Chinese medicinal material quality detection method, system, equipment and readable storage medium

Abstract

The present application relates to a method, system, device and readable storage medium for detecting the quality of Chinese medicinal materials, and belongs to the technical field of Chinese medicine detection. The aforementioned method for detecting the quality of Chinese medicinal materials includes: obtaining multiple two-dimensional image data of at least one target Chinese medicinal material; performing image reconstruction processing on the multiple two-dimensional image data to obtain three-dimensional image data of the target Chinese medicinal material; and determining the quality of the target Chinese medicinal material based on the three-dimensional image data of the target Chinese medicinal material. The aforementioned method for detecting the quality of Chinese medicinal materials can comprehensively and intuitively display the internal information of Chinese medicinal materials by acquiring two-dimensional images and performing three-dimensional reconstruction, with higher detection precision and accuracy; realize non-destructive detection, maintain the integrity of the sample, and facilitate subsequent research and reuse; significantly improve detection efficiency; and improve the objectivity and consistency of the detection results.

Description

Technical Field

[0001] The present application relates to the technical field of traditional Chinese medicine detection, and specifically, to a method, system, equipment and readable storage medium for detecting the quality of traditional Chinese medicine. Background Art

[0002] As a traditional treasure of the Chinese nation, Chinese medicine has been passed down and developed for thousands of years, showing unique advantages in disease prevention and treatment, health and wellness. With the continuous expansion of the Chinese medicine market and the acceleration of the internationalization process, the quality control and safety assessment of Chinese medicine have become increasingly prominent, becoming an important bottleneck restricting its further development. Existing Chinese medicine detection technologies include: property identification and microscopic identification.

[0003] Character identification is one of the most basic and intuitive detection methods for Chinese herbal medicines. It preliminarily judges the authenticity and quality of Chinese herbal medicines by manually observing their shape, size, color, surface characteristics (such as texture, gloss, broken surface, etc.), smell and taste. For example, the rhizome of ginseng has a unique shape, with characteristics such as "reed head", "stem", "body", "whiskers" and "pearl dots"; while angelica is famous for its rich aroma and special bitter taste. Although this method is simple, it requires the appraiser to have rich practical experience and professional knowledge.

[0004] Microscopic identification uses a microscope to observe and analyze the microscopic structure of cells, tissues, and powders of Chinese medicinal materials to reveal their unique microscopic characteristics. This method can further verify the results of trait identification and distinguish between Chinese medicinal materials with similar morphology but different sources. For example, through microscopic observation, you can clearly see the cell morphology, arrangement, and inclusions of different plant tissues, such as the fiber bundle characteristics of Dendrobium and the star points (heteromorphic vascular bundles) of Rhubarb. Microscopic identification usually requires comparison and analysis in combination with professional microscopic maps of Chinese medicinal materials. However, this method requires operations such as cutting of Chinese medicinal materials, and is relatively time-consuming.

[0005] The existing trait identification and microscopic identification methods each have their own limitations. Trait identification is greatly affected by personal experience, and it is difficult to achieve objective standardization of the test results; while microscopic identification, although more accurate, is complex and time-consuming to operate and will cause damage to Chinese medicinal materials.

[0006] Therefore, the existing detection methods of traditional Chinese medicine still need to be improved. Summary of the invention

[0007] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present application is to provide a stable, reliable, efficient and non-destructive method for detecting traditional Chinese medicine.

[0008] Specifically, this application proposes the following technical solutions:

[0009] In the first aspect, the present application proposes a method for detecting the quality of Chinese medicinal materials. According to an embodiment of the present application, the method includes: acquiring multiple two-dimensional image data of at least one target Chinese medicinal material; performing image reconstruction processing on the multiple two-dimensional image data to obtain three-dimensional image data of the target Chinese medicinal material; and determining the quality of the target Chinese medicinal material based on the three-dimensional image data of the target Chinese medicinal material.

[0010] In some examples of the present application, the aforementioned Chinese medicinal material quality detection method can comprehensively and intuitively display the internal information of Chinese medicinal materials by acquiring two-dimensional images and performing three-dimensional reconstruction, with higher detection precision and accuracy; realize non-destructive detection, maintain the integrity of the sample, and facilitate subsequent research and reuse; significantly improve detection efficiency; and improve the objectivity and consistency of detection results.

