CN111192679A - Method and device for processing image data exception and storage medium - Google Patents
Method and device for processing image data exception and storage medium Download PDFInfo
- Publication number
- CN111192679A CN111192679A CN201911353205.7A CN201911353205A CN111192679A CN 111192679 A CN111192679 A CN 111192679A CN 201911353205 A CN201911353205 A CN 201911353205A CN 111192679 A CN111192679 A CN 111192679A
- Authority
- CN
- China
- Prior art keywords
- image data
- detection object
- abnormality
- processing
- personal terminal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 154
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000007246 mechanism Effects 0.000 claims abstract description 71
- 230000004044 response Effects 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims description 141
- 230000005856 abnormality Effects 0.000 claims description 59
- 238000003745 diagnosis Methods 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims 1
- 230000002159 abnormal effect Effects 0.000 abstract description 19
- 238000003672 processing method Methods 0.000 abstract description 4
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 abstract description 2
- 210000004072 lung Anatomy 0.000 description 21
- 238000000605 extraction Methods 0.000 description 13
- 201000010099 disease Diseases 0.000 description 7
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 239000003814 drug Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000001575 pathological effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 210000000038 chest Anatomy 0.000 description 4
- 230000000241 respiratory effect Effects 0.000 description 4
- 238000001356 surgical procedure Methods 0.000 description 4
- 210000000115 thoracic cavity Anatomy 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000009206 nuclear medicine Methods 0.000 description 2
- 230000000399 orthopedic effect Effects 0.000 description 2
- 201000003144 pneumothorax Diseases 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 208000012641 Pigmentation disease Diseases 0.000 description 1
- 206010035664 Pneumonia Diseases 0.000 description 1
- 206010035742 Pneumonitis Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011976 chest X-ray Methods 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 230000005823 lung abnormality Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 238000002600 positron emission tomography Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000002603 single-photon emission computed tomography Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/10108—Single photon emission computed tomography [SPECT]
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Radiology & Medical Imaging (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a processing method, a device and a storage medium for image data abnormity, wherein the method comprises the steps of acquiring image data, carrying out target identification and abnormity identification on the image data, determining the emergency degree of the abnormity of a detected object in the image data, which needs medical treatment, and a manual processing mechanism or a personal terminal device corresponding to the detected object, and sending the emergency degree to the corresponding manual processing mechanism or the personal terminal device for processing. The manual processing mechanism or the personal terminal equipment responds to the image data according to the emergency degree, and the response mode of the manual processing mechanism or the personal terminal equipment is set through the response system, so that the image data can be responded in time. The method directly identifies the inspection object in the image data, realizes identification and positioning of the abnormal region by utilizing the deep learning technology, and can improve the processing efficiency of doctors based on the abnormal region in the subsequent application.
Description
Technical Field
The present invention relates to the field of medical imaging, and in particular, to a method, an apparatus, and a storage medium for processing image data anomalies.
Background
With the development of modern medicine, medical images are widely used because they can provide abundant information for clinical diagnosis. At present, many hospitals are divided into independent medical technical departments according to medical imaging equipment, wherein the radiology department has examination equipment corresponding to the radiology department, and the nuclear medicine department has equipment corresponding to the nuclear medicine department. Clinical medical images in various modes can complement and verify each other, so that the diagnosis level of diseases is improved, but doctors need to retrieve image data of patients from different departments for analysis due to mutual independence between medical departments, and unnecessary work of the doctors is increased.
In addition, a large number of patients need to be received by the hospital every day, the speed of reading the film by the doctor is far faster than the speed of generating the picture by the equipment, the time for obtaining the diagnosis result by the patient is prolonged, and the diagnosis efficiency of the doctor is reduced.
Disclosure of Invention
The invention provides a method and a device for processing image data abnormity and a storage medium, which can assist a doctor in diagnosis and improve the working efficiency of the doctor.
In one aspect, the present invention provides a method for processing image data exception, where the method includes:
acquiring image data, wherein the image data represents an object to be detected;
performing anomaly identification on a detection object in the image data based on an identification model corresponding to the detection object, and acquiring the emergency degree of the anomaly in the detection object needing medical treatment;
according to a detection object in the image data, determining a manual processing mechanism or a personal terminal device corresponding to the abnormality in the detection object;
and sending the image data to a manual processing mechanism or personal terminal equipment corresponding to the abnormity in the detection object for processing according to the emergency degree.
Another aspect provides an apparatus for processing image data exception, the apparatus comprising: the device comprises: the system comprises an image data acquisition module, an abnormality identification module, a processing mechanism determination module and an abnormality processing module;
the image data acquisition module is used for acquiring image data, and the image data is image data representing a detection object;
the abnormality identification module is used for carrying out abnormality identification on the detection object in the image data based on an identification model corresponding to the detection object, and acquiring the emergency degree of the abnormality in the detection object which needs medical treatment;
the processing mechanism determining module is used for determining a manual processing mechanism or a personal terminal device corresponding to the abnormity in the detection object according to the detection object in the image data;
and the abnormity processing module is used for sending the image data to a manual processing mechanism or personal terminal equipment corresponding to the abnormity in the detection object for processing according to the emergency degree.
Another aspect provides a computer-readable storage medium, where the storage medium includes a processor and a memory, where the memory stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by the processor to implement the method for processing the image data exception as described above.
