CN111477323A - Serious disease machine recognition system based on artificial intelligence - Google Patents
Serious disease machine recognition system based on artificial intelligence Download PDFInfo
- Publication number
- CN111477323A CN111477323A CN202010259212.7A CN202010259212A CN111477323A CN 111477323 A CN111477323 A CN 111477323A CN 202010259212 A CN202010259212 A CN 202010259212A CN 111477323 A CN111477323 A CN 111477323A
- Authority
- CN
- China
- Prior art keywords
- image
- sliding
- sliding rack
- medical
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 201000010099 disease Diseases 0.000 title claims abstract description 19
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 19
- 238000003745 diagnosis Methods 0.000 claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000036285 pathological change Effects 0.000 claims abstract description 7
- 231100000915 pathological change Toxicity 0.000 claims abstract description 7
- 230000008054 signal transmission Effects 0.000 claims abstract description 4
- 239000011521 glass Substances 0.000 claims description 104
- 230000007246 mechanism Effects 0.000 claims description 49
- 230000003902 lesion Effects 0.000 claims description 27
- 229910001285 shape-memory alloy Inorganic materials 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000003709 image segmentation Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 241000257303 Hymenoptera Species 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000002431 foraging effect Effects 0.000 claims description 3
- 239000005337 ground glass Substances 0.000 claims description 3
- 208000028399 Critical Illness Diseases 0.000 claims 4
- 241001270131 Agaricus moelleri Species 0.000 claims 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 14
- 229910052742 iron Inorganic materials 0.000 description 7
- 238000001125 extrusion Methods 0.000 description 4
- 238000002591 computed tomography Methods 0.000 description 3
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012546 transfer 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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]
Abstract
The invention belongs to the technical field of artificial intelligence medical treatment, in particular to a serious disease machine identification system based on artificial intelligence; the medical system comprises an image terminal, a medical terminal and a management terminal; the image terminal and the medical terminal are in signal transmission with the management terminal through the cloud server; the image terminal adopts an image processing device to carry out scanning recognition processing on the CT image shot before the patient is subjected to the re-diagnosis; the medical terminal carries out etiological diagnosis by recognizing the pathological change position of the similar typical medical case recorded in the management data of the system to form an etiological report; the management database of the management terminal stores typical cases treated by the hospital and records the corresponding etiology reports corrected by medical personnel to form a database in the hospital; the self-learning of the recognition system is facilitated; the medical staff can conveniently make and plan the treatment plan again for the patient in the follow-up visit; effective treating doctor treatment quality and high treatment efficiency.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence medical treatment, and particularly relates to an artificial intelligence-based major disease machine identification system.
Background
At present, China has few good doctors, and basically focuses on a few large hospitals in a central city, so that patients all over the country need to be confronted by the hospitals, and common patients need to queue for several weeks or even months to be treated. Hospitals in remote areas really have few or no effective doctors called experts. The misdiagnosis rate of the hospitals to difficult and complicated diseases is always high, the misdiagnosis condition of treating large diseases and small diseases often occurs in small hospitals with poor medical conditions, the optimal diagnosis and treatment time of patients is delayed, and even the lives of the patients are threatened.
With the continuous development of computer technology, intelligent medical identification systems have been implemented.
For example, the chinese patent discloses an industrial intelligent medical big data system, the patent application number is 2019101290536, and the system includes a big data server and a plurality of hospital diagnosis and treatment modules connected thereto through a network, and the hospital diagnosis and treatment modules and the big data server perform real-time data transmission; and the big data server is respectively connected with the user terminal, the artificial intelligent diagnosis platform and the expert system. Through the artificial intelligence diagnosis based on big data, the user can upload physical examination data in real time and check the preliminary diagnosis result based on artificial intelligence, can carry out further diagnosis to the high risk user, realizes the reposition of redundant personnel to the disease.
Although the above patent can make preliminary diagnosis for the user through the artificial intelligence diagnosis system, when the patient with the existing serious disease needs to make a double-diagnosis, because the description of the serious disease suffered by the patient who makes a double-diagnosis is unclear, and the patient who makes a double-diagnosis is not treated in the hospital when the patient is ill, the CT picture of the previous treatment needs to be analyzed again, and then the medical care personnel is easy to make wrong judgment, and the phenomenon of unclear judgment appears, thereby affecting the treatment quality and the treatment efficiency of the treating doctor.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides an artificial intelligence-based serious disease machine recognition system which is mainly used for solving the problems that when a patient with the existing serious disease needs to be subjected to a re-diagnosis, the re-diagnosis patient cannot be treated in a hospital when the patient is ill, and the CT picture of the previous treatment needs to be analyzed again, so that the medical staff can make wrong judgments easily, and the judgment is unclear, so that the treatment quality of a treating doctor and the treatment efficiency are influenced.
