CN111709906A - Medical image quality evaluation method and device - Google Patents
Medical image quality evaluation method and device Download PDFInfo
- Publication number
- CN111709906A CN111709906A CN202010283974.0A CN202010283974A CN111709906A CN 111709906 A CN111709906 A CN 111709906A CN 202010283974 A CN202010283974 A CN 202010283974A CN 111709906 A CN111709906 A CN 111709906A
- Authority
- CN
- China
- Prior art keywords
- network
- feature extraction
- medical image
- sub
- chest
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
- G06F18/21348—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis overcoming non-stationarity or permutations
-
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06T2207/10116—X-ray 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30008—Bone
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (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)
- Image Analysis (AREA)
Abstract
The invention provides a method and a device for evaluating the quality of a medical image, wherein the method comprises the following steps: acquiring a medical image sample, and labeling the medical image sample to obtain a training set; training a neural network detection model through a training set; acquiring a medical image to be evaluated; and inputting the medical image to be evaluated into the trained neural network detection model so as to output the evaluation result of the medical image to be evaluated. The invention can comprehensively and objectively carry out quality control evaluation on the medical image in real time.
Description
Technical Field
The invention relates to the technical field of medical image quality control, in particular to a quality evaluation method and a quality evaluation device for a medical image.
Background
CR (Computed Radiography)/DR (Digital Radiography, direct Digital flat panel X-ray imaging system) is one of the most popular devices in medical institutions, and is commonly owned by the primary medical institutions. The flat chest is the most common image examination method in routine physical examination and is also a necessary examination item for patient admission. Due to the fact that the brands of the medical institutions are numerous, the use levels of the medical institutions are different, the image quality is different, and the image quality directly influences the efficiency and accuracy of detection and diagnosis. Therefore, it is very necessary to ensure the image quality from the source through the quality control link.
At present, in image quality analysis, a quality control group periodically and randomly extracts partial images and carries out artificial comprehensive evaluation according to a quality control standard. However, the quality control method for X-ray chest radiograph based on manual spot check and scoring may not be able to perform quality control inspection for all medical institutions due to the shortage of human hands of quality control team. Meanwhile, the manual spot check only uses a very small number of samples in the mass data, has certain subjectivity and one-sidedness, cannot objectively and comprehensively reflect the overall shooting quality of the medical institution, and has bias on improving quality control measures. In addition, this method is retrospective and cannot be controlled in real time. In all the above cases, the image quality control operation may not achieve the expected effect.
Disclosure of Invention
The invention provides a quality evaluation method and a quality evaluation device for medical images, which can comprehensively and objectively evaluate the quality of the medical images in real time.
The technical scheme adopted by the invention is as follows:
a method of quality assessment of medical images, comprising the steps of: acquiring a medical image sample, and labeling the medical image sample to obtain a training set; training a neural network detection model through the training set; acquiring a medical image to be evaluated; and inputting the medical image to be evaluated into the trained neural network detection model so as to output the evaluation result of the medical image to be evaluated.
The medical image is an X-ray chest film.
The neural network detection model comprises a regional feature extraction network, a key point regression network and a classification network.
The regional feature extraction network comprises a scapula feature extraction sub-network, a chest piece edge feature extraction sub-network and a global feature extraction sub-network, the scapula feature extraction sub-network, the chest piece edge feature extraction sub-network and the global feature extraction sub-network all adopt a residual convolutional neural network as a backbone network, the scapula feature extraction sub-network is used for carrying out feature extraction on scapula regions of X-ray chest pieces to obtain scapula features, the chest piece edge feature extraction sub-network is used for carrying out feature extraction on four edge regions of the X-ray chest pieces, namely the upper edge region, the lower edge region, the left edge region, the right edge region and the left edge region to obtain edge features, and the global feature extraction sub-network is used for carrying out feature extraction on the whole X-ray chest pieces.
The key point regression network is used for regression positioning of T6 rib vertebra intersection points according to the global features to determine whether X-ray chest radiography is in the center, and the classification network is used for classifying whether scapulae are in the lung field or not according to the scapulae features and classifying whether the chest radiography is complete in the upper, lower, left and right directions according to the edge features.
A quality evaluation apparatus of a medical image, comprising: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a medical image sample and labeling the medical image sample to obtain a training set; a training module to train a neural network detection model through the training set; the second acquisition module is used for acquiring a medical image to be evaluated; and the evaluation module is used for inputting the medical image to be evaluated into the trained neural network detection model so as to output the evaluation result of the medical image to be evaluated.