The method comprises the steps of acquiring image data, carrying out target identification and abnormality identification on the image data, determining the emergency degree of the abnormality of a detection object in the image data, needing medical treatment, and a manual processing mechanism or a personal terminal device corresponding to the detection object, and sending the emergency degree to the corresponding manual processing mechanism or the personal terminal device for processing. The manual processing mechanism or the personal terminal equipment responds to the image data according to the emergency degree, and the response mode of the manual processing mechanism or the personal terminal equipment is set through the response system, so that the image data can be responded in time. The method directly identifies the examination object in the image data, realizes identification and positioning of the abnormal region by utilizing the deep learning technology, and can analyze and sequence the severity of the disease condition based on the identification and positioning, so that a doctor can read the film in sequence from complex disease condition to simple condition, and the treatment efficiency of the doctor is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of a method for processing an image data exception according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for processing image data exception according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for performing preliminary diagnosis by using an identification model in a method for processing image data anomalies according to an embodiment of the present invention;
fig. 4 is a flowchart of a method for processing image data according to the urgency level in a method for processing an image data exception according to an embodiment of the present invention;
fig. 5 is a flowchart of a method for responding to image data through an emergency response tree in a method for processing image data anomalies according to an embodiment of the present invention;
fig. 6 is a flowchart of a method for responding to image data through a response sequence in a method for processing an image data exception according to an embodiment of the present invention;
FIG. 7 is a flowchart of a method for false alarm determination in a method for processing image data abnormality according to an embodiment of the present invention;
FIG. 8 is a flowchart of a method for processing image data anomalies in a patient examination scenario according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an apparatus for processing image data exception according to an embodiment of the present invention;
fig. 10 is a schematic hardware structure diagram of an apparatus for implementing the method provided by the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like 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. Moreover, the terms "first," "second," and the like, 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.
Referring to fig. 1, an application scenario diagram of a processing method for image data exception according to an embodiment of the present invention is shown, where the application scenario includes a data acquisition device 110, a server 120, and a manual processing end 130. The data acquisition device 110 is used for acquiring image data and transmitting the image data to the server 120. The server 120 acquires the image data, performs object detection and abnormality identification on the image data, determines the emergency degree of the abnormality of the detection object in the image data, which requires medical treatment, and the manual processing terminal 130 corresponding to the detection object, and sends the emergency degree to the corresponding manual processing terminal 130 for processing.
In an embodiment of the present invention, the data acquisition device 110 may be a multi-modality Imaging device, and the multi-modality Imaging device may include Computed Tomography (CT), direct Digital Radiography (DR), Magnetic Resonance Imaging (MRI), Single-Photon Emission Computed Tomography (SPECT), Positron Emission Tomography (PET), and the like, and is configured to acquire image data of a detection object.
In the embodiment of the present invention, the server 120 may include a server running independently, or a distributed server, or a server cluster composed of a plurality of servers. The server 120 may include a network communication unit, a processor, a memory, and the like. Specifically, the server 120 may be configured to perform object detection and abnormality identification on the image data, and determine the emergency degree of the detected object requiring medical treatment for the abnormality of the image data and the manual processing end 130 corresponding to the detected object.
In the embodiment of the present invention, the manual processing terminal 130 includes a smart phone, a desktop computer, a tablet computer, a notebook computer, a digital assistant, a smart wearable device, and other types of physical devices. Specifically, the manual processing terminal 130 is configured to receive the emergency degree and the image data, and process the image data according to the emergency degree.
Referring to fig. 2, a method for processing image data exception is shown, which can be applied to a server side, and includes:
s210, image data is obtained, wherein the image data represents an object to be detected;
specifically, image data are collected through the multi-mode imaging device, the server obtains the image data to perform detection object identification, abnormality identification and emergency degree determination, and the image data are sent to the corresponding manual processing end.
Further, before the identifying an abnormality of the detection object in the image data based on the identification model corresponding to the detection object and acquiring the emergency degree that the abnormality in the detection object requires medical treatment, the method further includes:
and identifying a detection object in the image data, and determining an identification model corresponding to the detection object.
Specifically, feature extraction is performed on image data to obtain multi-scale feature information of the structural image data, a target extraction region corresponding to a detection object is generated based on the multi-scale feature information, the detection object corresponding to the image data is determined according to the target extraction region, and an identification model corresponding to the detection object is determined according to the detection object. For example, if it is determined by feature extraction that the detection target is a lung, the image data is input to a special lung recognition model to recognize lung abnormalities.
The image data is subjected to feature extraction, and the method for determining the detection object can be used for performing feature extraction through a deep neural network such as ResNet and DenseNet.
When feature extraction is performed through ResNet, feature extraction of a deep network needs to be performed through a residual error unit, and a residual error is a difference value between output and input. In one residual unit, feature information is extracted by convolution, and the input information is connected to the next residual unit through a bypass line, so that the next residual unit can directly learn the residual. The residual error unit can be a two-layer residual error unit or a three-layer residual error unit, the two-layer residual error unit can include two convolutions of 3x3, and the three-layer residual error unit performs the operation of first dimension reduction and then dimension lifting by using a mode of convolution of 1x1, convolution of 3x3 and convolution of 1x 1.
When feature extraction is performed through the DenseNet, in the deep neural network with the DenseNet structure, a certain layer of network can use feature information of all previous layers of networks, that is, output information of each layer of network is transmitted to the network of all following layers through a bypass, so that the feature information can be multiplexed in the network of all layers.
After the feature recognition is carried out on the detection object, the recognition model corresponding to the detection object can be determined, and the accuracy of subsequent abnormal recognition and emergency degree recognition is improved.
