradient of the identification model.
Optionally, in a possible implementation manner of the first aspect, before the identifying the CT images in the training sample set by the identification model, the method further includes:
acquiring a CT image at the current moment, and selecting CT images of a preset number of frames before and/or after the CT image;
and respectively inputting the CT image at the current moment and the selected CT image into the recognition model for training.
Optionally, in a possible implementation manner of the first aspect, before the identifying the CT images in the training sample set by the identification model, the method further includes:
and generating a 48 × 64 × 64 size volume data block by adopting a sliding window method for the CT image as an input of a recognition model for training.
Optionally, in a possible implementation manner of the first aspect, the preprocessing the received CT image includes:
and sequentially carrying out layer thickness segmentation, gray level correction, image noise and artifact removal on the CT image.
In a second aspect of the embodiments of the present invention, an intelligent image-based pneumoconiosis warning device is provided, including:
the preprocessing module is used for preprocessing the received CT image;
the segmentation module is used for sequentially carrying out rough segmentation and fine segmentation on the preprocessed pneumoconiosis CT image based on the recognition model to obtain a rough segmentation result and a fine segmentation result;
the fusion module is used for carrying out fusion processing on the rough segmentation result and the fine segmentation result to obtain a fusion result;
and the early warning module is used for carrying out pneumoconiosis early warning based on the fusion result.
Optionally, in a possible implementation manner of the second aspect, the method further includes:
the device comprises a setting unit, a processing unit and a processing unit, wherein the setting unit is used for presetting a training sample set, the training sample set comprises a plurality of frames of CT images, and each frame of CT image respectively has pneumoconiosis information and/or standard information;
the identification unit is used for enabling the identification model to identify the CT images in the training sample set, and obtaining a rough segmentation result, a fine segmentation result and a fusion result in sequence;
and the updating unit is used for enabling the identification model to compare the rough segmentation result, the fine segmentation result and the fusion result with the pneumoconiosis information and/or the standard information so as to update the parameter gradient of the identification model.
Optionally, in a possible implementation manner of the second aspect, the method further includes:
the first selection unit is used for acquiring the CT image at the current moment and selecting the CT images of the preset number of frames before and/or after the CT image;
and the first training unit is used for respectively inputting the CT image at the current moment and the selected CT image into the recognition model for training.
Optionally, in a possible implementation manner of the second aspect, the method further includes:
and the second training unit is used for generating a 48 × 64 × 64 size volume data block by adopting a sliding window method for the CT image and taking the volume data block as the input of the recognition model for training.
Alternatively, in one possible implementation form of the first aspect,
in a second aspect of the embodiments of the present invention, there is provided a method for generating a clock signal
In a third aspect of the embodiments of the present invention, a readable storage medium is provided, in which a computer program is stored, which, when being executed by a processor, is adapted to carry out the method according to the first aspect of the present invention and various possible designs of the first aspect of the present invention.
The pneumoconiosis early warning method, the device and the storage medium based on the intelligent image can be used for deeply learning CT images of normal people and first-stage pneumoconiosis people, calculating the relevant weight and coefficient of the identified focus, training the identification model, early warning on lung pneumoconiosis relevant lesion and effectively improving accuracy and efficiency of pneumoconiosis screening. Moreover, early warning can discover the high risk group of pneumoconiosis among the related industrial personnel of the coal mine, and intervention can be taken as early as possible, so that the possibility of converting to pneumoconiosis is reduced.
Drawings
Fig. 1 is a flowchart of a pneumoconiosis warning method based on intelligent images;
FIG. 2 is a schematic diagram of CT image recognition by a recognition model;
fig. 3 is a structural diagram of a pneumoconiosis warning device based on intelligent 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 with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and 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.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that, in the present invention, "a plurality" means two or more. "and/or" is merely an association describing an associated object, meaning that three relationships may exist, for example, and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "comprises A, B and C" and "comprises A, B, C" means that all three of A, B, C comprise, "comprises A, B or C" means that one of A, B, C comprises, "comprises A, B and/or C" means that any 1 or any 2 or 3 of A, B, C comprises.
It should be understood that in the present invention, "B corresponding to a", "a corresponds to B", or "B corresponds to a" means that B is associated with a, and B can be determined from a. Determining B from a does not mean determining B from a alone, but may be determined from a and/or other information. And the matching of A and B means that the similarity of A and B is greater than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
The invention provides an intelligent image-based pneumoconiosis early warning method, which is shown in a flowchart of a first implementation mode in figure 1 and comprises the following steps:
and step S110, preprocessing the received CT image.
