Material composition classification

Abstract

The present disclosure provides an apparatus for material composition classification, the apparatus having circuitry configured to: acquire a material composition image, where the material composition image presents a material composition of a sample; classifying the material composition images as types of material compositions by associating each of the material composition images with a material composition type; and displaying a graphical user interface, where the graphical user interface includes a first state element and a second state element, where the first state element indicates an unapproved state of a result obtained based on the classification of the material composition image, and where the second state element indicates an unapproved state of a result obtained based on the classification of the material composition image. The second state element is indicative of an in-review state of the classified material composition image, and wherein the classified material composition image is associated with the first state element or the second state element based on respective classification results of classifying the material composition image.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to material composition classification, and more particularly, to material composition classification of a biological sample. BACKGROUND

[0002] Devices and methods for material composition classification are known, which acquire an image of a sample flowing through a flow cell. Based on a material composition of the sample detected within the image, the material composition image is classified into a known category. By such classification, a concentration of the material composition in the sample can be measured. Such devices and methods are known, for example, from Unexamined Japanese Patent Application Publication No. 2020-085535. SUMMARY

[0003] TECHNICAL PROBLEM

[0004] Although devices and methods for material composition classification are known, there is still a need to provide a device and method for material composition classification.

[0005] SOLUTION TO THE PROBLEM

[0006] According to a first aspect, the present disclosure provides a device for material composition classification, the device comprising circuitry configured to:

[0007] acquire material composition images, wherein the material composition images present material compositions of a sample;

[0008] classify the material composition images into types of material compositions by associating each of the material composition images with a type of material composition; and

[0009] display a graphical user interface, wherein the graphical user interface comprises a first status element and a second status element, wherein the first status element indicates an unapproved status of a result obtained based on the classification of the material composition images, and wherein the second status element indicates an under review status of the classified material composition images, and wherein the classified material composition images are associated with the first status element or the second status element based on respective classification results of classifying the material composition images.

[0010] According to a second aspect, the present disclosure provides a system for material composition classification, the system comprising:

[0011] the device according to the first aspect; and

[0012] a remote processing device as a second processing device, wherein the first processing device and the second processing device are each configured to communicate with each other via a network, wherein the second processing device comprises circuitry configured to:

[0013] obtaining classified material component images from the first processing device; receiving operator input based on a graphical user interface; and

[0014] reclassifying material component images of the obtained classified material component images based on the received operator input, the reclassifying being performed with a higher classification accuracy than the classification of the classified material component images.

[0015] According to a third aspect, the disclosure provides a method for material component classification, the method comprising the steps of:

[0016] obtaining material component images, wherein the material component images present material components of a sample;

[0017] classifying the material component images into types of material components by associating each of the material component images with a type of material component; and

[0018] displaying a graphical user interface, wherein the graphical user interface comprises a first status element and a second status element, wherein the first status element indicates an unapproved status of a result obtained based on classified material component images, and wherein the second status element indicates an under review status of classified material component images, and wherein the classified material component images are associated with the first status element or the second status element based on respective classification results of classifying the material component images.

[0019] According to a fourth aspect, the disclosure provides a computer program for material component classification, the computer program comprising instructions which, when executed by a processor, cause the processor to perform the method according to the third aspect.

[0020] Further aspects of the disclosure are set out in the dependent claims, the drawings and the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 is a perspective view showing a configuration example of a urine material component analysis device for material component classification according to an embodiment taught herein.

[0022] Figure 2 is a side view showing a urine material component analysis device according to Figure 1 an embodiment taught herein.

[0023] Figure 3 is a block diagram showing an example of a material component processing system according to an embodiment taught herein.

[0024] Figure 4 is a block diagram showing a material component processing system according to Figure 3a functional block diagram of an example of the first processing device.

[0025] Figure 5 is a flowchart showing an example of a measurement process of the first processing device. Figure 3

[0026] Figure 6 is a flowchart showing an example of a reclassification process of the second processing device.

[0027] Figure 7 is a diagram showing an example of a material composition image.

[0028] Figure 8 is a diagram showing an example of a status screen.

[0029] Figure 9 is a diagram showing an example of a work list screen.

[0030] Figure 10 is a diagram showing an example of a dashboard screen.

[0031] Figure 11 is a diagram showing an example of a gallery screen.

[0032] Figure 12 is a diagram showing an example of an approval screen.

[0033] Figure 13 is a diagram showing an example of a material composition display screen.

[0034] Figure 14 is a flowchart showing an example of a reclassification process of the second processing device.

[0035] Figure 15 is a flowchart showing an example of a re-measurement process of the first processing device.

[0036] Figure 16 is a diagram showing an example of a settings screen.

[0037] Figure 17 is a diagram showing an example of an automatic review request determination screen.

[0038] Figure 18 is a diagram showing an example of a flag condition settings screen.

[0039] Figure 19 is a diagram showing an example of a material composition condition settings screen.