S220, carrying out abnormity identification on the detection object in the image data based on an identification model corresponding to the detection object, and acquiring the emergency degree of the abnormity in the detection object which needs medical treatment;
specifically, the identification model corresponding to the detection object is a dedicated identification model trained for a certain detection object, for example, when the detection object is a lung, the corresponding identification model is a lung identification model. When the model training is carried out, the special recognition models corresponding to different detection objects are trained according to the different detection objects. The dedicated identification model is used for identifying the abnormality of a specific detection object, for example, the lung identification model is only used for identifying the abnormality of the lung, but not for identifying the abnormality of other detection objects such as the liver or the bone.
Meanwhile, the identification model corresponding to the detection object can also be an identification model for a certain data acquisition device, for example, the identification model can be a model for identifying the detection object in an X-ray film as a lung, and the model only identifies the abnormality for the X-ray film and the lung.
And extracting the structural features of the detection object to obtain structural feature information of the detection object, performing semantic analysis on the structural feature information, and performing anomaly identification on the detection object in the image data. When semantic analysis is carried out, the image of the detection object in the image data is segmented pixel by pixel, and the segmented pixel information is classified according to the preset structure classification category. And acquiring the pixel information with abnormal pixel values from each classified type of pixel information, and integrating the pixel information with abnormal pixel values to obtain an abnormal area in the detection object. The abnormal region may be a pathological region, and further analysis of the abnormal region is required to determine the urgency of the abnormality in the test subject requiring medical treatment.
When the emergency degree of the abnormal areas in the detection object needing medical treatment is determined, the abnormal areas are compared with preset pathological early warning indexes, the pathological early warning indexes are index information representing the abnormal levels of pathological structure areas, and the emergency degree of the abnormal areas in the detection object needing medical treatment is determined according to the levels of the pathological early warning indexes matched with the abnormal areas in the comparison result.
For example, assuming that the image data is a chest film and the detection object is a lung, the lung region on the chest film is segmented pixel by pixel through semantic analysis, and a shadow region with abnormal pigment values is found, the shadow region needs to be further analyzed, the shape and size of the shadow are compared with a preset pathology early warning index, and the emergency degree of medical treatment of the shadow region is judged.
Due to the particularity of disease diagnosis, the probability of false recognition can be reduced through a recognition model special for a detection object, the recognition accuracy is improved, and the range of an abnormal region can be determined in a pixel-by-pixel segmentation mode, so that the judgment of the emergency degree is assisted, and the accuracy of determining the emergency degree is improved.
Further, referring to fig. 3, the recognition model may further include a preliminary diagnosis function, and the method for performing the preliminary diagnosis further includes:
s310, analyzing the image data according to the emergency degree of the abnormality in the detection object needing medical treatment to obtain initial diagnosis information;
and S320, sending the initial diagnosis information and the image data to the manual processing mechanism or the personal terminal equipment for analysis to obtain target diagnosis information.
Specifically, when training a recognition model corresponding to a detection target, the recognition model may be trained as a model having recognition and diagnosis functions. The identification model obtains the abnormality in the detection object, obtains the emergency degree of the abnormality in the detection object needing medical treatment through the abnormality in the detection object, and can further perform preliminary diagnosis on the abnormality in the detection object. For example, if the image data is a chest radiograph and the detection target is a lung, and if it is recognized that a shadow region exists in the lung, a preliminary diagnosis can be made on the shadow region, and it is determined from the shape and size of the shadow that the shadow region is due to infection and the shadow region is due to tumor. And outputting the diagnosis result of the preliminary diagnosis to a manual processing end, and then carrying out further diagnosis.
Through the function of preliminary diagnosis, the step of artifical processing can be assisted, manual work load is reduced, and the efficiency of diagnosis is improved. And through the cooperation of the primary diagnosis and the manual diagnosis, the target diagnosis information is obtained by manually carrying out secondary diagnosis, so that the misdiagnosis of the primary diagnosis is avoided.
S230, according to a detection object in the image data, determining a manual processing mechanism or a personal terminal device corresponding to the abnormality in the detection object;
specifically, feature extraction is performed on image data to obtain multi-scale feature information of the structural image data, a target extraction area corresponding to a detection object is generated based on the multi-scale feature information, and the detection object corresponding to the image data is determined according to the target extraction area. And determining a manual processing mechanism or personal terminal equipment corresponding to the detection object according to the detection object, wherein the corresponding relation between the detection object and the manual processing mechanism or the personal terminal equipment is preset. For example, if the determined detection object is a bone, the corresponding manual processing mechanism is an orthopedics department, and the personal terminal device is a terminal device of an orthopedics doctor.
And S240, sending the image data to a manual processing mechanism or a personal terminal device corresponding to the abnormity in the detection object for processing according to the emergency degree.
Further, referring to fig. 4, sending the image data to a manual processing mechanism or a personal terminal device corresponding to the abnormality in the detection object for processing according to the emergency degree includes:
s410, sorting image data corresponding to different detection objects based on the emergency degree to obtain a sequence of the image data;
and S420, sending the image data to a manual processing mechanism or a personal terminal device corresponding to the abnormality in the detection object for processing according to the sequence of the image data.
Specifically, after the emergency degree corresponding to the abnormality of the detection object in each piece of video data is obtained, the video data may be sorted according to the emergency degree, the video data with the higher emergency degree may be sent to the manual processing mechanism or the personal terminal device for processing, and the video data with the lower emergency degree may be sent to the manual processing mechanism or the personal terminal device for processing. For example, when there are two lung images, one of the lung images has a high urgency level, and the other lung image has a low urgency level, the lung image with the high urgency level is transmitted to a manual processing mechanism or a personal terminal device for processing before the lung image with the low urgency level, so as to avoid delaying the disease condition.
