Medical projection image detection device and method

Abstract

The invention discloses a medical projection image detection device and method, and relates to the technical field of medical instruments, the medical projection image detection device comprises a detection bed mechanism, the detection bed mechanism comprises a support frame connected with the ground, the top of the support frame is fixedly connected with a lying table, and the top of the lying table is fixedly connected with a sponge pad; and a man-machine interaction mechanism. The multi-spectral projection technology is adopted, ionizing radiation harm is avoided, the system is suitable for a patient needing multiple times of detection, meanwhile, the multi-spectral projection module projects light rays with different wavelengths to form a composite projection image containing tissue morphology, blood flow distribution and metabolic characteristics, the CCD sensor and the optical filter are combined, the image contrast and details are improved, and the detection accuracy is improved. More comprehensive diagnosis information is provided, the image processing and analysis module is based on an artificial intelligence algorithm, the image is automatically subjected to preprocessing, feature extraction and focus recognition, manual intervention is reduced, and the diagnosis efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly relates to a medical projection image detection device and method. Background Art

[0002] A projection image detection device is a device used for medical image generation, processing, and analysis. It mainly projects specific energy to penetrate the human body or biological tissue, combines with a detector to receive signals and generate images, so as to assist in disease diagnosis, surgical navigation, or treatment monitoring.

[0003] Currently, traditional detection devices, such as X-rays, CTs, etc., have ionizing radiation. When used for a long time or frequently, they will cause health damage to patients and medical staff, especially not suitable for sensitive groups such as pregnant women and children. At the same time, conventional detection means are limited by the imaging principle, and the image clarity and contrast are insufficient. It is difficult to obtain multi-dimensional information such as tissue morphology, blood flow distribution, and metabolic characteristics at the same time, and there are certain inconveniences in use. Summary of the Invention

[0004] The present invention provides a medical projection image detection device and method to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A medical projection image detection device and method, including a detection bed mechanism. The detection table mechanism includes a support frame connected to the ground. The top of the support frame is fixedly connected with a flat lying table, and a sponge pad is fixedly connected to the top of the flat lying table; a human-computer interaction mechanism. The human-computer interaction mechanism includes a first mounting frame. One end of the first mounting frame is fixedly connected to the surface of the support frame, and the other end of the first mounting frame away from the support frame is rotatably connected to a control terminal with an internal image processing and analysis module; a detection mechanism. The detection mechanism includes a second mounting frame. One end of the second mounting frame is fixedly connected to the surface of the support frame, and the other end of the second mounting frame away from the support frame is fixedly connected with a mounting top plate, and the mounting top plate is arranged directly above the flat lying table.

[0007] A further improvement of the technical solution of the present invention is that: the detection bed mechanism further includes a headrest, and the bottom of the headrest is fixedly connected to the top of the flat lying table.

[0008] A further improvement of the technical solution of the present invention is that: the human-computer interaction mechanism further includes a control panel. The control panel includes a display screen and control buttons, and the control panel is arranged on one side of the control terminal.

[0009] A further improvement of the technical solution of the present invention is that: the detection mechanism further includes a motor, and the surface of the motor is fixedly connected to the surface of the mounting top plate.

[0010] A further improvement of the technical solution of the present invention lies in that one end of the motor rotating shaft is fixedly connected with a threaded rod, the surface of the threaded rod is threadedly connected with a driving member, and a guide rod is slidably connected inside the driving member.

[0011] A further improvement of the technical solution of the present invention lies in that a data storage and transmission module is fixedly connected to the top of the inner cavity of the driving member, an image acquisition module is fixedly connected to the inner wall of the driving member, and a multi-spectral projection module is arranged inside the image acquisition module.

[0012] A further improvement of the technical solution of the present invention lies in that the multi-spectral projection module integrates projection light sources of visible light, infrared light, and ultraviolet light with different wavelengths, selects a specific spectrum for projection according to the detection requirements, and the projection light source is uniformly projected onto the patient's detection site through an optical lens group to form a composite projection image containing tissue morphology, blood flow distribution, and metabolic characteristic information.

[0013] A further improvement of the technical solution of the present invention lies in that the image acquisition module uses a CCD sensor to collect images projected onto the patient's detection site in real time. The sensor is equipped with a filter to selectively receive light of a specific wavelength, enhancing the contrast and details of the image.

[0014] A further improvement of the technical solution of the present invention lies in that the image processing and analysis module is based on an artificial intelligence algorithm to preprocess, extract features, and identify lesions from the collected images. The preprocessing includes image denoising, enhancement, and registration to improve the image quality. The feature extraction algorithm automatically identifies edge, texture, and color features in the image and compares them with the lesion database.

[0015] A further improvement of the technical solution of the present invention lies in: S1: Patient preparation; the patient takes a suitable position according to the detection site to ensure that the detection area is exposed;

[0016] S2: Parameter setting; select appropriate projection light source wavelength and intensity according to the patient's detection site and clinical needs;

[0017] S3: Image acquisition; the multi-spectral projection module projects light onto the patient's detection site, and the image acquisition module captures the projection image in real time to form a medical image containing multi-dimensional information;

[0018] S4: Image analysis: The image processing algorithm performs denoising and enhancement preprocessing on the original image to improve the image quality. The neural network model based on deep learning extracts features from the preprocessed image, automatically identifies the location, size, and morphological features of the lesion, and compares them with the standard lesion features in the database to judge the nature of the lesion;

[0019] S5: Result review; The processed image and analysis results are displayed on the human-computer interaction interface, and the doctor can review and correct the results in combination with clinical experience;

[0020] S6: Report generation; The system automatically generates a diagnostic report, including detailed information about the lesion and detection confidence, for the doctor's reference.

[0021] Due to the adoption of the above technical solution, the technical progress achieved by the present invention compared with the prior art is:

[0022] The present invention provides a medical projection image detection device and method. By adopting multi-spectral projection technology, it avoids the harm of ionizing radiation and is applicable to patients who need multiple detections. At the same time, the multi-spectral projection module projects light of different wavelengths to form a composite projection image containing tissue morphology, blood flow distribution, and metabolic characteristics. Combined with a CCD sensor and a filter, it improves the image contrast and details, providing more comprehensive diagnostic information. The image processing and analysis module automatically preprocesses the image, extracts features, and identifies lesions based on artificial intelligence algorithms, reducing manual intervention and improving the diagnostic efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is the front view structural schematic diagram of the present invention;

[0024] Figure 2 is the front structure schematic diagram of the present invention;

[0025] Figure 3 is the bottom view structural schematic diagram of the present invention;

[0026] Figure 4 is the partial detection mechanism structural schematic diagram of the present invention;

[0027] Figure 5 is the detection mechanism decomposition structural schematic diagram of the present invention;

[0028] Figure 6 is the bottom view structural schematic diagram of the detection mechanism in the decomposed state of the present invention;

[0029] Figure 7 is the method flow block diagram of the present invention.

[0030] In the figure: 11, support frame; 12, flat lying table; 13, sponge pad; 14, headrest; 21, first mounting frame; 22, control terminal; 23, control panel; 31, second mounting frame; 32, mounting top plate; 33, motor; 34, threaded rod; 35, driving member; 36, guide rod; 37, data storage and transmission module; 38, image acquisition module; 39, multi-spectral projection module. DETAILED DESCRIPTION OF THE INVENTION

[0031] The present invention will be further described in detail below in conjunction with embodiments:

[0032] Embodiment 1

[0033] As Figures 1-7 shown, the present invention provides a medical projection image detection device and method, including a detection bed mechanism. The detection table mechanism includes a support frame 11 connected to the ground. The top of the support frame 11 is fixedly connected to a flat lying table 12, and a sponge pad 13 is fixedly connected to the top of the flat lying table 12; a human-computer interaction mechanism, which includes a first mounting frame 21. One end of the first mounting frame 21 is fixedly connected to the surface of the support frame 11, and the end of the first mounting frame 21 away from the support frame 11 is rotatably connected to a control terminal 22 with an internal image processing and analysis module; a detection mechanism, which includes a second mounting frame 31. One end of the second mounting frame 31 is fixedly connected to the surface of the support frame 11, and the end of the second mounting frame 31 away from the support frame 11 is fixedly connected to a mounting top plate 32, and the mounting top plate 32 is arranged directly above the flat lying table 12.

[0034] In this embodiment, the support frame 11 stably supports the flat lying table 12, and the sponge pad 13 improves the comfort of the patient and ensures the stability of the body position during the detection process. The first mounting frame 21 of the human-computer interaction mechanism connects the control terminal 22 to the support frame 11. The control terminal 22 can rotate to adapt to different viewing angles, and the built-in image processing and analysis module provides core support for subsequent data processing. The second mounting frame 31 of the detection mechanism fixedly installs the mounting top plate 32 directly above the flat lying table 12, providing a structural basis for projection and image acquisition.

[0035] Embodiment 2

[0036] As Figures 1-7As shown, based on Embodiment 1, the present invention provides a technical solution: Preferably, the detection bed mechanism further includes a headrest 14, the bottom of the headrest 14 is fixedly connected to the top of the flat lying platform 12, the human-computer interaction mechanism further includes a control panel 23, the control panel 23 includes a display screen and control buttons, the control panel 23 is arranged on one side of the control terminal 22, the detection mechanism further includes a motor 33, the surface of the motor 33 is fixedly connected to the surface of the installation top plate 32, one end of the rotating shaft of the motor 33 is fixedly connected to a threaded rod 34, the surface of the threaded rod 34 is threadedly connected to a driving member 35, a guide rod 36 is slidably connected inside the driving member 35, a data storage and transmission module 37 is fixedly connected to the top of the inner cavity of the driving member 35, an image acquisition module 38 is fixedly connected to the inner wall of the driving member 35, a multi-spectral projection module 39 is arranged inside the image acquisition module 38, the multi-spectral projection module 39 integrates projection light sources of visible light, infrared light, and ultraviolet light with different wavelengths, selects a specific spectrum for projection according to the detection requirements, and the projection light source is evenly projected onto the patient's detection site through an optical lens group to form a composite projection image containing tissue morphology, blood flow distribution, and metabolic characteristic information. The image acquisition module 38 uses a CCD sensor to collect the image projected onto the patient's detection site in real time, and the sensor is equipped with a filter to selectively receive light of a specific wavelength, enhancing the contrast and details of the image. The image processing and analysis module is based on an artificial intelligence algorithm to preprocess, extract features, and identify lesions for the collected image. The preprocessing includes image denoising, enhancement, and registration to improve the image quality. The feature extraction algorithm automatically identifies the edge, texture, and color features in the image and compares them with the lesion database.

[0037] In this embodiment, the headrest 14 provides support for the patient's head, enhancing the detection experience. The control panel 23 of the human-computer interaction mechanism integrates a display screen and control buttons, facilitating the doctor to monitor the detection parameters in real time, adjust the settings, and view the images. The detection mechanism drives the threaded rod 34 to rotate through the motor 33, driving the driving member 35 to move left and right along the guide rod 36, realizing the position adjustment of the multi-spectral projection module 39 and the image acquisition module 38. The multi-spectral projection module 39 integrates visible light, infrared light, and ultraviolet light sources and is evenly projected onto the patient's detection site through an optical lens group to form a composite projection image containing tissue morphology, blood flow distribution, and metabolic characteristics. The image acquisition module 38 uses a CCD sensor and a filter to selectively receive light of a specific wavelength, enhancing the contrast and details of the image. The image processing and analysis module is based on an artificial intelligence algorithm to preprocess the image such as denoising, enhancement, and registration, and realizes the accurate identification of lesions through feature extraction and comparison with the lesion database.

[0038] Embodiment 3

[0039] As Figures 1-7As shown, on the basis of Embodiment 1, the present invention provides a technical solution: Preferably, it includes S1: Patient preparation; The patient adopts a suitable position according to the detection site to ensure that the detection area is exposed; S2: Parameter setting; According to the patient's detection site and clinical needs, select a suitable projection light source wavelength and intensity; S3: Image acquisition; The multispectral projection module projects light onto the patient's detection site, and the image acquisition module captures the projection image in real time to form a medical image containing multi-dimensional information; S4: Image analysis: The image processing algorithm performs denoising and enhancement preprocessing on the original image to improve the image quality. The neural network model based on deep learning extracts features from the preprocessed image, automatically identifies the location, size, and morphological features of the lesion, and compares them with the standard lesion features in the database to judge the nature of the lesion; S5: Result review; The processed image and analysis results are displayed on the human-computer interaction interface, and the doctor can review and correct the results in combination with clinical experience; S6: Report generation; The system automatically generates a diagnostic report, including detailed information about the lesion and the detection confidence level, for the doctor's reference.

[0040] In this embodiment, through S1 patient preparation: The patient adopts a supine or lateral position according to the detection site such as the head or limb to ensure that the detection area is fully exposed, and the headrest 14 and the sponge pad 13 provide comfortable support. S2 parameter setting: The doctor selects the detection mode through the control panel 23, such as blood vessel detection or tumor screening, and the system automatically matches the optimal projection light source wavelength and intensity. For example, ultraviolet light is selected for detecting skin tumors, and infrared light is selected for detecting blood vessel distribution. S3 image acquisition: The multispectral projection module 39 projects light of the selected wavelength onto the patient's detection site, and the CCD sensor captures the projection image in real time. The filter ensures that only the target wavelength light is received to form a medical image with high contrast. S4 image analysis: The image processing algorithm performs preprocessing such as denoising and enhancement on the original image. The neural network model based on deep learning automatically extracts features such as edges, textures, and colors, compares them with the standard lesion features in the database, and judges the nature of the lesion, such as benign, malignant, and location. S5 result review: The processed image and analysis results are displayed on the display screen of the control terminal 22, and the doctor reviews them in combination with clinical experience and adjusts the parameters to re-acquire the image if necessary. S6 report generation: The system automatically generates a diagnostic report containing the location, size, and nature of the lesion for the doctor's reference or for storing in the patient's file.

[0041] Next, specifically describe the working principle of the medical projection image detection device and method.

[0042] As Figures 1-7As shown, the patient lies on a flat table 12 supported by a support frame 11. The headrest 14 and the sponge pad 13 provide comfortable support. The doctor sets the detection parameters through the control panel 23 of the man-machine interaction mechanism and selects the light source wavelength and intensity of the multi-spectral projection module 39. The motor 33 drives the threaded rod 34 to rotate, driving the driving member 35 to move left and right along the guide rod 36, adjusting the multi-spectral projection module 39 below the installation top plate 32 to a suitable position, so that it projects visible light, infrared light or ultraviolet light onto the detection site, and forms a composite projection image containing information such as tissue morphology and blood flow distribution through uniform irradiation by the optical lens group; the CCD sensor in the image acquisition module 38 is equipped with a filter, and it collects high-contrast images in real time and transmits them to the image processing and analysis module of the control terminal 22. Through artificial intelligence algorithms, preprocessing such as denoising and enhancement is performed, and features are extracted using a deep learning model and compared with the lesion database to automatically identify the location and nature of the lesions; the processing results are displayed on the control panel 23 in real time. After the doctor reviews, the system generates a diagnostic report containing detailed lesion information through the data storage and transmission module 37, realizing intelligent and radiation-free precision medical detection.

[0043] The above has generally described the present invention in detail. However, based on the present invention, some modifications or improvements can be made, which are obvious to those of ordinary skill in the technical field. Therefore, modifications or improvements made without departing from the spirit of the present invention are within the protection scope of the present invention.

Claims

1. A medical projection image detection device, characterized in that: including a detection bed mechanism, the detection table mechanism includes a support frame (11) connected to the ground, the top of the support frame (11) is fixedly connected with a flat lying table (12), and a sponge pad (13) is fixedly connected to the top of the flat lying table (12); a human-computer interaction mechanism, the human-computer interaction mechanism includes a first mounting frame (21), one end of the first mounting frame (21) is fixedly connected to the surface of the support frame (11), and a control terminal (22) with an built-in image processing and analysis module is rotatably connected to the end of the first mounting frame (21) away from the support frame (11); a detection mechanism, the detection mechanism includes a second mounting frame (31), one end of the second mounting frame (31) is fixedly connected to the surface of the support frame (11), and a mounting top plate (32) is fixedly connected to the end of the second mounting frame (31) away from the support frame (11), and the mounting top plate (32) is arranged directly above the flat lying table (12).

2. The medical projection image detection device according to claim 1, wherein: The detection bed mechanism further includes a headrest (14), and the bottom of the headrest (14) is fixedly connected to the top of the flat lying table (12).

3. A medical projection image detection device according to claim 1, characterized in that: The human-computer interaction mechanism further includes a control panel (23), the control panel (23) includes a display screen and control buttons, and the control panel (23) is arranged on one side of the control terminal (22).

4. A medical projection image detection device according to claim 1, wherein: The detection mechanism further includes a motor (33), and the surface of the motor (33) is fixedly connected to the surface of the mounting top plate (32).

5. The medical projection image detection device according to claim 4, wherein: One end of the rotating shaft of the motor (33) is fixedly connected with a threaded rod (34), a driving member (35) is threadedly connected to the surface of the threaded rod (34), and a guide rod (36) is slidably connected inside the driving member (35).

6. The medical projection image detection device according to claim 5, characterized in that: A data storage and transmission module (37) is fixedly connected to the top of the inner cavity of the driving member (35), an image acquisition module (38) is fixedly connected to the inner wall of the driving member (35), and a multi-spectral projection module (39) is arranged inside the image acquisition module (38).

7. The medical projection image detection device according to claim 6, wherein: The multi-spectral projection module (39) integrates projection light sources of visible light, infrared light, and ultraviolet light with different wavelengths, selects a specific spectrum for projection according to the detection requirements, and the projection light source is evenly projected onto the patient's detection site through an optical lens group to form a composite projection image containing tissue morphology, blood flow distribution, and metabolic characteristic information.

8. The medical projection image detection device according to claim 6, characterized in that: The image acquisition module (38) uses a CCD sensor to collect images projected onto the patient's detection site in real time. The sensor is equipped with a filter to selectively receive light of a specific wavelength, enhancing the contrast and details of the image.

9. A medical projection image detection device according to claim 1, characterized in that: The image processing and analysis module is based on an artificial intelligence algorithm to preprocess, extract features, and identify lesions from the collected images. The preprocessing includes image denoising, enhancement, and registration to improve the image quality. The feature extraction algorithm automatically identifies edge, texture, and color features in the image and compares them with the lesion database.

10. A method for using a medical projection image detection device according to claims 1-9, characterized in that: including S1: Patient preparation; The patient assumes a suitable position according to the detection site to ensure that the detection area is exposed; S2: Parameter setting; According to the patient's detection site and clinical needs, select the appropriate projection light source wavelength and intensity; S3: Image acquisition; The multispectral projection module projects light onto the patient's detection site, and the image acquisition module captures the projection image in real time to form a medical image containing multi-dimensional information; S4: Image analysis: The image processing algorithm performs denoising and enhancement preprocessing on the original image to improve the image quality. The neural network model based on deep learning extracts features from the preprocessed image, automatically identifies the location, size, and morphological features of the lesion, and compares them with the standard lesion features in the database to determine the nature of the lesion; S5: Result review; The processed image and analysis results are displayed on the human-computer interaction interface, and the doctor can review and correct the results in combination with clinical experience; S6: Report generation; The system automatically generates a diagnostic report, including detailed information about the lesion and the detection confidence level, for the doctor's reference.

Images