CN111179252B - Cloud platform-based digestive tract disease focus auxiliary identification and positive feedback system - Google Patents
Cloud platform-based digestive tract disease focus auxiliary identification and positive feedback system Download PDFInfo
- Publication number
- CN111179252B CN111179252B CN201911396391.2A CN201911396391A CN111179252B CN 111179252 B CN111179252 B CN 111179252B CN 201911396391 A CN201911396391 A CN 201911396391A CN 111179252 B CN111179252 B CN 111179252B
- Authority
- CN
- China
- Prior art keywords
- digestive tract
- cloud platform
- inference model
- image
- inference
- 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.)
- Active
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- 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
- G06T2207/30—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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Endoscopes (AREA)
Abstract
The invention discloses a cloud platform-based digestive tract focus auxiliary identification and positive feedback system, which comprises: the data acquisition device is configured to acquire an alimentary canal image to be identified and transmit the alimentary canal image to the cloud platform; the cloud platform is configured to establish an inference model, construct a training set and carry out optimization training on the inference model; deducing the digestive tract position and the lesion type of the received image by using the deduction model, and respectively storing the image and the recognition result of the digestive tract lesion; the online error correction module is configured to enable the doctor client to check the inferred result online, and label and correct the inferred error result; and the online optimization module is configured to add the corrected images into the training set and train the inference model again. The invention can improve the accuracy of digestive tract focus identification and improve the detection rate of digestive system diseases.
Description
Technical Field
The invention relates to the technical field of cloud platform data processing, in particular to a digestive tract lesion auxiliary identification and positive feedback system based on a cloud platform.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The judgment of the digestive tract diseases usually adopts the steps of obtaining a digestive tract image through a digestive tract endoscope, and then analyzing and identifying the image to judge whether a focus exists.
At present, analysis and identification of digestive tract images are usually realized by visual observation of doctors and manual marking of lesion positions, but because artificial intelligent identification models and products are distributed in multiple departments of multiple hospitals, the number of digestive endoscopy images generated every day is huge, data is private data, and meanwhile, the data needs to be collected to a uniform position, so that data sharing is difficult, the accuracy of data identification is low, and missed diagnosis and misdiagnosis are easily caused.
Disclosure of Invention
In order to solve the problems, the invention provides a cloud platform-based auxiliary identification and positive feedback system for the digestive tract focus, which is used for carrying out auxiliary identification on the digestive tract focus based on the cloud platform, can realize data sharing, can reduce the calculation pressure of edge equipment, and can ensure the data safety of an identification model.
In some embodiments, the following technical scheme is adopted:
digestive tract focus auxiliary identification and positive feedback system based on cloud platform includes:
the data acquisition device is configured to acquire an alimentary canal image to be identified and transmit the alimentary canal image to the cloud platform;
the cloud platform is configured to establish an inference model, construct a training set and carry out optimization training on the inference model; performing digestive tract lesion inference on the received image by using the inference model, and respectively storing the image and a digestive tract lesion identification result;
the online error correction module is configured to enable the doctor client to check the inferred result online, and label and correct the inferred error result;
and the online optimization module is configured to add the corrected images into the training set and train the inference model again.
Specifically, the cloud platform includes:
at least one inference unit: the system is configured to establish an inference model and infer the type of the digestive tract focus and the focus position on the image;
at least one training unit: configured to optimally train the inference model;
at least one file storage unit: configured to store the received image;
a data storage unit: is configured to store the inference result.
After receiving a request for performing digestive tract lesion inference on an image, the cloud platform uniformly distributes the request to corresponding inference units in a load balancing mode.
In other embodiments, the following technical solutions are adopted:
a terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions adapted to be loaded by a processor and for performing the following process:
acquiring a digestive tract image to be identified, and transmitting the digestive tract image to a cloud platform;
establishing an inference model by the cloud platform, and constructing a training set to carry out optimization training on the inference model; performing digestive tract lesion inference on the received image by using the inference model, and respectively storing the image and a digestive tract lesion identification result;
the doctor client checks the inferred result on line, and labels and corrects the inferred result;
and adding the corrected images into a training set, and re-training the inference model.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, intelligent auxiliary identification of the digestive tract lesion is realized through the Internet and the cloud computing technology, and data sharing can be realized; the medical expert can correct the focus structure with the recognition error on line, and an AI algorithm engineer can optimize the algorithm and update the model on line aiming at the image with the recognition error, thereby continuously improving the recognition performance of the model, further improving the accuracy of the recognition of the digestive tract focus and improving the detection rate of digestive system diseases.