[0040] Figure 20 is a diagram showing an example of a qualitative condition settings screen. DETAILED DESCRIPTION

[0041] ​In the following, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Throughout the drawings, components and processes having similar operations, actions, or functions are indicated by the same reference numerals, and repeated descriptions will be omitted where appropriate. In each drawing, the present disclosure is illustrated schematically to the extent that it can be fully understood. The teachings herein are not limited to the examples shown. In this description, configurations or well-known configurations not directly related to the present disclosure may be omitted.

[0042] Provide a reference Figure 1 Before providing a detailed description of the implementation methods, some general explanations will be given.

[0043] As mentioned at the beginning, apparatus and methods for classifying material composition are generally known, which acquire images of samples flowing through a flow chamber. Based on the material composition of the sample detected within the image, the material composition image is classified into a known category. Through this classification, the concentration of the material composition in the sample can be measured.

[0044] It has been recognized that the classification of material composition images may be problematic when the concentration of the measured material components is outlier.

[0045] Therefore, some embodiments relate to an apparatus for classifying material composition, the apparatus including circuitry configured to: acquire material composition images, wherein the material composition images present the material composition of a sample; classify the material composition images as a type of material composition by associating each of the material composition images with a material composition type; and display a graphical user interface, wherein the graphical user interface includes a first status element and a second status element, wherein the first status element indicates an unapproved status of the result obtained based on the classification of the material composition images, and wherein the second status element indicates a review status of the classified material composition images, and wherein the classified material composition images are associated with the first status element or the second status element based on the corresponding classification result of classifying the material composition images, as discussed in more detail below.

[0046] A graphical user interface is configured as a human-computer interface to present information to the user and provide interactive elements for controlling the device.

[0047] A graphical user interface may include at least two types of elements: information elements for presenting information and interactive elements for interacting with the device. In some cases, elements may provide both functions simultaneously: information element functions and interactive element functions.

[0048] Interactive elements can be configured to interact with users via a graphical user interface, such as by receiving user input via an input device (such as a pointer device, keyboard, touch screen, voice command, gesture recognition, etc.).

[0049] In some implementations, by providing a first state element and a second state element, users with limited technical and medical knowledge can quickly manage the classification of device and material composition images. Therefore, compared to implementations without automatic classification, implementations that do not perform automatic association between classified material composition images and the first or second state element based on the corresponding classification results of the material composition images, and implementations that do not provide such information to the user, the user can operate the device and monitor the classification progress of the material composition images.

[0050] In some embodiments, the graphical user interface includes an approval element displayed when a user interacts with a first state element, wherein the approval element is configured to display information associated with the classified material composition image based on the classified material composition image. In some embodiments, this information is associated with or includes the result obtained from the classification based on the material composition image. In some embodiments, a user can interact with the approval element to approve the classification of the classified material composition image. In some embodiments, the result obtained from the classification based on the material composition image is also approved.

[0051] In some embodiments, the information associated with the classified material composition image includes at least one of material composition concentration and qualitative test results. This information may be associated with or include the results obtained from the classification based on the material composition image. Therefore, in some embodiments, the result is or includes at least one of material composition concentration and qualitative test results. Thus, the user (operator) can check the classification of the classified material composition image based on at least one of material composition concentration and qualitative test results, for example, whether reclassification is required.

[0052] The approval element can be configured to receive user input, wherein the circuitry can be further configured to transmit the associated classified material composition image to a remote processing device for reclassification based on the received user input. Therefore, the user (or operator) can easily reclassify the classified material composition image.

[0053] The circuit can be further configured to determine the concentration of a certain type of material component in a sample based on the number of material component images classified as such, as discussed further below.

[0054] In some implementations, the second status element indicates the review status of a classified material composition image that is undergoing reclassification. Therefore, in certain situations, the status information of the classified material composition image is visible to the user.

[0055] In some implementations, the graphical user interface includes a third status element indicating the pending approval status of reclassified component images. Thus, the user can obtain information about which reclassified component images may require approval (in some implementations, this includes which results were obtained based on the reclassified component images). In some cases, when the user interacts with the third status element, the associated reclassified component image is approved. Additionally (or alternatively), in some cases, the results obtained based on the reclassified component images are approved.

[0056] In some implementations, the circuitry is further configured to automatically determine, based on predefined conditions, a reclassification of the material composition image from the classified material composition image, wherein the reclassification is performed with a higher classification accuracy than the classification of the material composition image, as discussed further below.

[0057] Predefined conditions can be configured by the user, as discussed further below.

[0058] In some cases, the graphical user interface includes a condition setting element configured to set predefined conditions based on user input. This condition setting element may include at least one of material composition condition settings and qualitative condition settings. Therefore, the user can set at least one of the material composition condition and qualitative condition, thereby setting predefined conditions based on which it can be determined whether the material composition image should be reclassified.

[0059] Some embodiments relate to a system for classifying material composition, the system having the aforementioned device as a first processing device; and a remote processing device as a second processing device, as described above and below, wherein the first processing device and the second processing device are each configured to communicate with each other via a network, wherein the second processing device has circuitry configured to obtain a classified material composition image from the first processing device; receive operator input based on a graphical user interface; and, based on the received operator input, reclassify the obtained classified material composition image to a higher classification accuracy than the classification of the classified material composition image, as described above and further below.