The technical scheme adopted by the invention for solving the technical problems is as follows: the invention relates to a serious disease machine identification system based on artificial intelligence, which comprises an image terminal, a medical terminal and a management terminal; the image terminal and the medical terminal are in signal transmission with the management terminal through the cloud server;
the image terminal adopts an image processing device to perform scanning identification processing on the CT image shot before the patient is subjected to the re-diagnosis; the image terminal comprises an image input unit, an image segmentation unit and an image identification unit;
the image input unit adopts an image input mechanism and is used for inputting a plurality of CT images shot before the patient is subjected to the double-examination into the image scanning mechanism, the image scanning mechanism scans the images and inputs the scanned CT image information into the identification system;
the image segmentation unit is used for segmenting the CT image scanned, collected and input by the image input unit by adopting an image algorithm module, and can also be used for segmenting the CT image shot after the patient is subjected to a back-visit;
the image recognition unit is used for recognizing the CT image which is segmented enough by the image segmentation unit and recognizing the position of a focus or lesion in the scanned CT image;
the medical terminal comprises a lesion screening unit, a cause analysis unit and a cause diagnosis unit;
the lesion screening unit screens the position of the focus or lesion identified by the image identification unit of the CT image shot before the patient is subjected to the re-diagnosis and the position of the focus or lesion of the CT image shot after the patient is subjected to the re-diagnosis, so as to screen out the position of lesion position difference;
the etiology analysis unit analyzes the etiology of the differential lesion positions screened by the lesion screening unit through typical medical cases recorded in an intelligent database of the recognition system, wherein the etiology analysis unit comprises the density and the real component proportion of ground glass;
the etiology diagnosis unit is used for performing etiology diagnosis on the etiology of the different pathological change positions analyzed by the etiology analysis unit through recognizing the pathological change positions of similar typical medical cases recorded in the management data of the system to form an etiology report;
the management terminal comprises a report uploading unit, a report correcting unit and an intelligent database;
the report uploading unit transmits the etiology report diagnosed by the etiology diagnosis unit to an operation computer of a medical worker through a local area network in a hospital, and the medical worker preliminarily diagnoses the etiology of the patient through the operation computer;
the report correction unit is used for combining the etiology report diagnosed by the system with the etiology judgment of the medical staff, and further correcting the etiology report generated by the system;
the intelligent database stores typical cases treated by a hospital and records the corresponding etiology reports corrected by medical personnel to form a database in the hospital; the self-learning of the recognition system is facilitated.
Preferably, the image algorithm module adopts an ant colony algorithm; the ant colony algorithm is a probability algorithm which is obtained in the process of researching foraging of ants and is used for searching for an optimized path; in medical image processing, image segmentation is often performed based on the similarity of gray levels inside regions and the discontinuity of gray levels between regions; therefore, the CT image input by the image input unit can be segmented by utilizing the positive feedback effect of the ant colony algorithm and a distributed computing mode.
Preferably, the management terminal further comprises a data synchronization unit; the data synchronization unit transmits the CT image data diagnosed and labeled by medical personnel with abundant clinical experience to the identification system in real time and synchronously in a manual input mode; the data synchronization unit can also record medical records issued by a treating doctor to a patient or electronic medical record data of the patient into the identification system in a wireless transmission mode.
The image processing device comprises an image scanning mechanism and an image input mechanism, wherein the image scanning mechanism comprises an image scanner and fixed guide strips, the upper end and the lower end of the image scanner are fixedly provided with the fixed guide strips, the side surface of the image scanner is provided with the image input mechanism, the image input mechanism comprises a picture box, a transparent glass frame, a rotating column, a conveying belt, an elastic memory alloy plate, an L type elastic block, a guide sliding strip and a sliding baffle, the picture box is fixedly arranged on the side wall of the image scanner, the upper end surface of the picture box is provided with a plurality of plugging cavities, the transparent glass frame is plugged into the picture box in a sliding mode through the plugging cavities, a CT picture is plugged into the transparent glass frame, a pair of rotating columns is vertically and rotatably arranged at the right side position of the picture box and sleeved with the conveying belt, the other pair of rotating columns is horizontally arranged at the bottom end position of the picture box and sleeved with the conveying belt, one pair of rotating columns is arranged on the bottom end position of the picture box and is connected with the elastic memory alloy plate, the sliding strip arranged on the sliding guide strip, the sliding guide strip is arranged on the sliding strip, the sliding guide strip, the sliding block, the sliding guide strip is arranged on the sliding guide strip, the sliding block is arranged on the sliding guide strip, the sliding block, the sliding strip is arranged on the sliding guide strip, the sliding guide strip, the sliding strip is arranged on the sliding strip, the sliding block, the sliding strip is arranged on the sliding strip, the sliding strip is fixed end surface of the sliding strip, the sliding strip is arranged on the sliding strip, the sliding strip;
when the transparent glass slide guiding mechanism is used for guiding a CT scanning glass slide plate to slide to a CT scanning guide frame, the medical staff can respectively insert a plurality of CT pictures into the transparent glass frame, then the CT scanning guide frame is inserted into a picture box through an insertion cavity, meanwhile, the medical staff can insert the transparent glass frame into the picture box through a clamping device, the bottom end of the picture box is rotatably provided with a L type elastic block which can support the transparent glass frame, an electromagnetic block arranged on the upper end face of a L type elastic block is electrified to adsorb an iron block at the bottom end of the transparent glass frame, the transparent glass frame is adsorbed onto a L type elastic block of a conveying belt, the conveying belt drives the horizontally arranged conveying belt to rotate along with the rotation of the tubular motor, the conveying belt drives the plurality of transparent glass frames to move towards the front end face of the picture box, and after the transparent glass frame moves to the guide frame, the transparent glass scanning guide frame can slide to the glass scanning glass frame to the glass frame, so that the transparent scanning glass scanning guide frame slides to the glass scanning guide frame, the glass scanning guide frame can slide to the glass scanning glass frame, the glass scanning guide frame, the glass scanning glass frame can slide to the glass frame, the glass scanning glass frame, the glass scanning glass frame, the glass scanning glass frame, the scanning glass.