Further, if the emergency degree is the highest level, the image data is sent to the personal terminal device corresponding to the abnormality in the detection object for processing.
Specifically, when the urgency level is the highest level, which indicates that the examiner may be in danger of life, the examiner needs to be directly notified to the individual, that is, the image data corresponding to the urgency level is sent to the personal terminal device for processing, for example, when a pneumothorax condition which may endanger life exists in the lung is detected and an emergency operation needs to be performed, the examiner needs to be quickly notified to a corresponding doctor who can perform the operation to perform the operation on the patient as soon as possible. At the moment, the image data and the emergency degree are directly sent to the personal terminal equipment, and a doctor is informed to process as soon as possible.
The image data are sequenced according to the magnitude of the emergency degree, so that the condition of an inspector with high emergency can be prevented from being delayed, and the image data with the highest emergency degree are directly sent to the personal terminal equipment through setting, so that a doctor can respond in time.
Further, referring to fig. 5, the manual processing mechanism or the personal terminal device may respond to the image data with different degrees of urgency, and the responding method includes:
s510, classifying the manual processing mechanism and the personal terminal equipment according to a preset detection object;
s520, taking the classified manual processing mechanism and the classified personal terminal device as tree nodes, and establishing an emergency response tree;
s530, when image data is responded, judging an executable node in a manual processing mechanism or a personal terminal device corresponding to a current detection object by traversing the emergency response tree;
and S540, processing the image data of the current detection object based on the executable node to obtain an analysis result of the image data.
Specifically, the manual processing mechanism and the personal terminal device are classified according to a preset detection object, for example, when the detection object is a lung, the corresponding manual processing mechanism is a consulting room of thoracic surgery or respiratory medicine, and the corresponding personal terminal device is a doctor of thoracic surgery and a doctor of respiratory medicine. And after classifying each manual processing mechanism and the personal terminal equipment according to different detection objects, establishing an emergency response tree. The emergency response tree can be provided with two-level nodes, wherein the first-level node is a detection object, and the second-level node is a manual processing mechanism and a personal terminal device corresponding to the detection object.
The second-level node can classify operations and operations as required again under the condition that the identification model can output a preliminary diagnosis result, and subdivides the operations into a manual processing mechanism and a personal terminal device which can perform the operations and a manual processing mechanism and a personal terminal device which do not need to perform the operations. When the emergency degree needs to be responded, the whole emergency response tree is traversed according to the specific situation of the image data corresponding to the emergency degree, and the matched manual processing mechanism or the personal terminal equipment is obtained to carry out the response. For example, if the image data is lung data, the image data is sent to a manual processing means and a personal terminal device that perform an operation when the initial diagnosis result is pneumothorax, and is sent to a manual processing means and a personal terminal device that do not perform an operation when the initial diagnosis result is pneumonitis.
And during the process of performing the emergency response tree, judging whether the current node is occupied, and if the current node is occupied, selecting the next node to respond to the image data. And if all the nodes under the same classification are occupied, selecting the nodes with less queuing number to respond to the image data according to the queuing number of each node. And queuing the image data waiting for response at each node, determining a response sequence according to the emergency degree, and responding by the image data with high emergency degree preferentially.
When the emergency response tree is constructed, a node switch can be added, the on-off time of the node switch is set according to the duty condition of each manual processing mechanism or individual, the node can be used as a response object to respond when the node switch is turned on, and the node does not respond to the image data if the node switch is turned off.
The response system is designed in an emergency response tree mode, and nodes capable of responding can be quickly determined in a traversal mode so as to respond to the image data in time.
Further, referring to fig. 6, the manual processing mechanism or the personal terminal device may respond to the image data with different degrees of urgency, and the responding method includes:
s610, classifying the manual processing mechanism and the personal terminal equipment according to a preset detection object;
s620, sorting the classified manual processing mechanisms and the personal terminal equipment according to a preset response sequence to obtain a response sequence of each type of manual processing mechanism and personal terminal equipment to the image data;
s630, judging a response object in a manual processing mechanism or personal terminal equipment corresponding to the current detection object based on the response sequence;
and S640, processing the image data of the current detection object based on the response object to obtain an analysis result of the image data.
Specifically, the manual processing mechanism and the personal terminal device are classified according to a preset detection object, for example, when the detection object is a lung, the corresponding manual processing mechanism is a consulting room of thoracic surgery or respiratory medicine, and the corresponding personal terminal device is a doctor of thoracic surgery and a doctor of respiratory medicine. After the manual processing mechanisms and the personal terminal equipment are classified according to different detection objects, response sequences are directly preset, and the response sequences of the manual processing mechanisms and the personal terminal equipment of each class are arranged. For example, when A, B, C, D, E diagnostic rooms are provided under a certain type of detection object, A, B, C, D, E responses can be set, that is, when the first image data is sent, the first image data is transmitted to the A diagnostic room, the A diagnostic room responds, when the second image data is sent, the second image data is transmitted to the B diagnostic room, the B diagnostic room responds, and so on.
Further, priorities can be set in the response system to determine that a certain office or a certain person responds to image data with high urgency preferentially. In addition, the response sequence can be set every day according to the on-duty list of doctors, whether a doctor in a sitting position exists in a consulting room, and the like. For example, under a certain kind of detection object, A, B, C, D, E five consulting rooms are corresponded, eight doctors of a, b, c, d, e, f, g and h are corresponded, the preset sequence is that responses are carried out according to A, B, C, D, E or the sequence of a, b, c, d, e, f, g and h, if a doctor and e doctor on the first day are not in work, a doctor and e doctor are skipped when image data are responded in daytime, and the response sequence is six doctors of b, c, d, f, g and h.
