A heat imaging guidance based underarm minimally invasive treatment planning method

Abstract

This invention discloses a method for planning minimally invasive axillary treatment based on thermal imaging, belonging to the field of medical image processing technology. The method includes: acquiring and preprocessing infrared thermal imaging data of the patient's axillary region to generate a thermal imaging sequence; calculating the temperature change amplitude, temperature rise rate, and local temperature gradient of each pixel based on the thermal imaging sequence to generate a set of sweat gland activity features; inputting the sweat gland activity feature set into a pre-established sweat gland activity prediction model to obtain the sweat gland activity distribution results within a future preset time window; using the sweat gland activity distribution results as the optimization target, and combining axillary risk tissue constraints, optimizing the path position, insertion angle, and depth of action of the minimally invasive needle path to generate the optimal minimally invasive needle path. This invention improves the positioning accuracy and treatment consistency of minimally invasive axillary treatment by constructing a sweat gland activity prediction mechanism based on thermal imaging sequences and linking it with minimally invasive needle path constraint optimization.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, and in particular to a method for planning minimally invasive axillary treatment based on thermal imaging guidance. Background Technology

[0002] With the development of minimally invasive medical technology and medical imaging technology, the treatment methods for diseases related to the axillary region are gradually evolving from traditional surgical excision towards more refined and minimally invasive approaches. Current techniques often use energy forms such as radiofrequency, laser, or microwave to locally destroy the sweat glands in the axilla, thereby reducing sweat gland secretion. In practice, doctors typically combine their experience with the patient's anatomy, local palpation, or auxiliary imaging to determine the treatment area and, based on experience, determine the minimally invasive needle path and energy application parameters. In recent years, infrared thermal imaging technology, due to its ability to reflect the temperature distribution characteristics of the skin surface, has been gradually introduced into the assessment of sweat gland activity and intraoperative auxiliary positioning. By collecting thermal information from the axillary region, it helps identify areas of active sweat glands, thus providing a certain reference for minimally invasive treatment.

[0003] However, current applications of thermal imaging technology largely remain at the level of static temperature distribution observation or simple experience-based judgment. It typically identifies high-temperature areas based on single frames or a small number of thermal images, lacking analysis of dynamic changes in sweat gland activity and failing to establish an effective linkage mechanism with minimally invasive treatment path planning. Furthermore, during minimally invasive treatment, needle path design relies heavily on the surgeon's experience, lacking a systematic optimization method based on functional distribution and anatomical constraints. This can lead to discrepancies between the treatment path and the actual active distribution of sweat glands, thus affecting the consistency and accuracy of treatment outcomes. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a thermal imaging-guided axillary minimally invasive treatment planning method, which solves the problems of difficulty in accurately predicting sweat gland activity and lack of functional guidance optimization in needle path planning during axillary minimally invasive treatment.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for planning minimally invasive axillary treatment based on thermal imaging, comprising, Infrared thermal imaging data of the patient's axillary region was collected and preprocessed to generate a thermal imaging sequence. Based on the thermal imaging sequence, the temperature change amplitude, temperature rise rate and local temperature gradient of each pixel were calculated to generate a set of sweat gland activity features. The set of sweat gland activity features is input into a pre-established sweat gland activity prediction model to obtain the sweat gland activity distribution results within a future preset time window. The sweat gland activity distribution results are used as the optimization target. Combined with the axillary risk tissue constraint conditions, the path position, insertion angle and action depth of the minimally invasive needle path are constrained and optimized to generate the optimal minimally invasive needle path. The system collects thermal imaging data in real time during minimally invasive treatment. When the local temperature change exceeds the preset threshold, it is identified as an abnormal area. Based on the location of the abnormal area and the degree of temperature deviation, the position of the minimally invasive needle path and the energy output parameters are corrected according to the preset adjustment rules. Postoperative thermal imaging data was acquired and compared with the results of sweat gland activity distribution. The parameters of the sweat gland activity prediction model were then adjusted based on the comparison results.