[0060] Some implementations relate to a method for classifying material composition, the method comprising the steps of: acquiring material composition images, wherein the material composition images present the material composition of a sample; classifying the material composition images as a type of material composition by associating each of the material composition images with a material composition type; and displaying a graphical user interface, wherein the graphical user interface includes a first status element and a second status element, wherein the first status element indicates an unapproved status as a result obtained based on the classification of the material composition images, and wherein the second status element indicates a review status of the classified material composition images, and wherein the classified material composition images are associated with either the first status element or the second status element based on a corresponding classification result of classifying the material composition images, as discussed herein.

[0061] Some implementations relate to a computer program for classifying material composition, the computer program including instructions that, when executed by a processor (or more processors, circuits, or computers), cause the processor (or more processors, circuits, or computers) to perform the methods described above.

[0062] Some implementations relate to an apparatus for classifying material composition, the apparatus having circuitry configured to: acquire material composition images, wherein the material composition images present the material composition of a sample; classify the material composition images as a type of material composition by associating each of the material composition images with a material composition type; and automatically determine, based on predefined conditions, to reclassify the classified material composition images, wherein the reclassification is performed with a higher classification accuracy than the classification of the material composition images.

[0063] The device can be configured as a medical device for use by a user (operator), and it can be configured based on a standard (general purpose) computer, but it can also be based on any other type of electronic device capable of performing the functions described herein.

[0064] The circuit may include one or more processors (e.g., at least one of a central processing unit and a graphics processing unit), a field-programmable gate array, an application-specific integrated circuit, or other known electronic components implemented in a standard computer.

[0065] Material composition images can be obtained based on at least one image of a sample. In other words, an image of a sample can represent one or more material components, such that algorithms based on pattern recognition, machine learning, or other techniques as described herein and known to those skilled in the art, as will be described in more detail below, can extract and thereby generate one or more material composition images based on an image. In some embodiments, each material composition image presents one material component detected in an image.

[0066] In the case of capturing multiple images of a sample, for each captured sample image, a material composition image is extracted, and the material composition images can be sorted or grouped according to the corresponding type of material component detected in the image. Therefore, in some embodiments, the number of material composition images representing a specific type of material component can be correlated with the concentration of that specific type of material component in the sample.

[0067] By associating each element in the material composition image with the type of material composition, the material composition image is classified according to the type of material composition.

[0068] As will be further detailed below, the classification of material components can include, for example, red blood cells, white blood cells, non-squamous epidermal cells, squamous epithelial cells, bacteria, crystals, yeast, hyaline casts, other casts, mucus, sperm, leukocyte clusters, and other material components. Therefore, in some embodiments, the material components of detected associated material component images are classified into (e.g., predetermined) categories, wherein the predetermined classification may be based on, for example, a predetermined set of categories, including a predefined set of categories or classifications (where, for example, different categories or classifications correspond to different (types) of material components (or groups of material components, etc.)). In some embodiments, material components and associated material component images that cannot be associated with a predetermined category or classification cannot be classified and can therefore be considered or defined as unclassified.

[0069] The association between a material composition image and a material composition type can be based on the detected material composition type, which is then detected in the corresponding material composition image.

[0070] Furthermore, based on predefined conditions, the material composition images are automatically reclassified from the original classifications, with a higher accuracy than the initial classification. Therefore, in some implementations, material composition images can be investigated more thoroughly and automatically without requiring the operator or user of the equipment to determine whether the images are correctly classified or if any problems exist.

[0071] As mentioned above and will be discussed in more detail below, the classification of material composition images is typically based on pattern recognition algorithms or machine learning algorithms. The accuracy of such machine learning algorithms usually depends on the quantity and quality of the training data. This accuracy can also depend on other factors, such as the kernel size used for the convolutional neural network, the number of neurons in the neural network, or other parameters of such machine learning algorithms, which will also be discussed in more detail below.

[0072] In some implementations, the classification performed by the device may be less accurate than the reclassification of the material composition image. Reclassification can be performed by a specially trained person using pattern recognition, machine learning algorithms with higher accuracy than the association algorithms used for (the first) classification, etc., as will be discussed in further detail below.

[0073] In some implementations, predefined conditions are associated with the concentration of a material component in the sample. The concentration can be associated with the concentration of a specific material component in the sample, which can be represented by a material composition image.

[0074] In some embodiments, the circuitry is further configured to determine the concentration of a certain type of material component in the sample based on the number of material component images classified as that type of material component. Therefore, in some embodiments, the number of material components representing a particular material component, i.e., the type of material component, can indicate or represent the concentration of that type of material component in the sample.

[0075] In some implementations, the concentration of a type of material component is used as a predefined condition, for example, in the form of a threshold. Therefore, the predefined condition can be defined such that if the concentration of a type of material component exceeds a predefined threshold for that type of material component, reclassification should be performed.

[0076] In some implementations, the predefined conditions can also be met when the concentration is within a predefined range of concentration values, or when, for example, the concentration is zero or below (or equal to) a predefined threshold, such that a zero concentration or a very low concentration of a type of material component is expected to be present in the sample, indicating a malfunction of the device, circuit, or concentration measurement.