The medical image is an X-ray chest film.
The neural network detection model comprises a regional feature extraction network, a key point regression network and a classification network.
The regional feature extraction network comprises a scapula feature extraction sub-network, a chest piece edge feature extraction sub-network and a global feature extraction sub-network, the scapula feature extraction sub-network, the chest piece edge feature extraction sub-network and the global feature extraction sub-network all adopt a residual convolutional neural network as a backbone network, the scapula feature extraction sub-network is used for carrying out feature extraction on scapula regions of X-ray chest pieces to obtain scapula features, the chest piece edge feature extraction sub-network is used for carrying out feature extraction on four edge regions of the X-ray chest pieces, namely the upper edge region, the lower edge region, the left edge region, the right edge region and the left edge region to obtain edge features, and the global feature extraction sub-network is used for carrying out feature extraction on the whole X-ray chest pieces.
The key point regression network is used for regression positioning of T6 rib vertebra intersection points according to the global features to determine whether X-ray chest radiography is in the center, and the classification network is used for classifying whether scapulae are in the lung field or not according to the scapulae features and classifying whether the chest radiography is complete in the upper, lower, left and right directions according to the edge features.
The invention has the beneficial effects that:
the invention trains the neural network detection model through the medical image sample, and obtains the evaluation result of the medical image to be evaluated through the trained neural network detection model, thereby being capable of carrying out quality control evaluation on the medical image comprehensively and objectively in real time.
Drawings
FIG. 1 is a flow chart of a method of quality assessment of a medical image according to an embodiment of the present invention;
FIG. 2 is a block diagram of a neural network detection model according to an embodiment of the present invention;
fig. 3 is a block diagram schematically illustrating a medical image quality evaluation apparatus according to an embodiment of the present invention.
Detailed Description
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.
As shown in fig. 1, the method for evaluating the quality of a medical image according to an embodiment of the present invention includes the steps of:
and S1, acquiring the medical image sample, and labeling the medical image sample to obtain a training set.
In one embodiment of the invention, the medical image is an X-ray chest film. The method can acquire a plurality of X-ray chest pictures as samples and respectively mark corresponding quality results, such as whether a certain X-ray chest picture shooting position is in the center, whether shoulder blades are in the field of the lung or not, and whether the chest pictures are up, down, left and right complete or not. Several chest X-ray samples containing labels may constitute a training set. It should be understood that the greater the number of samples in the training set, the more accurate the model trained subsequently, and the number of specific samples can be determined according to the actual evaluation requirement.
And S2, training the neural network detection model through the training set.
And S3, acquiring the medical image to be evaluated.
And S4, inputting the medical image to be evaluated into the trained neural network detection model to output the evaluation result of the medical image to be evaluated.
In one embodiment of the present invention, as shown in FIG. 2, the neural network detection model includes a regional feature extraction network, a keypoint regression network, and a classification network.
The regional feature extraction network comprises a scapula feature extraction sub-network, a chest piece edge feature extraction sub-network and a global feature extraction sub-network, the scapula feature extraction sub-network, the chest piece edge feature extraction sub-network and the global feature extraction sub-network all adopt a residual convolutional neural network as backbone networks, the scapula feature extraction sub-network is used for carrying out feature extraction on scapula regions of X-ray chest pieces to obtain scapula features, the chest piece edge feature extraction sub-network is used for carrying out feature extraction on four edge regions of the X-ray chest pieces, namely the upper edge region, the lower edge region, the left edge region, the right edge region and the left edge region to obtain edge features, and the global feature extraction sub-network is used for carrying out feature extraction on the whole X.
The key point regression network can perform regression positioning on T6 rib vertebra intersection points according to the global characteristics to determine whether X-ray chest radiography is in the center, the classification network can classify whether scapulae are in the lung field or not according to the scapulae characteristics, and can classify whether the chest radiography is complete or not according to the edge characteristics.
The training set obtained in step S1 may be input into the neural network detection model to obtain corresponding model parameters, thereby determining a model for medical image quality evaluation.
In one embodiment of the present invention, the medical image to be evaluated may be a positive position X-ray chest film, or a posterior-anterior position or anterior-posterior position X-ray chest film.
In one embodiment of the present invention, the medical image may be preprocessed, for example, pixel normalization, before being input into the neural network detection model.