Wherein, step S110 includes:
and sequentially carrying out layer thickness segmentation, gray level correction, image noise and artifact removal on the CT image. By preprocessing the CT image, the processed CT image does not generate errors in the segmentation process, so that the accuracy of the recognition result or the training sample is guaranteed.
In the intelligent detection task of pneumoconiosis, many small focuses (<1mm) are identified, for example, first stage pneumoconiosis, but manual labeling of these small focuses is laborious and easy to miss, which makes it difficult to identify the small focuses in lung by supervised learning. Therefore, the invention adopts an unsupervised learning mode to detect the pulmonary tiny focus. The unsupervised learning method utilizes the CNN network to extract features and then realizes the detection and identification of the target through a clustering strategy.
And S120, carrying out rough segmentation and fine segmentation on the preprocessed pneumoconiosis CT image in sequence based on the recognition model to obtain a rough segmentation result and a fine segmentation result.
In step S120, as shown in fig. 2, the 2D CNN and the 3D CNN are respectively used to perform segmentation of the lung organ, and a coarse segmentation result and a fine segmentation result are obtained. The 2D CNN network is to extract overall features, and the 3D CNN network is to extract rich detailed information. The overall characteristics of the lung image are guaranteed through the 2D CNN network, the detail characteristics of the lung image are guaranteed through the 3D CNN network, and then an accurate segmentation result is obtained.
And S130, carrying out fusion processing on the rough segmentation result and the fine segmentation result to obtain a fusion result. And fusing the rough segmentation result and the fine segmentation result in an addition mode to obtain a fusion result, so that the fusion result respectively comprises an integral feature and a detail feature.
And S140, carrying out pneumoconiosis early warning based on the fusion result.
After the fusion result is obtained, the focus of <1mm can be detected, and if the focus of <1mm exists in the lung in the fusion result, the pneumoconiosis early warning is carried out at the moment.
In an embodiment of step S140, the invention may also perform a pneumoconiosis warning on the relevant industrial personnel by combining the fusion result and the clinical professional history data, that is, perform the pneumoconiosis warning based on the fusion result, the clinical professional history data of the relevant industrial personnel, and the hematological index. Wherein, the clinical occupational history data includes age, sex, work category, occupational age, etc., and the hematological indicators include biochemistry, gene detection, etc. For example, if the relevant industry is older, has a longer occupational age, shows a less functional lung in the gene, etc., the probability of producing pneumoconiosis will be higher.
The lung is identified through the identification model, tissues such as blood vessels, bronchus and the like in the CT image are removed, the region of interest in the CT image is obtained, the region of interest is only the lung, micro nodules and abnormal lung textures in the region of interest are identified through the 2D CNN network, and the blood vessels and the bronchus in the region of interest are identified through the 3D CNN network. And fusing the recognition results of the 2D CNN and the 3D CNN to obtain a three-dimensional visual image of the organ.
In one possible embodiment, the recognition model is trained by the steps comprising:
presetting a training sample set, wherein the training sample set comprises a plurality of frames of CT images, and each frame of CT image respectively has pneumoconiosis information and/or standard information.
The identification model identifies the CT images in the training sample set, and a rough segmentation result, a fine segmentation result and a fusion result are obtained in sequence.
The identification model compares the rough segmentation result, the fine segmentation result and the fusion result with the pneumoconiosis information and/or the standard information to update the parameter gradient of the identification model.
In one possible embodiment, before the recognition model recognizes the CT images in the training sample set, the method further includes:
acquiring a CT image at the current moment, and selecting CT images of a preset number of frames before and/or after the CT image;
and respectively inputting the CT image at the current moment and the selected CT image into the recognition model for training.
In order to alleviate the deficiency of the spatial feature extraction capability of the 2D CNN in the process of training the recognition model, the technical scheme provided by the invention combines a plurality of frames of medical images together to be used as the input of the network for training the model, for example, the original input image is 512 multiplied by 1, and the images of the previous and next 4 frames are combined at present, so that the size of the input image is 512 multiplied by 9.
In one possible embodiment, before the recognition model recognizes the CT images in the training sample set, the method further includes:
and generating a 48 × 64 × 64 size volume data block by adopting a sliding window method for the CT image as an input of a recognition model for training.