[0077] Concentration can be provided, for example, as a percentage per volume, but it can also be provided as the amount of component per image area, the weight per volume, the absolute amount, or any other variable or figure known to those skilled in the art to represent material concentration.

[0078] In some implementations, predefined conditions are associated with the classification accuracy of material components. For example, if the classification accuracy of a particular material component is below (or equal to) a predefined threshold, it can be determined that reclassification is necessary. On the other hand, in some cases, very high classification accuracy exceeding (or equal to) an upper threshold can indicate a malfunction in the equipment or concentration measurement.

[0079] As indicated, in some implementations, classification accuracy is specific to classifying a material composition image into a particular type of material composition. In other words, classification accuracy may be lower for a first type of material composition (image) and higher for a second type of material composition (image). For example, material composition detection accuracy may differ for different material compositions, and therefore classification accuracy may also differ. In some cases, the mapping between detected material composition types and associated classifications (categories) may also be ambiguous, allowing different classifications to be associated with the same type of material composition, or conversely, different types of material compositions to be associated with the same classification, resulting in lower classification accuracy.

[0080] In some implementations, predefined conditions are associated with quality values. Quality values ​​can indicate the quality of a measurement, such as the measurement of a sample, the imaging quality used to generate an image of material composition, the overall quality of the device, etc., which will be explained in more detail below.

[0081] A quality value can be obtained by measuring the quality of a sample. In some embodiments, the circuitry is also configured to measure the quality of the sample to obtain a quality value. A quality value can also be obtained based on performing a test, which will be described in more detail below, such as in conjunction with a qualitative urine test that produces results indicating one or more quality values.

[0082] In some implementations, predefined conditions are also associated with error messages indicating anomalies related to sample quality measurements. For example, the device may detect at least one of the following: errors during sample testing, device malfunctions, malfunctions of sensors or any other electrical components, etc. Error messages may also include “flags” indicating that an error event occurred during setup, which will be discussed in more detail below.

[0083] In some implementations, predefined conditions can be configured by the user, for example, by setting at least one or more conditions such as the occurrence of events, errors, thresholds, etc., and the material composition image can be automatically reclassified based on these conditions, as described herein.

[0084] In some embodiments, the circuitry is further configured to transmit the classified material composition image for reclassification to a remote processing device, which will also be discussed in more detail below. The device and the remote processing device may be configured to communicate with each other, for example, via a network, the Internet, wirelessly or wiredly, via a direct link or protocol (e.g., TCP / IP, etc.) or other types of communication described herein, or any other type of digital communication suitable and known to those skilled in the art for digital communication between electronic devices or apparatuses.

[0085] In this document, the remote processing device is also referred to as the second processing device, and the device described herein is also referred to as the first processing device.

[0086] The remote processing device may have circuitry configured to perform any of the methods, functions, and features described herein.

[0087] Furthermore, the remote processing device can be located remotely from the device, so that it is not housed in the same enclosure as the device, but is separate from it. However, this disclosure is not limited in this respect, and in some embodiments, the remote processing device can be remote at a functional level. Therefore, the communication link between the device for material composition classification and the remote processing device can be adapted to the setup, the distance between the device and the remote processing device, and the type of connection technically suitable for transmitting digital data (such as material composition images and other data as described herein) between the device and the remote processing device.

[0088] In some embodiments, the circuitry is further configured to determine a set of classified material composition images, based on which reclassification is performed. Therefore, in some embodiments, determining a subset of material composition images for reclassification and transmitting this subset to a remote processing device can reduce the total amount of data transmitted and the processing load required to reclassify the material composition images. Furthermore, the set of classified material composition images can be determined, for example, based on at least one of the following: one or more predefined categories or classes, the type of material composition, the number of material composition images, predefined criteria, etc. For example, for a particular category or classification, it can be known in advance that the classification accuracy may be lower than that of other categories or classifications. The same applies to the type of material composition, such that for a particular type of material composition, it can be known in advance that the classification accuracy may be lower than that of other types. In some cases, a smaller number of material composition images (for a particular material composition) may indicate lower classification accuracy.

[0089] In some implementations, the set of images of the classified material composition (only) is sent (or transmitted) to a remote processing device, as described above.

[0090] In some implementations, the circuitry is configured to additionally transmit classification information associated with the classified material composition image to a remote processing device. The classification information can then be used by the remote processing device to perform reclassification.

[0091] In some implementations, the circuitry is further configured to determine whether predefined conditions are met. For example, if predefined conditions are met, the material composition image is automatically reclassified.

[0092] The steps to determine whether the predefined conditions are met may include determining at least one of the following: the magnitude relationship between the concentration of a material component of a user-specified type and a user-specified threshold; the magnitude relationship between the quality value representing the qualitative test result of the sample and the threshold; and the occurrence status of the user-specified error item in the error message, as discussed above and will be discussed in more detail below.

[0093] In some implementations, the sample is urine.

[0094] Some implementations relate to an apparatus for reclassifying material composition, the apparatus having circuitry configured to reclassify a classified material composition image to a type of material composition by associating each of the material composition images with a type of material composition, wherein the reclassification is performed with a higher classification accuracy than the classification of the classified material composition images, wherein the apparatus is also referred herein as a remote processing device or a second processing device.