Through the model training and evaluating steps, the evaluation results of whether the shooting position of the X-ray chest film to be evaluated is in the midpoint, whether the scapula is in the lung field or not, whether the chest film is complete up, down, left and right, and the like can be obtained.
According to the quality evaluation method of the medical image, the neural network detection model is trained through the medical image sample, and the evaluation result of the medical image to be evaluated is obtained through the trained neural network detection model, so that the quality control evaluation can be comprehensively and objectively carried out on the medical image in real time.
Corresponding to the quality evaluation method of the medical image in the embodiment, the invention also provides a quality evaluation device of the medical image.
As shown in fig. 3, the apparatus for evaluating the quality of a medical image according to an embodiment of the present invention includes a first obtaining module 10, a training module 20, a second obtaining module 30, and an evaluating module 40. The first obtaining module 10 is configured to obtain a medical image sample, and label the medical image sample to obtain a training set; the training module 20 is used for training the neural network detection model through a training set; the second obtaining module 30 is used for obtaining a medical image to be evaluated; the evaluation module 40 is configured to input the medical image to be evaluated into the trained neural network detection model, so as to output an evaluation result of the medical image to be evaluated.
In one embodiment of the invention, the medical image is an X-ray chest film. The method can acquire a plurality of X-ray chest pictures as samples and respectively mark corresponding quality results, such as whether a certain X-ray chest picture shooting position is in the center, whether shoulder blades are in the field of the lung or not, and whether the chest pictures are up, down, left and right complete or not. Several chest X-ray samples containing labels may constitute a training set. It should be understood that the greater the number of samples in the training set, the more accurate the model trained subsequently, and the number of specific samples can be determined according to the actual evaluation requirement.
In one embodiment of the present invention, as shown in FIG. 2, the neural network detection model includes a regional feature extraction network, a keypoint regression network, and a classification network.
The regional feature extraction network comprises a scapula feature extraction sub-network, a chest piece edge feature extraction sub-network and a global feature extraction sub-network, the scapula feature extraction sub-network, the chest piece edge feature extraction sub-network and the global feature extraction sub-network all adopt a residual convolutional neural network as backbone networks, the scapula feature extraction sub-network is used for carrying out feature extraction on scapula regions of X-ray chest pieces to obtain scapula features, the chest piece edge feature extraction sub-network is used for carrying out feature extraction on four edge regions of the X-ray chest pieces, namely the upper edge region, the lower edge region, the left edge region, the right edge region and the left edge region to obtain edge features, and the global feature extraction sub-network is used for carrying out feature extraction on the whole X.
The key point regression network can perform regression positioning on T6 rib vertebra intersection points according to the global characteristics to determine whether X-ray chest radiography is in the center, the classification network can classify whether scapulae are in the lung field or not according to the scapulae characteristics, and can classify whether the chest radiography is complete or not according to the edge characteristics.
The training set obtained by the first obtaining module 10 may be input into the neural network detection model to obtain corresponding model parameters, so as to determine a model for medical image quality evaluation.
In one embodiment of the present invention, the medical image to be evaluated may be a positive position X-ray chest film, or a posterior-anterior position or anterior-posterior position X-ray chest film.
In an embodiment of the present invention, the medical image may be pre-processed, for example, pixel normalized, by the second obtaining module 30 before being input into the neural network detection model.
Through the model training of the training module 20 and the evaluation of the evaluation module 40, the evaluation results such as whether the shooting position of the X-ray chest film to be evaluated is in the midpoint, whether the scapula is in the lung field or not, whether the chest film is complete in the upper, lower, left and right sides, and the like can be obtained.
According to the quality evaluation device of the medical image, the neural network detection model is trained through the medical image sample, and the evaluation result of the medical image to be evaluated is obtained through the trained neural network detection model, so that the quality control evaluation can be comprehensively and objectively carried out on the medical image in real time.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The meaning of "plurality" is two or more unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A method for quality assessment of medical images, comprising the steps of:
acquiring a medical image sample, and labeling the medical image sample to obtain a training set;
training a neural network detection model through the training set;
acquiring a medical image to be evaluated;
and inputting the medical image to be evaluated into the trained neural network detection model so as to output the evaluation result of the medical image to be evaluated.
2. The method of claim 1, wherein the medical image is an X-ray chest radiograph.
3. The method of claim 2, wherein the neural network detection model comprises a regional feature extraction network, a keypoint regression network, and a classification network.