And determining a response object responding to the image data and processing the image data by adjusting a preset response sequence and a daily response sequence or directly inputting a doctor duty list into a response system.
The preset response sequence mode is used for responding the image data, and the response object can be flexibly adjusted, so that the image data can be responded in time.
Further, referring to fig. 7, after the processing the image data of the current detection object to obtain the analysis result of the image data, the method further includes:
s710, judging whether the emergency degree of the abnormality in the detection object requiring medical treatment is false alarm or not according to the analysis result;
and S720, if the alarm is false, the emergency degree that the abnormality in the detection object needs medical treatment is cancelled.
Specifically, after the image data is manually processed, the emergency degree corresponding to the image data can be adjusted, and if the emergency degree in the current image data is found to be false alarm manually, the emergency degree of the current image data can be cancelled, so that the situation that the false alarm information occupies emergency medical resources is avoided. And then, the misinformation information can be input into the recognition model for learning, so that the re-misinformation of the recognition model can be avoided, and the resolution capability of the recognition model is improved.
In one embodiment, referring to fig. 8, image data of multiple modalities of the examiner are extracted from each modality image device, and corresponding modalities and detection objects are automatically identified. And selecting a trained deep learning model corresponding to the detection object according to the mode corresponding to the image and the detection object. For example, after a chest X-ray image is acquired, a corresponding model is extracted according to an early warning index corresponding to a chest film. And inputting the image data generated in real time into the model as an input image, and calculating and outputting whether the abnormality exists through the model. If yes, further outputting the abnormal position, and outputting an evaluation value of the emergency degree. And transmitting the image data to a doctor with the value of the corresponding department according to the abnormity reported by the model and the evaluation result, performing reading confirmation again by the doctor, performing manual processing on the image data, and then transmitting the result to an inspector in real time in a short message mode and the like.
In a specific embodiment, a trained neural network is used to analyze whether the identified location is abnormal. The training method of the neural network can comprise the following steps:
and acquiring the image data corresponding to the corresponding modality and the insist object and the labeling information of the image data. The annotation information of the image data includes whether there is an abnormality, a specific location where the abnormality occurs, an emergency degree of the abnormality requiring medical treatment, and the like, and in practical application, the annotation information of the image data is annotated by a doctor according to an index of detection and early warning. The recognition model is trained by using the data as training samples.
Aiming at different modes, different inspection parts and different early warning indexes, a targeted detection and segmentation network is designed. For detecting related tasks, a deep neural network of feature extraction is used to detect the presence or absence of specified abnormalities, such as bumps. For the segmentation-related task, the abnormal region can be segmented out pixel by pixel. Based on the results obtained by detecting and dividing the network, the emergency condition is evaluated by combining medical related knowledge, and the emergency degree is estimated.
The embodiment of the invention provides a processing method of image data abnormity, which comprises the steps of acquiring image data, carrying out target identification and abnormity identification on the image data, determining the emergency degree of the abnormity of a detection object in the image data, which needs medical treatment, and a manual processing mechanism or personal terminal device corresponding to the detection object, and sending the emergency degree to the corresponding manual processing mechanism or personal terminal device for processing. The manual processing mechanism or the personal terminal equipment responds to the image data according to the emergency degree, and the response mode of the manual processing mechanism or the personal terminal equipment is set through the response system, so that the image data can be responded in time. The method directly identifies the examination object in the image data, realizes identification and positioning of the abnormal region by utilizing the deep learning technology, and can analyze and sequence the severity of the disease condition based on the identification and positioning, so that a doctor can read the film in sequence from complex disease condition to simple condition, and the treatment efficiency of the doctor is improved.
An embodiment of the present invention further provides a device for processing image data exception, please refer to fig. 9, where the device includes: an image data acquisition module 910, an abnormality recognition module 920, a processing mechanism determination module 930, and an abnormality processing module 940;
the image data acquiring module 910 is configured to acquire image data, where the image data is image data representing a detection object;
the anomaly identification module 920 is configured to perform anomaly identification on a detection object in the image data based on an identification model corresponding to the detection object, and acquire an emergency degree of medical treatment for an anomaly in the detection object;
the processing mechanism determining module 930 is configured to determine, according to a detection object in the image data, a manual processing mechanism or a personal terminal device corresponding to an abnormality in the detection object;
the exception handling module 940 is configured to send the image data to a manual handling mechanism or a personal terminal device corresponding to the exception in the detection object for handling the image data according to the urgency level.
The device provided in the above embodiments can execute the method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For details of the processing method of the image data exception, reference may be made to the method for processing the image data exception provided in any embodiment of the present invention.
The present embodiment also provides a computer-readable storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are loaded by a processor and execute the method for processing the image data exception described above in the present embodiment.
The present embodiment further provides an apparatus, which includes a processor and a memory, where the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the method for processing the image data exception described above in the present embodiment.
The device may be a computer terminal, a mobile terminal or a server, and the device may also participate in forming the apparatus or system provided by the embodiments of the present invention. As shown in fig. 10, the computer terminal 10 (or mobile terminal 10 or server 10) may include one or more (shown as 1002a, 1002b, … …, 1002 n) processors 1002 (the processors 1002 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), memory 1004 for storing data, and a transmission device 1006 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 10 is merely illustrative and is not intended to limit the structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 10, or have a different configuration than shown in FIG. 10.
It should be noted that the one or more processors 1002 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single, stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal 10 (or mobile terminal). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).