By arranging a plurality of inference servers on the cloud platform, parallel processing of data can be realized, and the data processing capacity of the cloud platform is improved.
Through a plurality of training servers, the training speed of the inference model can be improved, and meanwhile, the identification accuracy of the inference model is improved through continuous optimization of a training set.
Drawings
Fig. 1 is a schematic structural diagram of a cloud platform according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a working process of a cloud platform-based digestive tract lesion auxiliary identification and positive feedback system in an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
In one or more embodiments, the present invention provides a system for assisted identification and positive feedback of a digestive tract lesion based on a cloud platform, comprising:
(1) the data acquisition device is configured to acquire an alimentary canal image to be identified and transmit the alimentary canal image to the cloud platform;
specifically, the doctor acquires an image of the digestive tract to be identified through a graphic workstation. The image-text workstation is software for recording the inspection process and acquires the image of the endoscope through a video acquisition card;
and the image-text workstation calls a Web API (application program interface) of the cloud platform through a computer network to submit the digestive tract image to the cloud platform.
(2) The cloud platform is configured to establish an inference model, construct a training set and carry out optimization training on the inference model; performing digestive tract lesion inference on the received image by using the inference model, and respectively storing digestive tract lesion identification results (including types and positions);
specifically, referring to fig. 1, the cloud platform includes:
at least one inference unit: the system is configured to establish an inference model and infer the type of the digestive tract focus and the focus position on the image;
at least one training unit: configured to optimally train the inference model;
at least one file storage unit: configured to store the received image;
a data storage unit: is configured to store the inference result.
The cloud platform forwards the digestive tract lesion inference application to one inference server by using a load balancing technology, each inference unit corresponds to one inference server, and the cloud platform can increase data inference capacity by increasing the number of the inference servers so as to deal with recognition of a large number of digestive tract images.
And the inference server calls an inference model to identify the position and the type of the digestive tract lesion contained in the image and returns an identification result to the image-text workstation according to the original path.
The inference server stores the pictures in a file server, each file storage unit corresponds to one file server, and simultaneously stores the identification result in a database server (namely a data storage unit).
The cloud platform can expand the storage space by increasing the number of the file servers, and upload the stored images to the file servers, so that local file storage can be reduced, and local storage resources can be optimized.
The optimal training of the inference model is realized through a training unit; each training unit corresponds to one training server, and the cloud platform can improve the training speed by increasing the number of the training servers.
In this embodiment, the training unit is configured to acquire an image of a gastrointestinal region, mark a category to be identified and an auxiliary category for inferring an interference image, and construct a training set, where the category to be identified includes a first-level category and a second-level category, and the second-level category belongs to a sub-category of the first-level category.
Specifically, the first class includes: upper gastrointestinal tract: epiglottis, esophagus, cardia, fundus ventriculi, corpus gastri, antrum gastri, angle gastri, pylorus, duodenal bulbus, and descending duodenum; lower digestive tract: ileocecal, colonic, sigmoid, rectal; the secondary classes belong to the sub-classes of the colon, including ascending, transverse and descending;
the auxiliary category is a preset interference image category and is used for eliminating interference images; the assistance categories include: the appendiceal opening, the effusion, the distance between the lens and the intestinal wall is less than a preset value, the lens is shielded, the intestinal cavity is contracted, the intestinal cavity is incomplete and fuzzy, bubbles, bright light, mucus and residual fecal mass.
To cover all cases during the examination of the digestive tract foci, specific classifications are shown, for example, in table 1:
TABLE 1 image Classification and selection principles
The intestinal cavity is poor in inspiration or inflation and good in inflation, and can be judged according to the air volume in the intestinal cavity.
In the embodiment, the classification to be detected is the classification to be identified in the digestive tract examination, and as the background of the digestive tract image is single and is easily interfered by special factors, the addition of auxiliary classification is beneficial to eliminating interference and more accurately screening effective images.
The first class is a primary judgment, and the second class is a secondary judgment by using a fine-grained classification network because the similarity of ascending, transverse and descending colon is too high so as to improve the identification accuracy.
The training unit acquires a plurality of digestive tract part images containing known digestive tract focuses and marks regions of the known digestive tract focuses; and training a digestive tract focus region inference model according to the marked training image.
The inference model comprises a digestive tract part inference model A and a digestive tract part inference model B; the digestive tract region inference model a is used to infer a primary class and an auxiliary class, and the digestive tract region inference model B is used to infer a secondary class.