[0011] In the second aspect, the present application proposes a Chinese medicinal material quality detection system. According to an embodiment of the present application, the system includes: a two-dimensional image data acquisition module, used to acquire multiple two-dimensional image data of at least one target Chinese medicinal material; a three-dimensional image data acquisition module, used to perform image reconstruction processing on the multiple two-dimensional image data to obtain the three-dimensional image data of the target Chinese medicinal material; a Chinese medicinal material quality detection module, used to determine the quality of the target Chinese medicinal material based on the three-dimensional image data of the target Chinese medicinal material.

[0012] In some examples of this application, the aforementioned system converts two-dimensional image data into three-dimensional images through three-dimensional reconstruction technology, which improves the detection precision and accuracy, and can fully display the internal microstructure of Chinese medicinal materials to ensure more accurate quality judgment. And the use of non-destructive testing methods does not damage the Chinese medicinal material samples, retains the integrity of the samples, and is conducive to subsequent analysis and reuse. The automated data acquisition, image reconstruction and quality inspection processes significantly improve the inspection efficiency, reduce manual intervention, and ensure the objectivity and consistency of the results.

[0013] In a third aspect, the present application proposes a computer program product. According to an embodiment of the present application, the computer program product includes: computer instructions; when part or all of the computer instructions are run on a computer, the method for detecting the quality of Chinese medicinal materials as described in the first aspect of the present application is executed.

[0014] In a fourth aspect, the present application proposes a computing device. According to an embodiment of the present application, the computing device includes: a processor and a memory; the memory is used to store a computer program; the processor is used to execute the computer program to implement the Chinese medicinal material quality detection method as described in the first aspect of the present application.

[0015] In a fifth aspect, the present application proposes a computer-readable storage medium. According to an embodiment of the present application, the computer-readable storage medium stores computer instructions or programs, and when the computer instructions or programs are run on a computer, the method for detecting the quality of Chinese medicinal materials as described in the first aspect of the present application is executed.

[0016] The aforementioned computer program product, computing device, and computer-readable storage medium automatically execute the Chinese medicinal material quality detection method through computer instructions, thereby realizing efficient, accurate, automated, non-destructive, and objective Chinese medicinal material quality detection. Secondly, the characteristics of the instructions make the above method highly consistent, stable, and reliable in different application scenarios.

[0017] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A schematic diagram of a method for detecting the quality of Chinese medicinal materials provided for a specific embodiment of this application;

[0020] Figure 2 A schematic diagram of a neural network structure provided for a specific implementation of this application;

[0021] Figure 3 Schematic diagram of a Chinese medicinal material quality detection system provided for a specific implementation of this application;

[0022] Figure 4 A schematic diagram of an electronic device provided for a specific embodiment of the present application;

[0023] Figure 5 Schematic diagram of cross-section of raw turtle shell and vinegar turtle shell provided in the examples of the present application;

[0024] Figure 6 A schematic diagram of the confusion matrix results of distinguishing raw and vinegar turtle shells using a pre-trained neural network provided in an embodiment of the present application;

[0025] Figure 7 Schematic diagram of cross section of soft and non-soft donkey-hide gelatin provided in the examples of the present application;

[0026] Figure 8A schematic diagram of the confusion matrix results of using a trained neural network to discriminate whether donkey-hide gelatin is runny or not provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In the present application, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In the description of the present application, unless otherwise specified, "multiple" refers to two or more than two.

[0029] At present, the existing Chinese medicinal materials quality detection methods have some shortcomings, such as the difficulty in ensuring the consistency of the detection results, detection loss, low detection efficiency, etc. In order to solve at least one of the above problems, the present application proposes a Chinese medicinal materials quality detection method, a data annotation device, a computer program product, a computing device, and a computer-readable storage medium. They are described below:

[0030] Quality testing methods for Chinese herbal medicines

[0031] On the one hand, this application proposes a method for detecting the quality of Chinese medicinal materials, referring to Figure 1 , the method comprising:

[0032] S10, acquiring a plurality of two-dimensional image data of at least one target Chinese medicinal material.

[0033] In some examples of the present application, the aforementioned target Chinese medicinal materials include but are not limited to turtle shell, donkey-hide gelatin, malt, vinegar-soaked bupleurum, bergamot, spinach seed, licorice, jujube bark, curcuma, pseudostellaria, valerian, atractylodes, scutellaria, astragalus and codonopsis.

[0034] It is understandable that in the quality inspection of Chinese medicinal materials, based on the size of the Chinese medicinal materials, the aforementioned target Chinese medicinal materials can be one piece or multiple pieces.

[0035] In some examples of the present application, the aforementioned multiple two-dimensional image data are two-dimensional image data of the target Chinese medicinal material at different angles. The aforementioned two-dimensional image data are X-ray projection images, and the quality of Chinese medicinal materials is judged based on images obtained by X-ray photography, which is non-destructive to Chinese medicinal materials, so that they can still be recycled after detection.

[0036] The aforementioned X-ray projection image is obtained by computer tomography (CT) or Micro-CT.

[0037] Micro-CT technology is a technology that uses X-rays to collect transmission image signals and reconstruct three-dimensional images of the detected object. Conventional micro-computed tomography is mostly used for imaging small batches of samples or small animals, and has not been used for quality detection of Chinese medicinal materials. In some examples of this application, the inventor unexpectedly discovered that by using Micro-CT to collect two-dimensional images and reconstruct three-dimensional images, it is possible to achieve high detection accuracy and high-accuracy quality detection of Chinese medicinal materials without damaging the inspected Chinese medicinal materials, and the detection efficiency is also significantly improved. And this technology is not affected by human subjective factors in the detection of Chinese medicinal materials, and can effectively improve the accuracy and consistency of the test results.

[0038] Based on Micro-CT technology, it is possible to obtain the internal microstructure and detailed information of Chinese medicinal materials without loss, generate 3D images of the internal structure of Chinese medicinal materials, and understand the internal information of Chinese medicinal materials more intuitively.

[0039] S20, performing image reconstruction processing on the plurality of two-dimensional image data to obtain three-dimensional image data of the target Chinese medicinal material.

[0040] The aforementioned image reconstruction process includes: filtering a plurality of two-dimensional image data, and then back-projecting the filtered data based on the geometric features of the cone beam and the flat-panel detector, and finally obtaining a reconstructed three-dimensional image. GPU acceleration can also be used in the filtering and back-projection processes. In some examples of the present application, the Feldkamp-Davis-Kress algorithm is used to perform three-dimensional reconstruction of the X-ray projection image. In other examples of the present application, the Feldkamp-Davis-Kress algorithm accelerated by GPU is used to perform three-dimensional reconstruction of the X-ray projection image, thereby increasing the speed of three-dimensional reconstruction and improving detection efficiency.

[0041] S30, determining the quality of the target Chinese medicinal material based on the three-dimensional image data of the target Chinese medicinal material.

[0042] Step S30 further includes: 1) obtaining slice information of the three-dimensional image data, the slice information including: at least one of the cross section, coronal plane and sagittal plane of the three-dimensional image; 2) inputting the slice information into a trained neural network model to determine the quality of the target Chinese medicinal material.

[0043] The aforementioned target Chinese medicinal material quality can be excellent, good, or poor; it can also be scored, such as 80 points or more are considered good quality, 50-80 points are considered average quality, and below 50 points are considered poor quality. The discrimination method can be set based on actual needs, and this application does not make specific limitations.

[0044] The aforementioned neural network model is a computing model or algorithm that processes and analyzes input data to automatically predict classification results. In some examples of the present application, the aforementioned neural network model is selected from a convolutional neural network or a deep convolutional neural network.

[0045] In some examples of the present application, selectable neural network structures include but are not limited to VGG19, UNet or their variants.

[0046] In some examples of this application, reference Figure 2 , the neural network model includes: an input layer, a feature extraction layer, a regularization layer, a classification layer and an output layer. Among them, the feature extraction layer includes a convolution layer, a BN (batch normalization) layer, a ReLU layer, a pooling layer, a convolution layer, a BN layer and a ReLU layer, the regularization layer can be a dropout layer, and the classification layer includes a fully connected layer and a softmax layer. The inventors of the present application added a regularization layer to the basic neural network model and found that the accuracy of traditional Chinese medicine quality detection was significantly improved.

[0047] The training of the neural network model is carried out in a supervised learning manner. The two-dimensional image data of each Chinese herbal medicine used for training is not less than 100, preferably not less than 500, and more preferably not less than 1000. In some examples of the present application, the sign of completion of the training is that the accuracy of the validation set in the trained model is not less than 95%.

[0048] In some examples of the present application, the target Chinese medicinal material quality index analysis result can be further determined. Specifically, it includes: A) performing image segmentation processing on the three-dimensional image to determine the three-dimensional image information of any target Chinese medicinal material; B) determining the target Chinese medicinal material quality index analysis result based on the three-dimensional image information of any target Chinese medicinal material. The quality of the target Chinese medicinal material is assisted in judging the quality based on the quality index analysis result.

[0049] The aforementioned image segmentation process can use a variety of existing methods, such as the watershed method. Specifically, first, a threshold is used to transform the three-dimensional image into a three-dimensional mask; then the Euclidean distance transform of the binary image is calculated, and the inversion operation and smoothing are performed; then the watershed transform of the result of the previous step is calculated to obtain a segmentation mask, and each mask corresponds to a separate Chinese medicinal material. Finally, the segmentation mask and the original CT image are used to calculate the quality index of the Chinese medicinal materials in the volume element.

[0050] In some examples of the present application, the aforementioned quality indicators include: average CT value and porosity.

[0051] The average CT value is determined based on the CT values ​​of all pixels or the CT values ​​of all pixels in a predetermined area. The predetermined area may be a region of interest.

[0052] In some examples of the present application, if the target Chinese medicinal material is one type, the average CT value is determined based on the average CT value corresponding to each pixel of all pixels contained in the three-dimensional image of the target Chinese medicinal material.

[0053] In some examples of the present application, if there is more than one target Chinese medicinal material, the average CT value of each Chinese medicinal material is determined based on the average CT value corresponding to each pixel of all pixels contained in the three-dimensional image of each target Chinese medicinal material. Furthermore, the average CT value of all Chinese medicinal materials and the standard deviation of the average CT value of the Chinese medicinal materials can also be determined based on the average CT value of each Chinese medicinal material.

[0054] The porosity is determined based on the number of pixels occupied by air and low CT value areas. The low CT value area is an area below a predetermined CT threshold, and the predetermined CT threshold can be set based on experimental requirements.

[0055] In some examples of the present application, if the target Chinese medicinal material is one type, the porosity is determined based on the percentage of the number of pixels occupied by air in all pixels contained in the three-dimensional image of the target Chinese medicinal material.

[0056] In some examples of the present application, if there is more than one target Chinese medicinal material, the porosity of each Chinese medicinal material is determined based on the percentage of the number of pixels occupied by air in all pixels contained in the three-dimensional image of each target Chinese medicinal material. Furthermore, the average porosity of all Chinese medicinal materials and the standard deviation of the porosity of the Chinese medicinal materials can also be determined based on the porosity of each Chinese medicinal material.

[0057] In other examples of the present application, the standard detection index threshold of the Chinese medicinal material, that is, the average CT value and porosity threshold, can also be determined based on the standard Chinese medicinal material. The quality of the target Chinese medicinal material is determined based on the difference between the target Chinese medicinal material detection index threshold and the standard detection index threshold. For example, the standard threshold of the average CT value of Chinese medicinal material A is 20,

[0058] The porosity is 10. If the average CT value of the target Chinese medicinal material is higher than 20 and the porosity is higher than 10, the quality of the target Chinese medicinal material is considered to be excellent.

[0059] Chinese herbal medicine quality inspection system

[0060] On the other hand, this application proposes a Chinese herbal medicine quality detection system, referring to Figure 3 The system includes: a two-dimensional image data acquisition module 100, a three-dimensional image data acquisition module 200 and a Chinese herbal medicine quality detection module 300.

[0061] Module 100, used to obtain multiple two-dimensional image data of at least one target Chinese medicinal material;

[0062] In some examples of the present application, the aforementioned plurality of two-dimensional image data are X-ray projection images.

[0063] Module 200 is used to perform image reconstruction processing on the multiple two-dimensional image data to obtain three-dimensional image data of the target Chinese medicinal material;

[0064] In some examples of the present application, the Feldkamp-Davis-Kress algorithm is used to perform three-dimensional reconstruction on the X-ray projection image.

[0065] Module 300 is used to determine the quality of the target Chinese medicinal material based on the three-dimensional image data of the target Chinese medicinal material.

[0066] In some examples of the present application, based on the three-dimensional image data of the target Chinese medicinal material, determining the quality of the target Chinese medicinal material includes: 1) acquiring slice information of the three-dimensional image data, the slice information including: at least one of the cross section, the coronal plane and the sagittal plane of the three-dimensional image; 2) inputting the slice information into a trained neural network model to determine the quality of the target Chinese medicinal material;

[0067] In some examples of the present application, the neural network model is selected from a convolutional neural network or a deep convolutional neural network. The neural network model includes: an input layer, a feature extraction layer, a regularization layer, a classification layer and an output layer.

[0068] In some examples of the present application, the aforementioned system further includes: a quality index acquisition submodule, used to determine the quality index analysis results of the target Chinese medicinal materials through steps A)-B): A) performing image segmentation processing on the three-dimensional image to determine the three-dimensional image information of any target Chinese medicinal material; B) determining the quality index analysis results of the target Chinese medicinal materials based on the three-dimensional image information of any target Chinese medicinal material.

[0069] In some examples of the present application, the quality index includes: an average CT value and a porosity, wherein the average CT value is determined based on the CT values ​​of all pixels or the CT values ​​of all pixels in a predetermined area; and the porosity is determined based on the number of pixels occupied by air and low CT value areas.

[0070] In some examples of the present application, the aforementioned modules are connected, wherein the aforementioned connection includes physical connection and network connection.

[0071] The above-mentioned Chinese medicinal materials quality inspection system has the following advantages:

[0072] 1. Non-destructive testing: Micro CT can perform high-precision imaging of the internal structure of Chinese medicinal materials without destroying them, thus preserving the integrity of the samples and facilitating subsequent research or reuse;

[0073] 2. High-precision detection: The resolution can be as high as several microns, which can clearly show the microstructure and details inside the Chinese medicinal materials;

[0074] 3. Three-dimensional visualization: It can generate 3D images of the internal structure of Chinese medicinal materials, provide intuitive and comprehensive spatial information, and help to deeply understand and analyze the microscopic characteristics of medicinal materials;

[0075] 4. Improve detection efficiency and robustness: Compared with traditional detection technology, the combination of Micro CT and automated image segmentation methods or artificial intelligence methods can complete the detection process faster, reduce human errors, and improve the accuracy and consistency of detection results.

[0076] It should be understood that the system embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Figure 3 The system shown can execute the embodiment of the above-mentioned Chinese medicinal material quality detection method, and the operations and / or functions performed by each module in the system correspond to the method embodiment, which will not be described here for the sake of brevity.

[0077] The system of the embodiment of the present application is described above from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or a combination of hardware and software modules in the decoding processor to perform. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.

[0078] Computer program product, computing device, and computer readable storage medium

[0079] In another aspect of the present application, the present application proposes a computer program product, a computing device, and a computer-readable storage medium. Based on the aforementioned computer program product, computing device, or computer-readable storage medium, the aforementioned Chinese medicinal material quality detection method is executed.

[0080] Descriptions of computer program products, computing devices, or computer-readable storage media may refer to each other. This article takes electronic devices as an example for detailed description. The so-called electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Computing devices can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0081] like Figure 4As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 502 or a computer program loaded from a storage unit 508 to a RAM (Random Access Memory) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An I / O (Input / Output) interface 505 is also connected to the bus 504.

[0082] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0083] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as a Chinese herbal medicine quality detection method. For example, in some embodiments, the Chinese herbal medicine quality detection method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the aforementioned Chinese medicinal material quality detection method in any other appropriate manner (for example, by means of firmware).

[0084] In the present application, the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the aforementioned program may be printed, because the aforementioned program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting or processing in other suitable ways as necessary, and then storing it in a computer memory. The various computer-readable storage media described in the present invention may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing and / or carrying instructions and / or data.

[0085] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0086] A person of ordinary skill in the art may understand that all or part of the steps in the method of the above-mentioned embodiment may be completed by instructing related hardware through a program, and the aforementioned program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0087] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0088] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0089] It should be noted that the features and technical effects described in this article for different aspects can be used as reference for each other and will not be repeated here.

[0090] The embodiments of the present application will be described in more detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, but cannot be understood as limiting the present application.

[0091] Example 1: Detection of the degree of processing of turtle shell

[0092] This example is intended to verify the feasibility of the technical solution of the present application and the accuracy of the quality detection of Chinese medicinal materials.

[0093] (1) Equipment preparation

[0094] First, ensure that all components of the Micro-CT imaging system (including high-precision X-ray source, high-resolution detector, sample rotation stage and control system) are installed correctly and in good working condition. Preheat and calibrate the equipment to ensure that the imaging quality and accuracy meet the requirements.

[0095] (2) Processing of Chinese medicine samples

[0096] The turtle shell samples to be tested are taken and sent to the scanning platform through the conveying port, and it is ensured that the samples are in a stable state and will not move or deform during the scanning process.

[0097] (3) Scan parameter settings

[0098] According to the characteristics of the traditional Chinese medicine samples and the detection requirements, appropriate scanning parameters are set in the control system, such as X-ray energy, exposure time, scanning resolution, etc., where the tube voltage is 75kV, the tube current is 180mA, and the middle field of view is selected.

[0099] (4) Image acquisition

[0100] Start the Micro-CT imaging system to scan the Chinese medicine samples. Under the continuous rotation of the sample rotating table, the X-ray source emits X-rays that penetrate the sample and are received by the high-resolution detector. The raw data recorded by the detector will be transmitted to the computer for further processing.

[0101] (5) Image processing and analysis

[0102] The collected raw data were processed using the image processing and analysis software integrated in the equipment. First, the raw data was converted into a three-dimensional image through an image reconstruction algorithm to show the internal structure of the Chinese medicine sample. Then, cross-sectional images of turtle shells were randomly selected within the effective field of view. A total of 7,200 cross-sectional images were generated from 9 batches of turtle shell samples. 768 cross-sectional images were extracted from these 7,200 cross-sectional images and it was ensured that the interval between two cross-sectional images from the same batch of turtle shells was greater than 0.5 mm. The extracted cross-sectional images were then input into a pre-trained neural network model to judge the degree of processing of the turtle shells and give the Chinese medicine judgment results.

[0103] (6) Sample removal

[0104] After the sample scanning, image processing and analysis are completed, the equipment opens the discharge port and the sample automatically enters the discharge collection device for removal.

[0105] result: Figure 5 The internal structure images of raw turtle shell and vinegar-processed turtle shell are shown respectively, among which 1-3 are three cross-sectional images obtained by scanning the raw turtle shell, and 2-4 are three cross-sectional images obtained by scanning the vinegar-processed turtle shell. Figure 6 The confusion matrix of the neural network discrimination results. Among the 621 prediction results of "raw turtle shell", 100% are correct; among the 147 prediction results of "vinegar-processed turtle shell", 98% are correct and 2% are wrong; among the 624 "raw turtle shell" images, 99.% are correctly predicted as "raw turtle shell" and 0.5% are misjudged; among the 144 "vinegar-processed turtle shell" images, 100% are correctly predicted. In general, the discrimination accuracy of raw turtle shell and vinegar-processed turtle shell is 99.6%.

[0106] Example 2: Detection of the degree of preparation of donkey-hide gelatin

[0107] This example is intended to verify the feasibility of the technical solution of the present application and the accuracy of the quality detection of Chinese medicinal materials.

[0108] (1) Equipment preparation

[0109] First, ensure that all components of the Micro-CT imaging system (including high-precision X-ray source, high-resolution detector, sample rotation stage and control system) are installed correctly and in good working condition. Preheat and calibrate the equipment to ensure that the imaging quality and accuracy meet the requirements.

[0110] (2) Processing of Chinese medicine samples

[0111] The donkey-hide gelatin samples to be tested are taken and sent to the scanning table through the conveyor port, and it is ensured that the samples are in a stable state and will not move or deform during the scanning process. In this case, in order to verify the feasibility of the technical solution, a total of 40 donkey-hide gelatin beads were scanned, and each donkey-hide gelatin bead was scanned separately. These 40 donkey-hide gelatin beads came from 20 batches of donkey-hide gelatin samples, of which 6 batches of donkey-hide gelatin were runny samples and 14 batches of donkey-hide gelatin were non-runny samples. Each batch of donkey-hide gelatin contained 2 donkey-hide gelatin beads.

[0112] (3) Scan parameter settings

[0113] According to the characteristics of Chinese medicine samples and detection requirements, appropriate scanning parameters are set in the control system, such as X-ray energy, exposure time, scanning resolution, etc., where the tube voltage is 45 kV, the tube current is 275 μA, and the middle field of view is selected.

[0114] (4) Image acquisition

[0115] Start the Micro-CT imaging system to scan the Chinese medicine samples. Under the continuous rotation of the sample rotating table, the X-ray source emits X-rays that penetrate the sample and are received by the high-resolution detector. The raw data recorded by the detector will be transmitted to the computer for further processing.

[0116] (5) Image processing and analysis

[0117] The collected raw data were processed using the image processing and analysis software integrated in the equipment. First, the raw data was converted into a three-dimensional image through an image reconstruction algorithm to show the internal structure of the Chinese medicine sample. A total of 40 three-dimensional images were generated for the 40 donkey-hide gelatin bead samples. From these 40 three-dimensional images, the 2.5mm cross-sectional, coronal and sagittal two-dimensional images near the image center of mass were extracted, and 21 images were extracted at intervals of 0.25mm for each angle, for a total of 2520 two-dimensional images. Then 1312 images were extracted from these 2520 two-dimensional images and input into the pre-trained neural network model to judge the degree of processing of the turtle shell and give the Chinese medicine judgment results.

[0118] (6) Sample removal

[0119] After the sample scanning, image processing and analysis are completed, the equipment opens the discharge port and the sample automatically enters the discharge collection device for removal.

[0120] result: Figure 7 The internal structure images of soft donkey-hide gelatin and non-soft donkey-hide gelatin are shown respectively, among which 1-3 are soft donkey-hide gelatin, and 4-6 are non-soft donkey-hide gelatin. Figure 8 The neural network discriminant matrix of whether donkey-hide gelatin is runny or not is shown. Among the 173 "runny" prediction results, 86.7% are correct and 13.3% are wrong; among the 1139 "non-runny" prediction results, 99.8% are correct and 0.2% are correct; among the 152 "runny" images, 98.7% are correctly predicted as "runny" and 1.3% are predicted as "non-runny"; among the 1160 "non-runny" images, 98% are correctly predicted as "non-runny" and 2% are predicted as "runny". In general, 98.1% of the predictions are correct.

[0121] Example 3: Malt processing degree detection

[0122] This embodiment aims to assist in detecting the quality of Chinese medicinal materials through quality indicators (such as average CT value and porosity).

[0123] (1) Equipment preparation

[0124] First, ensure that all components of the Micro-CT imaging system (including high-precision X-ray source, high-resolution detector, sample rotation stage and control system) are installed correctly and in good working condition. Preheat and calibrate the equipment to ensure that the imaging quality and accuracy meet the requirements.

[0125] (2) Processing of Chinese medicine samples

[0126] The batch of malt particles to be tested are taken and sent to the scanning table through the conveyor port, and the sample is ensured to be in a stable state and will not move or deform during the scanning process. In this case, in order to verify the feasibility of the technical solution, two batches of malt samples with different roasting times were scanned, including 9 roasting time points, namely 0, 5min, 10min, 15min, 20min, 22.5min, 25min, 27.5min, and 30min. The number of malt particles at each roasting time point in each batch is about 100.

[0127] (3) Scan parameter settings

[0128] According to the characteristics of Chinese medicine samples and detection requirements, appropriate scanning parameters are set in the control system, such as X-ray energy, exposure time, scanning resolution, etc., where the tube voltage is 45 kV, the tube current is 275 μA, and the middle field of view is selected.

[0129] (4) Image acquisition

[0130] Start the Micro-CT imaging system to scan the Chinese medicine samples. Under the continuous rotation of the sample rotating table, the X-ray source emits X-rays that penetrate the sample and are received by the high-resolution detector. The raw data recorded by the detector will be transmitted to the computer for further processing.

[0131] (5) Image processing and analysis

[0132] The collected raw data were processed using the image processing and analysis software integrated in the equipment. First, the raw data was converted into a three-dimensional image through an image reconstruction algorithm to show the internal structure of the Chinese medicine sample. Then, a quantitative analysis program (based on traditional machine learning methods for image segmentation and average CT value and porosity calculation) was selected to determine the average CT value and porosity of the malt.

[0133] (6) Sample removal

[0134] After the sample scanning, image processing and analysis are completed, the equipment opens the discharge port and the sample automatically enters the discharge collection device for removal.

[0135] The average CT value and porosity test results of malt with different roasting time are shown in Table 1. As the malt roasting time increases from 0 to 30 minutes, the average CT value of the malt decreases from -63.11HU to -229.79HU, and the porosity increases from 53.8% to 89.57%.

[0136] Table 1 Average CT value and porosity results of malt with different roasting time

[0137]

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0139] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application without departing from the principles and purpose of the present application.

Claims

1. A method for detecting the quality of Chinese medicinal materials, characterized in that: include: Acquire multiple two-dimensional image data of at least one target Chinese medicinal material; Performing image reconstruction processing on the multiple two-dimensional image data to obtain three-dimensional image data of the target Chinese medicinal material; Based on the three-dimensional image data of the target Chinese medicinal material, the quality of the target Chinese medicinal material is determined.

2. The method according to claim 1, characterized in that The plurality of two-dimensional image data are X-ray projection images; Optionally, determining the quality of the target Chinese medicinal material based on the three-dimensional image data of the target Chinese medicinal material comprises: 1) acquiring slice information of the three-dimensional image data, wherein the slice information includes: at least one of a cross section, a coronal plane, and a sagittal plane of the three-dimensional image; 2) inputting the slice information into a trained neural network model to determine the quality of the target Chinese medicinal material; Optionally, the neural network model is selected from a convolutional neural network or a deep convolutional neural network.

3. The method according to claim 2, characterized in that The neural network model includes: an input layer, a feature extraction layer, a regularization layer, a classification layer and an output layer.

4. The method according to claim 1, characterized in that: Further including: Determine the analysis results of the quality indicators of the target Chinese medicinal materials.

5. The method according to claim 4, characterized in that Determine the target Chinese medicinal material quality index analysis results through steps A)-B): A) performing image segmentation processing on the three-dimensional image to determine the three-dimensional image information of any target Chinese medicinal material; B) Based on the three-dimensional image information of any one of the target Chinese medicinal materials, determining the quality index analysis result of the target Chinese medicinal material.

6. The method according to claim 4 or 5, characterized in that: The quality indicators include: average CT value and porosity.

7. The method according to claim 6, characterized in that The average CT value is determined based on the CT values ​​of all pixels or the CT values ​​of all pixels in a predetermined area; Optionally, the porosity is determined based on the number of pixels occupied by air and low CT value areas.

8. A Chinese herbal medicine quality detection system, characterized in that: include: A two-dimensional image data acquisition module, used to acquire a plurality of two-dimensional image data of at least one target Chinese medicinal material; A three-dimensional image data acquisition module, used to perform image reconstruction processing on the multiple two-dimensional image data to obtain three-dimensional image data of the target Chinese medicinal material; The Chinese medicinal material quality detection module is used to determine the quality of the target Chinese medicinal material based on the three-dimensional image data of the target Chinese medicinal material.

9. A computing device, characterized in that include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program to implement the method for detecting the quality of traditional Chinese medicine according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions or programs. When the computer instructions or programs are executed on a computer, the method for detecting the quality of traditional Chinese medicinal materials according to any one of claims 1 to 7 is executed.

Images