[0095] The circuitry of a device for reclassifying material composition can be configured to perform any of the methods, functions, and features described herein.

[0096] Some implementations relate to a system for classifying material composition, the system including the device for classifying material composition described herein as a first processing unit, and including a remote processing unit, as described herein, as a second processing unit, wherein the first processing unit and the second processing unit are each configured to communicate with each other via a network, wherein the second processing unit has circuitry configured to obtain a classified material composition image from the first processing unit; receive operator input based on a graphical user interface; and, based on the received operator input, reclassify the obtained classified material composition image to a higher classification accuracy than the classification of the classified material composition image.

[0097] As indicated above, the first processing device and the second processing device can communicate with each other via any type of communication link.

[0098] The operator of the second processing device can be an expert user in the (re)classification of material composition images. The graphical user interface can be configured to provide the operator with information and a human-machine interface with graphical elements for interacting with the second processing device, as described herein.

[0099] In some implementations, the operator input includes at least one of the following: selecting a material composition image, selecting a classification of the material composition, and selecting a reclassification method.

[0100] In some embodiments, the circuitry of the second processing device is further configured to transmit the reclassification results of the material composition image to the first processing device. Therefore, the first processing device can display, for example, the reclassification results to a user.

[0101] Some implementations relate to corresponding methods for material composition classification, the methods comprising the steps of: acquiring a material composition image, wherein the material composition image presents the material composition of a sample; classifying the material composition image as a type of material composition by associating each of the material composition images with a material composition type; and automatically determining, based on predefined conditions, a reclassification of the classified material composition image, wherein the reclassification is performed with a higher classification accuracy than the classification of the material composition image, as described herein, and also relates to devices for material composition classification. Furthermore, all functions, methods, and features that can be performed by circuitry may (at least in part) be part of the method for material composition classification.

[0102] Some implementations relate to a computer program for classifying material composition, the computer program including instructions that, when executed by a processor (or a plurality of processors or circuits or computers), cause the processor to perform the methods described herein.

[0103] In some embodiments, a non-transitory computer-readable recording medium is also provided in which a computer program is stored, which, when executed by a processor (or a plurality of processors or circuits or computers), enables the methods described herein to be performed.

[0104] Unless otherwise specified, all units and entities described in this specification may be implemented as integrated circuit logic, such as on a chip or in a circuit, and unless otherwise specified, the functionality provided by these units and entities may be implemented by software.

[0105] Back Figure 1 , Figure 1This is a perspective view illustrating an example configuration of a urine material composition analysis device 70 for material composition classification according to embodiments taught herein. In some embodiments, the device for material composition classification may be configured as the urine material composition analysis device 70.

[0106] like Figure 1 As shown, the urine material composition analysis device 70 includes a flow chamber 40, a housing 72, a camera 74, and a light source 76. Figure 1 The arrow UP in the image indicates the upper side of the urine material composition analysis device 70 in the vertical direction.

[0107] The flow chamber 40 is suitable for urine material composition testing (urine sediment test), in which material components in the urine sample are imaged by camera 74 by introducing a urine sample, as an example sample, along with sheath fluid, to perform various analyses based on the shape, etc., of the material components in the acquired image. Camera 74 is an example of an imaging unit. Urine samples can include many different types of material components. Examples of types of material components include red blood cells, white blood cells, epithelial cells, casts, and bacteria. In this example, in urine material composition testing, each of the following in the urine sample—red blood cells, white blood cells, non-squamous epithelial cells, squamous epithelial cells, bacteria, crystals, yeast, hyaline casts, other casts (also known as pathological casts), mucus, sperm, and white blood cell clusters—is set as the target to be measured, and the concentration of the target urine material component in the urine is measured. However, the urine material composition analysis device 70 is an example of a material composition analysis device that can be used for material composition classification according to the teachings herein. Therefore, the description herein applies to material composition testing of blood, cells, body fluids, etc., as test objects or samples.

[0108] In the urine material composition analysis device 70, a flow chamber 40 is disposed within a housing 72. A recessed portion 72A is formed in the housing 72, and the flow chamber 40 is inserted into the recessed portion 72A. A portion of the housing 72 including the recessed portion 72A is formed of a transparent member (e.g., glass). A camera 74 is disposed within the housing 72 facing the flow chamber 40. Above the housing 72, a light source 76 is disposed facing the camera 74, and the flow chamber 40 is inserted between the light source 76 and the camera 74. The camera 74 is positioned to image the sample fluid flowing through the flow chamber 40.

[0109] The urine material composition analysis device 70 includes a first supply device 78 that supplies sample fluid to a sample inlet port 42 in a sample flow path (not shown) within a flow chamber 40. The first supply device 78 includes a supply tube 80 having one end connected to the sample inlet port 42. The first supply device 78 also includes a pump 82 disposed (e.g., along the middle) of the supply tube 80. A source of sample fluid is connected to the other end of the supply tube 80. In this example, a Spitz tube 84 storing the sample fluid is disposed in the other end of the supply tube 80. A barcode label displaying a barcode representing a sample ID used to uniquely identify the sample in the Spitz tube 84 can be affixed to a side surface of the Spitz tube 84.