4. The method according to claim 3, wherein the regional feature extraction network comprises a scapula feature extraction sub-network, a chest piece edge feature extraction sub-network and a global feature extraction sub-network, the scapula feature extraction sub-network, the chest piece edge feature extraction sub-network and the global feature extraction sub-network all use a residual convolutional neural network as a backbone network, the scapula feature extraction sub-network is used for feature extraction of scapula regions of X-ray chest pieces to obtain scapula features, the chest piece edge feature extraction sub-network is used for feature extraction of four edge regions of the X-ray chest pieces up and down to obtain edge features, and the global feature extraction sub-network is used for feature extraction of the whole X-ray chest pieces to obtain global features.
5. The method for quality assessment of medical images according to claim 4, wherein said keypoint regression network is used for regression positioning of T6 rib vertebra crossing points according to said global features to determine whether X-ray chest radiography is in the midpoint, said classification network is used for classifying whether scapulae are in the outside and inside of the lung field according to said scapulae features and classifying whether the chest radiography is complete or not according to said edge features.
6. A quality evaluation apparatus of a medical image, characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a medical image sample and labeling the medical image sample to obtain a training set;
a training module to train a neural network detection model through the training set;
the second acquisition module is used for acquiring a medical image to be evaluated;
and the evaluation module is used for inputting the medical image to be evaluated into the trained neural network detection model so as to output the evaluation result of the medical image to be evaluated.
7. The apparatus for quality evaluation of medical image according to claim 1, wherein said medical image is an X-ray chest radiograph.
8. The apparatus according to claim 7, wherein the neural network detection model includes a regional feature extraction network, a keypoint regression network, and a classification network.
9. The apparatus for evaluating the quality of a medical image according to claim 8, wherein the regional feature extraction network comprises a sub-network for scapula feature extraction, a sub-network for chest edge feature extraction, and a sub-network for global feature extraction, each of the sub-networks for scapula feature extraction, the sub-network for chest edge feature extraction, and the sub-network for global feature extraction adopts a residual convolutional neural network as a backbone network, the sub-network for scapula feature extraction is used for feature extraction of scapula regions of an X-ray chest film to obtain scapula features, the sub-network for chest edge feature extraction is used for feature extraction of four edge regions of the X-ray chest film to obtain edge features, and the sub-network for global feature extraction is used for feature extraction of the entire X-ray chest film to obtain global features.
10. The apparatus for quality evaluation of medical images according to claim 9, wherein said keypoint regression network is configured to regressively locate a T6 rib vertebra intersection point according to said global feature to determine whether the X-ray chest radiography is at the midpoint, and said classification network is configured to classify whether the scapulae are outside the lung field according to said scapulae feature and to classify whether the chest radiography is complete in the upper, lower, left and right directions according to said edge feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010283974.0A CN111709906A (en) | 2020-04-13 | 2020-04-13 | Medical image quality evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010283974.0A CN111709906A (en) | 2020-04-13 | 2020-04-13 | Medical image quality evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111709906A true CN111709906A (en) | 2020-09-25 |
Family
ID=72536747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010283974.0A Pending CN111709906A (en) | 2020-04-13 | 2020-04-13 | Medical image quality evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709906A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767307A (en) * | 2020-12-28 | 2021-05-07 | 上海联影智能医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN113112463A (en) * | 2021-03-31 | 2021-07-13 | 上海联影智能医疗科技有限公司 | Medical image quality evaluation method, electronic device, and storage medium |