The memory 1004 may be used for storing software programs and modules of application software, such as program instructions/data storage devices corresponding to the method described in the embodiment of the present invention, and the processor 1002 executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, implementing one of the above-described methods for generating a self-attention network-based time-series behavior capture block. The memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1004 may further include memory located remotely from the processor 1002, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 1006 is used for receiving or sending data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 1006 includes a Network adapter (NIC) that can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 1006 can be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or mobile terminal).
The present specification provides method steps as described in the examples or flowcharts, but may include more or fewer steps based on routine or non-inventive labor. The steps and sequences recited in the embodiments are but one manner of performing the steps in a multitude of sequences and do not represent a unique order of performance. In the actual system or interrupted product execution, it may be performed sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
The configurations shown in the present embodiment are only partial configurations related to the present application, and do not constitute a limitation on the devices to which the present application is applied, and a specific device may include more or less components than those shown, or combine some components, or have an arrangement of different components. It should be understood that the methods, apparatuses, and the like disclosed in the embodiments may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a division of one logic function, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or unit modules.
Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for processing image data exception, the method comprising:
acquiring image data, wherein the image data represents an object to be detected;
performing anomaly identification on a detection object in the image data based on an identification model corresponding to the detection object, and acquiring the emergency degree of the anomaly in the detection object needing medical treatment;
according to a detection object in the image data, determining a corresponding manual processing mechanism or personal terminal equipment corresponding to the abnormality in the detection object;
and sending the image data to a manual processing mechanism or personal terminal equipment corresponding to the abnormity in the detection object for processing according to the emergency degree.
2. The method for processing video data abnormality according to claim 1, wherein said sending the video data to a manual processing mechanism or a personal terminal device corresponding to the abnormality in the detection object for processing according to the degree of urgency includes:
based on the emergency degree, sorting the image data corresponding to different detection objects to obtain a sequence of the image data;
and sending the image data to a manual processing mechanism or a personal terminal device corresponding to the abnormality in the detection object for processing according to the sequence of the image data.
3. The method as claimed in claim 2, wherein the sending the video data to a manual processing mechanism or a personal terminal device corresponding to the abnormality in the detected object according to the emergency degree comprises:
and if the emergency degree is the highest level, sending the image data to the personal terminal equipment corresponding to the abnormality in the detection object for processing.
4. The method for processing the image data exception as claimed in claim 1, further comprising:
classifying the manual processing mechanism and the personal terminal equipment according to a preset detection object;
taking the classified manual processing mechanism and the personal terminal device as tree nodes, and establishing an emergency response tree;
when image data is responded, the executable nodes in the manual processing mechanism or the personal terminal equipment corresponding to the current detection object are judged by traversing the emergency response tree;
and processing the image data of the current detection object based on the executable node to obtain an analysis result of the image data.
5. The method for processing the image data exception as claimed in claim 1, further comprising:
classifying the manual processing mechanism and the personal terminal equipment according to a preset detection object;
according to a preset response sequence, sequencing the classified manual processing mechanisms and the personal terminal equipment to obtain a response sequence of each type of manual processing mechanism and personal terminal equipment to the image data;
based on the response sequence, judging a response object in a manual processing mechanism or personal terminal equipment corresponding to the current detection object;
and processing the image data of the current detection object based on the response object to obtain an analysis result of the image data.
6. The method for processing image data abnormality according to any one of claims 4 or 5, further comprising, after processing the image data of the current detection object and obtaining the analysis result of the image data:
judging whether the emergency degree of the abnormality in the detection object requiring medical treatment is false alarm or not according to the analysis result;
and if the detection result is false alarm, the emergency degree that the abnormality in the detection object needs medical treatment is cancelled.
7. The method for processing the image data abnormality according to claim 1, wherein before the abnormality recognition of the detection object in the image data is performed based on the recognition model corresponding to the detection object and the urgency level of the abnormality in the detection object requiring medical treatment is acquired, the method further includes:
and identifying a detection object in the image data, and determining an identification model corresponding to the detection object.
8. The method for processing the image data exception as claimed in claim 1, further comprising:
analyzing the image data according to the emergency degree of the abnormality in the detection object needing medical treatment to obtain initial diagnosis information;
and sending the initial diagnosis information and the image data to the manual processing mechanism or the personal terminal equipment for analysis to obtain target diagnosis information.
9. An apparatus for processing image data exception, the apparatus comprising: the system comprises an image data acquisition module, an abnormality identification module, a processing mechanism determination module and an abnormality processing module;
the image data acquisition module is used for acquiring image data, and the image data is image data representing a detection object;
the abnormality identification module is used for carrying out abnormality identification on the detection object in the image data based on an identification model corresponding to the detection object, and acquiring the emergency degree of the abnormality in the detection object which needs medical treatment;
the processing mechanism determining module is used for determining a manual processing mechanism or a personal terminal device corresponding to the abnormity in the detection object according to the detection object in the image data;
and the abnormity processing module is used for sending the image data to a manual processing mechanism or personal terminal equipment corresponding to the abnormity in the detection object for processing according to the emergency degree.