[0007] As a preferred embodiment of the thermal imaging-guided axillary minimally invasive treatment planning method of the present invention, the generation of the thermal imaging sequence includes the following steps: The patient's axillary region was fixed in position, and an infrared device was used to continuously scan the axillary region to obtain thermal imaging data at each time frame; The thermal imaging data of each time frame are standardized and combined in chronological order to generate a standardized thermal imaging sequence.

[0008] As a preferred embodiment of the thermal imaging-guided axillary minimally invasive treatment planning method of the present invention, the generation of the sweat gland activity feature set includes the following steps: Based on the thermal imaging sequence, the temperature value corresponding to each pixel in each time frame is extracted, and the temperature sequence of each pixel is established. Based on the temperature sequence, the difference between the maximum and minimum temperature values ​​of each pixel within a preset time window is calculated to obtain the temperature change amplitude. Based on the temperature changes of adjacent time frames in the temperature sequence, the rate of temperature change per unit time is calculated to obtain the temperature rise rate of each pixel. In each time frame, taking each pixel as the center and combining the temperature distribution of its neighboring pixels, the temperature change in the spatial direction is calculated to obtain the local temperature gradient. The temperature change amplitude, temperature rise rate and local temperature gradient are normalized and then associated and organized according to the spatial location of pixels to generate multidimensional feature vectors for each pixel. By integrating the multidimensional feature vectors of all pixels, a set of sweat gland activity features is generated.

[0009] As a preferred embodiment of the thermal imaging-guided axillary minimally invasive treatment planning method of the present invention, the step of inputting the set of sweat gland activity features into a pre-established sweat gland activity prediction model to obtain the sweat gland activity distribution results within a future preset time window includes the following steps: The sweat gland activity feature set is mapped according to the pixel spatial location to construct a feature distribution matrix corresponding to the axillary region, which serves as the input data for the sweat gland activity prediction model. The continuous feature distribution matrix is ​​input into the pre-trained sweat gland activity prediction model to calculate the sweat gland activity intensity of each pixel and obtain the corresponding activity response value. Spatial reconstruction of the active response values ​​is performed to correspond one-to-one with the actual spatial location of the axillary region, generating an initial sweat gland activity distribution map; The initial sweat gland activity distribution map is extrapolated over time to obtain the trend of sweat gland activity changes in each region within a future preset time window. Based on the trend of sweat gland activity changes, the activity response values ​​of each pixel are weighted and integrated to generate a sweat gland activity distribution result that characterizes the future sweat gland activity distribution in the axillary region.

[0010] As a preferred embodiment of the thermal imaging-guided axillary minimally invasive treatment planning method of the present invention, the step of constraining and optimizing the path position, insertion angle, and depth of action of the minimally invasive needle to generate the optimal minimally invasive needle path includes the following steps: Based on the distribution of sweat gland activity, the spatial location and distribution range of highly active areas are extracted to generate a set of target areas to be treated. Acquire spatial location information of blood vessels, nerves and lymphatic tissues in the axillary region, and generate a risk tissue constraint area based on a preset safety distance; Using the set of target areas to be treated as the coverage target, the path position, insertion angle and depth of action of the minimally invasive needle path are used as adjustable parameters to construct a set of needle path parameters; Based on the spatial relationship between the set of needle path parameters and the risk organization constraint area, needle path parameters that do not meet the safety distance constraint are screened out to form a set of candidate needle paths. In the candidate needle path set, each candidate needle path is selected and ranked according to the evaluation rules of coverage of high-activity areas and path continuity; The optimal minimally invasive needle path is selected based on the combination of needle path parameters that best covers the target area and meets the risk organization constraints.