[0110] The urine material composition analysis apparatus 70 includes a second supply device 86 that supplies sheath fluid to a sheath fluid inlet port 44 in a sheath flow path (not shown) within a flow chamber 40. The second supply device 86 includes a supply tube 88 connected to one end of the sheath fluid inlet port 44, a pump 90 disposed along (e.g., in the middle) of the supply tube 88, and a tank 92 connected to the other end of the supply tube 88 for storing the sheath fluid. In some implementations of a material composition analysis apparatus, device, or system for material composition classification, the second supply device 86 may be omitted or may supply different fluids to support the material composition classification of the sample. In some implementations, two or more supply devices may be used in addition to the first sample supply device 78 that supplies the sample.

[0111] In the flow chamber 40, a discharge port 46 is provided between the sample inlet port 42 and the sheath fluid inlet port 44. A discharge pipe (not shown) is connected to one end of the discharge port 46, and a waste container (not shown) is connected to the other end of the discharge port 46. The flow chamber 40 may include a confluence section where the sample introduced from the sample inlet port 42 and the sheath fluid introduced from the sheath fluid inlet port 44 converge, such that the confluenced fluids flow in a flow path. The material composition in the sample stream is imaged by a camera 74. In other words, by imagerizing the sample stream with the camera 74, an image representing the material composition in the sample stream is generated. In some embodiments, material composition images are extracted from these images, for example, to display specific types of material composition, which will also be discussed in more detail below.

[0112] Figure 2 It shows the basis Figure 1 Side view of the urine material composition analysis device 70.

[0113] like Figure 2 As shown, the urine material composition analysis device 70 includes a first processing device 10. For example... Figure 1 As shown, Figure 2The arrow UP in the image indicates the upper side of the urine material composition analysis device 70 in the vertical direction.

[0114] The first processing unit 10, which is described in more detail below and forms part of an apparatus for classifying material composition in some embodiments, controls each of the following operations: operation of camera 74, operation of light source operation unit 77 electrically connected to light source 76, operation of pump 82, and operation of pump 90. The first processing unit 10 causes light source 76 to emit light at predetermined intervals by applying pulse signals to light source operation unit 77. The first processing unit 10 drives pump 82 to control the flow rate of the sample and drives pump 90 to control the flow rate of the sheath fluid. Although... Figure 2 Although not shown, the first processing device 10 may include a plurality of cameras 74 and an optical system for guiding light to each of the cameras 74. The optical system is adjusted such that the cameras 74 are focused at different positions (depths) within the flow chamber 40. Thus, multiple images focused at the same position and at different depths on the horizontal plane can be simultaneously acquired by the multiple cameras 74. The simultaneously acquired images are stored... Figure 3 The storage unit 15 shown is described below. The depth direction referred to herein is the direction perpendicular to the sample flow direction, and refers to… Figure 2 The vertical direction within the flow chamber 40. In this implementation, the distance between each focal point and the wall surface of the flow chamber 40 located on the side closer to the camera 74 is different.

[0115] Figure 3 This is a block diagram illustrating an example of a material composition processing system 100 according to embodiments taught herein, which in some embodiments forms a system for classifying material compositions.

[0116] like Figure 3 As shown, the material composition processing system 100 includes a first processing unit 10 (in some embodiments, forming a device for classifying material components); a remote or second processing unit 20 (in some embodiments, forming a device for reclassifying material components); a qualitative analysis device for performing qualitative measurements of samples, in this example, a urine qualitative analysis device 30; and a server 35. The first processing unit 10 and the qualitative analysis device are connected to the second processing unit 20 via a network N, and the qualitative analysis device is linked to the material composition analysis device. Figure 3 In the example, the urine qualitative analysis device 30 is linked to the urine material composition analysis device 70.

[0117] The first processing device 10 includes a central processing unit (CPU) 11, a read-only memory (ROM) 12, a random access memory (RAM) 13, an input / output interface (I / O) 14, a storage unit 15, a display unit 16, an operation unit 17, a communication unit 18, and a connection unit 19 (wherein one or more of components 11 to 19 may form a circuit). The CPU 11 may be, for example, a processor, and may include a graphics processing unit (GPU), or may additionally provide a GPU for specific graphics calculations or for performing calculations such as machine learning algorithms (e.g., neural networks). The first processing device 10 may include fewer hardware components, different hardware components, or more hardware components (which may form a circuit in some embodiments) than those shown in the examples.

[0118] The first processing device 10 may be a general-purpose computer device such as a personal computer (PC) or a portion thereof. The first processing device 10 may also be a portable computer device such as a smartphone or tablet terminal or a portion thereof. The functions of the first processing device 10 and / or thereof described herein may be divided into multiple units. For example, the first processing device 10 may include a first unit that controls a measurement system such as a camera 74, a light source 76, a pump 82, and a pump 90 as described above, and a second unit that processes and analyzes images acquired by the camera 74. The first processing device 10 may be externally connected to the material composition analysis device. That is, while the first processing device 10 may be at least partially located inside the material composition analysis device, for example, within the housing 72 of the urine material composition analysis device 70, the first processing device 10 or a portion thereof may be located externally and connected to the material composition analysis device via cables or the like.

[0119] The control unit 10A may be formed by a CPU 11, ROM 12, RAM 13, and I / O 14. In some implementations, the control unit 10A has the function of controlling a measurement system such as a camera 74, a light source 76, a pump 82, and a pump 90. In some implementations, the control unit 10A has the function of processing (inspecting, analyzing, verifying, etc.) the images acquired by the camera 74. The CPU 11, ROM 12, RAM 13, and I / O 14 can be interconnected via a bus.

[0120] Each functional unit, including storage unit 15, display unit 16, operation unit 17, communication unit 18, and connection unit 19, is connected to I / O 14. The functional units can communicate with CPU 11 through I / O 14.

[0121] Control unit 10A may be a sub-control unit that controls part of the operation of the first processing device 10, or it may be part of a main control unit that controls the overall operation of the first processing device 10 (which may be a circuit of the first processing device or a part thereof). As part or all of each block of control unit 10A, integrated circuits or integrated circuit (IC) chipsets, such as large-scale integration (LSI), may be used. As individual blocks, separate circuits may be used, or integrated circuits may be used where some or all of the blocks are integrated. The blocks may be configured integrally, or a portion of a block may be configured separately. A portion of each block may be provided separately. The integration of control unit 10A is not limited to LSI, and dedicated circuits or general-purpose processors may be used. At least some functions of control unit 10A may be executed using software instructions stored in a non-transitory storage medium, such as storage unit 15.

[0122] As storage unit 15, for example, a hard disk drive (HDD), a solid-state drive (SSD), flash memory, or some combination thereof is used. Storage unit 15 stores a processing program 15A for performing the measurement and remeasurement processes described below. Processing program 15A may be stored in ROM 12 and may also be referred to as the first processing program. As storage unit 15, the memory may be externally attached or may be subsequently expanded.

[0123] The processing program 15A may be pre-installed, for example, in the first processing device 10. The processing program 15A may be implemented by storing it in a non-volatile, non-transitory storage medium or by distributing it via network N and appropriately installing or upgrading it in the first processing device 10. Examples of non-volatile, non-transitory storage media include optical disc read-only memory (CD-ROM), magneto-optical disc, HDD, digital versatile disc read-only memory (DVD-ROM), flash memory, memory cards, or some combination thereof.

[0124] Display unit 16 is, for example, a liquid crystal display (LCD) or an organic electroluminescent (EL) display. Display unit 16 may integrally include a touch panel. Operation unit 17 may provide, for example, a device such as a keyboard or mouse for input operations. A user can send instructions to the first processing device 10 by operating operation unit 17. Display unit 16 displays the results of a process executed according to instructions received from the user, or various types of information such as notifications for the process.

[0125] The communication unit 18 is connected to a network N such as the Internet, a local area network (LAN), a wide area network (WAN), or any combination thereof. The communication unit 18 can communicate wirelessly with the second processing device 20 via the network N, via one or more communication lines, or any combination thereof.

[0126] In some implementations, the connection unit 19 connects a measurement system, such as a camera 74, a light source 76, a pump 82, and a pump 90, to the first processing device 10. The measurement system is controlled by the aforementioned control unit 10A. The connection unit 19 also serves as an input port through which images output from the camera 74 are input.

[0127] The second processing device 20 according to this embodiment includes a CPU 21, a ROM 22, a RAM 23, an input / output interface (I / O) 24, a storage unit 25, a display unit 26, an operation unit 27, and a communication unit 28 (wherein, in some embodiments, one or more of components 21 to 28 may form the circuitry of the second processing device). The CPU 21 may be, for example, a processor, and may include a GPU, or may additionally provide a GPU for specific graphics calculations or for performing calculations such as machine learning algorithms (e.g., neural networks). The second processing device 20 may include fewer hardware components, different hardware components, or more hardware components (which may form the circuitry in some embodiments) than those shown in the examples.

[0128] The second processing device 20 may be a general-purpose computer device such as a PC or a portion thereof. The second processing device 20 may also be a portable computer device such as a smartphone or tablet terminal or a portion thereof. The second processing device 20 typically performs a greater amount of data processing than the first processing device 10; therefore, in some embodiments, the second processing device 20 is capable of providing higher classification accuracy than the first processing device 10. Thus, although not essential, it is advantageous that the memory access speed in the second processing device 20 is faster than the memory access speed in the first processing device 10, and it is also advantageous that the processing speed of the CPU 21 in the second processing device 20 is faster than the processing speed of the CPU 11 in the first processing device 10.

[0129] The control unit 20A may be formed by a CPU 21, a ROM 22, a RAM 23, and an I / O 24 (and may be a circuit of the first processing device or a part thereof). The various units including the CPU 21, ROM 22, RAM 23, and I / O 24 are interconnected by a bus.

