Information processing method, program, information processing device, model generating method, and balloon catheter manufacturing method

Abstract

Provided are an information processing method and the like capable of easily measuring the pressure resistance of a balloon for a balloon catheter. A computer acquires spectral data of light from a tube that has been formed into a balloon for a balloon catheter, the light being generated by irradiating the tube with near-infrared light. The computer then identifies information relating to the pressure resistance of the tube on the basis of the acquired spectral data.

Description

Information processing method, program, information processing device, model generation method, and balloon catheter manufacturing method

[0001] The present disclosure relates to an information processing method, a program, an information processing device, a model generation method, and a balloon catheter manufacturing method.

[0002] Intravascular treatment is performed as a treatment method for lesions such as stenosis or occlusion in blood vessels, in which a treatment device such as a balloon catheter or a stent is percutaneously inserted into the blood vessel to dilate the lesion. Patent Document 1 discloses a technology for manufacturing a balloon catheter with low sliding resistance and excellent operability.

[0003] International Publication No. 2010 / 131554

[0004] Since balloon catheters expand the lesion by inserting a balloon into the blood vessel and expanding it at the lesion, the balloon must be pressure-resistant. Therefore, there is a need for a technology that can easily measure the pressure resistance of a balloon, for example, during the manufacturing process of balloon catheters.

[0005] In one aspect, an object of the present invention is to provide an information processing method and the like that can easily measure the pressure resistance of a balloon for a balloon catheter.

[0006] (1) The present disclosure relates to an information processing method in which a computer acquires spectroscopic data of light from a tube formed into a balloon for a balloon catheter when near-infrared light is irradiated onto the tube, and identifies information regarding the pressure resistance of the tube based on the acquired spectroscopic data.

[0007] (2) In the information processing method of (1) above, it is preferable that the computer further performs a process of performing multivariate analysis on the spectroscopic data to obtain the distribution of each wavelength component contained in the light from the tube, and identifying information regarding the pressure resistance of the tube based on the distribution of each wavelength component.

[0008] (3) In the information processing method of (2) above, it is preferable that the computer further executes a process of identifying information relating to the pressure resistance of the tube based on the distribution of a specific wavelength component in the distribution of each wavelength component.

[0009] (4) In the information processing method of (2) above, it is preferable that the computer further executes a process of acquiring information about the pressure resistance of the tube by inputting the distribution of each wavelength component obtained by performing multivariate analysis on the spectroscopic data into a learning model that has been trained to output information about the pressure resistance of the tube when the distribution of each wavelength component contained in the light from the tube is input.

[0010] (5) In the information processing method described in any one of (1) to (4) above, it is preferable that the computer further executes a preprocessing process including normalization, smoothing, and differentiation on the spectroscopic data.

[0011] (6) In the information processing method described in any one of (1) to (5) above, it is preferable that the computer further executes a process of acquiring spectroscopic data of light from the pre-molded tube generated by irradiating near-infrared light onto the pre-molded tube before it is balloon-molded, and identifying information regarding the pressure resistance of the pre-molded tube based on the acquired spectroscopic data.

[0012] (7) In the information processing method described in any one of (1) to (6) above, it is preferable that the computer further executes a process of acquiring the spectroscopic data using a near-infrared spectrometer or a hyperspectral camera.

[0013] (8) The present disclosure also provides a program that causes a computer to execute a process of acquiring spectroscopic data of light from a tube formed into a balloon for a balloon catheter when near-infrared light is irradiated onto the tube, and identifying information regarding the pressure resistance of the tube based on the acquired spectroscopic data.

[0014] (9) The present disclosure also provides an information processing device including a control unit, which acquires spectroscopic data of light from a tube formed into a balloon for a balloon catheter when near-infrared light is irradiated onto the tube, and identifies information regarding the pressure resistance of the tube based on the acquired spectroscopic data.

[0015] (10) The present disclosure also provides a model generation method in which a computer acquires training data that associates the distribution of each wavelength component contained in light from a tube generated by irradiating the tube with near-infrared light and information related to the pressure resistance of the tube, and uses the acquired training data to generate a learning model that outputs information related to the pressure resistance of the tube when the distribution of each wavelength component contained in the light from the tube is input.

[0016] (11) The present disclosure also provides a balloon catheter manufacturing method including the steps of: molding a tube into a balloon for use in a balloon catheter using a balloon molding machine; irradiating the balloon-molded tube with near-infrared light using a light-emitting unit; acquiring spectroscopic data of the light from the balloon-molded tube; identifying the pressure resistance or pressure resistance value of the balloon-molded tube based on the acquired spectroscopic data; determining whether the identified pressure resistance or pressure resistance value is equal to or greater than a reference value; and connecting the balloon-molded tube, whose pressure resistance or pressure resistance value is determined to be equal to or greater than the reference value, to a balloon catheter shaft.

[0017] In one aspect, the pressure resistance of a balloon for a balloon catheter can be easily measured.

[0018] 1 is a block diagram showing an example of the configuration of a measurement system; FIG. 2 is an explanatory diagram of a balloon to be measured; FIG. 3 is an explanatory diagram showing an example of the record layout of an analysis result DB; FIG. 4 is an explanatory diagram showing an example of the configuration of a learning model; FIG. 5 is an explanatory diagram of an example of the configuration of a learning model; FIG. 6 is an explanatory diagram of a component analysis process; FIG. 7 is an explanatory diagram of a component analysis process; FIG. 8 is an explanatory diagram of a component analysis process; FIG. 9 is an explanatory diagram of a component analysis process; FIG. 10 is a flowchart showing an example of a processing procedure for generating a learning model; FIG. 11 is a flowchart showing an example of a processing procedure for estimating a withstand pressure value; FIG. 12 is an explanatory diagram of a component analysis result of spectroscopic data of a tube; FIG. 13 is an explanatory diagram showing an example of a record layout of a DB stored in an information processing device of embodiment 2; FIG. 14 is an explanatory diagram showing an example of a record layout of a DB stored in an information processing device of embodiment 2; FIG. 15 is a flowchart showing an example of a processing procedure for estimating a withstand pressure value of embodiment 2.

[0019] Hereinafter, the information processing method, program, information processing device, model generation method, and balloon catheter manufacturing method of the present disclosure will be described in detail with reference to the drawings showing embodiments thereof.

[0020] (Embodiment 1) An information processing device for measuring the pressure resistance of a balloon attached to a shaft tube and constituting a balloon catheter will be described. The balloon catheter in this embodiment is a catheter that is inserted into a hollow organ such as a blood vessel, bile duct, pancreatic duct, bronchi, esophagus, intestine, or urethra.

[0021] 1 is a block diagram showing an example of the configuration of a measurement system. The measurement system of this embodiment includes an information processing device 10 and a spectroscopic device 20, which are communicatively connected by wired communication via a cable or wireless communication. The information processing device 10 and the spectroscopic device 20 may also be communicatively connected via a network, which may be the Internet, a public communication line, or a LAN (Local Area Network) constructed within a facility where the measurement system is installed.

[0022] The spectroscopic device 20 is a device that irradiates a measurement object (in this embodiment, a balloon used in a balloon catheter) with near-infrared light, receives the light from the measurement object, and acquires spectroscopic data (spectral data) by decomposing the received light into wavelengths. For example, a near-infrared spectroscopic device, a hyperspectral camera, or the like can be used. The spectroscopic device 20 includes a light-emitting unit 21, a light-receiving unit 22, a signal processing unit 23, and a communication unit 24. The light-emitting unit 21 emits near-infrared light having a wavelength in the range of approximately 750 nm to 2500 nm. The light-receiving unit 22 receives the near-infrared light emitted by the light-emitting unit 21 from the measurement object (reflected light or transmitted light). The spectroscopic device 20 may be a reflection-type spectroscopic device that receives reflected light from the measurement object of the near-infrared light irradiated by the light-emitting unit 21, or a transmission-type spectroscopic device that receives transmitted light of the irradiated near-infrared light that has passed through the measurement object. The signal processing unit 23 generates spectral data by decomposing the light received by the light receiving unit 22 into wavelengths. The communication unit 24 is a communication module for directly communicating with the information processing device 10 and transmits the spectral data generated by the signal processing unit 23 to the information processing device 10. Note that the communication unit 24 may also be a communication module for connecting to a network, in which case the spectral data is transmitted to the information processing device 10 via the network.

[0023] In addition to the above-described configuration, the spectroscopic device 20 may be configured to include an input unit that accepts user input and a display unit such as a liquid crystal display or an organic EL display. The spectroscopic device 20 may also be configured to include a polarizing plate on the light-receiving surface side of the light-receiving unit 22, and to receive light (reflected light or transmitted light) from the measurement object through the polarizing plate. Because the spectroscopic data is proportional to the absorbance of the measurement object, qualitative and quantitative evaluations of the characteristics of the measurement object can be performed from the obtained spectroscopic data (the absorbance indicated by the spectroscopic data). In this embodiment, the information processing device 10 performs qualitative and quantitative evaluations of the pressure resistance of the measurement object based on the spectroscopic data acquired by the spectroscopic device 20.

[0024] The information processing device 10 is a device capable of various information processing and information transmission and reception, and is composed of, for example, a personal computer, a server computer, etc. The information processing device 10 has a control unit 11, a memory unit 12, a communication unit 13, an input unit 14, a display unit 15, a reading unit 16, etc., and these units are connected via a bus. The control unit 11 has one or more processors, such as a central processing unit (CPU), a micro-processing unit (MPU), a graphics processing unit (GPU), a general-purpose computing on graphics processing units (GPGPU), or a tensor processing unit (TPU). The control unit 11 appropriately executes a program P stored in the memory unit 12 to perform various information processing, control processing, etc., that the information processing device 10 should perform. Note that if the control unit 11 has multiple processors, each process may be executed by the same processor, or each process may be executed by a different processor.

[0025] The storage unit 12 includes RAM (Random Access Memory), flash memory, a hard disk, an SSD (Solid State Drive), etc. The storage unit 12 pre-stores a program P (program product) executed by the control unit 11 and various data necessary for executing the program P. The storage unit 12 temporarily stores data generated when the control unit 11 executes the program P. The storage unit 12 also stores a learning model M that has learned training data, for example, through machine learning. The learning model M is a machine learning model that has learned predetermined training data. For example, the learning model M receives information indicating the results of component analysis (spectral analysis) of spectroscopic data acquired by the spectroscopic device 20 as input and outputs data regarding the pressure resistance of a measurement object (a measurement object that reflects or transmits light related to the spectroscopic data). The learning model M is expected to be used as a program module constituting artificial intelligence software. The learning model M performs a predetermined calculation on input values ​​and outputs the calculation result. The storage unit 12 stores data such as coefficients and thresholds of functions that define this calculation as the learning model M. The storage unit 12 also stores an analysis result DB 12 a. The learning model M and / or the analysis result DB 12 a may be stored in another storage device connected to the information processing device 10 or in another storage device with which the information processing device 10 can communicate.

[0026] The communication unit 13 has a configuration similar to the communication unit 24 of the spectroscopic device 20, and receives spectroscopic data acquired by the spectroscopic device 20 from the spectroscopic device 20. The communication unit 13 may be configured to receive spectroscopic data from the spectroscopic device 20 via a network. The input unit 14 accepts operation input by a user and sends a control signal corresponding to the operation content to the control unit 11. The display unit 15 is a liquid crystal display, an organic EL display, or the like, and displays various information in accordance with instructions from the control unit 11. The input unit 14 and the display unit 15 may be a touch panel configured as an integrated unit. The input unit 14 and the display unit 15 are not essential, and the information processing device 10 may be configured to accept operations through a connected terminal device and output information to be displayed to an external display device.

[0027] The reading unit 16 reads information stored in a portable storage medium 10a, such as a CD (Compact Disc), a DVD (Digital Versatile Disc), a USB (Universal Serial Bus) memory, or an SD (Secure Digital) card. The program P and various data stored in the storage unit 12 may be read by the control unit 11 from the portable storage medium 10a via the reading unit 16 and stored in the storage unit 12. The program P and various data may be written to the storage unit 12 during the manufacturing stage of the information processing device 10, or may be downloaded by the control unit 11 from another device via the communication unit 13 and stored in the storage unit 12.

[0028] The information processing device 10 is not limited to a single computer, but may be a multi-computer including multiple computers. Furthermore, the information processing device 10 may be a virtual machine virtually constructed within a single device by software, or may be a cloud server. In the following description, the information processing device 10 is described as a single computer. Furthermore, the program P may be executed on a single computer, or on multiple computers interconnected via a network.

[0029] 2A and 2B are explanatory diagrams of a balloon to be measured. As shown in FIG. 2A, a balloon is manufactured by, for example, blowing air into a resin tube manufactured by extrusion molding using a balloon molding machine to expand the tube (balloon molding). FIG. 2B shows a method for measuring a balloon using a transmission-type spectroscopic device 20. Measurement is performed using the spectroscopic device 20 while a predetermined number of balloons (three in FIG. 2B) are held in a row on a holding member that holds the tube portions at both ends. The measurement process using the spectroscopic device 20 may be performed during the manufacturing process of a balloon catheter, for example, after a tube has been molded into a balloon using a balloon molding machine.

[0030] FIG. 3 is an explanatory diagram showing an example of the record layout of the analysis result DB 12a. The analysis result DB 12a is a database that stores the results of a balloon analysis process (pressure resistance measurement process) using the spectroscopic device 20. The analysis result DB 12a shown in FIG. 3 includes a tube ID column, a molding condition column, a spectroscopic data column, a component analysis result column, a pressure resistance column, and other columns, and stores information about balloons molded from tubes in association with the tube ID. The tube ID column stores identification information (tube ID) uniquely assigned to the tube before balloon molding. The molding condition column stores parameter settings (setting conditions) that can be set for the molding device used to mold the tube into a balloon. Note that the molding condition column may store, in addition to the setting conditions, material information about the tube material and environmental information about the surrounding environment during balloon molding. The spectroscopic data column stores spectroscopic data acquired from the balloon through measurement processing by the spectroscopic device 20. The component analysis result column stores information about the results of component analysis processing performed on the spectroscopic data. The component analysis processing performed on the spectroscopic data will be described later. The spectroscopic data and component analysis results may be stored in a predetermined area of ​​the memory unit 12 rather than in the analysis result DB 12a. In this case, the spectroscopic data column and component analysis result column store information for reading each data (e.g., a folder name and file name indicating the data storage location). The pressure resistance column stores information regarding the pressure resistance of the balloon. The pressure resistance information may include the pressure resistance value, the results of a pressure test performed on the balloon (pass / fail), and the yield of the molding process. The yield indicates the percentage of molded balloons that passed the pressure test. The contents stored in the analysis result DB 12a are not limited to the example shown in FIG. 3.

[0031] 4A and 4B are explanatory diagrams showing an example of the configuration of the learning model M. The learning model M shown in FIG. 4A is trained to receive input information indicating the results of component analysis of spectroscopic data acquired from a balloon using a spectroscopic device 20, perform a calculation to estimate the pressure resistance value of the balloon based on the input data, and output the calculated result. The learning model M can be configured using algorithms such as a support vector machine (SVM), a decision tree, a random forest, a convolutional neural network (CNN), or a transformer, or may be configured by combining multiple algorithms. The information indicating the component analysis results, which is input data, includes the types and contributions of a predetermined number (approximately 2 to 7) of components in descending order of contribution (content ratio). The pressure resistance value, which is output data, may be any numerical value or may be within a range of values ​​that can be assumed as a pressure resistance value.

[0032] The learning model M is generated by machine learning using training data that associates information indicating the results of component analysis of the training spectroscopic data with a correct pressure resistance value. The correct pressure resistance value can be a measurement result (pressure resistance value) obtained by performing pressure resistance measurements on an actually manufactured balloon. The learning model M learns to output a correct pressure resistance value when information indicating the results of component analysis of the spectroscopic data included in the training data is input. Specifically, the learning model M performs calculations based on the input information, estimates the pressure resistance value of the balloon from which the spectroscopic data was obtained, and obtains an estimated result. The learning model M then compares the estimated pressure resistance value with the correct pressure resistance value and optimizes parameters such as the weights (coupling coefficients) between neurons so that the two values ​​approximate each other. The parameter optimization method is not particularly limited, but examples include the steepest descent method and the backpropagation method. As a result, a learning model M that outputs a pressure resistance value of a balloon when information indicating the results of component analysis of the spectroscopic data is input is obtained.

[0033] The withstand voltage value output by the learning model M shown in Figure 4A is a numerical value expressed as a continuous value, and the learning model M outputs one of the continuous values ​​as a so-called regression problem. However, it may also be configured to consider it as a classification problem and determine one of selectable numerical values ​​or numerical ranges (numeric values ​​or numerical ranges that can be taken as the withstand voltage value) for the withstand voltage value. In this case, the learning model M determines the optimal numerical value or numerical range for the withstand voltage value from multiple preset numerical values ​​or numerical ranges and outputs the determination result.

[0034] FIG. 4B shows a modified example of the learning model M. The learning model M1 shown in FIG. 4B receives input data similar to that of the learning model M shown in FIG. 4A, performs a calculation to estimate the results of a pressure test on the balloon based on the input data, and outputs the calculation results. The learning model M1 has multiple output nodes, each of which is associated with a label indicating whether the pressure test result on the balloon is pass or fail. Each output node outputs a probability (certainty) that the pressure test result should be determined to be pass or fail. The output value of each output node is, for example, a value between 0 and 1, and the sum of the probabilities output from each output node is 1.0 (100%). With the above-described configuration, when information indicating the component analysis results of the spectroscopic data is input, the learning model M1 outputs information regarding whether the pressure test result on the balloon is pass or fail (certainty regarding pass or fail). The information processing device 10 identifies the label (pass or fail) associated with the output node that outputs the largest output value (certainty) among the output values ​​from each output node in the learning model M1 as information related to the pressure resistance of the balloon to be predicted. Note that instead of having two output nodes that output the confidence levels for pass or fail, the learning model M1 may be configured to have a single output node that outputs information corresponding to the label (pass or fail) with the higher confidence level.

[0035] The learning model M1 is generated by machine learning using training data that associates information indicating the component analysis results of the training spectroscopic data with correct pressure test results. The correct pressure test results can be information indicating the test results (pass or fail) obtained by conducting a pressure test on an actually manufactured balloon. When information indicating the component analysis results of the spectroscopic data included in the training data is input, the learning model M1 learns so that the output value from the output node corresponding to the correct label (correct test result) approaches 1.0 and the output value from the other output node approaches 0.0. In the learning process, the learning model M1 performs calculations based on the information indicating the component analysis results of the input spectroscopic data to calculate output values ​​from each output node. The learning model M1 then compares the calculated output values ​​of each output node with values ​​corresponding to the correct label (1 for the output node corresponding to the correct label and 0 for the other output nodes) and optimizes parameters used in the calculation process so that the calculated output values ​​approximate the correct label. Here, parameters such as weights between neurons in the learning model M1 are optimized using backpropagation, steepest descent, or the like. This results in a learning model M1 that, when information indicating the results of component analysis of spectroscopic data is input, estimates information indicating the results of the pressure test on the balloon (pass or fail) and outputs the estimated result.

[0036] The learning models M and M1 may be trained on another learning device. The trained learning models M and M1 generated by training on another learning device are downloaded from the learning device to the information processing device 10 via a network or via a portable storage medium 10a and stored in the storage unit 12. The learning models M and M1 are not limited to the configurations shown in Figures 4A and 4B and may be configured to estimate, for example, the yield in the molding process for molding a balloon based on information indicating the component analysis results of the spectroscopic data.

[0037] The information processing device 10 prepares the learning models M and M1 as described above in advance, and when conducting a pressure resistance test on a balloon, estimates the pressure resistance value of the balloon or the results of the pressure resistance test using the learning models M and M1. The following describes an example of a configuration in which the information processing device 10 estimates the pressure resistance value of a balloon using the learning model M.

[0038] Here, we will explain the component analysis process (spectral analysis process) performed on spectroscopic data acquired using the spectroscopic device 20. FIGS. 5A to 6C are explanatory diagrams of the component analysis process. The left side of FIGS. 5A and 5B shows spectroscopic data, which are graphs with wavelength on the horizontal axis and absorbance on the vertical axis. The spectroscopic data acquired by the spectroscopic device 20 has overlapping absorbance (spectral) peaks for each component being measured, resulting in the peaks of each component being obscured, as shown on the left side of FIGS. 5A and 5B. Furthermore, as shown on the left side of FIG. 5B, the spectroscopic data exhibits a fluctuating baseline as the absorbance of each component changes. The baseline is expressed as a linear function (y = ax + b), and the example on the left side of FIG. 5B shows two baselines, one solid and one dashed. Furthermore, because spectroscopic data cannot capture the characteristics of each component based solely on wavelength changes at a single wavelength, it is necessary to analyze the change in absorbance (spectral change) across the entire wavelength range. Therefore, in this embodiment, preprocessing is performed on the spectroscopic data to expose hidden peaks and correct the baselines to eliminate variations between the baselines, and then multivariate analysis processing is performed to analyze the components contained in the spectroscopic data.

[0039] Preprocessing includes smoothing, normalization, and derivative processing. Smoothing reduces noise contained in the spectroscopic data, while normalization reduces the effect of the characteristics of the object being measured on the spectroscopic data. Second-order differentiation, as shown by the dashed circle on the right side of FIG. 5A, makes it possible to reveal absorbance peaks hidden in the spectroscopic data. Furthermore, as shown in FIG. 5B, the baseline represented by a linear function becomes y = 0, eliminating fluctuations between baselines.

[0040] Examples of the smoothing process that can be used include a moving average calculation process, a Gaussian filter process, a median filter process, and a Savitzky-Golay filter process. Examples of the normalization process that can be used include a standard normal variate (SNV) process and a multiplicative scatter correction (MSC) process. Examples of the differentiation process that can be used include a gap-segment process and a Savitzky-Golay filter process. Note that SNV processing is known to be able to appropriately suppress the influence of the film thickness of the measurement target on the spectroscopic data. In this embodiment, since the measurement target is a balloon, it is preferable to use SNV processing as the normalization process. Furthermore, since Savitzky-Golay filtering can simultaneously perform two filter processes, smoothing and differentiation, it is preferable to use Savitzky-Golay filtering as the smoothing process and differentiation process.

[0041] Examples of multivariate analysis include principal component analysis, cluster analysis, partial least squares discriminant analysis (PLS-DA), soft independent modeling of class analogy (SIMCA) classification, SVM, multiple regression analysis, principal component regression analysis, and PLS regression analysis. Figures 6A and 6B show the results of component analysis performed on the preprocessed spectroscopic data. Figure 6A shows a score plot representing the relationship between the scores of the first principal component (PC1) and the second principal component (PC2) obtained by the component analysis, with the scores of the first principal component on the horizontal axis and the scores of the second principal component on the vertical axis. In the score plot of Figure 6A, triangles indicate balloons that have experienced low-pressure bursts, squares indicate balloons that have experienced circumferential transverse cracks, and circles indicate normal balloons. As can be seen from Figure 6A, the relationship between the scores of the first and second principal components can be used to determine whether the balloon being measured is normal (whether a burst will occur). FIG. 6B shows a graph representing the change in loading value of the first principal component (PC1), with the horizontal axis representing wavelength and the vertical axis representing the loading value of the first principal component. As can be seen from FIG. 6B , the peak of the first principal component (the distribution of specific wavelength components) can be identified as indicated by the dashed circle. In particular, CH group peaks are detected near 750 nm, 900 nm, 1200 nm, 1400 nm, and 1700 nm. Based on the differences between these peaks, the characteristics of the object can be determined, and the level of pressure resistance (e.g., whether or not the object will pass a pressure resistance test) can be estimated (sorted). As described above, the characteristics of the object can be determined based on the scores and loading values ​​of each component contained in the spectroscopic data. In this embodiment, the pressure resistance of the balloon to be measured is estimated from the component analysis results of the spectroscopic data. FIG. 6C shows the case where the peak wavelength of the first principal component shown in FIG. 6B is identified based on spectroscopic data acquired by a hyperspectral camera. The absorbance of the peak wavelength is extracted from the spectroscopic data, and image data is generated based on the extracted absorbance. In FIG. 6C, the balloons that failed the pressure test are shown on the left, and the balloons that passed the pressure test are shown on the right.As shown in Figure 6C, if the peak wavelength of the principal component (e.g., the first principal component) can be identified, an image showing the characteristics of the object to be measured (in Figure 6C, the level of pressure resistance) can be presented based on the absorbance of the identified wavelength.

[0042] Next, the generation process of the learning model M will be described. FIG. 7 is a flowchart showing an example of the generation process procedure of the learning model M. The following process is performed by the control unit 11 of the information processing device 10 according to the program P stored in the storage unit 12, but may also be performed by another learning device. In the process shown in FIG. 7, the control unit 11 of the information processing device 10 first generates training data, and then uses the generated training data to train the learning model M. Note that the information processing device 10 previously collects and stores in the storage unit 12 the spectroscopic data used for the training data and the pressure resistance value of the balloon to be measured from which the spectroscopic data was obtained.

[0043] The control unit 11 reads one set of spectral data and breakdown voltage values ​​for training data stored in the memory unit 12 (S11). The control unit 11 performs the above-described preprocessing on the acquired spectral data (S12) and then performs multivariate analysis (S13). For example, the control unit 11 performs SNV processing (normalization processing) as preprocessing, followed by Savitzky-Golay filtering (smoothing processing and differentiation processing), and then performs principal component analysis as multivariate analysis. This allows the control unit 11 to obtain component analysis results for the spectral data (distribution of each wavelength component contained in the light from the balloon). The control unit 11 generates training data by assigning the breakdown voltage value acquired in step S11 to the acquired component analysis results as the correct breakdown voltage value, and stores the training data in the memory unit 12 (S14). The control unit 11 stores the generated training data, for example, in a training DB (not shown) provided in the memory unit 12.

[0044] The control unit 11 determines whether or not there is unprocessed data that has not been used to generate the training data among the sets of spectral data and withstand voltage values ​​for the training data (S15). If it determines that there is unprocessed data (S15: YES), the control unit 11 returns to step S11. The control unit 11 then executes the processes of steps S11 to S14 for the sets of unprocessed spectral data and withstand voltage values. The control unit 11 repeats the processes of steps S11 to S15 until it determines that there is no unprocessed data. As a result, training data to be used for learning the learning model M is generated and accumulated based on the spectral data and withstand voltage values ​​prepared for the training data.

[0045] If it is determined that there is no unprocessed data (S15: NO), the control unit 11 performs training on the learning model M using the accumulated training data. Specifically, the control unit 11 reads one piece of training data stored in the training DB (S16) and extracts the component analysis result for one pixel included in the read training data (S17). The control unit 11 then performs a training process on the learning model M using the component analysis result for one pixel and the withstand voltage value included in the training data (S18). Here, the control unit 11 inputs information indicating the component analysis result for one pixel into the learning model M and obtains an output value from the learning model M. The control unit 11 then compares the output value from the learning model M with the correct withstand voltage value included in the training data and optimizes parameters such as the weights between neurons in the learning model M using, for example, backpropagation so that the output value and the correct withstand voltage value approximate each other.

[0046] The control unit 11 determines whether there are any component analysis results for unprocessed pixels among the component analysis results included in the training data read out in step S16 (S19). If it determines that there are any (S19: YES), the control unit 11 returns to step S17. The control unit 11 then executes the processes of steps S17 to S18 for the component analysis results for the unprocessed pixels. That is, the control unit 11 extracts the component analysis result for one unprocessed pixel and performs a learning process for the learning model M using the component analysis result for the extracted one pixel and the withstand voltage value included in the training data. The control unit 11 repeats the processes of steps S17 to S19 until it determines that there are no unprocessed pixels. This allows the component analysis results for each pixel included in the component analysis result of one piece of spectral data prepared as training data to be used in learning the learning model M.

[0047] If the control unit 11 determines that there are no component analysis results for unprocessed pixels (S19: NO), it determines whether there is any unprocessed training data that has not been subjected to learning processing among the training data stored in step S14 (S20). If it determines that there is unprocessed training data (S20: YES), the control unit 11 returns to the processing of step S16 and executes the processing of steps S16 to S19 for the unprocessed training data. If it determines that there is no unprocessed training data (S20: NO), the control unit 11 ends the series of processing.

[0048] The above-described process generates a learning model M that is trained to output the withstand pressure value of the target balloon for the spectroscopic data when the results of the component analysis process on the spectroscopic data are input. Thus, the information processing device 10 can use the learning model M to estimate the withstand pressure value of the target balloon from the component analysis results of the spectroscopic data acquired from the target balloon using the spectroscopic device 20. In the above-described process, the training data generation process in steps S11 to S15 and the learning model M generation process in steps S16 to S20 may be performed by separate devices. The learning model M can be further optimized by repeatedly performing the learning process using the training data described above. Furthermore, the already trained learning model M may be fine-tuned (transfer learning) using training data for each balloon manufacturing factory or each balloon size. In this case, a learning model M tailored to each manufacturing factory or each size is generated, enabling the estimation of an appropriate withstand pressure value for each manufacturing factory or each size.

[0049] The process of estimating the pressure resistance value of a balloon using the learning model M configured as described above will be described below. FIG. 8 is a flowchart showing an example of the procedure for estimating the pressure resistance value. The control unit 11 of the information processing device 10 determines whether there is a balloon for which spectral data is stored in the analysis result DB 12a but component analysis results are not stored, and if it is determined that there is a balloon, the control unit 11 performs the following process for that balloon.

[0050] The control unit 11 acquires spectral data of the balloon to be processed from the analysis result DB 12a (S31). The control unit 11 performs preprocessing on the acquired spectral data (S32) and then performs multivariate analysis (S33). Steps S32 to S33 are the same as steps S12 to S13 in FIG. 7, and the control unit 11 thereby acquires component analysis results for the spectral data (distribution of each wavelength component contained in the light from the balloon) and stores the acquired component analysis results in the analysis result DB 12a in association with the tube ID of the balloon.

[0051] The control unit 11 extracts the component analysis result for one pixel from the component analysis result for the spectroscopic data (S34). Then, the control unit 11 estimates the withstand voltage value of the measurement object corresponding to the extracted component analysis result for one pixel (S35). Here, the control unit 11 inputs information indicating the component analysis result for one pixel into the learning model M and obtains the withstand voltage value as an output value from the learning model M. Note that the process of estimating the withstand voltage value from the component analysis result is not limited to processing using the learning model M and may be rule-based processing. For example, the withstand voltage value corresponding to the component analysis result can be estimated by previously associating the component analysis result for the spectroscopic data with the withstand voltage value. Alternatively, the distribution of a specific wavelength component (e.g., peak wavelength) with the withstand voltage value may be previously associated, and the withstand voltage value corresponding to the distribution of a specific wavelength component in the component analysis result for the measurement object may be estimated. The control unit 11 stores the estimated withstand voltage value in the memory unit 12, for example, by associating it with the identification information of the corresponding pixel.

[0052] The control unit 11 determines whether there are any component analysis results for unprocessed pixels among the component analysis results acquired in step S33 (S36), and if it determines that there are (S36: YES), the process returns to step S34. The control unit 11 then executes the processes of steps S34 to S35 for the component analysis results for the unprocessed pixels. The control unit 11 repeats the processes of steps S34 to S36 until it determines that there are no unprocessed pixels. As a result, a withstand voltage value based on the component analysis results for each pixel of the spectral data is estimated and stored in the storage unit 12.

[0053] If it is determined that there are no component analysis results for unprocessed pixels (S36: NO), the control unit 11 identifies the withstand pressure value of the balloon based on the withstand pressure values ​​estimated for each pixel in step S35 (S37). For example, the control unit 11 calculates the ratio of the estimated withstand pressure values ​​for each pixel and identifies the withstand pressure value with the largest ratio as the withstand pressure value of the balloon. Alternatively, the control unit 11 may identify the smallest withstand pressure value among the withstand pressure values ​​estimated for each pixel as the withstand pressure value of the balloon. Alternatively, the control unit 11 may identify the average of the withstand pressure values ​​estimated for each pixel as the withstand pressure value of the balloon. The control unit 11 stores the identified withstand pressure value of the balloon in the analysis result DB 12a in association with the tube ID of the balloon (S38), and terminates the process.

[0054] Through the above-described process, the information processing device 10 of this embodiment can estimate the withstand pressure value of a balloon based on the spectroscopic data acquired from the balloon using the spectroscopic device 20 and store the estimated withstand pressure value in the analysis result DB 12a. Note that, after the process of step S37, the control unit 11 may output an alert to notify a user (e.g., a balloon manufacturer) if, for example, the identified withstand pressure value is less than a predetermined value. Furthermore, when the control unit 11 receives a request to view the withstand pressure values ​​of each balloon stored in the analysis result DB 12a, the control unit 11 may display, on the display unit 15, a screen displaying the withstand pressure value of each balloon in association with the tube ID, for example. In this case, withstand pressure values ​​less than the predetermined value may be highlighted to warn the user.

[0055] In this embodiment, the process of measuring the pressure resistance value of the balloon using the spectroscopic device 20 and the information processing device 10 may be performed after a tube is molded into a balloon during the manufacturing process of a balloon catheter. For example, a balloon is molded from a tube using a balloon molding machine, and the light-emitting unit 21 of the spectroscopic device 20 irradiates the molded balloon (the balloon-molded tube) with near-infrared light, and the light-receiving unit 22 receives the light from the balloon to acquire spectroscopic data. The control unit 11 of the information processing device 10 then determines the pressure resistance value or pressure resistance level of the balloon (e.g., whether it will pass a pressure resistance test) based on the spectroscopic data acquired by the spectroscopic device 20, determines whether the determined pressure resistance value is equal to or greater than a reference value, or whether the determined pressure resistance is equal to or greater than a reference value (e.g., pass), and connects the balloon to a balloon catheter shaft if the determined pressure resistance value or pressure resistance is equal to or greater than the reference value. This manufacturing process enables the manufacture of a balloon catheter using a balloon whose pressure resistance value or pressure resistance meets the reference value. Alternatively, the process of measuring the pressure resistance value of the balloon may be performed after the molded balloon is connected to a balloon catheter shaft. In this case, a balloon catheter is manufactured by molding a tube into a balloon using a balloon molding machine and connecting the molded balloon to a balloon catheter shaft. The light-emitting unit 21 of the spectroscopic device 20 then irradiates the balloon of the balloon catheter with near-infrared light, and the light-receiving unit 22 receives the light from the balloon to acquire spectroscopic data. The control unit 11 of the information processing device 10 then identifies the pressure resistance or pressure resistance of the balloon based on the spectroscopic data acquired by the spectroscopic device 20, determines whether the identified pressure resistance or pressure resistance is equal to or greater than a reference value, and, if the pressure resistance or pressure resistance is equal to or greater than the reference value, allows the balloon catheter to be used.

[0056] In this embodiment, the spectroscopic device 20 may be either a near-infrared spectroscopic device or a hyperspectral camera, and may be either a reflective or transmissive type. Furthermore, it is preferable that the preprocessing and multivariate analysis performed on the spectroscopic data be highly accurate in estimating the pressure resistance of the balloon based on the results of component analysis performed on the spectroscopic data. For example, a highly accurate estimation based on the generated learning model M is used.

[0057] In this embodiment, the process of estimating the balloon's withstand pressure value from the component analysis results is not limited to being performed locally by the information processing device 10. For example, a server may be provided to execute the process of estimating the balloon's withstand pressure value from the component analysis results. In this case, the information processing device 10 may be configured to transmit information indicating the component analysis results for one pixel extracted in step S34 of FIG. 8 to the server and receive the estimated withstand pressure value from the server.

[0058] (Embodiment 2) An information processing device for measuring the pressure resistance of a tube before it is molded into a balloon will be described. The measurement system of this embodiment can be realized using devices similar to those of the measurement system of embodiment 1 shown in Figure 1, so a description of the configuration of each device will be omitted. In addition to the configuration shown in Figure 1, the information processing device 10 of this embodiment has an advice DB 12b stored in the memory unit 12, which registers advice on molding conditions for molding a balloon based on the pressure resistance value of the tube. Note that the analysis result DB 12a of this embodiment has a slightly different configuration from the analysis result DB 12a of embodiment 1.

[0059] Furthermore, the information processing device 10 of this embodiment stores a tube learning model in addition to the learning model M (referred to as the balloon learning model M in this embodiment) in the storage unit 12. The balloon learning model M and the tube learning model have the same configuration, and the learning model trained using training data based on spectroscopic data acquired from balloons is the balloon learning model M, while the learning model trained using training data based on spectroscopic data acquired from tubes is the tube learning model. In addition to being configured to output a pressure resistance value or a pressure resistance test result, the tube learning model may also be configured to perform a calculation to determine whether the tube being measured has high pressure resistance, low pressure resistance, or is incapable of forming a balloon (balloon formation not possible), and output the calculation result. In this case, the tube learning model has three output nodes corresponding to the labels high pressure resistance, low pressure resistance, and incapable of forming a balloon, and each output node outputs the probability (confidence factor) that the tube being measured should be determined to have high pressure resistance, low pressure resistance, or incapable of forming a balloon. The output value from each output node is, for example, a value between 0 and 1, and the sum of the probabilities output from each output node is 1.0 (100%). Even with this configuration of the tube learning model, it is possible to estimate an evaluation of the pressure resistance of the tube being measured.

[0060] 9A and 9B are explanatory diagrams illustrating the results of component analysis of the spectroscopic data of a tube. The score plots in FIGS. 9A and 9B have the same configuration as the score plots in FIGS. 6A and 6B, and the plotted objects are the component analysis results obtained by component analysis of the spectroscopic data of the tube. In the score plot in FIG. 9A, squares indicate tubes that failed the pressure test, and circles indicate tubes that passed. In the component analysis results of the spectroscopic data of the tube, the relationship between the first principal component score and the second principal component score can also be used to determine whether the tube being measured is normal (whether it passes the pressure test). Furthermore, as indicated by the dashed circle in the graph in FIG. 9B, the peak of the first principal component can be identified. Therefore, even for tubes before balloon molding, the characteristics of the measurement object can be determined based on the scores and loading values ​​of each component contained in the spectroscopic data. In this embodiment, the pressure resistance of the measurement object is estimated based on the results of the component analysis of the spectroscopic data.

[0061] 10A and 10B are explanatory diagrams showing examples of record layouts of DBs 12a and 12b stored in the information processing device 10 according to the second embodiment. FIG. 10A shows the analysis result DB 12a, and FIG. 10B shows the advice DB 12b. The analysis result DB 12a according to the second embodiment shown in FIG. 10A includes a tube ID column, a tube analysis information column, a molding condition column, a balloon analysis information column, etc., and stores information about the tube and information about the balloon molded from the tube in association with the tube ID. The tube analysis information column includes a spectroscopic data column, a component analysis result column, and a pressure resistance column, and stores spectroscopic data acquired from the tube using the spectroscopic device 20, information about the results of a component analysis process performed on the spectroscopic data, and information about the pressure resistance of the tube in association with each other. The balloon analysis information column includes a spectroscopic data column, a component analysis result column, and a pressure resistance column, and stores spectroscopic data acquired from the balloon using the spectroscopic device 20, information about the results of a component analysis process performed on the spectroscopic data, and information about the pressure resistance of the balloon in association with each other. The spectroscopic data sequence, component analysis result sequence, and pressure resistance sequence contained in the balloon analysis information sequence are stored as the same information as the spectroscopic data sequence, component analysis result sequence, and pressure resistance sequence in the analysis result DB 12a of embodiment 1 shown in Figure 3.

[0062] The advice DB 12b shown in Figure 10B includes an ID column, a pressure resistance column, a molding condition advice column, etc., and stores, in association with an ID, the pressure resistance of the tube (e.g., the pressure resistance value) and advice regarding the molding conditions when molding a balloon from the tube.

[0063] Fig. 11 is a flowchart showing an example of a procedure for estimating a pressure resistance value according to the second embodiment. The process shown in Fig. 11 is the process shown in Fig. 8 with steps S41 to S42 added instead of step S38. The process shown in Fig. 8 and the process shown in Fig. 11 differ only in that the target of processing is spectral data of a balloon or spectral data of a tube, and the specific processing content is the same. For example, the control unit 11 of the information processing device 10 determines whether there is a tube for which spectral data of the tube is stored in the analysis result DB 12a but the component analysis results of the tube are not stored, and if it is determined that there is, performs the following processing for the tube:

[0064] In this embodiment, the control unit 11 acquires spectroscopic data of a tube to be processed from the analysis result DB 12a (S31). The control unit 11 performs preprocessing on the acquired spectroscopic data (S32), and then performs multivariate analysis (S33). As a result, the control unit 11 acquires component analysis results for the spectroscopic data of the tube, and stores the acquired component analysis results in the analysis result DB 12a in association with the tube ID of the tube.

[0065] The control unit 11 extracts the component analysis result for one pixel from the component analysis result for the tube spectroscopic data (S34), and estimates the withstand pressure value of the measurement object (tube) corresponding to the one pixel from the component analysis result for the extracted one pixel (S35). Here, the control unit 11 reads out the tube learning model from the storage unit 12, inputs information indicating the component analysis result for one pixel into the tube learning model, and obtains the withstand pressure value of the tube as an output value from the tube learning model.

[0066] The control unit 11 determines whether or not there are any component analysis results for unprocessed pixels among the component analysis results acquired in step S33 (S36), and if it determines that there are (S36: YES), the process returns to step S34. If it determines that there are no component analysis results for unprocessed pixels (S36: NO), the control unit 11 identifies the withstand pressure value of the tube based on the withstand pressure value estimated for each pixel in step S35 (S37).

[0067] In this embodiment, the control unit 11 reads from the advice DB 12b advice on molding conditions for the identified tube's withstand pressure value, and based on the read advice, identifies molding conditions for balloon molding the tube for the identified withstand pressure value (S41). For example, if the advice is "standard temperature + 2°C," the control unit 11 identifies "standard temperature + 2°C" as the molding condition. Note that if a predetermined value is set as the standard temperature, the control unit 11 may identify a temperature obtained by adding 2°C to the predetermined standard temperature as the molding condition temperature. The control unit 11 then stores the tube's withstand pressure value identified in step S37 and the molding conditions identified in step S41 in the analysis result DB 12a in association with the tube's tube ID (S42), and terminates the process.

[0068] Through the above-described process, in this embodiment, the pressure resistance value of the tube can be estimated based on the spectroscopic data acquired from the tube to be measured using the spectroscopic device 20 and stored in the analysis result DB 12a. Furthermore, if the molding conditions for the balloon molding corresponding to the tube's pressure resistance value are registered, the molding conditions corresponding to the estimated pressure resistance value can be identified. Regarding the tube's pressure resistance value, when a viewing request is received, the control unit 11 may display a screen on the display unit 15 displaying the pressure resistance value of each tube in association with the tube ID. In this case, if there are molding conditions requiring attention, such as molding conditions based on advice corresponding to the tube's pressure resistance value, the pressure resistance value or molding conditions may be highlighted to provide a warning. The user (balloon manufacturer) can mold a high-precision balloon by molding the balloon using the proposed molding conditions.

[0069] This embodiment achieves the same effects as the first embodiment. Furthermore, this embodiment can estimate the pressure resistance of the tube before balloon formation and store it in the analysis result DB 12a. Furthermore, this embodiment can present the molding conditions for balloon formation based on the estimated pressure resistance of the tube, thereby enabling high-precision balloon formation and improving the yield of the molding process. While the first embodiment described above is configured to measure (estimate) the pressure resistance of a balloon formed into a balloon, this embodiment is configured to measure (estimate) the pressure resistance of the tube before balloon formation. Therefore, by combining the first and second embodiments, it is possible to measure the pressure resistance of both the tube and the balloon. The modifications described in the first embodiment, as appropriate, can also be applied to this embodiment.

[0070] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims.

[0071] REFERENCE SIGNS LIST 10 Information processing device 11 Control unit 12 Storage unit 13 Communication unit 20 Spectroscopic device 21 Light emitting unit 22 Light receiving unit 23 Signal processing unit 24 Communication unit M Learning model

Claims

1. An information processing method in which a computer executes a process of acquiring spectroscopic data of light generated from a tube formed into a balloon for a balloon catheter by irradiating the tube with near-infrared light, and identifying information regarding the pressure resistance of the tube based on the acquired spectroscopic data.

2. The information processing method according to claim 1, wherein the computer executes a process of performing multivariate analysis on the spectroscopic data to obtain a distribution of each wavelength component contained in the light from the tube, and identifying information relating to the pressure resistance of the tube based on the distribution of each wavelength component.

3. The information processing method according to claim 2, wherein the computer executes a process of identifying information relating to the pressure resistance of the tube based on a distribution of a specific wavelength component in the distribution of each of the wavelength components.

4. The information processing method according to claim 2, wherein the computer executes a process of inputting the distribution of each wavelength component obtained by performing multivariate analysis on the spectroscopic data into a learning model that has been trained to output information regarding the pressure resistance of the tube when the distribution of each wavelength component contained in the light from the tube is input, and acquiring information regarding the pressure resistance of the tube.

5. The information processing method according to any one of claims 1 to 4, wherein the computer executes a process of performing pre-processing including normalization, smoothing, and differentiation on the spectroscopic data.

6. The information processing method according to any one of claims 1 to 4, wherein the computer executes the process of acquiring spectroscopic data of light from the pre-molded tube generated by irradiating the pre-molded tube with near-infrared light before it is molded into a balloon, and identifying information relating to the pressure resistance of the pre-molded tube based on the acquired spectroscopic data.

7. The information processing method according to any one of claims 1 to 4, wherein the computer executes a process of acquiring the spectroscopic data using a near-infrared spectroscopic device or a hyperspectral camera.

8. A program for causing a computer to execute a process of acquiring spectroscopic data of light generated from a tube formed into a balloon for a balloon catheter by irradiating the tube with near-infrared light, and identifying information regarding the pressure resistance of the tube based on the acquired spectroscopic data.

9. An information processing device having a control unit, wherein the control unit acquires spectroscopic data of light from a tube generated by irradiating near-infrared light onto a tube formed into a balloon for a balloon catheter, and identifies information relating to the pressure resistance of the tube based on the acquired spectroscopic data.

10. A model generation method in which a computer executes a process of acquiring training data that associates the distribution of each wavelength component contained in the light from a tube generated by irradiating the tube with near-infrared light and information related to the pressure resistance of the tube, and using the acquired training data, generating a learning model that outputs information related to the pressure resistance of the tube when the distribution of each wavelength component contained in the light from the tube is input.

11. A method for manufacturing a balloon catheter, comprising the steps of: molding a tube into a balloon for a balloon catheter using a balloon molding machine; irradiating the balloon-molded tube with near-infrared light using a light-emitting unit to obtain spectroscopic data of the light from the balloon-molded tube; specifying the pressure resistance or pressure resistance value of the balloon-molded tube based on the obtained spectroscopic data; judging whether the specified pressure resistance or pressure resistance value is equal to or greater than a reference value; and connecting the balloon-molded tube whose pressure resistance or pressure resistance value is determined to be equal to or greater than the reference value to a balloon catheter shaft.

Images