Because of the video memory limitation, it is difficult to train the 3D CNN network on the original image size, so this project generates 48 × 64 × 64 volumetric data blocks as the input of the network by using the sliding window method, and trains the model.
The recognition model provided by the invention is used for preprocessing the medical image (removing blood vessels, bronchus and other tissues in the medical image). And then, carrying out segmentation on the suspected lesion area by using an unsupervised segmentation network. Because the suspected lesion needing to be processed is small and has weak dependence on space, the identification requirement can be met by a strategy of combining adjacent multiframe medical images.
In addition, at present, many unsupervised segmentation networks are based on the 2D CNN network, and many pre-training models can be used to improve the overall segmentation effect, so the 2D unsupervised segmentation network is adopted for lesion identification in the project.
The invention also provides a pneumoconiosis early warning device based on intelligent images, which is shown in the figure and has a schematic structural diagram, and the device comprises:
the preprocessing module is used for preprocessing the received CT image;
the segmentation module is used for sequentially carrying out rough segmentation and fine segmentation on the preprocessed pneumoconiosis CT image based on the recognition model to obtain a rough segmentation result and a fine segmentation result;
the fusion module is used for carrying out fusion processing on the rough segmentation result and the fine segmentation result to obtain a fusion result;
and the early warning module is used for carrying out pneumoconiosis early warning based on the fusion result.
In one possible embodiment, the method further comprises:
the device comprises a setting unit, a processing unit and a processing unit, wherein the setting unit is used for presetting a training sample set, the training sample set comprises a plurality of frames of CT images, and each frame of CT image respectively has pneumoconiosis information and/or standard information;
the identification unit is used for enabling the identification model to identify the CT images in the training sample set, and obtaining a rough segmentation result, a fine segmentation result and a fusion result in sequence;
and the updating unit is used for enabling the identification model to compare the rough segmentation result, the fine segmentation result and the fusion result with the pneumoconiosis information and/or the standard information so as to update the parameter gradient of the identification model.
In one possible embodiment, the method further comprises:
the first selection unit is used for acquiring the CT image at the current moment and selecting the CT images of the preset number of frames before and/or after the CT image;
and the first training unit is used for respectively inputting the CT image at the current moment and the selected CT image into the recognition model for training.
In one possible embodiment, the method further comprises:
and the second training unit is used for generating a 48 × 64 × 64 size volume data block by adopting a sliding window method for the CT image and taking the volume data block as the input of the recognition model for training.
The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Additionally, the ASIC may reside in user equipment. Of course, the processor and the readable storage medium may also reside as discrete components in a communication device. The readable storage medium may be a read-only memory (ROM), a random-access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
The present invention also provides a program product comprising execution instructions stored in a readable storage medium. The at least one processor of the device may read the execution instructions from the readable storage medium, and the execution of the execution instructions by the at least one processor causes the device to implement the methods provided by the various embodiments described above.
In the above embodiments of the terminal or the server, it should be understood that the Processor may be a Central Processing Unit (CPU), other general-purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A pneumoconiosis early warning method based on intelligent images is characterized by comprising the following steps:
preprocessing the received CT image;
carrying out rough segmentation and fine segmentation on the preprocessed pneumoconiosis CT image in sequence based on the recognition model to obtain a rough segmentation result and a fine segmentation result;
performing fusion processing on the rough segmentation result and the fine segmentation result to obtain a fusion result;
and carrying out pneumoconiosis early warning based on the fusion result.
2. The pneumoconiosis warning method based on intelligent image as claimed in claim 1,
training the recognition model by:
presetting a training sample set, wherein the training sample set comprises a plurality of frames of CT images, and each frame of CT image respectively has pneumoconiosis information and/or standard information;
the identification model identifies the CT images in the training sample set to sequentially obtain a rough segmentation result, a fine segmentation result and a fusion result;
the identification model compares the rough segmentation result, the fine segmentation result and the fusion result with the pneumoconiosis information and/or the standard information to update the parameter gradient of the identification model.
3. The pneumoconiosis warning method based on intelligent image as claimed in claim 2,
before the recognition model recognizes the CT images in the training sample set, the method further comprises the following steps:
acquiring a CT image at the current moment, and selecting CT images of a preset number of frames before and/or after the CT image;
and respectively inputting the CT image at the current moment and the selected CT image into the recognition model for training.