Preferably, the guide sliding mechanism comprises an elastic guide plate, a sliding elastic plate and a limiting spring, the elastic guide plate is fixedly arranged on the side wall of the fixed guide strip, the upper end surface of the elastic guide plate is provided with an elastic memory alloy plate in a sliding manner, the elastic guide plate is provided with a guide sliding groove, the sliding elastic plate is inserted into the guide sliding groove in a sliding manner through the limiting spring, the side end of the sliding elastic plate is flush with the upper end surface of the side wall of the L type elastic block, the upper surface of the sliding elastic plate is provided with a magnet block, when the conveyor belt drives the transparent glass plate magnetically attracted on the L type elastic block to move, after the joint of the transparent glass plate and the L type elastic block is contacted with the sliding elastic plate, the conveyor belt rotates continuously, at the moment, a control unit of the image terminal controls the power loss of an electromagnet arranged on the L type elastic block, so that the sliding elastic plate can be inserted into the bottom end of the transparent glass frame, the side wall of the L type elastic block can extrude and push the transparent glass frame onto the sliding elastic plate to push the sliding elastic plate to the sliding elastic plate to the sliding elastic plate on the sliding elastic frame, and then push the sliding elastic frame of the sliding elastic scanning glass frame to push the CT scanner, the lower elastic scanning glass frame, and the elastic scanning glass frame, the sliding elastic scanning glass plate, the elastic frame, the elastic scanning glass plate, the elastic scanning glass frame slides, the elastic scanning glass frame.
Preferably, the upper end surface of the side wall of the L-type elastic block is provided with an arc-shaped fillet, the end part of the sliding elastic plate is provided with a conical arc surface, the conical arc surface is inserted into the arc-shaped fillet in a sliding manner, when the device works, after the end part of the sliding elastic plate is contacted with the side wall of the L-type elastic block, the conical arc surface arranged at the end part of the sliding elastic plate can be rapidly inserted into the arc-shaped fillet of the L-type elastic block, along with the continuous movement of the L-type elastic block, the conical arc surface at the end part of the sliding elastic plate can form a transition surface to be inserted into the upper surface of the L-type elastic block, so that the transparent glass frame can be rapidly and stably transferred onto the sliding elastic plate, and when the L-type elastic block is extruded with the sliding elastic plate, the phenomenon that the transparent glass frame is inclined when being transferred onto the sliding elastic plate due to the thicker end part of the.
Preferably, the side face of the end part of the elastic memory alloy plate is provided with a clamping groove, the width of the clamping groove is larger than the thickness of the transparent glass plate, the inner side wall of the clamping groove is provided with a frosted layer, when the glass frame is attached to the side wall of the guide sliding strip under the extrusion force of the L-type elastic block, the transparent glass frame can be attached to the clamping groove formed in the elastic memory alloy plate, the clamping groove can play a role in laterally pushing and limiting the transparent glass plate, and the phenomenon that the transparent glass frame inclines when sliding due to the fact that the contact area of the transparent glass frame and the side end face of the elastic memory alloy plate is too small is effectively prevented, and further stable and accurate sliding of the transparent glass frame in the fixed guide strip is influenced.
The invention has the following beneficial effects:
1. according to the medical terminal, the image processing device is adopted to scan, identify and process the CT images shot before the patient is subjected to the re-diagnosis, the medical terminal is convenient for medical staff to quickly know the contents of a plurality of CT images shot before the patient is subjected to the re-diagnosis through the identification system, and the medical staff can conveniently make and plan the treatment scheme of the patient subjected to the re-diagnosis; the method can effectively prevent the patients who are subjected to the follow-up diagnosis from having unclear description of the major diseases, and the patients who are subjected to the follow-up diagnosis are not treated in the hospital when the patients are ill, so that the medical care personnel can make wrong judgment, the phenomenon that the judgment is unclear occurs, the CT pictures of the previous treatment need to be analyzed again, and the treatment quality of the treatment doctor and the treatment efficiency are influenced.