10. A storage medium comprising a processor and a memory, wherein the memory stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by the processor to implement the method for processing the image data exception according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353205.7A CN111192679B (en) | 2019-12-25 | 2019-12-25 | Method, device and storage medium for processing image data abnormality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353205.7A CN111192679B (en) | 2019-12-25 | 2019-12-25 | Method, device and storage medium for processing image data abnormality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111192679A true CN111192679A (en) | 2020-05-22 |
| CN111192679B CN111192679B (en) | 2024-04-19 |
Family
ID=70709376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911353205.7A Active CN111192679B (en) | 2019-12-25 | 2019-12-25 | Method, device and storage medium for processing image data abnormality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192679B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862778A (en) * | 2021-02-04 | 2021-05-28 | 上海联影智能医疗科技有限公司 | Scanning image detection method, electronic device and computer readable medium |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040205711A1 (en) * | 2003-04-10 | 2004-10-14 | Ishimitsu Michael Kazuo | System and method for creation of an object within an object hierarchy structure |
| JP2006245995A (en) * | 2005-03-03 | 2006-09-14 | Ricoh Co Ltd | Image-reading apparatus |
| TWI280866B (en) * | 2006-01-13 | 2007-05-11 | Associated Technology Corp Tai | Statistic measure for abnormal area image of human body |
| US20090279772A1 (en) * | 2008-05-12 | 2009-11-12 | General Electric Company | Method and System for Identifying Defects in NDT Image Data |
| US20110075938A1 (en) * | 2009-09-25 | 2011-03-31 | Eastman Kodak Company | Identifying image abnormalities using an appearance model |
| CN102918558A (en) * | 2010-01-28 | 2013-02-06 | 拉德罗吉克斯公司 | Methods and systems for analyzing, prioritizing, visualizing, and reporting medical images |
| CN104641397A (en) * | 2012-07-24 | 2015-05-20 | 爱克发医疗保健公司 | Method, apparatus and system for automated spine labeling |
| US20170330320A1 (en) * | 2016-05-13 | 2017-11-16 | National Jewish Health | Systems and methods for automatic detection and quantification of pathology using dynamic feature classification |
| CN107563431A (en) * | 2017-08-28 | 2018-01-09 | 西南交通大学 | A kind of image abnormity detection method of combination CNN transfer learnings and SVDD |
| CN107767935A (en) * | 2017-09-15 | 2018-03-06 | 深圳市前海安测信息技术有限公司 | Medical image specification processing system and method based on artificial intelligence |
| CN108288499A (en) * | 2018-01-22 | 2018-07-17 | 沈阳东软医疗系统有限公司 | A kind of automatic point is examined method and device |
| CN108305671A (en) * | 2018-01-23 | 2018-07-20 | 深圳科亚医疗科技有限公司 | By computer implemented medical image dispatching method, scheduling system and storage medium |
| CN109544551A (en) * | 2018-12-06 | 2019-03-29 | 合肥鑫晟光电科技有限公司 | The detection method and device of health status |
| CN109686444A (en) * | 2018-12-27 | 2019-04-26 | 上海联影智能医疗科技有限公司 | System and method for medical image classification |
| CN109738137A (en) * | 2019-01-02 | 2019-05-10 | 山东交通学院 | Earth and rockfill dam leakage real-time monitoring and fast diagnosis method based on image comparison |
| CN109767820A (en) * | 2018-05-29 | 2019-05-17 | 深圳市智影医疗科技有限公司 | A kind of diagnosis based on image/examining report generation method, device and equipment |
| CN110189306A (en) * | 2019-05-14 | 2019-08-30 | 上海联影智能医疗科技有限公司 | The corresponding compressing vessels of abnormal area determine method and apparatus in brain image |
| CN110210286A (en) * | 2019-04-17 | 2019-09-06 | 平安科技（深圳）有限公司 | Abnormality recognition method, device, equipment and storage medium based on eye fundus image |
| CN110321905A (en) * | 2019-07-11 | 2019-10-11 | 广东工业大学 | Abnormal area detection method, system and associated component based on semantic segmentation |
| CN110335253A (en) * | 2019-06-05 | 2019-10-15 | 平安科技（深圳）有限公司 | Eyes image processing method, device, equipment and computer readable storage medium |
| CN110348431A (en) * | 2019-08-26 | 2019-10-18 | 闫戎 | A kind of disease pre-warning method, device, equipment and system |
| CN110458154A (en) * | 2019-09-12 | 2019-11-15 | 腾讯科技（深圳）有限公司 | Face identification method, device and computer readable storage medium |
| CN110459303A (en) * | 2019-06-27 | 2019-11-15 | 浙江工业大学 | Medical imaging abnormal detector based on depth migration |
| CN110559007A (en) * | 2019-07-23 | 2019-12-13 | 北京赛迈特锐医疗科技有限公司 | Intelligent diagnosis system and method for skull CT flat scan image |
-
2019
- 2019-12-25 CN CN201911353205.7A patent/CN111192679B/en active Active
Patent Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040205711A1 (en) * | 2003-04-10 | 2004-10-14 | Ishimitsu Michael Kazuo | System and method for creation of an object within an object hierarchy structure |
| JP2006245995A (en) * | 2005-03-03 | 2006-09-14 | Ricoh Co Ltd | Image-reading apparatus |
| TWI280866B (en) * | 2006-01-13 | 2007-05-11 | Associated Technology Corp Tai | Statistic measure for abnormal area image of human body |
| US20090279772A1 (en) * | 2008-05-12 | 2009-11-12 | General Electric Company | Method and System for Identifying Defects in NDT Image Data |
| US20110075938A1 (en) * | 2009-09-25 | 2011-03-31 | Eastman Kodak Company | Identifying image abnormalities using an appearance model |
| CN102918558A (en) * | 2010-01-28 | 2013-02-06 | 拉德罗吉克斯公司 | Methods and systems for analyzing, prioritizing, visualizing, and reporting medical images |