4. The pneumoconiosis warning method based on intelligent image as claimed in claim 2,
before the recognition model recognizes the CT images in the training sample set, the method further comprises the following steps:
and generating a 48 × 64 × 64 size volume data block by adopting a sliding window method for the CT image as an input of a recognition model for training.
5. The pneumoconiosis warning method based on intelligent image as claimed in claim 1,
preprocessing the received CT images includes:
and sequentially carrying out layer thickness segmentation, gray level correction, image noise and artifact removal on the CT image.
6. The utility model provides a pneumoconiosis early warning device based on intelligence image which characterized in that includes:
the preprocessing module is used for preprocessing the received CT image;
the segmentation module is used for sequentially carrying out rough segmentation and fine segmentation on the preprocessed pneumoconiosis CT image based on the recognition model to obtain a rough segmentation result and a fine segmentation result;
the fusion module is used for carrying out fusion processing on the rough segmentation result and the fine segmentation result to obtain a fusion result;
and the early warning module is used for carrying out pneumoconiosis early warning based on the fusion result.
7. The pneumoconiosis warning device based on intelligent images as claimed in claim 6, further comprising:
the device comprises a setting unit, a processing unit and a processing unit, wherein the setting unit is used for presetting a training sample set, the training sample set comprises a plurality of frames of CT images, and each frame of CT image respectively has pneumoconiosis information and/or standard information;
the identification unit is used for enabling the identification model to identify the CT images in the training sample set, and obtaining a rough segmentation result, a fine segmentation result and a fusion result in sequence;
and the updating unit is used for enabling the identification model to compare the rough segmentation result, the fine segmentation result and the fusion result with the pneumoconiosis information and/or the standard information so as to update the parameter gradient of the identification model.
8. The pneumoconiosis warning device based on intelligent images as claimed in claim 7,
further comprising:
the first selection unit is used for acquiring the CT image at the current moment and selecting the CT images of the preset number of frames before and/or after the CT image;
and the first training unit is used for respectively inputting the CT image at the current moment and the selected CT image into the recognition model for training.
9. The pneumoconiosis warning device based on intelligent images as claimed in claim 7,
further comprising:
and the second training unit is used for generating a 48 × 64 × 64 size volume data block by adopting a sliding window method for the CT image and taking the volume data block as the input of the recognition model for training.
10. A readable storage medium, in which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110843831.5A CN113610785A (en) | 2021-07-26 | 2021-07-26 | Pneumoconiosis early warning method and device based on intelligent image and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110843831.5A CN113610785A (en) | 2021-07-26 | 2021-07-26 | Pneumoconiosis early warning method and device based on intelligent image and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610785A true CN113610785A (en) | 2021-11-05 |
Family
ID=78305374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110843831.5A Pending CN113610785A (en) | 2021-07-26 | 2021-07-26 | Pneumoconiosis early warning method and device based on intelligent image and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610785A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760874A (en) * | 2016-03-08 | 2016-07-13 | 中国科学院苏州生物医学工程技术研究所 | CT image processing system and method for pneumoconiosis |
| CN108510489A (en) * | 2018-03-30 | 2018-09-07 | 四川元匠科技有限公司 | A kind of pneumoconiosis detection method and system based on deep learning |
| CN109598727A (en) * | 2018-11-28 | 2019-04-09 | 北京工业大学 | A kind of CT image pulmonary parenchyma three-dimensional semantic segmentation method based on deep neural network |
| CN110428896A (en) * | 2019-04-22 | 2019-11-08 | 应急总医院 | Occupational pneumoconiosis assists screening model of mind |
| CN111127482A (en) * | 2019-12-20 | 2020-05-08 | 广州柏视医疗科技有限公司 | CT image lung trachea segmentation method and system based on deep learning |
| CN111429421A (en) * | 2020-03-19 | 2020-07-17 | 北京推想科技有限公司 | Model generation method, medical image segmentation method, device, equipment and medium |