In the embodiment, the digestive tract position inference model A adopts an image classification model provided by a deep learning framework Keras application module; and (3) through a fine-grained classification network DFL-CNN, using a multi-branch structure to simultaneously utilize local information and global information of a lower digestive tract endoscope image in a training set, and training a local area in a characteristic supervision mode to obtain a digestive tract part inference model B.
Specifically, Keras is a highly modular, written in pure Python and backend with tensoflow, thano, and CNTK. Keras was generated to support rapid experiments. Keras understands a model as a working graph of sequences or data of one layer, and fully configurable modules can be freely combined together with minimum cost and are also easy to expand.
For fine-grained classification networks DFL-CNN (learning a cognitive Filter Bank within a CNN): global information is also crucial for fine-grained classification. One branch is needed to decode the global information. I.e. the normal conv + fc layer. And then selecting a proper higher-layer convolution, and separating out another branch to strengthen mid-level capability and pay attention to local information. The method can accurately locate the key area with resolution and extract effective features from the detected key area for classification.
And detecting the endoscope image of the digestive tract in real time based on the digestive tract part inference model A and the digestive tract part inference model B, excluding images belonging to auxiliary categories, and if the probability that the continuous N non-similar images are in the same category exceeds a preset threshold value, outputting the primary category and the secondary category to which the images belong, and further determining the accurate part of the digestive tract focus, wherein N is a positive integer greater than or equal to 3.
In this embodiment, the method for determining a non-similar image is as follows: and generating a hash sequence by a mean hash algorithm and calculating a Hamming distance, and judging the image to be a non-similar image when the Hamming distance is greater than a set Hamming distance threshold value.
The correlation algorithm is as follows:
(a) mean value hash algorithm
Zooming: the picture is scaled to 8 x 8, the structure is preserved, and the details are removed.
Graying: and converting into a 256-step gray scale map.
And (3) averaging: the average of all pixels of the gray map is calculated.
And (3) comparison: the pixel value greater than the average is noted as 1 and conversely as 0 for a total of 64 bits.
Generating a hash: and combining the 1 and 0 generated in the steps in sequence.
(b) Hamming distance calculation
The Hamming Distance/Hamming Distance is used for calculating the similarity of two vectors; that is, by comparing whether each bit of the vector is the same or not, if different, the hamming distance is added by 1, so as to obtain the hamming distance. The higher the vector similarity, the smaller the corresponding hamming distance. For example, positions 10001001 and 10110001 differ by 3.
(3) The online error correction module is configured to enable the doctor client to check the inferred result online, and label and correct the inferred error result;
specifically, the medical expert accesses a website provided by the cloud platform through a network, and inputs a user name and a password to log in the cloud platform. And entering an inferred result auditing page, checking the inferred result of the digestive tract lesion, marking the result of the identification error and correcting.
(4) And the online optimization module is configured to add the corrected images into the training set and train the inference model again.
Specifically, an algorithm engineer accesses a website provided by a cloud platform through a network, inputs a user name and a password to log in the cloud platform, and enters a model optimization page;
the training set is sorted on line, and the images corrected by medical experts are added into the training set;
the algorithm engineer can also adjust the network structure on line, control the training server to train the model on line, check the training data on line, adjust the training parameters on line, test the model performance on line, and issue the retrained model to the inference server on line.
In other embodiments, the algorithm engineer may formulate an automatic training plan, specify how to add the images to the training set, what conditions to start retraining the model, and automatically publish the new model to the inference server after the new model meets the conditions, to implement the automatic optimization function of the inference model.
Example two
In one or more embodiments, a terminal device is disclosed that includes a processor and a computer-readable storage medium, the processor to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, which are adapted to be loaded by the processor and to perform the following process, with reference to fig. 2:
acquiring a digestive tract image to be identified, and transmitting the digestive tract image to a cloud platform;
establishing an inference model by the cloud platform, and constructing a training set to carry out optimization training on the inference model; performing digestive tract lesion inference on the received image by using the inference model, and respectively storing the image and a digestive tract lesion identification result;
the doctor client checks the inferred result on line, and labels and corrects the inferred result;
and adding the corrected images into a training set, and re-training the inference model.