| CN113160942A (en) * | 2021-04-14 | 2021-07-23 | 中国科学院深圳先进技术研究院 | Image data quality evaluation method and device, terminal equipment and readable storage medium |
| CN116128854A (en) * | 2023-02-03 | 2023-05-16 | 深圳市儿童医院 | Hip joint ultrasonic image quality assessment method based on convolutional neural network |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160678A (en) * | 2015-09-02 | 2015-12-16 | 山东大学 | Convolutional-neural-network-based reference-free three-dimensional image quality evaluation method |
| CN106326886A (en) * | 2016-11-07 | 2017-01-11 | 重庆工商大学 | Finger-vein image quality evaluation method and system based on convolutional neural network |
| CN107609493A (en) * | 2017-08-25 | 2018-01-19 | 广州视源电子科技股份有限公司 | Optimize the method and device of face picture Environmental Evaluation Model |
| WO2018036276A1 (en) * | 2016-08-22 | 2018-03-01 | 平安科技（深圳）有限公司 | Image quality detection method, device, server and storage medium |
| CN108335293A (en) * | 2018-01-31 | 2018-07-27 | 泰康保险集团股份有限公司 | The determination method and device of picture quality |
| CN108791299A (en) * | 2018-05-16 | 2018-11-13 | 浙江零跑科技有限公司 | A kind of driving fatigue detection of view-based access control model and early warning system and method |
| CN109740541A (en) * | 2019-01-04 | 2019-05-10 | 重庆大学 | A kind of pedestrian weight identifying system and method |
| CN109801256A (en) * | 2018-12-15 | 2019-05-24 | 华南理工大学 | A kind of image aesthetic quality appraisal procedure based on area-of-interest and global characteristics |
| CN109859168A (en) * | 2018-12-28 | 2019-06-07 | 上海联影智能医疗科技有限公司 | A kind of X-ray rabat picture quality determines method and device |
| CN109978132A (en) * | 2018-12-24 | 2019-07-05 | 中国科学院深圳先进技术研究院 | A kind of neural network method and system refining vehicle identification |
| CN110111344A (en) * | 2019-05-13 | 2019-08-09 | 广州锟元方青医疗科技有限公司 | Pathological section image grading method, apparatus, computer equipment and storage medium |
| CN110213663A (en) * | 2019-05-22 | 2019-09-06 | 深圳壹账通智能科技有限公司 | Audio and video playing method, computer equipment and computer readable storage medium |
| CN110335259A (en) * | 2019-06-25 | 2019-10-15 | 腾讯科技（深圳）有限公司 | A kind of medical image recognition methods, device and storage medium |
| US20190340753A1 (en) * | 2018-05-07 | 2019-11-07 | Zebra Medical Vision Ltd. | Systems and methods for detecting an indication of a visual finding type in an anatomical image |
| CN110659690A (en) * | 2019-09-25 | 2020-01-07 | 深圳市商汤科技有限公司 | Neural network construction method and device, electronic equipment and storage medium |
| CN110779937A (en) * | 2019-10-11 | 2020-02-11 | 上海航天精密机械研究所 | Casting product internal defect intelligent detection device |
| CN110798572A (en) * | 2019-10-25 | 2020-02-14 | Oppo（重庆）智能科技有限公司 | Method, device, electronic equipment and medium for lighting screen |
| CN110796656A (en) * | 2019-11-01 | 2020-02-14 | 上海联影智能医疗科技有限公司 | Image detection method, image detection device, computer equipment and storage medium |
-
2020
- 2020-04-13 CN CN202010283974.0A patent/CN111709906A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160678A (en) * | 2015-09-02 | 2015-12-16 | 山东大学 | Convolutional-neural-network-based reference-free three-dimensional image quality evaluation method |
| WO2018036276A1 (en) * | 2016-08-22 | 2018-03-01 | 平安科技（深圳）有限公司 | Image quality detection method, device, server and storage medium |
| CN106326886A (en) * | 2016-11-07 | 2017-01-11 | 重庆工商大学 | Finger-vein image quality evaluation method and system based on convolutional neural network |
| CN107609493A (en) * | 2017-08-25 | 2018-01-19 | 广州视源电子科技股份有限公司 | Optimize the method and device of face picture Environmental Evaluation Model |
| CN108335293A (en) * | 2018-01-31 | 2018-07-27 | 泰康保险集团股份有限公司 | The determination method and device of picture quality |
| US20190340753A1 (en) * | 2018-05-07 | 2019-11-07 | Zebra Medical Vision Ltd. | Systems and methods for detecting an indication of a visual finding type in an anatomical image |
| CN108791299A (en) * | 2018-05-16 | 2018-11-13 | 浙江零跑科技有限公司 | A kind of driving fatigue detection of view-based access control model and early warning system and method |
| CN109801256A (en) * | 2018-12-15 | 2019-05-24 | 华南理工大学 | A kind of image aesthetic quality appraisal procedure based on area-of-interest and global characteristics |
| CN109978132A (en) * | 2018-12-24 | 2019-07-05 | 中国科学院深圳先进技术研究院 | A kind of neural network method and system refining vehicle identification |
| CN109859168A (en) * | 2018-12-28 | 2019-06-07 | 上海联影智能医疗科技有限公司 | A kind of X-ray rabat picture quality determines method and device |
| CN109740541A (en) * | 2019-01-04 | 2019-05-10 | 重庆大学 | A kind of pedestrian weight identifying system and method |
| CN110111344A (en) * | 2019-05-13 | 2019-08-09 | 广州锟元方青医疗科技有限公司 | Pathological section image grading method, apparatus, computer equipment and storage medium |
| CN110213663A (en) * | 2019-05-22 | 2019-09-06 | 深圳壹账通智能科技有限公司 | Audio and video playing method, computer equipment and computer readable storage medium |
| CN110335259A (en) * | 2019-06-25 | 2019-10-15 | 腾讯科技（深圳）有限公司 | A kind of medical image recognition methods, device and storage medium |
| CN110659690A (en) * | 2019-09-25 | 2020-01-07 | 深圳市商汤科技有限公司 | Neural network construction method and device, electronic equipment and storage medium |
| CN110779937A (en) * | 2019-10-11 | 2020-02-11 | 上海航天精密机械研究所 | Casting product internal defect intelligent detection device |
| CN110798572A (en) * | 2019-10-25 | 2020-02-14 | Oppo（重庆）智能科技有限公司 | Method, device, electronic equipment and medium for lighting screen |
| CN110796656A (en) * | 2019-11-01 | 2020-02-14 | 上海联影智能医疗科技有限公司 | Image detection method, image detection device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767307A (en) * | 2020-12-28 | 2021-05-07 | 上海联影智能医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN113112463A (en) * | 2021-03-31 | 2021-07-13 | 上海联影智能医疗科技有限公司 | Medical image quality evaluation method, electronic device, and storage medium |
| CN113160942A (en) * | 2021-04-14 | 2021-07-23 | 中国科学院深圳先进技术研究院 | Image data quality evaluation method and device, terminal equipment and readable storage medium |
| CN116128854A (en) * | 2023-02-03 | 2023-05-16 | 深圳市儿童医院 | Hip joint ultrasonic image quality assessment method based on convolutional neural network |
| CN116128854B (en) * | 2023-02-03 | 2023-11-10 | 深圳市儿童医院 | Hip joint ultrasonic image quality assessment method based on convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709906A (en) | Medical image quality evaluation method and device | |
| CN107767376B (en) | X-ray bone age prediction method and system based on deep learning | |
| CN109859168B (en) | X-ray chest radiography image quality determination method and device | |
| ES2914387T3 (en) | immediate study | |
| JP6807820B2 (en) | Image search device, method and program | |
| KR20200095504A (en) | 3D medical image analysis method and system for identifying vertebral fractures | |
| CN109919230A (en) | Based on the pyramidal medical image pulmonary nodule detection method of cycle specificity | |
| CN108257132A (en) | A kind of method of the CT image quality measures based on machine learning | |
| CN105640577A (en) | Method and system automatically detecting local lesion in radiographic image | |
| CN108846828A (en) | A kind of pathological image target-region locating method and system based on deep learning | |
| CN112699868A (en) | Image identification method and device based on deep convolutional neural network | |
| Tang et al. | CNN-based qualitative detection of bone mineral density via diagnostic CT slices for osteoporosis screening | |
| US20230057933A1 (en) | Storage medium, diagnosis support apparatus and diagnosis support method | |
| CN111640093A (en) | Quality control method for medical image and computer-readable storage medium | |
| CN109919912A (en) | A kind of quality evaluating method and device of medical image | |
| CN108324297A (en) | Image analysis method for assessing image data | |
| Caliskan et al. | A pilot study of a deep learning approach to submerged primary tooth classification and detection | |
| Flaucher et al. | Smartphone-based colorimetric analysis of urine test strips for at-home prenatal care | |
| Chang et al. | Development and validation of a deep learning-based algorithm for colonoscopy quality assessment | |
| Price et al. | Computerized diagnostic decision support system for the classification of preinvasive cervical squamous lesions | |
| Davis | Predictive modelling of bone ageing | |
| CN107680670A (en) | Medical image identification and diagnostic system and the method for a kind of no territory restriction | |
| TWI746249B (en) | Method for assessing cardiothoracic ratio and cardiothoracic ratio assessment system | |
| CN113537407A (en) | Image data evaluation processing method and device based on machine learning | |
| CN113592834A (en) | X-ray chest radiography image quality determination method and device |
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 |