| CN111768382A (en) * | 2020-06-30 | 2020-10-13 | 重庆大学 | Interactive segmentation method based on lung nodule growth form |
| CN111798424A (en) * | 2020-06-30 | 2020-10-20 | 广西医准智能科技有限公司 | Medical image-based nodule detection method and device and electronic equipment |
| CN112819819A (en) * | 2021-02-26 | 2021-05-18 | 泰康保险集团股份有限公司 | Pneumoconiosis grading method, device, medium and equipment based on deep learning |
| CN112991269A (en) * | 2021-02-07 | 2021-06-18 | 复旦大学 | Identification and classification method for lung CT image |
| CN113096109A (en) * | 2021-04-22 | 2021-07-09 | 四川大学 | Lung medical image analysis method, device and system |
-
2021
- 2021-07-26 CN CN202110843831.5A patent/CN113610785A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760874A (en) * | 2016-03-08 | 2016-07-13 | 中国科学院苏州生物医学工程技术研究所 | CT image processing system and method for pneumoconiosis |
| CN108510489A (en) * | 2018-03-30 | 2018-09-07 | 四川元匠科技有限公司 | A kind of pneumoconiosis detection method and system based on deep learning |
| CN109598727A (en) * | 2018-11-28 | 2019-04-09 | 北京工业大学 | A kind of CT image pulmonary parenchyma three-dimensional semantic segmentation method based on deep neural network |
| CN110428896A (en) * | 2019-04-22 | 2019-11-08 | 应急总医院 | Occupational pneumoconiosis assists screening model of mind |
| CN111127482A (en) * | 2019-12-20 | 2020-05-08 | 广州柏视医疗科技有限公司 | CT image lung trachea segmentation method and system based on deep learning |
| CN111429421A (en) * | 2020-03-19 | 2020-07-17 | 北京推想科技有限公司 | Model generation method, medical image segmentation method, device, equipment and medium |
| CN111768382A (en) * | 2020-06-30 | 2020-10-13 | 重庆大学 | Interactive segmentation method based on lung nodule growth form |
| CN111798424A (en) * | 2020-06-30 | 2020-10-20 | 广西医准智能科技有限公司 | Medical image-based nodule detection method and device and electronic equipment |
| CN112991269A (en) * | 2021-02-07 | 2021-06-18 | 复旦大学 | Identification and classification method for lung CT image |
| CN112819819A (en) * | 2021-02-26 | 2021-05-18 | 泰康保险集团股份有限公司 | Pneumoconiosis grading method, device, medium and equipment based on deep learning |
| CN113096109A (en) * | 2021-04-22 | 2021-07-09 | 四川大学 | Lung medical image analysis method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232383B (en) | Focus image recognition method and focus image recognition system based on deep learning model | |
| CN108464840B (en) | Automatic detection method and system for breast lumps | |
| CN108133476B (en) | Method and system for automatically detecting pulmonary nodules | |
| CN109543526B (en) | True and false facial paralysis recognition system based on depth difference characteristics | |
| KR102043130B1 (en) | The method and apparatus for computer aided diagnosis | |
| CN109858540B (en) | Medical image recognition system and method based on multi-mode fusion | |
| CN111553892B (en) | Lung nodule segmentation calculation method, device and system based on deep learning | |
| CN111462049B (en) | Automatic lesion area form labeling method in mammary gland ultrasonic radiography video | |
| CN1934589A (en) | Systems and methods providing automated decision support for medical imaging | |
| CN113420826B (en) | Liver focus image processing system and image processing method | |
| CN111667456A (en) | Method and device for detecting vascular stenosis in coronary artery X-ray sequence radiography | |
| CN110838114B (en) | Pulmonary nodule detection method, device and computer storage medium | |
| CN114782307A (en) | Enhanced CT image colorectal cancer staging auxiliary diagnosis system based on deep learning | |
| CN114581375A (en) | Method, device and storage medium for automatically detecting focus of wireless capsule endoscope | |
| KR100998630B1 (en) | Method for automatic classifier of lung diseases | |
| CN115272647A (en) | Lung image recognition processing method and system | |
| CN112579808A (en) | Data annotation processing method, device and system | |
| CN111754485A (en) | Artificial intelligence ultrasonic auxiliary system for liver | |
| CN111612749B (en) | Focus detection method and device based on lung image | |
| CN112861881A (en) | Honeycomb lung recognition method based on improved MobileNet model | |
| CN115880266B (en) | Intestinal polyp detection system and method based on deep learning | |
| CN113610785A (en) | Pneumoconiosis early warning method and device based on intelligent image and storage medium | |
| CN113488144B (en) | Slice image processing method | |
| CN115375632A (en) | Lung nodule intelligent detection system and method based on CenterNet model | |
| CN113554640A (en) | AI model training method, use method, computer device and storage medium |
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 |