It should be noted that the implementation manner of the foregoing process is implemented by the cloud platform-based digestive tract lesion auxiliary identification and positive feedback system introduced in the first embodiment, and is not described again.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (9)
1. Digestive tract focus auxiliary recognition and positive feedback system based on cloud platform, which is characterized by comprising:
the data acquisition device is configured to acquire an alimentary canal image to be identified and transmit the alimentary canal image to the cloud platform;
the cloud platform is configured to establish an inference model, construct a training set and carry out optimization training on the inference model; performing digestive tract lesion inference on the received image by using the inference model, and respectively storing the image and a digestive tract lesion identification result; a plurality of inference servers are arranged on the cloud platform, and data can be processed in parallel;
the online error correction module is configured to enable the doctor client to check the inferred result online, and label and correct the inferred error result;
the online optimization module is configured to add the corrected images into a training set and train the inference model again; performing online optimization algorithm and updating the model;
the cloud platform comprises at least one inference unit: the system is configured to establish an inference model and infer the type of the digestive tract focus and the focus position on the image; the inference unit trains an inference model using a training set; the inference model comprises a digestive tract part inference model A and a digestive tract part inference model B; the digestive tract part inference model A is used for inferring a primary class and an auxiliary class, and the digestive tract part inference model B is used for inferring a secondary class; the primary category is primarily judged, the secondary category is secondarily judged by using a fine-grained classification network, and the local information and the global information of the lower digestive tract endoscope image in the training set are simultaneously utilized by using a multi-branch structure through the fine-grained classification network, and the local area is trained in a feature supervision mode to obtain a digestive tract part inference model B.
2. The cloud platform-based digestive tract focus aided identification and positive feedback system of claim 1 wherein the cloud platform further comprises:
at least one training unit: configured to optimally train the inference model;
at least one file storage unit: configured to store the received image;
a data storage unit: is configured to store the inference result.
3. The cloud platform-based digestive tract lesion auxiliary identification and positive feedback system according to claim 2, wherein after receiving a request for digestive tract lesion inference on images, the cloud platform evenly distributes the request to corresponding inference units in a load balancing manner.
4. The cloud platform-based digestive tract focus auxiliary identification and positive feedback system according to claim 2, wherein the training unit is configured to acquire images of digestive tract parts, mark out categories to be identified and auxiliary categories for inferring interference images, and construct a training set, wherein the categories to be identified include a primary category and a secondary category, and the secondary category belongs to a sub-category of the primary category.
5. The cloud platform-based digestive tract focus aided identification and positive feedback system of claim 4 wherein the primary categories comprise: upper gastrointestinal tract: epiglottis, esophagus, cardia, fundus ventriculi, corpus gastri, antrum gastri, angle gastri, pylorus, duodenal bulbus, and descending duodenum; lower digestive tract: ileocecal, colonic, sigmoid, rectal; the secondary classes belong to the sub-classes of the colon, including ascending, transverse and descending;
the auxiliary category is a preset interference image category and is used for eliminating interference images; the auxiliary categories comprise appendix opening, effusion, lens distance smaller than a preset value from the intestinal wall, lens shielding, intestinal cavity contraction, incomplete and fuzzy intestinal cavity, bubbles, strong light, mucus and residual fecal mass.
6. The cloud platform-based digestive tract lesion assistant recognition and positive feedback system according to claim 4, wherein the training unit acquires a plurality of images of digestive tract parts containing known digestive tract lesions and labels the regions of the known digestive tract lesions; and training a digestive tract focus region inference model according to the marked training image.
7. The cloud platform-based digestive tract focus auxiliary identification and positive feedback system according to claim 6, wherein a digestive tract endoscopic image is detected in real time based on the digestive tract part inference model A and the digestive tract part inference model B, images belonging to auxiliary categories are excluded, if the probability that N consecutive non-similar images are all in the same category exceeds a preset threshold, a primary category and a secondary category to which the images belong are output, and the accurate position of the digestive tract focus is determined, wherein N is a positive integer greater than or equal to 3.
8. The cloud platform-based digestive tract focus aided identification and positive feedback system of claim 7 wherein the digestive tract site inference model A employs an image classification model provided by a deep learning framework Keras application module;
and (3) through a fine-grained classification network DFL-CNN, using a multi-branch structure to simultaneously utilize local information and global information of a lower digestive tract endoscope image in a training set, and training a local area in a characteristic supervision mode to obtain a digestive tract part inference model B.