| CN104641397A (en) * | 2012-07-24 | 2015-05-20 | 爱克发医疗保健公司 | Method, apparatus and system for automated spine labeling |
| US20170330320A1 (en) * | 2016-05-13 | 2017-11-16 | National Jewish Health | Systems and methods for automatic detection and quantification of pathology using dynamic feature classification |
| CN107563431A (en) * | 2017-08-28 | 2018-01-09 | 西南交通大学 | A kind of image abnormity detection method of combination CNN transfer learnings and SVDD |
| CN107767935A (en) * | 2017-09-15 | 2018-03-06 | 深圳市前海安测信息技术有限公司 | Medical image specification processing system and method based on artificial intelligence |
| CN108288499A (en) * | 2018-01-22 | 2018-07-17 | 沈阳东软医疗系统有限公司 | A kind of automatic point is examined method and device |
| CN108305671A (en) * | 2018-01-23 | 2018-07-20 | 深圳科亚医疗科技有限公司 | By computer implemented medical image dispatching method, scheduling system and storage medium |
| CN109767820A (en) * | 2018-05-29 | 2019-05-17 | 深圳市智影医疗科技有限公司 | A kind of diagnosis based on image/examining report generation method, device and equipment |
| CN109544551A (en) * | 2018-12-06 | 2019-03-29 | 合肥鑫晟光电科技有限公司 | The detection method and device of health status |
| CN109686444A (en) * | 2018-12-27 | 2019-04-26 | 上海联影智能医疗科技有限公司 | System and method for medical image classification |
| CN109738137A (en) * | 2019-01-02 | 2019-05-10 | 山东交通学院 | Earth and rockfill dam leakage real-time monitoring and fast diagnosis method based on image comparison |
| CN110210286A (en) * | 2019-04-17 | 2019-09-06 | 平安科技（深圳）有限公司 | Abnormality recognition method, device, equipment and storage medium based on eye fundus image |
| CN110189306A (en) * | 2019-05-14 | 2019-08-30 | 上海联影智能医疗科技有限公司 | The corresponding compressing vessels of abnormal area determine method and apparatus in brain image |
| CN110335253A (en) * | 2019-06-05 | 2019-10-15 | 平安科技（深圳）有限公司 | Eyes image processing method, device, equipment and computer readable storage medium |
| CN110459303A (en) * | 2019-06-27 | 2019-11-15 | 浙江工业大学 | Medical imaging abnormal detector based on depth migration |
| CN110321905A (en) * | 2019-07-11 | 2019-10-11 | 广东工业大学 | Abnormal area detection method, system and associated component based on semantic segmentation |
| CN110559007A (en) * | 2019-07-23 | 2019-12-13 | 北京赛迈特锐医疗科技有限公司 | Intelligent diagnosis system and method for skull CT flat scan image |
| CN110348431A (en) * | 2019-08-26 | 2019-10-18 | 闫戎 | A kind of disease pre-warning method, device, equipment and system |
| CN110458154A (en) * | 2019-09-12 | 2019-11-15 | 腾讯科技（深圳）有限公司 | Face identification method, device and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 杨晓慧;郑国芳;郭兴华;: "PACS对医学影像质量的控制与影响", 中国医疗设备, no. 11, 25 November 2010 (2010-11-25) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862778A (en) * | 2021-02-04 | 2021-05-28 | 上海联影智能医疗科技有限公司 | Scanning image detection method, electronic device and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111192679B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11850021B2 (en) | Dynamic self-learning medical image method and system | |
| US10937164B2 (en) | Medical evaluation machine learning workflows and processes | |
| US11710233B2 (en) | Three-dimensional medical image analysis method and system for identification of vertebral fractures | |
| CN106339571B (en) | Artificial neural network for classifying medical image data sets | |
| CN107004043B (en) | System and method for optimized detection and labeling of anatomical structures of interest | |
| Chauhan et al. | Role of gist and PHOG features in computer-aided diagnosis of tuberculosis without segmentation | |
| US9514416B2 (en) | Apparatus and method of diagnosing a lesion using image data and diagnostic models | |
| WO2014186838A1 (en) | A system and method for remote medical diagnosis | |
| CN106796621B (en) | Image report annotation recognition | |
| US11663718B2 (en) | Method for discriminating suspicious lesion in medical image, method for interpreting medical image, and computing device implementing the methods | |
| US20220301159A1 (en) | Artificial intelligence-based colonoscopic image diagnosis assisting system and method | |
| JP2019061579A (en) | Learning support device, operation method for learning support device, learning support program, learning support system, and terminal device | |
| CN112802000A (en) | Intelligent auxiliary diagnosis and treatment system for multi-modal medical images | |
| CN113470037A (en) | Data processing method, device and system | |
| CN112862778A (en) | Scanning image detection method, electronic device and computer readable medium | |
| CN104732086A (en) | Computer-assisted disease detection system based on cloud computing | |
| WO2024074921A1 (en) | Distinguishing a disease state from a non-disease state in an image | |
| CN111226287B (en) | Method, system, program product and medium for analyzing medical imaging data sets | |
| CN111192679B (en) | Method, device and storage medium for processing image data abnormality | |
| CN112236832A (en) | Diagnosis support system, diagnosis support method, and diagnosis support program | |
| CN112967246A (en) | X-ray image auxiliary device and method for clinical decision support system | |
| EP3624128A1 (en) | An apparatus and method for detecting an incidental finding | |
| WO2020030643A1 (en) | Processing medical images | |
| US11508065B2 (en) | Methods and systems for detecting acquisition errors in medical images | |
| Che et al. | Deep learning-based biological anatomical landmark detection in colonoscopy videos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |