3D stoma measuring and stoma base plate automatic cutting device

Abstract

The invention discloses a 3D (three-dimensional) stoma measuring and stoma base plate automatic cutting device, relates to the technical field of medical instruments, and aims to solve the technical problems that the traditional manual measurement error is large, the base plate cutting efficiency is low, the adaptability is poor, and the household precise nursing requirements of enterostomy patients are difficult to meet. The three-dimensional scanning module is used for performing three-dimensional scanning on the stoma skin surface and transmitting three-dimensional scanning data of the stoma skin surface to the measuring module; the data processing unit integrates a machine learning algorithm framework based on deep learning, and performs deep optimization processing on three-dimensional scanning data acquired by the 3D scanning module by taking a U-Net network as a core model; through high-precision modeling and contour recognition of the stoma three-dimensional form, the defect that three-dimensional data cannot be obtained through a traditional method is thoroughly overcome, the skin complication risk caused by cutting size deviation is effectively reduced, and the defects of leakage and dermatitis caused by errors of traditional manual measurement are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and more particularly to a 3D stoma measurement and stoma base plate automatic cutting device. Background Art

[0002] In the field of medical assistive devices, there are significant technical bottlenecks in the measurement and cutting of stoma base plates for home care of patients with colostomy. Traditional methods rely on manual measurement calipers or templates, which can only complete two-dimensional plane data collection and cannot obtain three-dimensional morphological information of the stoma. Clinical surveys show that more than 65% of stomas have complex morphological features such as irregular protrusions and tilt angles, and traditional measuring tools cannot accurately capture these details. Manual cutting or semi-automatic cutting machines require manual input of parameters, which are affected by factors such as operator experience and hand stability, resulting in an average error of 1.2-2.5mm between the cut base plate and the stoma edge, reducing the sealing of the base plate. According to authoritative clinical statistics, about 23% of contact dermatitis is caused by improper cutting, which not only increases the patient's pain, but may also lead to serious complications such as skin ulcers around the stoma. From an efficiency perspective, traditional manual cutting takes up to 3-5 minutes per session. If a complex stoma shape is encountered, the time cost of adjusting the cutting is even higher. In existing technologies, although some measuring devices have introduced digital elements, they lack a three-dimensional measurement compensation mechanism, making it difficult to adapt to stoma shapes of different diameters (15-50mm) and different base curvatures, and are even less compatible with various chassis models such as round, oval, and irregular shapes. With the increasing requirements for nursing efficiency and accuracy in home care scenarios, existing technologies can no longer meet patients' urgent needs for automated and personalized care. In view of this, we propose a 3D stoma measurement and automatic stoma chassis cutting device. Summary of the Invention

[0003] The purpose of the present invention is to provide a 3D stoma measurement and stoma chassis automatic cutting device to solve the technical problems of large errors in traditional manual measurement, low chassis cutting efficiency, poor adaptability, and difficulty in meeting the precise home care needs of intestinal stoma patients.

[0004] To solve the above technical problems, the present invention provides the following technical solutions: a 3D stoma measurement and stoma base plate automatic cutting device, comprising: a 3D scanning module, configured to perform a three-dimensional scan of the stoma skin surface and transmit the three-dimensional scan data of the stoma skin surface to the measurement module; The data processing unit integrates a deep learning-based machine learning algorithm framework and uses the U-Net network as the core model to perform in-depth optimization processing on the 3D scanning data obtained by the 3D scanning module; a measurement module, configured to perform stoma measurement based on the received three-dimensional scanning data, obtain stoma measurement data and cutting measurement data, and transmit the stoma measurement data and cutting measurement data to the stoma chassis model and the cutting module respectively; Stoma base plate model, used to generate stoma base plate models of different sizes and styles based on the stoma measurement data output by the measurement module; a cutting module, configured to cut the stoma base plate according to the received cutting measurement data and the stoma base plate model to obtain a cut stoma base plate; a calibration module for calibrating the stoma base plate cut by the cutting module based on the wrinkle measurement data of the stoma skin and the deformation measurement data caused by the compression and friction of the stoma base plate by the human body; A feedback module, used for feeding back the stoma base plate calibrated by the calibration module; The user module is configured to receive the stoma base plate model calibrated by the calibration module and fed back by the feedback module.

[0005] The present invention achieves high-precision modeling and contour recognition of the stoma's three-dimensional form through a 3D scanning module combined with the U-Net network algorithm of the data processing unit, completely resolving the defect of traditional methods in being unable to obtain three-dimensional data. In conjunction with the adaptive safety boundary algorithm, the cutting diameter is dynamically adjusted according to the stoma type and activity level to address the problem of dynamic size changes caused by differences in stoma types and daily activities in the background technology. The cutting roundness error is reduced from 15-20% of manual cutting to ≤5%, directly improving the geometric matching degree between the chassis and the stoma. It effectively reduces the risk of skin complications caused by cutting size deviations, and makes up for the shortcomings of traditional manual measurement that can cause leakage and dermatitis due to errors.

[0006] Preferably, the 3D scanning module includes: A 3D camera is used to perform three-dimensional scanning on the stoma skin surface to obtain depth data of the stoma skin surface; The force sensor is used to obtain wrinkle measurement data on the stoma skin surface and deformation measurement data caused by the stoma base plate being squeezed and rubbed by human skin. The force sensor is in contact with the stoma skin surface.

[0007] Preferably, the data processing unit performs depth optimization processing on the three-dimensional scanning data acquired by the 3D scanning module, comprising the following steps: A1: Normalize the original 3D scan data and map the coordinate values ​​to the range [-1, 1]. At the same time, use data augmentation technology to expand the training data set through random rotation, scaling, and flipping operations. A2: The weighted cross entropy loss function is introduced to solve the imbalance problem between the stoma area and the background. The formula is: ; Where, is the total number of pixels, is the true label, is the model prediction probability, and are the weight coefficients of positive and negative samples respectively; A3: Perform morphological operations on the segmentation results output by the network, remove noise points through erosion and dilation algorithms, and smooth the contour edges.

[0008] Preferably, the clipping measurement data introduces an adaptive safety margin algorithm, taking into account the dynamic change factors of the stoma, and the formula is: ; Where, is the cutting diameter, Measure the diameter of the stoma. is the basic value of the safety margin, is the stoma type coefficient, is the activity coefficient.

[0009] Preferably, the stoma base plate model introduces a shape similarity algorithm to calculate the similarity between the generated model and the historical well-fitted model, and the formula is: ; Where, is the similarity score, and are the number of feature points of the two models respectively, and is the corresponding feature point, is the feature point matching function.

[0010] Preferably, the cutting module includes: A pre-cutting device, configured to pre-cut the stoma base plate according to the received cutting measurement data and the stoma base plate model to obtain a pre-cut stoma base plate; A hot melt cutting module is used to hot melt cut the pre-cut stoma base plate to obtain a stoma base plate product; Wherein, the hot melt cutting module includes: A temperature control module, configured to control the temperature of the hot melt cutting tool according to the received cutting measurement data and the chassis material; The hot melt cutting tool is used to perform hot melt cutting on the stoma base plate according to the temperature control module to obtain the hot melt cutting result. The hot melt cutting tool is preferably a ceramic heating blade.

[0011] Preferably, the temperature control module controls the temperature of the hot melt cutting tool and introduces a dynamic temperature compensation formula: ; Where, is the cutting temperature, is the melting point of the material, is the material thickness coefficient, is the cutting speed compensation coefficient, is the ambient temperature influence coefficient, The difference between the current ambient temperature and the standard temperature.

[0012] Preferably, the calibration module includes: A pre-cutting control module is used to control the pre-cutting device based on the wrinkle measurement data of the stoma skin surface and the deformation measurement data caused by the compression and friction of the stoma base plate by the human skin, and calibrate and cut the stoma base plate after being cut by the cutting module; The hot melt cutting control module is used to control the hot melt cutting module to perform hot melt cutting on the calibrated stoma chassis to obtain the calibrated stoma chassis product.

[0013] Preferably, the calibration module performs calibration control on the pre-cutting and hot melt cutting processes, and introduces a calibration error correction algorithm, the formula of which is: ; Where, is the calibration correction, For the The error value of the measurement, is the average error value, is the number of measurements.

[0014] Preferably, the user module includes a chassis calibration model and a calibration model library for calibrating the stoma chassis cut by the cutting module based on the chassis calibration model, wherein the calibration model library includes: A stoma skin surface wrinkle calibration model, used to calibrate the stoma base plate cut out by the cutting module based on the wrinkle measurement data of the stoma skin surface; The stoma base plate deformation calibration model is used to calibrate the stoma base plate cut out by the cutting module based on the deformation measurement data generated by the stoma base plate being squeezed and rubbed by human skin.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention achieves high-precision modeling and contour recognition of the stoma's three-dimensional form through a 3D scanning module combined with the U-Net network algorithm of the data processing unit, completely resolving the defect of traditional methods in being unable to obtain three-dimensional data. In conjunction with the adaptive safety boundary algorithm, the cutting diameter is dynamically adjusted according to the stoma type and activity level to address the problem of dynamic size changes caused by differences in stoma types and daily activities in the background technology, so that the cutting roundness error is reduced from 15-20% of manual cutting to ≤5%, directly improving the geometric matching degree between the chassis and the stoma. It effectively reduces the risk of skin complications caused by cutting size deviations, and makes up for the shortcomings of traditional manual measurement that can cause leakage and dermatitis due to errors.

[0016] 2. This invention also utilizes a fully automated "scan-model-cut" process, combined with a hot-melt cutting module and a dynamic temperature compensation algorithm. This solution automatically matches cutting parameters based on the actual material properties, thickness, and ambient temperature, addressing the issues previously mentioned in the prior art regarding the impact of diverse chassis materials, varying thicknesses, and varying ambient temperatures on cutting results. This solution not only avoids edge burrs caused by manual cutting and reduces the physical irritation to the patient's skin caused by rough edges, but also shortens cutting time by over 90%, significantly improving operational efficiency and completely resolving the pain points of traditional methods, which suffer from low efficiency and high manual intervention.

[0017] 3. The present invention also uses a shape similarity algorithm to compare the matching degree of feature points of historically well-fitted models to generate a personalized chassis model, solving the problem in the background technology of "one-size-fits-all" cutting that cannot adapt to individual differences. At the same time, the calibration module combines the skin folds and chassis deformation data obtained by the force sensor, and dynamically adjusts the cutting parameters through the calibration error correction algorithm, which can respond to the dynamic changes of the patient's skin in real time. This innovation enables the device to adapt to more than 90% of common stoma shapes and chassis models, further improving the fitting accuracy and sealing in long-term use, and effectively solving the problem of frequent chassis replacement due to poor adaptability in the background technology, increased financial burden on patients, and nursing difficulties. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the overall architecture of the present invention. DETAILED DESCRIPTION

[0019] Example 1: Figure 1 As shown, the present invention relates to a 3D stoma measurement and stoma chassis automatic cutting device, comprising a 3D scanning module, a data processing unit, a measurement module, a stoma chassis model, a cutting module, a calibration module, a feedback module and a user module; The 3D scanning module is used to perform a three-dimensional scan on the stoma skin surface and transmit the three-dimensional scan data of the stoma skin surface to the measurement module; In an embodiment of the present invention, the 3D scanning module includes a 3D camera and a plurality of force sensors; The 3D camera is used to perform a three-dimensional scan of the stoma skin surface to obtain depth data of the stoma skin surface. The 3D camera uses a micro-structured light scanning head (wavelength 850nm) and can complete stoma three-dimensional modeling within 0.1s at a distance of 5cm with an accuracy of ±0.2mm. The force sensor is in contact with the stoma skin surface and is used to obtain wrinkle measurement data on the stoma skin surface and deformation measurement data caused by the stoma base plate being squeezed and rubbed by human skin.

[0020] The data processing unit integrates a machine learning algorithm framework based on deep learning, and uses the U-Net network as the core model to perform deep optimization processing on the three-dimensional scanning data obtained by the 3D scanning module; The U-Net network uses a symmetrical encoder-decoder structure, extracting features through contraction paths and restoring spatial information through expansion paths. It is particularly suitable for accurate segmentation of target areas in medical images. In the stoma contour recognition task, the network performs semantic segmentation on the depth data of the stoma skin surface: In an embodiment of the present invention, the data processing unit performs depth optimization processing on the three-dimensional scanning data acquired by the 3D scanning module, including the following steps: A1: Data preprocessing: Normalize the original 3D scan data and map the coordinate values ​​to the range [-1, 1]. At the same time, use data augmentation technology to expand the training data set through random rotation, scaling, and flipping operations to improve the model's generalization ability. A2: Network training: A weighted cross entropy loss function is introduced to solve the imbalance between the stoma area (positive sample) and the background (negative sample). The formula is: ; Where, is the total number of pixels, is the true label (0 or 1), is the model prediction probability, and The weight coefficients of positive and negative samples are respectively, and the weights are dynamically adjusted according to the number of samples of the two categories in the training data set. The training process uses the Adam optimizer, sets the initial learning rate to 0.001, and uses the cosine annealing learning rate scheduling strategy to prevent the model from overfitting. Finally, the segmentation loss function is minimized. , achieving high-precision automatic recognition of the stoma root contour; A3: Post-processing optimization: Perform morphological operations on the segmentation results output by the network, remove noise points through corrosion and expansion algorithms, smooth the contour edges, and further improve recognition accuracy.

[0021] The measurement module is used to measure the stoma based on the received three-dimensional scanning data, obtain stoma measurement data (the diameter of the narrowest part of the stoma, the major and minor axes of the elliptical stoma) and cutting measurement data (safety margin size), and transmit the stoma measurement data and cutting measurement data to the stoma chassis model and the cutting module respectively; In an embodiment of the present invention, the adaptive safety margin algorithm is introduced into the clipping measurement data, taking into account the dynamic change factor of the stoma (patient activity level), and the formula is: ; Where, is the cutting diameter, Measure the diameter of the stoma. is the basic value of the safety margin (1mm), is the stoma type coefficient (1 for ileostomy and 1.5 for colostomy), is the activity level coefficient (1 for resting state, 1.2 for light activity, 1.4 for moderate activity, and 1.6 for heavy activity); The stoma base plate model is used to generate stoma base plate models of different sizes and styles according to the stoma measurement data output by the measurement module; In an embodiment of the present invention, a shape similarity algorithm is introduced to calculate the similarity between the generated model and the historically well-fitted model. The formula is: ; Where, is the similarity score, and are the number of feature points of the two models respectively, and is the corresponding feature point, It is a feature point matching function (1 for successful matching and 0 for failure), and the model with high similarity is preferentially selected for subsequent processing.

[0022] The cutting module is used to cut the stoma base plate according to the received cutting measurement data and the stoma base plate model to obtain a cut stoma base plate; In an embodiment of the present invention, the cutting module includes a pre-cutting device and a hot melt cutting module; The pre-cutting device is used to pre-cut the stoma base plate according to the received cutting measurement data and the stoma base plate model to obtain a pre-cut stoma base plate; The hot melt cutting module is used to perform hot melt cutting on the pre-cut stoma base plate to obtain a stoma base plate product; Wherein, the hot melt cutting module includes a hot melt cutting tool and a temperature control module for controlling the temperature of the hot melt cutting tool; The temperature control module is used to control the temperature of the hot melt cutting tool (temperature controllable range 200-400°C) according to the received cutting measurement data and the chassis material (PU or hydrocolloid); The temperature control module controls the temperature of the hot melt cutting tool and introduces a dynamic temperature compensation formula: ; Where, is the cutting temperature, is the melting point of the material (220°C for PU and 250°C for hydrocolloid), is the material thickness coefficient (0.5-1.5, the coefficient increases by 0.1 for every 0.1mm increase in thickness), is the cutting speed compensation coefficient (the coefficient decreases by 0.05 for every 1mm / s increase in cutting speed), is the ambient temperature influence coefficient (the coefficient increases by 0.02 for every 1°C increase), The difference between the current ambient temperature and the standard temperature (25°C) is calculated. The ceramic heating blade cuts along a predetermined trajectory (cutting power 20W, speed 5mm / s), achieving precise cutting with a smooth, rounded edge to avoid damage to the stoma mucosa.

[0023] The hot melt cutting tool is used to perform hot melt cutting on the stoma base plate according to the temperature control module to obtain a hot melt cutting result. The hot melt cutting tool is preferably a ceramic heating blade.

[0024] The calibration module is used to calibrate the stoma base plate cut by the cutting module based on the wrinkle measurement data of the stoma skin and the deformation measurement data caused by the compression and friction of the stoma base plate by the human body; In an embodiment of the present invention, the calibration module includes a pre-cutting control module and a hot melt cutting control module; The pre-cutting control module is used to control the pre-cutting device based on the wrinkle measurement data of the stoma skin surface and the deformation measurement data caused by the stoma base plate being squeezed and rubbed by the human skin, and calibrate the stoma base plate cut by the cutting module; The hot melt cutting control module is used to control the hot melt cutting module to perform hot melt cutting on the calibrated stoma base plate to obtain a calibrated stoma base plate product; The calibration module performs calibration control on the pre-cutting and hot melt cutting processes and introduces a calibration error correction algorithm, the formula is: ; Where, is the calibration correction, For the The error value of the measurement, is the average error value, For the number of measurements, subsequent calibration parameters are adjusted according to the correction amount to improve the matching degree between the chassis and the stoma.

[0025] The feedback module is used to feed back the stoma base plate calibrated by the calibration module; The user module is used to receive the stoma base plate model calibrated by the calibration module and fed back by the feedback module; In an embodiment of the present invention, the user module includes a chassis calibration model and a calibration model library for calibrating the stoma chassis cut by the cutting module according to the chassis calibration model.

[0026] The calibration model library includes a stoma skin surface wrinkle calibration model and a stoma base deformation calibration model; The stoma skin surface wrinkle calibration model is used to calibrate the stoma base plate cut out by the cutting module based on the wrinkle measurement data of the stoma skin surface; The stoma base plate deformation calibration model is used to calibrate the stoma base plate cut out by the cutting module based on deformation measurement data generated by the stoma base plate being squeezed and rubbed by human skin.

[0027] Example 2: A 3D stoma measurement optimization processing method based on a model processing unit, comprising the following steps: S1: Data input and model generation: The three-dimensional scanning data of the stoma skin surface with different parameters are input into the measurement module. The data processing unit obtains the corresponding stoma measurement data after optimization processing by the machine learning algorithm. The stoma chassis model is generated according to the stoma measurement data. S2: Matching and preliminary cutting: Match the stoma base plate model with the cutting measurement data, generate adaptation data based on the matching results, and cut out the preliminary stoma base plate based on the adaptation data through the pre-cutting equipment and hot melt cutting module; S3: Contact area analysis: Use an infrared spectrometer to measure the distribution data of the contact area between the stoma chassis and human skin, mark the human skin contact area, and transmit the hardness data of the area to the stoma chassis model; measure the distribution data of the contact area during human movement, remove the area after touch, and obtain the residual area of ​​the chassis. Use a force sensor to obtain the extrusion force at different positions in the residual area. Introduce the contact pressure distribution evaluation formula: ; Where, is the average contact pressure, For the The pressure value of each measuring point, is the total number of measurement points used to evaluate contact pressure uniformity.

[0028] S4: Regional classification and parameter correction: Compare the extrusion pressure and maximum extrusion pressure in the residual area of ​​the chassis to divide the area into hard contact area and soft contact area; detect the height of the corresponding area after being squeezed to obtain the extrusion parameter; based on the humidity and pressure data of the contaminated area, calculate the ratio of the humidity value and the maximum pressure value in the contaminated area, and correct the extrusion parameter corresponding to the hard contact area. Introduce the regional hardness-pressure correlation algorithm: ; Where, Corrected hardness value, is the measured hardness value, is the correction factor, is the local pressure value, is the maximum pressure value, which improves the accuracy of regional classification; S5: Parameter processing and model correction: The extrusion parameters corresponding to the hard contact area and the ratio of the humidity in the contaminated area are averaged to obtain the final hard contact area parameters. Combined with the determined user stoma chassis size and style, the user stoma chassis model is corrected to obtain the final user stoma chassis model.

[0029] The embodiments disclosed in the present invention are preferred embodiments, but are not limited to them. Ordinary technicians in this field can easily understand the spirit of the present invention based on the above embodiments and make different extensions and changes. As long as they do not deviate from the spirit of the present invention, they are all within the scope of protection of the present invention.

Claims

1. A 3D stoma measurement and stoma base plate automatic cutting device, characterized in that: include: a 3D scanning module, configured to perform a three-dimensional scan of the stoma skin surface and transmit the three-dimensional scan data of the stoma skin surface to the measurement module; The data processing unit integrates a deep learning-based machine learning algorithm framework and uses the U-Net network as the core model to perform in-depth optimization processing on the 3D scanning data obtained by the 3D scanning module; a measurement module, configured to perform stoma measurement based on the received three-dimensional scanning data, obtain stoma measurement data and cutting measurement data, and transmit the stoma measurement data and cutting measurement data to the stoma chassis model and the cutting module respectively; Stoma base plate model, used to generate stoma base plate models of different sizes and styles based on the stoma measurement data output by the measurement module; a cutting module, configured to cut the stoma base plate according to the received cutting measurement data and the stoma base plate model to obtain a cut stoma base plate; a calibration module for calibrating the stoma base plate cut by the cutting module based on the wrinkle measurement data of the stoma skin and the deformation measurement data caused by the compression and friction of the stoma base plate by the human body; A feedback module, used for feeding back the stoma base plate calibrated by the calibration module; The user module is configured to receive the stoma base plate model calibrated by the calibration module and fed back by the feedback module.

2. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1 is characterized in that: The 3D scanning module includes: A 3D camera is used to perform three-dimensional scanning on the stoma skin surface to obtain depth data of the stoma skin surface; The force sensor is used to obtain wrinkle measurement data on the stoma skin surface and deformation measurement data caused by the stoma base plate being squeezed and rubbed by human skin. The force sensor is in contact with the stoma skin surface.

3. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1 is characterized in that: The data processing unit performs depth optimization processing on the three-dimensional scanning data obtained by the 3D scanning module, including the following steps: A1: Normalize the original 3D scan data and map the coordinate values ​​to the range [-1, 1]. At the same time, use data augmentation technology to expand the training data set through random rotation, scaling, and flipping operations. A2: The weighted cross entropy loss function is introduced to solve the imbalance problem between the stoma area and the background. The formula is: ； Where, is the total number of pixels, is the true label, is the model prediction probability, and are the weight coefficients of positive and negative samples respectively; A3: Perform morphological operations on the segmentation results output by the network, remove noise points through erosion and dilation algorithms, and smooth the contour edges.

4. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1 is characterized in that: The clipping measurement data introduces an adaptive safety margin algorithm, taking into account the dynamic changes of the stoma. The formula is: ； Where, is the cutting diameter, Measure the diameter of the stoma. is the basic value of the safety margin, is the stoma type coefficient, is the activity coefficient.

5. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1 is characterized in that: The stoma base model introduces a shape similarity algorithm to calculate the similarity between the generated model and the historical well-fitted model. The formula is: ； Where, is the similarity score, and are the number of feature points of the two models respectively, and is the corresponding feature point, is the feature point matching function.

6. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1, characterized in that: The cutting module includes: A pre-cutting device, configured to pre-cut the stoma base plate according to the received cutting measurement data and the stoma base plate model to obtain a pre-cut stoma base plate; A hot melt cutting module is used to hot melt cut the pre-cut stoma base plate to obtain a stoma base plate product; Wherein, the hot melt cutting module includes: A temperature control module, configured to control the temperature of the hot melt cutting tool according to the received cutting measurement data and the chassis material; The hot melt cutting tool is used to perform hot melt cutting on the stoma base plate according to the temperature control module to obtain the hot melt cutting result. The hot melt cutting tool is preferably a ceramic heating blade.

7. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 6, characterized in that: The temperature control module controls the temperature of the hot melt cutting tool and introduces a dynamic temperature compensation formula: ； Where, is the cutting temperature, is the melting point of the material, is the material thickness coefficient, is the cutting speed compensation coefficient, is the ambient temperature influence coefficient, The difference between the current ambient temperature and the standard temperature.

8. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1 is characterized in that: The calibration module includes: A pre-cutting control module is used to control the pre-cutting device based on the wrinkle measurement data of the stoma skin surface and the deformation measurement data caused by the compression and friction of the stoma base plate by the human skin, and calibrate and cut the stoma base plate after being cut by the cutting module; The hot melt cutting control module is used to control the hot melt cutting module to perform hot melt cutting on the calibrated stoma chassis to obtain the calibrated stoma chassis product.

9. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1, characterized in that: The calibration module performs calibration control on the pre-cutting and hot melt cutting processes and introduces a calibration error correction algorithm. The formula is: ； Where, is the calibration correction, For the The error value of the measurement, is the average error value, is the number of measurements.

10. The 3D stoma measurement and stoma base plate automatic cutting device according to claim 1, characterized in that: The user module includes a chassis calibration model and a calibration model library for calibrating the stoma chassis cut by the cutting module according to the chassis calibration model, wherein the calibration model library includes: A stoma skin surface wrinkle calibration model, used to calibrate the stoma base plate cut out by the cutting module based on the wrinkle measurement data of the stoma skin surface; The stoma base plate deformation calibration model is used to calibrate the stoma base plate cut out by the cutting module based on the deformation measurement data generated by the stoma base plate being squeezed and rubbed by human skin.

Images