9. A terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the following process:
acquiring an image of the alimentary tract to be identified and transmitting to the cloud platform according to any one of claims 1 to 8;
establishing an inference model by the cloud platform, and constructing a training set to carry out optimization training on the inference model; performing digestive tract lesion inference on the received image by using the inference model, and respectively storing the image and a digestive tract lesion identification result;
the doctor client checks the inferred result on line, and labels and corrects the inferred result;
and adding the corrected images into a training set, and re-training the inference model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396391.2A CN111179252B (en) | 2019-12-30 | 2019-12-30 | Cloud platform-based digestive tract disease focus auxiliary identification and positive feedback system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396391.2A CN111179252B (en) | 2019-12-30 | 2019-12-30 | Cloud platform-based digestive tract disease focus auxiliary identification and positive feedback system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111179252A CN111179252A (en) | 2020-05-19 |
| CN111179252B true CN111179252B (en) | 2021-02-05 |
Family
ID=70656076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911396391.2A Active CN111179252B (en) | 2019-12-30 | 2019-12-30 | Cloud platform-based digestive tract disease focus auxiliary identification and positive feedback system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179252B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112652382B (en) * | 2020-12-31 | 2022-05-06 | 山东大学齐鲁医院 | Gallbladder-pancreas disease multidisciplinary combined consultation and consultation system based on mobile terminal |
| CN112712515A (en) * | 2021-01-06 | 2021-04-27 | 重庆金山医疗器械有限公司 | Endoscope image processing method and device, electronic equipment and storage medium |
| CN113762419A (en) * | 2021-10-19 | 2021-12-07 | 重庆金山医疗技术研究院有限公司 | Focus recognition device of capsule endoscope image |
| CN114565538B (en) * | 2022-03-10 | 2024-03-01 | 山东大学齐鲁医院 | Endoscopic image processing method, system, storage medium and equipment |
| CN116784827B (en) * | 2023-02-14 | 2024-02-06 | 安徽省儿童医院 | Digestive tract ulcer depth and area measuring and calculating method based on endoscope |
| CN117528131B (en) * | 2024-01-05 | 2024-04-05 | 青岛美迪康数字工程有限公司 | AI integrated display system and method for medical image |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102946629A (en) * | 2012-10-25 | 2013-02-27 | 清华大学 | Online optimal scheduling solution for tail energy consumption of 3-G communication of mobile intelligent terminal |
| WO2017091834A1 (en) * | 2015-11-29 | 2017-06-01 | Arterys Inc. | Medical imaging and efficient sharing of medical imaging information |
| CN110502594A (en) * | 2019-07-10 | 2019-11-26 | 武汉数趣信息科技有限公司 | A kind of Remote sensing photomap tile real time fusion and online updating method |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881568A (en) * | 2015-04-27 | 2015-09-02 | 苏州敏宇医疗科技有限公司 | Cloud computation based early oncotherapy efficacy evaluation system and method |
| CN105468900B (en) * | 2015-11-20 | 2018-08-14 | 邹远强 | A kind of intelligent case history copying platform in knowledge based library |
| CN105303059B (en) * | 2015-11-20 | 2018-05-11 | 杭州看上科技有限公司 | A kind of remote diagnosis system based on Intelligent mobile equipment and intelligent big data analysis |
| CN106372390B (en) * | 2016-08-25 | 2019-04-02 | 汤一平 | A kind of self-service healthy cloud service system of prevention lung cancer based on depth convolutional neural networks |
| CN106339591B (en) * | 2016-08-25 | 2019-04-02 | 汤一平 | A kind of self-service healthy cloud service system of prevention breast cancer based on depth convolutional neural networks |
| CN106529137A (en) * | 2016-10-26 | 2017-03-22 | 象翌微链科技发展有限公司 | Cloud based CT image sharing method and device |
| US10249066B2 (en) * | 2017-04-14 | 2019-04-02 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for MPR streak reduction |
| CN107358055A (en) * | 2017-07-21 | 2017-11-17 | 湖州师范学院 | Intelligent auxiliary diagnosis system |
| CN109313937A (en) * | 2017-09-11 | 2019-02-05 | 深圳市得道健康管理有限公司 | Chinese medicine pulse assistant diagnosis system and method based on cloud computing platform |
| CN108573490B (en) * | 2018-04-25 | 2020-06-05 | 王成彦 | Intelligent film reading system for tumor image data |
| CN109512464A (en) * | 2018-11-23 | 2019-03-26 | 清华大学深圳研究生院 | A kind of disorder in screening and diagnostic system |