2. According to the invention, through the matching of the image scanner mechanism and the image input mechanism, the image input mechanism can carry out the same-position conveying operation on a plurality of CT pictures, so that the plurality of CT pictures can be accurately and efficiently conveyed to the side surface of the image scanner, the image scanner can carry out the rapid scanning and reading operation on the positioned CT pictures, and meanwhile, the transparent glass frame can carry out the installation operation on the CT pictures with different sizes, so that the image input mechanism can conveniently carry out the positioning scanning operation on the CT pictures with different sizes, the image input unit can conveniently carry out the accurate high-quality scanning operation on the CT pictures, and the artificial intelligent diagnosis and analysis operation of the focus or lesion position of a patient by the identification system is improved.
Drawings
The invention will be further explained with reference to the drawings.
FIG. 1 is a flow chart of the identification system of the present invention;
FIG. 2 is an assembly view of the image scanning mechanism and the image input mechanism of the present invention;
FIG. 3 is an internal structural view of an image input mechanism of the present invention;
FIG. 4 is a cross-sectional view of the picture box of the present invention;
FIG. 5 is an enlarged view of a portion of the invention at A in FIG. 4;
FIG. 6 is an assembly view of the guide slide mechanism of the present invention;
in the figure, an image scanning mechanism 1, an image scanner 2, a fixed guide bar 3, an image input mechanism 4, a picture box 41, a splicing chamber 411, a transparent glass frame 42, an iron block 421, a rotating column 43, a conveying belt 44, an elastic memory alloy plate 45, a clamping groove 451, an L type elastic block 46, a guide sliding bar 47, a sliding baffle 48, an electromagnetic block 5, a guide sliding mechanism 6, an elastic guide plate 61, a guide sliding groove 611, a sliding elastic plate 62 and a limit spring 63.
Detailed Description
The following describes a serious disease machine recognition system based on artificial intelligence according to an embodiment of the present invention with reference to fig. 1 to 6.
As shown in fig. 1-6, the serious disease machine recognition system based on artificial intelligence of the present invention comprises an image terminal, a medical terminal and a management terminal; the image terminal and the medical terminal are in signal transmission with the management terminal through the cloud server;
the image terminal adopts an image processing device to perform scanning identification processing on the CT image shot before the patient is subjected to the re-diagnosis; the image terminal comprises an image input unit, an image segmentation unit and an image identification unit;
the image input unit adopts an image input mechanism 4 and is used for inputting a plurality of CT images shot before the patient is subjected to the double-examination into the image scanning mechanism 1, the image scanning mechanism 1 scans the images and inputs the scanned CT image information into the identification system;
the image segmentation unit is used for segmenting the CT image scanned, collected and input by the image input unit by adopting an image algorithm module, and can also be used for segmenting the CT image shot after the patient is subjected to a back-visit;
the image recognition unit is used for recognizing the CT image which is segmented enough by the image segmentation unit and recognizing the position of a focus or lesion in the scanned CT image;
the medical terminal comprises a lesion screening unit, a cause analysis unit and a cause diagnosis unit;
the lesion screening unit screens the position of the focus or lesion identified by the image identification unit of the CT image shot before the patient is subjected to the re-diagnosis and the position of the focus or lesion of the CT image shot after the patient is subjected to the re-diagnosis, so as to screen out the position of lesion position difference;
the etiology analysis unit analyzes the etiology of the differential lesion positions screened by the lesion screening unit through typical medical cases recorded in an intelligent database of the recognition system, wherein the etiology analysis unit comprises the density and the real component proportion of ground glass;
the etiology diagnosis unit is used for performing etiology diagnosis on the etiology of the different pathological change positions analyzed by the etiology analysis unit through recognizing the pathological change positions of similar typical medical cases recorded in the management data of the system to form an etiology report;
the management terminal comprises a report uploading unit, a report correcting unit and an intelligent database;
the report uploading unit transmits the etiology report diagnosed by the etiology diagnosis unit to an operation computer of a medical worker through a local area network in a hospital, and the medical worker preliminarily diagnoses the etiology of the patient through the operation computer;
the report correction unit is used for combining the etiology report diagnosed by the system with the etiology judgment of the medical staff, and further correcting the etiology report generated by the system;
the intelligent database stores typical cases treated by a hospital and records the corresponding etiology reports corrected by medical personnel to form a database in the hospital; the self-learning of the recognition system is facilitated.
As an embodiment of the present invention, the image algorithm module adopts an ant colony algorithm; the ant colony algorithm is a probability algorithm which is obtained in the process of researching foraging of ants and is used for searching for an optimized path; in medical image processing, image segmentation is often performed based on the similarity of gray levels inside regions and the discontinuity of gray levels between regions; therefore, the CT image input by the image input unit can be segmented by utilizing the positive feedback effect of the ant colony algorithm and a distributed computing mode.
As an embodiment of the present invention, the management terminal further includes a data synchronization unit; the data synchronization unit transmits the CT image data diagnosed and labeled by medical personnel with abundant clinical experience to the identification system in real time and synchronously in a manual input mode; the data synchronization unit can also record medical records issued by a treating doctor to a patient or electronic medical record data of the patient into the identification system in a wireless transmission mode.
As an embodiment of the invention, the image processing device comprises an image scanning mechanism 1 and an image input mechanism 4, wherein the image scanning mechanism 1 comprises an image scanner 2 and a fixed guide bar 3, the upper end and the lower end of the image scanner 2 are fixedly provided with the fixed guide bar 3, the side surface of the image scanner 2 is provided with the image input mechanism 4, the image input mechanism 4 comprises a picture box 41, a transparent glass frame 42, a rotating column 43, a conveying belt 44, elastic memory alloy plates 45, L type elastic blocks 46, a guide slide bar 47 and a sliding baffle 48, the picture box 41 is fixedly arranged on the side wall of the image scanner 2, the upper end surface of the picture box 41 is provided with a plurality of inserting cavities 411, the transparent glass frame 42 is inserted into the picture box 41 in a sliding manner through the inserting cavities 411, a CT picture is inserted into the transparent glass frame 42, a pair of the rotating column 43 is vertically rotatably arranged on the right side surface of the picture box 41, the rotating column 43 is connected with the transparent glass frame 41, the sliding guide bar 47 is arranged on the sliding surface of the sliding iron plate 41, the sliding guide bar 44, the sliding guide bar 47, the sliding guide bar is arranged on the sliding surface of the sliding iron plate 45, the sliding guide bar 42, the sliding guide bar 6, the sliding iron plate is arranged on the sliding guide bar 6, the sliding iron plate, the sliding guide bar guide 4 is arranged on the sliding guide bar guide 4, the sliding guide bar guide;
when the medical staff needs to treat a patient who is subjected to a double-diagnosis, the patient who is subjected to the double-diagnosis needs to transfer a CT picture shot before the double-diagnosis to the medical staff for observation, the focus or the lesion position of the patient who is subjected to the double-diagnosis needs to be observed, whether the patient who is subjected to the double-diagnosis has a relapse or other lesion positions during rehabilitation is treated, the medical staff can respectively insert a plurality of CT pictures into the transparent glass frame 42 and then insert the CT pictures into the picture box 41 through the insertion cavity 411, meanwhile, the medical staff can insert the transparent glass frame 42 into the picture box 41 through the clamping device, the bottom end of the picture box 41 is rotatably provided with the elastic block 46 which can support the transparent glass frame 42, the electromagnetic block 5 arranged on the upper end face of the L-type elastic block 46 is electrically connected to adsorb the iron block 421 at the bottom end of the transparent glass frame 42, the transparent glass frame 42 is adsorbed to the elastic block L-shaped elastic block of the conveying belt 44, the tubular motor drives the horizontally arranged conveying belt 44 to rotate, the conveying belt 44 which drives the transparent glass frame 44 to drive the transparent glass frame 42 to rotate, the conveying belt 44 which is horizontally arranged, the conveying belt 44 which drives the transparent glass frame 42 to drive the transparent glass frame to slide, the transparent glass frame to slide along the transparent glass frame, the transparent glass frame 42, the transparent glass frame 42, the transparent glass frame can drive the transparent glass frame, the transparent glass scanning guide mechanism to slide, the transparent glass scanning guide mechanism, the transparent glass frame, the transparent glass scanning guide mechanism can slide, the transparent glass frame, the transparent glass scanning glass frame, the transparent glass scanning mechanism can slide, the transparent glass scanning mechanism can slide, the scanning mechanism can slide, the scanning mechanism can slide, the scanning mechanism can slide the scanning mechanism, the scanning mechanism can slide the.
As an embodiment of the invention, the guide sliding mechanism 6 comprises an elastic guide plate 61, a sliding elastic plate 62 and a limit spring 63, wherein the elastic guide plate 61 is fixedly arranged on the side wall of the fixed guide strip 3, the upper end surface of the elastic guide plate 61 is provided with an elastic memory alloy plate 45 in a sliding manner, the elastic guide plate 61 is provided with a guide sliding groove 611, the sliding elastic plate 62 is inserted in the guide sliding groove 611 in a sliding manner through the limit spring 63, the side end of the sliding elastic plate 62 is flush with the upper end surface of the side wall of the L type elastic block 46, and the upper surface of the sliding elastic plate 62 is provided with a magnet 421;
when the CT scanner scanning device works, the conveying belt 44 drives the transparent glass plate magnetically attracted on the L type elastic block 46 to move, after the joint of the transparent glass plate and the L type elastic block 46 is in contact with the sliding elastic plate 62, along with the continuous rotation of the conveying belt 44, the control unit of the image terminal controls the electromagnet arranged on the L type elastic block 46 to lose power, so that the sliding elastic plate 62 can be inserted into the bottom end of the transparent glass frame 42, meanwhile, the side wall of the L type elastic block 46 can extrude and push the transparent glass frame 42 onto the sliding elastic plate 62, at the moment, the magnet 421 arranged on the upper end face of the sliding elastic plate 62 can be electrified to fix the transparent glass frame 42 onto the sliding elastic plate 62, then the conveying belt 44 continues to rotate, the extrusion force of the sliding elastic plate 62 by the L type elastic block 46 on the sliding elastic guide plate 61 can enable the sliding elastic plate 62 to slide on the elastic guide plate 61, at the same time, the transparent glass frame 42 is attached to the side wall of the fixed guide bar 3, at the magnet 421 on the sliding elastic plate 62 loses power, the sliding elastic plate 62 is fixed under the L type elastic block 46, then the extrusion force is generated, the sliding elastic plate 62 is fixed under the sliding elastic block 46, the sliding elastic plate 62, the sliding glass frame 42 can be further, the sliding glass frame 44 can be pushed to push the sliding glass frame to push the CT scanner scanning device to push the sliding glass frame to move, the CT.
In an embodiment of the invention, an arc-shaped fillet is arranged on the upper end face of the side wall of the L-type elastic block 46, a tapered arc face is arranged at the end part of the sliding elastic plate 62 and is slidably inserted into the arc-shaped fillet, when the sliding elastic plate 62 is in contact with the side wall of the L-type elastic block 46, the tapered arc face arranged at the end part of the sliding elastic plate 62 is rapidly inserted into the arc-shaped fillet of the L-type elastic block 46, and with the continuous movement of the L-type elastic block 46, the tapered arc face at the end part of the sliding elastic plate 62 forms a transition face to be inserted into the upper surface of the L-type elastic block 46, so that the transparent glass frame 42 can be rapidly and stably transferred onto the sliding elastic plate 62, and the phenomenon that the transparent glass frame 42 is inclined on the sliding elastic plate 62 due to the thicker end part of the sliding elastic plate 62 when the L-type elastic block 46 is pressed against the sliding elastic plate 62 is effectively prevented, and further the stable movement operation of the transparent glass frame 42 is.
As an embodiment of the invention, the side surface of the end part of the elastic memory alloy plate 45 is provided with a clamping groove 451, the width of the clamping groove 451 is larger than the thickness of the transparent glass plate, the inner side wall of the clamping groove 451 is provided with a frosted layer, when the sliding elastic plate 62 drives the transparent glass frame 42 to be attached to the side wall of the guide slide bar 47 under the extrusion force of the L type elastic block 46, the transparent glass frame 42 can be attached to the clamping groove 451 arranged on the elastic memory alloy plate 45, the clamping groove 451 can play a side pushing and limiting role on the transparent glass plate, and the phenomenon that the side end surface contact area of the transparent glass frame 42 and the elastic memory alloy plate 45 is too small, so that the transparent glass frame 42 is inclined during sliding, and further the stable and accurate sliding of the transparent glass frame 42 in the fixed guide bar 3 is influenced.
In the description of the present invention, it is to be understood that the terms "center", "front", "rear", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore, should not be taken as limiting the scope of the present invention.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from its scope. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (7)
1. Serious disease machine identification system based on artificial intelligence, its characterized in that: the medical system comprises an image terminal, a medical terminal and a management terminal; the image terminal and the medical terminal are in signal transmission with the management terminal through the cloud server;
the image terminal adopts an image processing device to perform scanning identification processing on the CT image shot before the patient is subjected to the re-diagnosis; the image terminal comprises an image input unit, an image segmentation unit and an image identification unit;
the image input unit adopts an image input mechanism (4) and is used for inputting a plurality of CT images shot before the patient is subjected to the double-examination into the image scanning mechanism (1), the image scanning mechanism (1) scans the images and inputs the scanned CT image information into the recognition system;
the image segmentation unit is used for segmenting the CT image scanned, collected and input by the image input unit by adopting an image algorithm module, and can also be used for segmenting the CT image shot after the patient is subjected to a back-visit;
the image recognition unit is used for recognizing the CT image which is segmented enough by the image segmentation unit and recognizing the position of a focus or lesion in the scanned CT image;
the medical terminal comprises a lesion screening unit, a cause analysis unit and a cause diagnosis unit;
the lesion screening unit screens the position of the focus or lesion identified by the image identification unit of the CT image shot before the patient is subjected to the re-diagnosis and the position of the focus or lesion of the CT image shot after the patient is subjected to the re-diagnosis, so as to screen out the position of lesion position difference;
the etiology analysis unit analyzes the etiology of the differential lesion positions screened by the lesion screening unit through typical medical cases recorded in an intelligent database of the recognition system, wherein the etiology analysis unit comprises the density and the real component proportion of ground glass;
the etiology diagnosis unit is used for performing etiology diagnosis on the etiology of the different pathological change positions analyzed by the etiology analysis unit through the pathological change positions of the similar typical medical cases recorded in the intelligent database of the recognition system to form an etiology report;
the management terminal comprises a report uploading unit, a report correcting unit and an intelligent database;
the report uploading unit transmits the etiology report diagnosed by the etiology diagnosis unit to an operation computer of a medical worker through a local area network in a hospital, and the medical worker preliminarily diagnoses the etiology of the patient through the operation computer;
the report correction unit is used for combining the etiology report diagnosed by the system with the etiology judgment of the medical staff, and further correcting the etiology report generated by the system;
the intelligent database stores typical cases treated by a hospital and records the corresponding etiology reports corrected by medical personnel to form a database in the hospital; the self-learning of the recognition system is facilitated.
2. The artificial intelligence based critical illness machine identification system of claim 1, characterized by: the image algorithm module adopts an ant colony algorithm; the ant colony algorithm is a probability algorithm which is obtained in the process of researching foraging of ants and is used for searching for an optimized path; in medical image processing, image segmentation is carried out based on the similarity of gray scales inside regions and the discontinuity of gray scales between the regions; therefore, the CT image input by the image input unit can be segmented by utilizing the positive feedback effect of the ant colony algorithm and a distributed computing mode.
3. The artificial intelligence based critical illness machine identification system of claim 1, characterized by: the management terminal also comprises a data synchronization unit; the data synchronization unit transmits the CT image data diagnosed and labeled by medical personnel with abundant clinical experience to the identification system in real time and synchronously in a manual input mode; the data synchronization unit can also record medical records issued by a medical doctor to a patient or electronic medical record data of the patient into the identification system in a wireless transmission mode.
4. The system for identifying the serious disease machine based on the artificial intelligence is characterized by comprising an image scanner (2) mechanism (1) and an image input mechanism (4), wherein the image scanner (2) mechanism (1) comprises an image scanner (2) and a fixed guide bar (3), the upper end and the lower end of the image scanner (2) are fixedly provided with the fixed guide bar (3), the side surface of the image scanner (2) is provided with the image input mechanism (4), the image input mechanism (4) comprises a picture box (41), a transparent glass frame (42), a rotating column (43), a conveying belt (44), an elastic memory alloy plate (45), an L type elastic block (46), a guide slide bar (47) and a sliding baffle (48), the picture box (41) is fixedly arranged on the side wall of the image scanner (2), the upper end surface of the picture box (41) is provided with a plurality of inserting cavities (411) through inserting cavities (411) and is slidably inserted into the picture box (41), the sliding column guide bar (47) is arranged on the outer wall of the conveying belt (44), the sliding column guide bar (41) and the sliding column guide bar (44), the sliding column guide bar (44) is arranged on the sliding rack (44), the sliding rack (41), the sliding rack (44) is arranged on the sliding rack (44), the sliding rack (41) and the sliding rack (44), the sliding rack (44) is arranged on the sliding rack (44), the sliding rack (41), the sliding rack (44), the sliding rack (41) is arranged on the sliding rack (44), the sliding rack (4) is arranged on the sliding rack (4), the sliding rack (4) and the sliding rack (4), the sliding rack (4) is arranged on the sliding rack (4), the sliding rack (6), the sliding rack (4), the sliding rack (6), the sliding rack (4) is arranged on the sliding rack (4), the sliding rack (6), the sliding rack (4) and the sliding rack (4), the sliding rack (6), the sliding rack (4) is arranged on the sliding rack (4), the sliding rack (6), the sliding rack (4) and the sliding rack (4), the sliding rack (.
5. The important disease machine recognition system based on artificial intelligence is characterized in that the guide sliding mechanism (6) comprises an elastic guide plate (61), a sliding elastic plate (62) and a limiting spring (63), the elastic guide plate (61) is fixedly arranged on the side wall of the fixed guide strip (3), an elastic memory alloy plate (45) is arranged on the upper end face of the elastic guide plate (61) in a sliding mode, a guide sliding groove (611) is formed in the elastic guide plate (61), the sliding elastic plate (62) is inserted into the guide sliding groove (611) in a sliding mode through the limiting spring (63), the side end of the sliding elastic plate (62) is flush with the upper end face of the side wall of the L type elastic block (46), and a magnet block (421) is arranged on the upper surface of the sliding elastic plate (62).
6. The artificial intelligence based critical illness machine identification system according to claim 5, wherein the L-type elastic block (46) is provided with an arc-shaped fillet on the upper end face of the side wall, the sliding elastic plate (62) is provided with a conical arc on the end, and the conical arc is inserted into the arc-shaped fillet in a sliding mode.
7. The artificial intelligence based critical illness machine identification system of claim 6, wherein: the side surface of the end part of the elastic memory alloy plate (45) is provided with a clamping groove (451), and the width of the clamping groove (451) is larger than the thickness of the transparent glass plate; and a frosted layer is arranged on the inner side wall of the clamping groove (451).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010259212.7A CN111477323A (en) | 2020-04-03 | 2020-04-03 | Serious disease machine recognition system based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010259212.7A CN111477323A (en) | 2020-04-03 | 2020-04-03 | Serious disease machine recognition system based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111477323A true CN111477323A (en) | 2020-07-31 |
Family
ID=71750506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010259212.7A Pending CN111477323A (en) | 2020-04-03 | 2020-04-03 | Serious disease machine recognition system based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111477323A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114093505A (en) * | 2021-11-17 | 2022-02-25 | 山东省计算中心(国家超级计算济南中心) | Cloud-edge-end-architecture-based pathological detection system and method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109712705A (en) * | 2018-12-19 | 2019-05-03 | 中国石油大学(华东) | A kind of cholelithiasis intelligent diagnostics APP based on deep learning |
WO2019103912A2 (en) * | 2017-11-22 | 2019-05-31 | Arterys Inc. | Content based image retrieval for lesion analysis |
CN109872814A (en) * | 2019-03-04 | 2019-06-11 | 中国石油大学(华东) | A kind of cholelithiasis intelligent auxiliary diagnosis system based on deep learning |
US20190326007A1 (en) * | 2018-04-24 | 2019-10-24 | Siemens Healthcare Gmbh | Imaging and reporting combination in medical imaging |
-
2020
- 2020-04-03 CN CN202010259212.7A patent/CN111477323A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019103912A2 (en) * | 2017-11-22 | 2019-05-31 | Arterys Inc. | Content based image retrieval for lesion analysis |
US20190326007A1 (en) * | 2018-04-24 | 2019-10-24 | Siemens Healthcare Gmbh | Imaging and reporting combination in medical imaging |
CN109712705A (en) * | 2018-12-19 | 2019-05-03 | 中国石油大学(华东) | A kind of cholelithiasis intelligent diagnostics APP based on deep learning |
CN109872814A (en) * | 2019-03-04 | 2019-06-11 | 中国石油大学(华东) | A kind of cholelithiasis intelligent auxiliary diagnosis system based on deep learning |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114093505A (en) * | 2021-11-17 | 2022-02-25 | 山东省计算中心(国家超级计算济南中心) | Cloud-edge-end-architecture-based pathological detection system and method |
CN114093505B (en) * | 2021-11-17 | 2022-06-17 | 山东省计算中心(国家超级计算济南中心) | Cloud-edge-end-architecture-based pathological detection system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Shi et al. | Review of artificial intelligence techniques in imaging data acquisition, segmentation, and diagnosis for COVID-19 | |
US7346203B2 (en) | Methods and apparatus for processing image data to aid in detecting disease | |
CN107133969B (en) | A kind of mobile platform moving target detecting method based on background back projection | |
CN110911009A (en) | Clinical diagnosis aid decision-making system and medical knowledge map accumulation method | |
CN109272048A (en) | A kind of mode identification method based on depth convolutional neural networks | |
McBroom et al. | The clinicopathological meeting: a means of auditing diagnostic performance | |
CN111477323A (en) | Serious disease machine recognition system based on artificial intelligence | |
CN109934824B (en) | Method and system for detecting cervical vertebra and spinal cord height signals | |
KR100791021B1 (en) | Apparatus for pet-mri fusion table system | |
CN117115045A (en) | Method for improving medical image data quality based on Internet generation type artificial intelligence | |
CN112885464A (en) | Internal nasal disease real-time auxiliary diagnosis and treatment system based on Att-Res2-CE-Net | |
CN110728660B (en) | Method and device for lesion segmentation based on ischemic stroke MRI detection mark | |
CN112288752A (en) | Full-automatic coronary calcified focus segmentation method based on chest flat scan CT | |
Zhang et al. | Multistep Automated Data Labelling Procedure (MADLaP) for thyroid nodules on ultrasound: An artificial intelligence approach for automating image annotation | |
CN110132844A (en) | A kind of cell image data collection system and method, information data processing terminal | |
CN111077153A (en) | Multifunctional sperm quality analysis system | |
CN115035086A (en) | Intelligent tuberculosis skin test screening and analyzing method and device based on deep learning | |
CN110458087B (en) | Patient problem part labeling method based on deep learning | |
Nie et al. | Application of structural similarity analysis of visually salient areas and hierarchical clustering in the screening of similar wireless capsule endoscopic images | |
CN115311302B (en) | Femoral head avascular necrosis staged diagnostic system and storage medium | |
Fiaidhi et al. | An investigation into crohn’s disease lesions variability sensing using video colonoscopy and machine learning techniques | |
Scharcanski et al. | Diagnostic hysteroscopy video summarization and browsing | |
Du et al. | Chest X-ray Quality Assessment Method with Medical Domain Knowledge Fusion | |
CN114881980A (en) | Deep learning training method for clinical liver ultrasonic standard section recognition | |
CN117710325A (en) | Method and system for automatically identifying and tracking parathyroid glands in endoscopic thyroid surgery |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240315 |
|
AD01 | Patent right deemed abandoned |