[0011] As a preferred embodiment of the thermal imaging-guided axillary minimally invasive treatment planning method of the present invention, the real-time acquisition of thermal imaging data during the minimally invasive treatment process, and the determination of an abnormal area when the local temperature change exceeds a preset threshold, includes the following steps: Minimally invasive treatment is performed using the optimal minimally invasive needle path, and thermal imaging data of the axillary region is collected in real time during the treatment process; The real-time thermal imaging data is standardized to generate a real-time temperature distribution map, which is then spatially registered with the sweat gland activity distribution results. For each registered pixel, the difference between the real-time temperature value and the predicted temperature value is calculated to obtain the temperature deviation distribution; Pixels with temperature deviations exceeding a preset threshold are spatially clustered to form continuously distributed abnormal regions, and the location and range information of the abnormal regions are output.

[0012] As a preferred embodiment of the thermal imaging-guided axillary minimally invasive treatment planning method of the present invention, the step of correcting the position of the minimally invasive needle path and the energy output parameters according to a preset adjustment rule includes the following steps: Based on the location and extent of the abnormal area, the abnormal area is mapped to the corresponding minimally invasive needle path segment to determine the target needle path area that needs to be adjusted. Based on the degree of temperature deviation, abnormal areas are classified and processed into multiple deviation levels. For different deviation levels, the preset adjustment rules are invoked to determine the corresponding needle path adjustment strategy and energy output adjustment strategy; Based on the needle path adjustment strategy, the path position, insertion angle, and depth of action of the target needle path area are corrected, and based on the energy output adjustment strategy, the energy output parameters are adjusted.

[0013] As a preferred embodiment of the thermal imaging-guided axillary minimally invasive treatment planning method of the present invention, the step of acquiring postoperative thermal imaging data and performing a difference analysis with the sweat gland activity distribution results, and correcting the parameters of the sweat gland activity prediction model based on the difference results, includes the following steps: After the minimally invasive treatment is completed, thermal imaging is performed again on the patient's axillary area to obtain postoperative thermal imaging data and perform standardization and spatial registration processing. Based on the registered data, the postoperative temperature distribution and sweat gland activity distribution of each pixel are compared point by point, the temperature difference or activity deviation is calculated, and a difference distribution map is generated. Based on the differential distribution map, extract the overall and local deviation features of the axillary region; Based on the overall and local deviation characteristics, determine the range of parameters that need to be corrected and the direction of adjustment in the sweat gland activity prediction model; The parameters of the sweat gland activity prediction model are corrected according to the preset parameter update rules.

[0014] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the thermal imaging-guided axillary minimally invasive treatment planning method as described in the first aspect of the present invention.

[0015] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the thermal imaging-guided axillary minimally invasive treatment planning method as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By extracting multidimensional temperature features from thermal imaging sequences of the axillary region and constructing a set of sweat gland activity features, a refined characterization of the sweat gland functional state is achieved, improving the accuracy of sweat gland activity identification; by inputting sweat gland activity features into a prediction model to obtain the sweat gland activity distribution results, and using this as a target combined with risk tissue constraints to optimize the minimally invasive needle path planning, the treatment path and functional distribution are synergistically matched, improving the accuracy and safety of minimally invasive treatment; by identifying abnormal areas through real-time thermal imaging feedback during surgery and dynamically adjusting the needle path and energy output, adaptive control of the treatment process is achieved, enhancing the stability and controllability of the operation; finally, the prediction model is corrected by combining postoperative difference analysis, achieving continuous optimization and individualized adaptation of the model, and improving the consistency of the effect of minimally invasive axillary treatment. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a thermal imaging-guided minimally invasive axillary treatment planning method.

[0019] Figure 2 A schematic diagram to obtain the characteristics of sweat gland activity.

[0020] Figure 3 This is a flowchart for generating and optimizing the optimal minimally invasive needle path. Detailed Implementation

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0023] 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 phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0024] Reference Figures 1-3 This is one embodiment of the present invention, which provides a thermal imaging-guided minimally invasive axillary treatment planning method, including the following steps: Infrared thermal imaging data of the patient's axillary region was collected and preprocessed to generate a thermal imaging sequence. Based on the thermal imaging sequence, the temperature change amplitude, temperature rise rate, and local temperature gradient of each pixel were calculated to generate a set of sweat gland activity features.

[0025] Specifically, the patient's axillary region is fixed in position, and an infrared device is used to continuously scan the axillary region to obtain thermal imaging data at each time frame; The thermal imaging data of each time frame are standardized and combined in chronological order to generate a standardized thermal imaging sequence.

[0026] By fixing the patient's axillary region in position and using an infrared device for continuous scanning, stable acquisition of temperature information of the target area was achieved, ensuring the continuity and consistency of thermal imaging data acquisition and improving the reliability of the data source. By standardizing the thermal imaging data of each time frame and combining them in chronological order, a thermal imaging sequence with uniform scale and temporal correlation was generated, making subsequent temperature change analysis comparable and timely, improving the effectiveness of thermal imaging data in sweat gland activity analysis, and providing a stable data foundation for subsequent feature extraction and activity prediction.

[0027] Furthermore, based on the thermal imaging sequence, the temperature value corresponding to each pixel in each time frame is extracted, and a temperature sequence for each pixel is established. Based on the temperature sequence, the difference between the maximum and minimum temperature values ​​of each pixel within a preset time window is calculated to obtain the temperature change amplitude. Based on the temperature changes of adjacent time frames in the temperature sequence, the rate of temperature change per unit time is calculated to obtain the temperature rise rate of each pixel. In each time frame, taking each pixel as the center and combining the temperature distribution of its neighboring pixels, the temperature change in the spatial direction is calculated to obtain the local temperature gradient. The temperature change amplitude, temperature rise rate and local temperature gradient are normalized and then associated and organized according to the spatial location of pixels to generate multidimensional feature vectors for each pixel. By integrating the multidimensional feature vectors of all pixels, a set of sweat gland activity features is generated.

[0028] By extracting temperature values ​​from each pixel based on thermal imaging sequences and constructing temperature sequences, a continuous characterization of temperature changes in the axillary region over time was achieved, providing fundamental data support for reflecting the dynamic activity of sweat glands. By calculating the amplitude of temperature changes and the rate of temperature rise, a quantitative characterization of the activity level and trends of sweat glands was achieved, enabling effective identification of functional differences in different regions. Simultaneously, by introducing local temperature gradient analysis, the spatial temperature distribution characteristics were characterized, enhancing the ability to identify the spatial distribution of sweat gland activity. By normalizing multiple temperature features and constructing multi-dimensional feature vectors, a unified expression and association of multi-source features was completed. Furthermore, by integrating these features to form a set of sweat gland activity features, a comprehensive description of the sweat gland activity state in the axillary region was achieved, improving the accuracy and stability of subsequent activity prediction.

[0029] The set of sweat gland activity features is input into a pre-established sweat gland activity prediction model to obtain the distribution results of sweat gland activity within a future preset time window. Using the sweat gland activity distribution results as the optimization target, combined with the axillary risk tissue constraint conditions, the path position, insertion angle and depth of action of the minimally invasive needle path are constrained and optimized to generate the optimal minimally invasive needle path.

[0030] Specifically, the set of sweat gland activity features is mapped according to the spatial location of pixels to construct a feature distribution matrix corresponding to the axillary region, which serves as the input data for the sweat gland activity prediction model. The continuous feature distribution matrix is ​​input into the pre-trained sweat gland activity prediction model to calculate the sweat gland activity intensity of each pixel, and the corresponding activity response value is obtained. The formula is as follows: ; in, For time index, For the preset time point, For spatial location, for Time and space location Location, future time The sweat gland activity value at that time For the pre-trained sweat gland activity prediction model, For spatial location The amplitude of temperature change at that location, For spatial location The rate of temperature rise at that location, For spatial location Local temperature gradient at that location , , These are the weighting coefficients for the temperature change amplitude, temperature rise rate, and local temperature gradient obtained from pre-training.

[0031] Spatial reconstruction of the active response values ​​is performed to correspond one-to-one with the actual spatial location of the axillary region, generating an initial sweat gland activity distribution map; The initial sweat gland activity distribution map is extrapolated over time to obtain the trend of sweat gland activity changes in each region within a future preset time window. Based on the trend of sweat gland activity changes, the activity response values ​​of each pixel are weighted and integrated to generate a sweat gland activity distribution result that characterizes the future sweat gland activity distribution in the axillary region.

[0032] By mapping the set of sweat gland activity features according to pixel spatial location and constructing a feature distribution matrix, the correspondence between feature data and axillary spatial structure is realized, improving data utilization efficiency. By inputting the continuous feature distribution matrix into a pre-trained sweat gland activity prediction model, the intensity of sweat gland activity at each pixel is calculated, obtaining activity response information reflecting local functional state and improving the ability to identify the degree of sweat gland activity. By performing time extrapolation processing on the initial distribution map and combining it with the change trend for weighted integration, a predictive description of future sweat gland activity distribution is realized, providing a forward-looking basis for minimally invasive treatment path planning and improving the scientific nature of treatment decisions.

[0033] Furthermore, based on the distribution of sweat gland activity, the spatial location and distribution range of highly active areas are extracted to generate a set of target areas to be treated. Acquire spatial location information of blood vessels, nerves and lymphatic tissues in the axillary region, and generate a risk tissue constraint area based on a preset safety distance; Using the set of target areas to be treated as the coverage target, the path position, insertion angle and depth of action of the minimally invasive needle path are used as adjustable parameters to construct a set of needle path parameters; Based on the spatial relationship between the set of needle path parameters and the risk organization constraint area, needle path parameters that do not meet the safety distance constraint are screened out to form a set of candidate needle paths. In the candidate needle path set, each candidate needle path is selected and ranked according to the evaluation rules of coverage of high-activity areas and path continuity; The optimal minimally invasive needle path is selected based on the combination of needle path parameters that best covers the target area and meets the risk organization constraints.

[0034] By extracting the spatial location of highly active areas based on the distribution of sweat gland activity and generating a set of target areas for treatment, precise definition of the treatment target area was achieved, providing clear functional guidance for minimally invasive intervention and improving treatment targeting. By acquiring the spatial location information of blood vessels, nerves, and lymphatic tissues and constructing risk tissue constraint areas, effective avoidance of key anatomical structures was achieved, ensuring the safety of the treatment process. By constructing a set of needle path parameters and combining them with spatial constraint relationships to form a set of candidate needle paths, unreasonable paths were pre-eliminated, improving the rationality of path design. At the same time, by optimizing and ranking the candidate needle paths according to coverage and path continuity, a comprehensive balance between treatment efficiency and path operability was achieved, and the optimal minimally invasive needle path was finally selected, improving the scientificity and accuracy of treatment path planning.

[0035] The system collects thermal imaging data in real time during minimally invasive treatment. When the local temperature change exceeds the preset threshold, it is identified as an abnormal area. Based on the location of the abnormal area and the degree of temperature deviation, the position of the minimally invasive needle path and the energy output parameters are corrected according to the preset adjustment rules.

[0036] Specifically, minimally invasive treatment is performed using the optimal minimally invasive needle path, and thermal imaging data of the axillary region is collected in real time during the treatment process; The real-time thermal imaging data is standardized to generate a real-time temperature distribution map, which is then spatially registered with the sweat gland activity distribution results. For each registered pixel, the difference between the real-time temperature value and the predicted temperature value is calculated to obtain the temperature deviation distribution; Pixels with temperature deviations exceeding a preset threshold are spatially clustered to form continuously distributed abnormal regions, and the location and range information of the abnormal regions are output.

[0037] By implementing treatment based on the optimal minimally invasive needle path and simultaneously acquiring thermal imaging data of the axillary region, the treatment process and temperature information acquisition were synchronized, providing a data foundation for real-time status monitoring and improving the observability of the treatment process. Standardizing the real-time thermal imaging data and spatially registering it with the sweat gland activity distribution results enabled a correlation between the actual temperature distribution and the predicted functional distribution, enhancing the accuracy of data comparison and analysis. Calculating the deviation between real-time and predicted temperatures and constructing a temperature deviation distribution allowed for a quantitative characterization of treatment effect deviations, enabling timely identification of potential abnormalities. Furthermore, spatial clustering of abnormal pixels to form continuous abnormal regions enabled spatial integration and localization of local abnormal states, improving the stability and reliability of abnormality identification.

[0038] Furthermore, based on the location and extent of the abnormal area, the abnormal area is mapped to the corresponding minimally invasive needle path segment to determine the target needle path area that needs to be adjusted. Based on the degree of temperature deviation, abnormal areas are classified and processed into multiple deviation levels. For different deviation levels, the preset adjustment rules are invoked to determine the corresponding needle path adjustment strategy and energy output adjustment strategy; Based on the needle path adjustment strategy, the path position, insertion angle, and depth of action of the target needle path area are corrected, and based on the energy output adjustment strategy, the energy output parameters are adjusted.

[0039] By mapping the location and extent of abnormal areas to corresponding minimally invasive needle path segments, a precise correlation between abnormal states and specific operational paths is achieved, thereby clearly identifying the target needle path areas requiring adjustment and improving the targeting of adjustments. By classifying abnormal areas according to the degree of temperature deviation, different degrees of abnormality are distinguished, providing a basis for differentiated control and enhancing the precision of the adjustment strategy. By calling preset adjustment rules for different deviation levels, corresponding adjustment strategies for needle paths and energy are determined, achieving standardization and controllability of the adjustment process. Simultaneously, by correcting needle path positions, insertion angles, and depths of action, as well as synchronously adjusting energy output parameters, synergistic optimization of the treatment path and intensity of action is achieved, improving the adaptability and overall stability of the minimally invasive treatment process.

[0040] Postoperative thermal imaging data was acquired and compared with the results of sweat gland activity distribution. The parameters of the sweat gland activity prediction model were then adjusted based on the comparison results.

[0041] Specifically, after the minimally invasive treatment is completed, thermal imaging is performed again on the patient's axillary area to obtain postoperative thermal imaging data, which is then standardized and spatially registered. Based on the registered data, the postoperative temperature distribution and sweat gland activity distribution of each pixel are compared point by point, the temperature difference or activity deviation is calculated, and a difference distribution map is generated. Based on the differential distribution map, extract the overall and local deviation features of the axillary region; Based on the overall and local deviation characteristics, determine the range of parameters that need to be corrected and the direction of adjustment in the sweat gland activity prediction model; The parameters of the sweat gland activity prediction model are corrected according to the preset parameter update rules.

[0042] By performing re-thermal imaging of the axillary region after minimally invasive treatment and then standardizing and spatially registering the data, postoperative data was aligned with preoperative predictions, ensuring the accuracy of subsequent analysis. By comparing postoperative temperature distribution and sweat gland activity distribution point-by-point and generating a difference distribution map, a refined characterization of treatment deviations was achieved, intuitively reflecting the treatment coverage. By extracting overall and local deviation features, a comprehensive analysis of global effects and local differences was realized, providing multi-level evidence for model correction. Simultaneously, the adjustment range and direction of model parameters were determined based on deviation features and corrected, enabling targeted optimization and adaptive updating of the prediction model, improving its predictive accuracy and stability in subsequent applications.

[0043] This embodiment also provides a computer device applicable to the thermal imaging-guided axillary minimally invasive treatment planning method, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the thermal imaging-guided axillary minimally invasive treatment planning method as proposed in the above embodiment.

[0044] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0045] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the thermal imaging-guided axillary minimally invasive treatment planning method as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0046] In summary, this invention achieves refined characterization of sweat gland function by extracting multidimensional temperature features from thermal imaging sequences of the axillary region and constructing a set of sweat gland activity features, thereby improving the accuracy of sweat gland activity identification. By inputting sweat gland activity features into a prediction model to obtain sweat gland activity distribution results, and using this as a target combined with risk tissue constraints to optimize the minimally invasive needle path planning, the treatment path and functional distribution are synergistically matched, improving the precision and safety of minimally invasive treatment. Through real-time intraoperative thermal imaging feedback to identify abnormal areas and dynamically adjust the needle path and energy output, adaptive control of the treatment process is achieved, enhancing the stability and controllability of the operation. Finally, postoperative difference analysis is combined to correct the prediction model, achieving continuous model optimization and individualized adaptation, thus improving the consistency of minimally invasive axillary treatment outcomes.

[0047] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for planning minimally invasive axillary treatment based on thermal imaging, characterized in that: include, Infrared thermal imaging data of the patient's axillary region was collected and preprocessed to generate a thermal imaging sequence. Based on the thermal imaging sequence, the temperature change amplitude, temperature rise rate and local temperature gradient of each pixel were calculated to generate a set of sweat gland activity features. The set of sweat gland activity features is input into a pre-established sweat gland activity prediction model to obtain the sweat gland activity distribution results within a future preset time window. The sweat gland activity distribution results are used as the optimization target. Combined with the axillary risk tissue constraint conditions, the path position, insertion angle and action depth of the minimally invasive needle path are constrained and optimized to generate the optimal minimally invasive needle path. The system collects thermal imaging data in real time during minimally invasive treatment. When the local temperature change exceeds the preset threshold, it is identified as an abnormal area. Based on the location of the abnormal area and the degree of temperature deviation, the position of the minimally invasive needle path and the energy output parameters are corrected according to the preset adjustment rules. Postoperative thermal imaging data was acquired and compared with the results of sweat gland activity distribution. The parameters of the sweat gland activity prediction model were then adjusted based on the comparison results.

2. The axillary minimally invasive treatment planning method based on thermal imaging as described in claim 1, characterized in that: The generation of the thermal imaging sequence includes the following steps: The patient's axillary region was fixed in position, and an infrared device was used to continuously scan the axillary region to obtain thermal imaging data at each time frame; The thermal imaging data of each time frame are standardized and combined in chronological order to generate a standardized thermal imaging sequence.

3. The axillary minimally invasive treatment planning method based on thermal imaging as described in claim 2, characterized in that: The generation of the sweat gland activity feature set includes the following steps: Based on the thermal imaging sequence, the temperature value corresponding to each pixel in each time frame is extracted, and the temperature sequence of each pixel is established. Based on the temperature sequence, the difference between the maximum and minimum temperature values ​​of each pixel within a preset time window is calculated to obtain the temperature change amplitude. Based on the temperature changes of adjacent time frames in the temperature sequence, the rate of temperature change per unit time is calculated to obtain the temperature rise rate of each pixel. In each time frame, taking each pixel as the center and combining the temperature distribution of its neighboring pixels, the temperature change in the spatial direction is calculated to obtain the local temperature gradient. The temperature change amplitude, temperature rise rate and local temperature gradient are normalized and then associated and organized according to the spatial location of pixels to generate multidimensional feature vectors for each pixel. By integrating the multidimensional feature vectors of all pixels, a set of sweat gland activity features is generated.

4. The axillary minimally invasive treatment planning method based on thermal imaging as described in claim 3, characterized in that: The step of inputting a set of sweat gland activity features into a pre-established sweat gland activity prediction model to obtain the distribution of sweat gland activity within a future preset time window includes the following steps: The sweat gland activity feature set is mapped according to the pixel spatial location to construct a feature distribution matrix corresponding to the axillary region, which serves as the input data for the sweat gland activity prediction model. The continuous feature distribution matrix is ​​input into the pre-trained sweat gland activity prediction model to calculate the sweat gland activity intensity of each pixel and obtain the corresponding activity response value. Spatial reconstruction of the active response values ​​is performed to correspond one-to-one with the actual spatial location of the axillary region, generating an initial sweat gland activity distribution map; The initial sweat gland activity distribution map is extrapolated over time to obtain the trend of sweat gland activity changes in each region within a future preset time window. Based on the trend of sweat gland activity changes, the activity response values ​​of each pixel are weighted and integrated to generate a sweat gland activity distribution result that characterizes the future sweat gland activity distribution in the axillary region.

5. The axillary minimally invasive treatment planning method based on thermal imaging as described in claim 4, characterized in that: The process of constraining and optimizing the path position, insertion angle, and depth of action of the minimally invasive needle to generate the optimal minimally invasive needle path includes the following steps: Based on the distribution of sweat gland activity, the spatial location and distribution range of highly active areas are extracted to generate a set of target areas to be treated. Acquire spatial location information of blood vessels, nerves and lymphatic tissues in the axillary region, and generate a risk tissue constraint area based on a preset safety distance; Using the set of target areas to be treated as the coverage target, the path position, insertion angle and depth of action of the minimally invasive needle path are used as adjustable parameters to construct a set of needle path parameters; Based on the spatial relationship between the set of needle path parameters and the risk organization constraint area, needle path parameters that do not meet the safety distance constraint are screened out to form a set of candidate needle paths. In the candidate needle path set, each candidate needle path is selected and ranked according to the evaluation rules of coverage of high-activity areas and path continuity; The optimal minimally invasive needle path is selected based on the combination of needle path parameters that best covers the target area and meets the risk organization constraints.

6. The axillary minimally invasive treatment planning method based on thermal imaging as described in claim 5, characterized in that: The real-time acquisition of thermal imaging data during minimally invasive treatment, and the determination of an abnormal area when the local temperature change exceeds a preset threshold, includes the following steps: Minimally invasive treatment is performed using the optimal minimally invasive needle path, and thermal imaging data of the axillary region is collected in real time during the treatment process; The real-time thermal imaging data is standardized to generate a real-time temperature distribution map, which is then spatially registered with the sweat gland activity distribution results. For each registered pixel, the difference between the real-time temperature value and the predicted temperature value is calculated to obtain the temperature deviation distribution; Pixels with temperature deviations exceeding a preset threshold are spatially clustered to form continuously distributed abnormal regions, and the location and range information of the abnormal regions are output.

7. The axillary minimally invasive treatment planning method based on thermal imaging as described in claim 6, characterized in that: The step of correcting the position of the minimally invasive needle path and the energy output parameters according to the preset adjustment rules includes the following steps: Based on the location and extent of the abnormal area, the abnormal area is mapped to the corresponding minimally invasive needle path segment to determine the target needle path area that needs to be adjusted. Based on the degree of temperature deviation, abnormal areas are classified and processed into multiple deviation levels. For different deviation levels, the preset adjustment rules are invoked to determine the corresponding needle path adjustment strategy and energy output adjustment strategy; Based on the needle path adjustment strategy, the path position, insertion angle, and depth of action of the target needle path area are corrected, and based on the energy output adjustment strategy, the energy output parameters are adjusted.

8. The axillary minimally invasive treatment planning method based on thermal imaging as described in claim 7, characterized in that: The process of acquiring postoperative thermal imaging data and performing a difference analysis with the results of sweat gland activity distribution, and then correcting the parameters of the sweat gland activity prediction model based on the difference results, includes the following steps: After the minimally invasive treatment is completed, thermal imaging is performed again on the patient's axillary area to obtain postoperative thermal imaging data and perform standardization and spatial registration processing. Based on the registered data, the postoperative temperature distribution and sweat gland activity distribution of each pixel are compared point by point, the temperature difference or activity deviation is calculated, and a difference distribution map is generated. Based on the differential distribution map, extract the overall and local deviation features of the axillary region; Based on the overall and local deviation characteristics, determine the range of parameters that need to be corrected and the direction of adjustment in the sweat gland activity prediction model; The parameters of the sweat gland activity prediction model are corrected according to the preset parameter update rules.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the thermal imaging-guided axillary minimally invasive treatment planning method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the thermal imaging-guided axillary minimally invasive treatment planning method as described in any one of claims 1 to 8.

Images