Automatically operated microscope and system

Abstract

The invention belongs to the field of microscopes, and particularly discloses an automatic operation microscope and system, and the microscope comprises a main body, a driving mechanism, and an identification mechanism. The driving mechanism comprises a first steering engine and a second steering engine, a gear is arranged at the output end of the first steering engine, a sleeve is arranged at the output end of the second steering engine, and a connecting piece is arranged between the gear and the second steering engine; the two groups of driving mechanisms are respectively positioned on the main body and the movable seat; the position of the glass slide is detected through the camera, an image is transmitted to the processor so as to automatically control the objective table and the glass slide on the objective table to move transversely or longitudinally on the movable seat, the visual recognizer recognizes the microscopic image of the glass slide through the objective lens, and whether focusing is conducted or not is judged through the definition of the microscopic image. And then the movable seat and the glass slide are driven to move up and down, so that the microscope can be automatically controlled to perform microscopic recognition operation, and the working efficiency is improved.

Description

Technical Field

[0001] The invention belongs to the field of microscopes, and in particular relates to an automatically operated microscope and system. Background Art

[0002] Microscopic identification is an important technical means for identifying medicinal materials. It mainly uses a microscope to identify the tissue structure, cell shape, characteristics of inclusions and optical properties of minerals in slices, powders, dissociated tissues or surface preparations of medicinal materials (decoction pieces) and preparations containing medicinal material powder.

[0003] However, the existing technology requires the operator to manually align the light, manually adjust the slide movement, and manually adjust the focus during the operation of the microscope. This process is extremely cumbersome and consumes a lot of energy. In addition, the identification of microscopic structures mainly depends on the experience of the operator. The experience levels of different operators vary, resulting in a long time and low accuracy in the entire microscopic identification process. These problems are particularly prominent when analyzing a large number of samples in scientific research or conducting quality inspections on medicinal materials in actual production. Low efficiency and high costs have become problems that need to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to provide an automatically operated microscope and system to solve the problem mentioned in the above background technology that the traditional manual operation by operators is required, which is costly and inefficient.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An automatically operated microscope and system, comprising a main body, a driving mechanism and an identification mechanism; a movable seat is movably provided on the main body, a stage is movably provided on the movable seat, upper and lower coarse adjustment knobs and upper and lower fine adjustment knobs are rotatably provided on the main body, a lateral adjustment knob and a longitudinal adjustment knob are rotatably provided on the movable seat, and an eyepiece is fixedly installed on the top of the main body; the driving mechanism comprises a first servo and a second servo, a gear is provided at the output end of the first servo, a sleeve is provided at the output end of the second servo, and a connecting piece is provided between the gear and the second servo; the driving mechanism is provided with two groups, and the two groups of the driving mechanism are respectively located on the main body and the movable seat; the identification mechanism comprises an observation tube arranged at the top of the eyepiece, a visual identifier is installed at the top of the observation tube, a processor is installed at the top of the visual identifier, and a camera is provided on the main body at the top of the stage.

[0007] Preferably, the two gears are respectively engaged with the upper and lower coarse adjustment knobs and the lateral adjustment knob, and the two sleeves are respectively engaged with the upper and lower fine adjustment knobs and the longitudinal adjustment knob.

[0008] Preferably, the connecting member comprises an insert rod movably arranged on the gear, a fixing frame is fixedly mounted on the second servo engine, the fixing frame is sleeved with the insert rod, and a limit bolt is threadedly arranged on the fixing frame.

[0009] Preferably, a fixing plate is fixedly mounted on the servo one, and the two servo ones are respectively connected to the main body and the movable seat through the fixing plate.

[0010] Preferably, a light-through hole is provided at the center of the movable seat, and a tablet pressing clamp is provided on the stage.

[0011] Preferably, an objective lens is installed at the bottom of the eyepiece via a converter, and a driving member is provided at the input end of the converter.

[0012] An AI recognition control system, comprising:

[0013] A data acquisition module, used to obtain the position of the slide on the stage and the microscopic image;

[0014] An image processing and analysis module is used to analyze the clarity index of the microscopic image, determine whether the current image is in focus, and obtain a determination result;

[0015] A control command generating module, used for sending a slide positioning signal to the microscope according to the position of the slide on the stage, and sending a focus signal and an objective lens switching signal to the microscope according to the judgment result;

[0016] The AI ​​recognition module is used to analyze the microscopic image using a deep learning model, identify the microscopic structure type and characteristics therein, and obtain an identification result.

[0017] Preferably, the microscopic image is preprocessed before analyzing the microscopic image using the deep learning model, and the preprocessing includes image cropping, normalization, and enhancement operations.

[0018] Preferably, the deep learning model includes:

[0019] S1. Collect a large amount of microscopic image data of various medicinal materials and decoction pieces, and have professionals annotate the microscopic structures in the images, marking different tissue structures, cell shapes, and inclusion feature information;

[0020] S2, cleaning and normalizing the collected image data, and dividing them into training set, validation set and test set according to a certain ratio;

[0021] S3, use the training set data to train the VGG model, and continuously adjust the weights and biases of the model through the back propagation algorithm;

[0022] S4. During the training process, regularly use the validation set data to evaluate the model, monitor the performance indicators of the model, and adjust the model's hyperparameters based on the validation results.

[0023] S5. Use the test set data to perform a final evaluation on the trained model, calculate the model's accuracy, recall, and F1 value indicators, and evaluate the model's generalization ability on unknown data;

[0024] S6. Save the qualified models.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] The present invention detects the position of the glass slide by a camera and transmits the image to a processor, so as to automatically control the stage together with the glass slide thereon to move horizontally or vertically on the movable seat until the glass slide is aligned with the light hole. The visual identifier recognizes the microscopic image of the glass slide through the objective lens, and determines whether it is in focus by the clarity of the microscopic image. The movable seat is then driven to move up and down together with the glass slide. After the focus is clear, the microscopic image is sent to the processor for recognition processing, so as to be displayed on the display screen of the processor for convenient viewing by personnel. The microscope can be automatically controlled to perform microscopic recognition operations without the need for manual adjustment by the staff, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0028] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0029] Figure 2 It is a rear view of the present invention;

[0030] Figure 3 It is a schematic diagram of the driving mechanism structure of the present invention;

[0031] Figure 4 It is a schematic diagram of the structure of the driving mechanism of the present invention;

[0032] Figure 5 It is a system module block diagram of the present invention.

[0033] In the figure: 1. main body; 101. movable seat; 1011. light hole; 102. stage; 1021. film clamp; 103. eyepiece; 1031. converter; 1032. objective lens; 104. up and down coarse adjustment knob; 105. up and down fine adjustment knob; 106. lateral adjustment knob; 107. longitudinal adjustment knob; 2. driving mechanism; 201. servo one; 202. gear; 203. fixing plate; 204. fixing frame; 205. limit bolt; 206. servo two; 207. sleeve; 208. plug rod; 3. recognition mechanism; 301. observation tube; 302. visual identifier; 303. processor; 304. camera. DETAILED DESCRIPTION

[0034] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0035] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0036] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0037] As attached Figure 1 , 2 and attached Figure 3 As shown:

[0038] Embodiment 1: This embodiment provides an automatically operated microscope and system, including a main body 1, a driving mechanism 2 and an identification mechanism 3; a movable seat 101 is movably provided on the main body 1, a stage 102 is movably provided on the movable seat 101, an upper and lower coarse adjustment knob 104 and an upper and lower fine adjustment knob 105 are rotatably provided on the main body 1, a lateral adjustment knob 106 and a longitudinal adjustment knob 107 are rotatably provided on the movable seat 101, and an eyepiece 103 is fixedly installed on the top of the main body 1; the driving mechanism 2 includes a steering gear 1 201 and a steering gear 206, the steering gear 101 includes a steering gear 202, and a steering gear 203 includes a steering gear 204 and a steering gear 206. A gear 202 is provided at the output end of the first machine 201, a sleeve 207 is provided at the output end of the second servo 206, and a connecting piece is provided between the gear 202 and the second servo 206; two groups of driving mechanisms 2 are provided, and the two groups of driving mechanisms 2 are respectively located on the main body 1 and the movable seat 101; the recognition mechanism 3 includes an observation tube 301 arranged on the top of the eyepiece 103, a visual identifier 302 is installed on the top of the observation tube 301, a processor 303 is installed on the top of the visual identifier 302, and a camera 304 is provided on the main body 1 at the top of the stage 102.

[0039] The upper and lower coarse adjustment knobs 104 and the upper and lower fine adjustment knobs 105 are used to control the up and down movement of the movable seat 101, the lateral adjustment knob 106 is used to control the lateral movement of the stage 102, and the longitudinal adjustment knob 107 is used to control the longitudinal movement of the stage 102. The driving structure is a conventional structure of an existing microscope, so it is not redundantly described. The outer surfaces of the upper and lower coarse adjustment knobs 104, the upper and lower fine adjustment knobs 105, the lateral adjustment knob 106 and the longitudinal adjustment knob 107 are all provided with anti-slip grooves, and are engaged with the gear 202 or engaged with the sleeve 207 through the anti-slip grooves to ensure stability;

[0040] When the user needs to perform microscopic observation, the glass slide is first placed on the stage 102. At this time, the camera 304 will detect the position of the glass slide and transmit the image to the processor 303 to automatically control the servo 1 201 and the servo 2 206 located on the movable seat 101. The servo 1 201 will drive the gear 202 to rotate, and then drive the lateral adjustment knob 106 to rotate through the gear 202, so as to control the stage 102 and the glass slide thereon to move horizontally on the movable seat 101. At the same time, the servo 2 206 will drive the sleeve 207 to rotate, and then drive the longitudinal adjustment knob 107 to rotate through the sleeve 207, so as to control the stage 102 and the glass slide thereon to move longitudinally on the movable seat 101 until the glass slide is aligned with the light hole 1011.

[0041] The visual identifier 302 will identify the microscopic image of the slide through the objective lens 1032, and will determine whether it is in focus based on the clarity of the microscopic image. Then, based on the judgment result, a control signal will be sent to the servo 1 201 and the servo 2 206 on the main body 1. The servo 1 201 will drive the up and down coarse adjustment knobs 104 to rotate through the gear 202, and then quickly drive the movable seat 101 together with the slide to move up and down. The servo 2 206 will drive the up and down fine adjustment knobs 105 to rotate through the sleeve 207, and then slowly drive the movable seat 101 together with the slide to move up and down, thereby improving the adjustment accuracy. After the focus is clear, the microscopic image will be sent to the processor 303 for recognition processing, so as to be displayed on the display screen of the processor 303 for easy viewing by personnel. The microscope can be automatically controlled to perform microscopic recognition operations without the need for manual adjustment by the staff, thereby improving work efficiency.

[0042] Specifically, the two gears 202 are respectively engaged with the upper and lower coarse adjustment knobs 104 and the lateral adjustment knob 106 , and the two sleeves 207 are respectively engaged with the upper and lower fine adjustment knobs 105 and the longitudinal adjustment knob 107 .

[0043] Specifically, a light hole 1011 is disposed at the center of the movable seat 101 , and a tablet pressing clamp 1021 is disposed on the stage 102 .

[0044] Specifically, an objective lens 1032 is installed at the bottom of the eyepiece 103 through a converter 1031 , and a driving member is provided at the input end of the converter 1031 .

[0045] As can be seen from the above, the slide can be clamped and fixed on the stage 102 by the slide clamp 1021 , and the converter 1031 can be automatically driven to rotate by the driving member, thereby automatically switching the objective lens 1032 .

[0046] As attached Figure 4 As shown:

[0047] Embodiment 2: This embodiment is basically the same as the previous embodiment, except that the connecting member includes an insert rod 208 movably arranged on the gear 202, a fixing frame 204 is fixedly installed on the servo 206, the fixing frame 204 is sleeved with the insert rod 208, and a limit bolt 205 is threadedly arranged on the fixing frame 204.

[0048] Specifically, a fixing plate 203 is fixedly mounted on the servo 1 201 , and the two servos 1 201 are connected to the main body 1 and the movable seat 101 respectively through the fixing plate 203 .

[0049] As can be seen from the above, when the driving mechanism 2 needs to be disassembled for maintenance, or the user needs to use the microscope manually, the servo 1 201 can be separated from the main body 1 or the movable seat 101 through the fixing plate 203, and then the servo 2 206 can be pulled to separate the sleeve 207 from the upper and lower fine-tuning knobs 105 or the longitudinal adjustment knob 107. During the process, the gear 202 will be separated from the upper and lower coarse-tuning knobs 104 or the lateral adjustment knob 106. At this time, the driving mechanism 2 can be separated from the microscope, and then the limit bolt 205 is rotated to release the fixed connection relationship between the fixing frame 204 and the insertion rod 208. At this time, the fixing frame 204 is pulled to separate it from the insertion rod 208, and the servo 1 201 can be separated from the servo 2 206, thereby reducing the occupied area of ​​the device. At the same time, when local damage occurs, it will not affect the work of other parts. Subsequently, the eyepiece is installed on the eyepiece 103, and it can be manually operated and used, which is convenient for personnel to use. It can be expanded and modified without affecting the traditional microscope, thereby reducing costs.

[0050] As attached Figure 5 As shown:

[0051] Embodiment 3: This embodiment is basically the same as the previous embodiment, except that it is an AI recognition control system, including:

[0052] A data acquisition module, used to acquire the position of the glass slide on the stage 102 and the microscopic image;

[0053] The image processing and analysis module is used to analyze the clarity index of the microscopic image, determine whether the current image is in focus, and obtain the judgment result;

[0054] A control command generating module, used for sending a slide positioning signal to the microscope according to the position of the slide on the stage 102, and sending a focus signal and an objective lens switching signal to the microscope according to the judgment result;

[0055] Compare the clarity value of the current image with a preset threshold. If the clarity value is greater than the threshold, the image is considered to be in focus and the focusing operation is stopped; otherwise, the focusing operation continues. If the clarity value shows an upward trend, a control command is issued to drive the stage 102 to move upward, and vice versa;

[0056] The AI ​​recognition module is used to analyze microscopic images using a deep learning model, identify the types and characteristics of microscopic structures, and obtain identification results.

[0057] Specifically, the microscopic images are preprocessed before being analyzed by the deep learning model. The preprocessing includes image cropping, normalization, and enhancement operations to improve the image quality and make it meet the input requirements of the deep learning model.

[0058] Specifically, the deep learning model includes:

[0059] S1. Collect a large amount of microscopic image data of various medicinal materials and decoction pieces, and have professionals annotate the microscopic structures in the images, marking different tissue structures, cell shapes, and inclusion feature information;

[0060] S2, cleaning and normalizing the collected image data, and dividing them into training set, validation set and test set according to a certain ratio;

[0061] S3, use the training set data to train the VGG model, and continuously adjust the weight and bias of the model through the back propagation algorithm, so that the loss function value of the model on the training set gradually decreases, thereby improving the model's ability to recognize microstructures;

[0062] S4. During the training process, regularly use the validation set data to evaluate the model, monitor the model's performance indicators such as accuracy, loss value, etc., and adjust the model's hyperparameters such as learning rate, batch size, etc. according to the validation results to prevent the model from overfitting or underfitting.

[0063] S5. Use the test set data to perform a final evaluation on the trained model, calculate the model's accuracy, recall, and F1 value indicators, and evaluate the model's generalization ability on unknown data;

[0064] S6. Save the qualified models.

[0065] From the above, it can be seen that the automatically operated microscope and system can achieve fast and accurate focusing, AI analysis of microscopic images, and accurate output of identification results.

[0066] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure of performing the function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to several modifications still falling within the scope of the appended claims.

[0067] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0068] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0069] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An automatically operated microscope and system, characterized in that: It comprises a main body (1), a driving mechanism (2) and an identification mechanism (3); A movable seat (101) is movably provided on the main body (1), a loading platform (102) is movably provided on the movable seat (101), upper and lower coarse adjustment knobs (104) and upper and lower fine adjustment knobs (105) are rotatably provided on the main body (1), a transverse adjustment knob (106) and a longitudinal adjustment knob (107) are rotatably provided on the movable seat (101), and a sight head (103) is fixedly installed on the top of the main body (1); The driving mechanism (2) comprises a steering gear 1 (201) and a steering gear 2 (206); the output end of the steering gear 1 (201) is provided with a gear (202); the output end of the steering gear 2 (206) is provided with a sleeve (207); and a connecting piece is provided between the gear (202) and the steering gear 2 (206); The driving mechanism (2) is provided in two groups, and the two groups of the driving mechanism (2) are respectively located on the main body (1) and the movable seat (101); The identification mechanism (3) comprises an observation tube (301) arranged on the top of the eyepiece (103), a visual identifier (302) is installed on the top of the observation tube (301), a processor (303) is installed on the top of the visual identifier (302), and a camera (304) is arranged on the main body (1) on the top of the stage (102).

2. An automatically operated microscope and system according to claim 1, characterized in that: The two gears (202) are respectively meshed with the upper and lower coarse adjustment knobs (104) and the transverse adjustment knob (106), and the two sleeves (207) are respectively engaged with the upper and lower fine adjustment knobs (105) and the longitudinal adjustment knob (107).

3. An automatically operated microscope and system according to claim 1, characterized in that: The connecting member comprises an insert rod (208) movably arranged on the gear (202); a fixing frame (204) is fixedly installed on the second steering gear (206); the fixing frame (204) is sleeved with the insert rod (208); and a limit bolt (205) is threadedly arranged on the fixing frame (204).

4. An automatically operated microscope and system according to claim 1, characterized in that: A fixing plate (203) is fixedly mounted on the steering gear one (201), and the two steering gears one (201) are respectively connected to the main body (1) and the movable seat (101) through the fixing plate (203).

5. The automatically operated microscope and system according to claim 1, characterized in that: A light-through hole (1011) is provided at the center of the movable seat (101), and a tablet pressing clamp (1021) is provided on the object stage (102).

6. An automatically operated microscope and system according to claim 1, characterized in that: An objective lens (1032) is installed at the bottom of the eyepiece (103) via a converter (1031), and a driving member is arranged at the input end of the converter (1031).

7. An AI recognition control system, characterized in that: include: A data acquisition module, used to acquire the position of the glass slide on the stage (102) and a microscopic image; An image processing and analysis module is used to analyze the clarity index of the microscopic image, determine whether the current image is in focus, and obtain a determination result; A control command generating module is used to send a slide positioning signal to the microscope according to the position of the slide on the stage (102), and to send a focus signal and an objective lens switching signal to the microscope according to the judgment result; The AI ​​recognition module is used to analyze the microscopic image using a deep learning model, identify the microscopic structure type and characteristics therein, and obtain an identification result.

8. An automatically operated microscope and system according to claim 1, characterized in that: The microscopic image is preprocessed before analyzing the microscopic image using the deep learning model, and the preprocessing includes image cropping, normalization, and enhancement operations.

9. An automatically operated microscope and system according to claim 1, characterized in that: The deep learning model includes: S1. Collect a large amount of microscopic image data of various medicinal materials and decoction pieces, and have professionals annotate the microscopic structures in the images, marking different tissue structures, cell shapes, and inclusion feature information; S2, cleaning and normalizing the collected image data, and dividing them into training set, validation set and test set according to a certain ratio; S3, use the training set data to train the VGG model, and continuously adjust the weights and biases of the model through the back propagation algorithm; S4. During the training process, regularly use the validation set data to evaluate the model, monitor the performance indicators of the model, and adjust the model's hyperparameters based on the validation results. S5. Use the test set data to perform a final evaluation on the trained model, calculate the model's accuracy, recall, and F1 value indicators, and evaluate the model's generalization ability on unknown data; S6. Save the qualified models.

Images