| CN109686440B (en) * | 2018-12-20 | 2023-12-05 | 深圳市新产业眼科新技术有限公司 | Online intelligent diagnosis cloud platform, operation method thereof and readable storage medium |
| CN109903839A (en) * | 2019-02-22 | 2019-06-18 | 武汉凯德维斯生物技术有限公司 | A kind of medical imaging diagosis system based on cloud platform |
| CN110277166B (en) * | 2019-06-28 | 2020-05-15 | 屈兴玲 | Auxiliary diagnosis system and method for palace laparoscope |
-
2019
- 2019-12-30 CN CN201911396391.2A patent/CN111179252B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102946629A (en) * | 2012-10-25 | 2013-02-27 | 清华大学 | Online optimal scheduling solution for tail energy consumption of 3-G communication of mobile intelligent terminal |
| WO2017091834A1 (en) * | 2015-11-29 | 2017-06-01 | Arterys Inc. | Medical imaging and efficient sharing of medical imaging information |
| CN110502594A (en) * | 2019-07-10 | 2019-11-26 | 武汉数趣信息科技有限公司 | A kind of Remote sensing photomap tile real time fusion and online updating method |
Non-Patent Citations (2)
| Title |
|---|
| Artificial intelligence in medicine and cardiac imaging: Harnessing big data and advanced computing to provide personalized medical diagnosis and treatment;Dilsizian S E等;《Current Cardiology Reports》;20141231;第16卷(第1期);第441页 * |
| 基于深度置信网络的脑血管病风险预警研究;杨星;《中国优秀硕士学位论文全文数据库 医药卫生科技辑》;20160715(第7期);第E070-39页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111179252A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179252B (en) | Cloud platform-based digestive tract disease focus auxiliary identification and positive feedback system | |
| CN111048170B (en) | Digestive endoscopy structured diagnosis report generation method and system based on image recognition | |
| CN110600122B (en) | Digestive tract image processing method and device and medical system | |
| US20240081618A1 (en) | Endoscopic image processing | |
| US10860930B2 (en) | Learning method, image recognition device, and computer-readable storage medium | |
| CN111128396B (en) | Digestive tract disease auxiliary diagnosis system based on deep learning | |
| WO2020103676A1 (en) | Image identification method and apparatus, system, and storage medium | |
| WO2021008328A1 (en) | Image processing method and device, terminal, and storage medium | |
| JP2024045234A (en) | Image scoring for intestinal pathology | |
| CN111275118B (en) | Chest film multi-label classification method based on self-correction type label generation network | |
| CN114663426B (en) | Bone age assessment method based on key bone region positioning | |
| CN115082747B (en) | Zero-sample gastric ulcer classification system based on block confrontation | |
| CN112466466B (en) | Digestive tract auxiliary detection method and device based on deep learning and computing equipment | |
| CN114581375A (en) | Method, device and storage medium for automatically detecting focus of wireless capsule endoscope | |
| CN111723852B (en) | Robust training method for target detection network | |
| Rifai et al. | Analysis for diagnosis of pneumonia symptoms using chest X-ray based on MobileNetV2 models with image enhancement using white balance and contrast limited adaptive histogram equalization (CLAHE) | |
| CN115115897A (en) | Multi-modal pre-trained gastric tumor classification system | |
| CN117058467B (en) | Gastrointestinal tract lesion type identification method and system | |
| CN116758042A (en) | Intestinal metaplasia severity grading system based on deformation transducer | |
| CN116309039A (en) | Intelligent X-ray image splicing method, storage medium and processor | |
| Stancilas et al. | Detection of Pathological Markers in Colonoscopy Images using YOLOv7 | |
| CN114581402A (en) | Capsule endoscope quality inspection method, device and storage medium | |
| CN116612340B (en) | Peptic ulcer part classification method, device and readable storage medium | |
| CN111950584B (en) | Intelligent identification method and system for position integrity in X-ray chest radiography | |
| CN117726992B (en) | Nursing skill training auxiliary system and method |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Feng Jian Inventor after: Li Yanqing Inventor after: Zhou Ruchen Inventor after: Lai Yonghang Inventor after: Zuo Xiuli Inventor after: Yang Xiaoyun Inventor after: Li Zhen Inventor after: Shao Xuejun Inventor after: Xin Wei Inventor before: Feng Jian Inventor before: Li Yanqing Inventor before: Zhou Ruchen Inventor before: Lai Yonghang Inventor before: Zuo Xiuli Inventor before: Yang Xiaoyun Inventor before: Li Zhen Inventor before: Shao Xuejun Inventor before: Xin Wei |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |