A multimodal imaging film reading device
By designing a multi-modal image reading device, combining the film and the film reading device for information interoperability, the accurate positioning of the sample and efficient image feature extraction are achieved, and the recognition rate and accuracy of medical images are improved.
Patent Information
- Application Number
- CN202210185730.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-02-28
- Publication Date
- 2025-08-05
- Estimated Expiration
- 2042-02-28
AI Technical Summary
In the prior art, the imaging system and the image processing system are relatively independent, resulting in poor medical image feature extraction effect.
A multi-modal image reading device is designed, combining the film picking device and the film reading device for information interoperability, accurately positioning and fixing of samples through the luminous back plate and the clamping component, and image features are extracted and displayed using the main control module.
It improves the recognition rate and accuracy of medical images, real-time reading of video images on the display module and auxiliary display of diagnostic results.
Smart Images

Figure CN114628025B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of film reading devices, and in particular to a multi-modal imaging film reading device. Background Art
[0002] Medical imaging refers to the technology and processing process of obtaining internal tissue images of the human body or a part of the human body in a non-invasive manner for medical treatment or medical research. It includes the following two relatively independent research directions: medical imaging systems and medical image processing.
[0003] The former refers to the process of image formation, including research on issues such as imaging mechanisms, imaging devices, and imaging system analysis; the latter refers to further processing of the obtained images, the purpose of which is either to restore the originally unclear images, or to highlight certain feature information in the images, or to perform pattern classification on the images, etc. Chinese Patent Application No. CN110321946A discloses a multi-modal medical image recognition method and device based on deep learning, which uses a medical imaging device to collect medical image data; an image enhancement algorithm to enhance the collected images; an extraction program to extract the features of the collected images; a recognition program to recognize the extracted features; a conversion program to perform conversion operations on different modal medical images; a printer to print the collected images; and a display to display the information of the collected medical image data. The present invention improves the effect of image feature extraction through an image feature extraction module; at the same time, through the modal conversion module, by means of three-dimensional reconstruction, registration, and segmentation, it ensures that the corresponding images of the first modal image and the second modal image are highly matched;
[0004] However, in the prior art, the imaging system and the image processing are two relatively independent systems; the effect of medical image feature extraction in the image processing system is poor.
[0005] To solve the above problems, a multi-modal imaging film reading device is proposed in the present application. Summary of the Invention
[0006] (I) Invention Objectives
[0007] To solve the technical problems in the background art, the present invention proposes a multi-modal imaging film reading device. In the present invention, the photographing device and the film reading device are combined for information intercommunication, and the video image of the photographing can be read on the display module, which can improve the recognition rate compared with the traditional method of reading sample films and has higher accuracy.
[0008] (II) Technical Solutions
[0009] To solve the above technical problems, the present invention provides a multi-modal imaging film reading device, including a chassis and a main control module arranged on the top of the chassis;
[0010] A base is provided at the bottom of the chassis, and a display module and a recessed identification area are provided at the front of the chassis; a light-emitting backplane is provided in the identification area; a light source is built into the chassis and projects towards the light-emitting backplane; an embedded coding identification module is provided on the light-emitting backplane; the coding identification module is signal-connected to the main control module, and the coding identification module is signal-transmission-connected to the display module; a clamping component is provided on the identification area, and the clamping component is located above the light-emitting backplane;
[0011] The clamping component includes a fixed plate, a movable plate and a positioning member; the fixed plate is provided on the side facing the light-emitting backplane, the movable plate is arranged in parallel at the front end of the fixed plate, and the movable plate slides relative to the top plate of the identification area; an installation cavity is formed between the movable plate and the fixed plate; the positioning member is provided on the fixed plate and is located in the installation cavity; a through groove for the positioning member to insert is provided on the movable plate; an electromagnet is provided in the installation cavity, one end of the electromagnet is fixedly installed on the fixed plate, and the other end has a certain gap with the movable plate; an elastic member is provided on the outer periphery of the electromagnet, and both ends of the elastic member are connected to the fixed plate and the movable plate respectively; a slot is provided on the positioning member, an elastic contact member is provided in the slot, a contact switch is provided on the positioning member, the contact switch is located in the slot and above the contact member; the contact member moves up and down in the slot.
[0012] Preferably, a plurality of positioning pins are preset on the base; the base is fixedly installed in cooperation with the ground through the positioning pins.
[0013] Preferably, a wire groove is provided on the back of the chassis; the power supply wire and the signal wire are clamped in the installation groove and connected to the main control module.
[0014] Preferably, a control button is provided on the main control module, and the control button controls the lighting and turning off of the light source in the chassis.
[0015] Preferably, a plurality of heat dissipation holes are provided on the top of the main control module.
[0016] Preferably, the length of the fixed plate is longer than that of the movable plate.
[0017] Preferably, a communication module is built into the main control module, and the communication module communicates with the local database through a communication server.
[0018] Preferably, an image feature extraction module is built into the main control module for extracting the image features of the sample piece.
[0019] Preferably, a photographing device takes pictures of the patient to obtain sample piece image information, and the image information is stored in the local database in the form of videos and pictures.
[0020] Preferably, the local database encrypts and encodes the original information through an encryption coding module; encrypted codes are generated on the sample piece.
[0021] The above technical solution of the present invention has the following beneficial technical effects:
[0022] 1. The power supply line and the signal line supply power to the chassis and the main control module and transmit signals; the power supply line and the signal line are clamped in the wire groove, which is convenient for storage and use. The main control module is arranged on the top of the chassis, effectively avoiding water splashing into the main control module to prevent damage.
[0023] 2. A notch is provided at the top of the sample piece to prevent it from being placed upside down during film reading; when the sample piece is installed with the film reading area, the notch of the sample piece is aligned with the positioning member and inserted upward; the fixing plate is longer than the movable plate, which is convenient for guiding the sample piece.
[0024] 3. In the present invention, the photographing device and the film reading device are combined for information intercommunication, and the video image taken can be read on the display module, which can improve the recognition rate and accuracy compared with the traditional sample piece reading. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 It is a schematic front view of the chassis of the film reading device in the present invention;
[0026] Figure 2 It is a schematic rear view of the chassis in the present invention;
[0027] Figure 3 It is a schematic diagram of the structure of the clamping component in the present invention;
[0028] Figure 4 It is a schematic cross-sectional view of the clamping component in the present invention;
[0029] Figure 5 It is a schematic diagram of the working process of the present invention.
[0030] Reference numerals: 1. Chassis; 2. Base; 3. Positioning pin; 4. Display module; 5. Main control module; 6. Control button; 7. Heat dissipation hole; 8. Light-emitting backplane; 9. Film reading area; 10. Coding recognition module; 11. Wire groove; 12. Clamping component; 121. Fixing plate; 122. Movable plate; 123. Through groove; 124. Positioning member; 125. Electromagnet; 126. Elastic member; 127. Contact member; 128. Contact switch. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0031] To make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present invention.
[0032] As Figure 1-2As shown in the figure, a multi-modal image reading device proposed by the present invention includes a chassis 1 and a main control module 5 arranged on the top of the chassis 1;
[0033] In this embodiment, a base 2 is provided at the bottom of the chassis 1, and a plurality of positioning pins 3 are preset on the base 2; the base 2 is fixedly installed in cooperation with the ground through the positioning pins 3; a display module 4 and a recessed identification area 9 are provided at the front of the chassis 1; a light-emitting backplane 8 is provided in the identification area 9; a light source is built in the chassis 1, and the light source projects towards the light-emitting backplane 8; an embedded coding recognition module 10 is provided on the light-emitting backplane 8; a clamping component 12 is provided on the identification area 9, and the clamping component 12 is located above the light-emitting backplane 8; a wire groove 11 is provided on the back of the chassis 1; the power supply wire and the signal wire are clamped in the installation groove and connected to the main control module 5;
[0034] A control button 6 is provided on the main control module 5, and the control button 6 controls the lighting and turning off of the light source in the chassis 1; the coding recognition module 10 is signal-connected to the main control module 5, and the coding recognition module 10 is signal-transmission-connected to the display module 4.
[0035] It should be noted that the power supply wire and the signal wire supply power to the chassis 1 and the main control module 5 and transmit signals; the power supply wire and the signal wire are clamped in the wire groove 11, which is convenient for storage and use. The main control module 5 is arranged on the top of the chassis 1, effectively avoiding water splashing into the main control module 5 to prevent damage; a plurality of heat dissipation holes 7 are provided on the top of the main control module 5 for convenient heat dissipation; the identification area 9 on the chassis 1 is convenient for identifying sample pieces; the identification content can be displayed on the display module 4.
[0036] As Figure 3-4 shown, the clamping component 12 includes a fixed plate 121, a movable plate 122 and a positioning member 124; the fixed plate 121 is arranged on the side facing the light-emitting backplane 8, the movable plate 122 is arranged in parallel at the front end of the fixed plate 121, and the movable plate 122 slides relative to the top plate of the identification area 9; an installation cavity is formed between the movable plate 122 and the fixed plate 121; the positioning member 124 is arranged on the fixed plate 121 and is located in the installation cavity; a through groove 123 for the positioning member 124 to insert is provided on the movable plate 122; an electromagnet 125 is arranged in the installation cavity, one end of the electromagnet 125 is fixedly installed on the fixed plate 121, and the other end has a certain gap with the movable plate 122; an elastic member 126 is arranged on the outer periphery of the electromagnet 125, and both ends of the elastic member 126 are connected to the fixed plate 121 and the movable plate 122 respectively; a slot is provided on the positioning member 124, an elastic contact member 127 is arranged in the slot, a contact switch 128 is arranged on the positioning member 124, the contact switch 128 is located in the slot, and the contact switch 128 is located above the contact member 127; the contact member 127 moves up and down in the slot.
[0037] It should be noted that a notch is provided at the top of the sample piece to prevent it from being placed upside down during film reading. When installing the sample piece and the identification area 9, the notch of the sample piece is aligned with the positioning member 124 and inserted upward. The length of the fixed plate 121 is longer than that of the movable plate 122, which facilitates guiding the sample piece. The notch of the sample piece is stuck in the slot of the positioning member 124. When pushed upward, the contact member 127 in the slot moves upward. When it contacts the contact switch 128, the main control module 5 controls the electromagnet 125 to be powered on and generate a magnetic force, thereby attracting the movable plate 122 towards the fixed plate 121, and at the same time, the elastic member 126 remains in a compressed state. The sample piece is fixed by the clamping action of the movable plate 122. When removing the sample piece, the contact member 127 resets and the movable plate 122 bounces off.
[0038] As Figure 5 shown, the main control module 5 is built-in with a communication module, and the communication module is communicatively connected to the local database through a communication server; the imaging device captures image information and stores it in the local database; the main control module 5 is built-in with an image feature extraction module for extracting the image features of the sample piece.
[0039] The working principle and usage process of the present invention are as follows: The imaging device takes pictures of the patient to obtain sample piece image information, and the image information is stored in the local database in the form of videos and pictures; the local database encrypts and encodes the original information through an encryption and encoding module; after the patient obtains the sample piece, it is installed in the identification area 9 of the chassis 1; the clamping component 12 on the identification area 9 can clamp the sample piece; for the installed sample piece, its coding position is directly opposite to the coding recognition module 10; the coding recognition module 10 recognizes the coding on the sample piece; the coding information is communicatively connected to the local database through the communication server, and the image information under this coding is sent to the main control module 5 and displayed through the display module 4; at the same time, the control button 6 on the main control module 5 can be pressed to control the lighting of the light-emitting backplane 8; the image feature extraction module on the main control module 5 extracts the features in the image information and marks them on the display module 4, and at the same time displays the predicted diagnosis results; at the same time, the doctor can consult the sample piece in combination with the light-emitting backplane 8, and compare the consulted results with the diagnosis results displayed on the display module 4; to assist the doctor in identifying the inspection results. Mark the correct identification results and correct the wrong identification results; the data in the local database is accumulated and then undergoes machine learning based on a neural network to improve the subsequent identification accuracy; in the present invention, the imaging device and the film reading device are combined for information intercommunication, and the video images taken can be read on the display module, which can improve the recognition rate and has higher accuracy compared to the traditional method of reading sample pieces.
[0040] It should be understood that the above specific embodiments of the present invention are only used for exemplary illustration or explanation of the principles of the present invention, and do not constitute a limitation to the present invention. Therefore, any modifications, equivalent replacements, improvements, etc. made without departing from the spirit and scope of the present invention shall be included within the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all variations and modifications that fall within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.
Claims
1. A multimodal image reading device, characterized in that: It includes a chassis (1) and a main control module (5) arranged on the top of the chassis (1); The bottom of the chassis (1) is provided with a base (2), the front of the chassis (1) is provided with a display module (4) and an inwardly recessed identification area (9); a light-emitting back panel (8) is provided in the identification area (9); the chassis (1) has a built-in light source, and the light source is projected toward the light-emitting back panel (8); an embedded code recognition module (10) is provided on the light-emitting back panel (8) for scanning the encrypted code on the sample and communicating with the main control module (5); The coding recognition module (10) is connected to the main control module (5) for signal transmission, and the coding recognition module (10) is connected to the display module (4) for signal transmission; a clamping component (12) is provided on the recognition area (9), and the clamping component (12) is located above the light-emitting back panel (8); The clamping assembly (12) includes a fixed plate (121), a movable plate (122) and a positioning member (124); the fixed plate (121) is arranged on one side toward the light-emitting back plate (8), the movable plate (122) is arranged parallel to the front end of the fixed plate (121), and the movable plate (122) keeps sliding relative to the top plate of the identification area (9); a mounting cavity is formed between the movable plate (122) and the fixed plate (121); the positioning member (124) is arranged on the fixed plate (121) and is located in the mounting cavity; a through groove (123) for inserting the positioning member (124) is provided on the movable plate (122); an electromagnet (125) is provided in the mounting cavity, and one end of the electromagnet (125) is fixedly mounted on the fixed plate (121). There is a certain gap between the other end and the movable plate (122); an elastic member (126) is provided on the outer periphery of the electromagnet (125), and the two ends of the elastic member (126) are respectively connected to the fixed plate (121) and the movable plate (122); a slot is provided on the positioning member (124), and an elastic contact member (127) is provided in the slot, and a contact switch (128) is provided on the positioning member (124), and the contact switch (128) is located in the slot, and the contact switch (128) is located above the contact member (127); the contact member (127) moves up and down in the slot, and after triggering the contact switch (128), the electromagnet (125) is controlled to be energized to adsorb the movable plate (122).
2. The multimodal image reading device according to claim 1, wherein: A plurality of positioning pins (3) are preset on the base (2); the base (2) is fixedly installed in cooperation with the ground through the positioning pins (3).
3. The multimodal image reading device according to claim 1, wherein: A cable trough (11) is provided on the back of the chassis (1); the power supply line and the signal line are clamped in the installation trough and connected to the main control module (5).
4. The multimodal image reading device according to claim 1, wherein: A control button (6) is provided on the main control module (5), and the control button (6) controls the light source in the chassis (1) to turn on and off.
5. The multimodal image reading device according to claim 1, wherein: A plurality of heat dissipation holes (7) are provided on the top of the main control module (5).
6. The multimodal image reading device according to claim 1, wherein: The fixed plate (121) is longer than the movable plate (122).
7. The multimodal image reading device according to claim 1, wherein: The main control module (5) has a built-in communication module, and the communication module communicates with the local database via the communication server.
8. The multimodal image reading device according to claim 7, characterized in that: The main control module (5) has a built-in image feature extraction module for extracting image features of the sample.
9. The multimodal image reading device according to claim 7, wherein: The imaging device takes pictures of the patient to obtain sample image information, and the image information is stored in the local database in the form of video and pictures.
10. The multimodal image reading device according to claim 7, wherein: The local database encrypts and encodes the original information through the encryption coding module; the encryption code is produced on the sample.
Citation Information
Patent Citations
Electronic film watching device
CN108983426A
Multi-modal medical image recognition method and device based on deep learning
CN110321946A