[0130] Each functional unit, including storage unit 25, display unit 26, operation unit 27, and communication unit 28, is connected to I / O 24. The functional units can communicate with CPU 21 through I / O 24.

[0131] As storage unit 25, for example, an HDD, SSD, flash memory, or some combination thereof is used. Storage unit 25 stores a processing program 25A for performing the reclassification process described below. Processing program 25A may be stored in ROM 22 and may be referred to as a second processing program. As storage unit 25, the memory may be externally attached or may be subsequently expanded.

[0132] The processing program 25A may be pre-installed in, for example, the second processing device 20. The processing program 25A may be implemented by storing it in a non-volatile, non-transitory storage medium or distributing it via a network N for appropriate installation or upgrade in the second processing device 20. Examples of non-volatile, non-transitory storage media include CD-ROMs, magneto-optical disks, HDDs, DVD-ROMs, flash memory, memory cards, or some combination thereof.

[0133] Display unit 26 is, for example, an LCD or OLED display. Display unit 26 may integrally include a touch panel. Operation unit 27 may provide, for example, a device such as a keyboard or mouse for input operations. The user sends instructions to the second processing device 20 by operating operation unit 27. Display unit 26 displays the results of a process executed according to instructions received from the user, or various types of information such as notifications for the process.

[0134] The communication unit 28 is connected to a network N, such as the Internet, a LAN, a WAN, or any combination thereof. The communication unit 28 can communicate wirelessly with the first processing device 10 via the network N, via one or more communication lines, or any combination thereof.

[0135] In this example, the urine qualitative analysis device 30 and the urine material composition analysis device 70 are linked via a urine sample transport path. The urine qualitative analysis device 30 is an apparatus for performing a urine qualitative test on a urine sample. For example, a urine qualitative test is a test in which a test strip, called a colorimetric strip, is immersed in urine to measure the color change by reacting with a target component in the urine sample, thereby determining the presence of the target component in the urine sample, or measuring the concentration of the analyte in the urine sample (thus providing a mass value in some embodiments). Although not shown, the urine qualitative analysis device 30 may include a barcode reader for reading the sample ID of the sample to be tested from a barcode label attached to the side surface of the Spitz tube 84, and the urine qualitative test results of the urine sample tested by the urine qualitative analysis device 30 and the sample ID of the urine sample are linked (associated) with each other and transmitted via network N to a server 35, for example, for storage. When an error occurs during the measurement of a urine sample, the urine qualitative analysis device 30 links the error information of the urine sample with the sample ID of the urine sample and sends the link information to the server 35 via network N.

[0136] Next, we will refer to Figure 4 Detailed description of the functional configuration of the first processing device 10 according to this embodiment. Figure 4 It shows the basis Figure 3 A functional block diagram of an example of the first processing device 10.

[0137] In some implementations, the CPU 11 of the first processing device 10 can execute the program 15A stored in the storage unit 15 by writing the program 15A into the RAM 13 and executing the program 15A. Figure 4 The function of each of the units shown.

[0138] like Figure 4 As shown, the CPU 11 of the first processing device 10 is used as an acquisition unit 11A, a first classification unit 11B, a calculation unit 11C, a transmission unit 11D, a receiving unit 11E, an output unit 11F, and a receiving unit 11G.

[0139] Storage unit 15 can store a first trained model 15B used by the first classification unit 11B to classify images.

[0140] The acquisition unit 11A extracts multiple types of material components from the sample as material component images 3 from multiple images (hereinafter also referred to as "sample images"; for example, 300 images or 1000 images) obtained by imaging the sample flowing through the flow chamber 40 with camera 74, and acquires one or more extracted material component images. Specifically, the first classification unit 11B extracts the material component image 3 from each of the sample images using various known techniques, such as image processing like binarization or contour extraction, methods using machine learning, or methods using pattern matching. Each of the material component images 3 includes one material component. In other words, each of the material component images 3 represents one material component.

[0141] The first classification unit 11B classifies the material composition image 3 acquired by the acquisition unit 11A into any of the predetermined categories of detected components (e.g., the type, size, and shape of the material component, and the presence or absence of a kernel), thereby obtaining a classified material composition image. The set of material composition images 3 classified into any predetermined category by the first classification unit 11B, i.e., the material composition image group (or set), is temporarily stored in the storage unit 15 for each sample. Therefore, for each sample, the storage unit 15 can store classified material composition images, each associated with a specific category or classification, which in turn is associated with a specific type of material component. As a method for classifying the material composition images 3, various known techniques are applied, such as machine learning methods or pattern matching methods. For example, the first trained model 15B is used to classify the material composition image group according to this embodiment. The first trained model 15B is a model generated by machine learning training data obtained by associating previously acquired material composition images 3 with detected components in each predetermined category. That is, it is assumed that the training data is labeled data. The first trained model 15B receives the material composition image 3 as input and outputs the components detected in each predetermined category. For example, a convolutional neural network (CNN) is used as the training model for machine learning. For example, deep learning is used as a machine learning method. The material composition image group consists of individual material composition images 3, and therefore will also be referred to as the material composition image group 3 using the same reference numerals as material composition image 2.

[0142] The main classifications of material components include, for example, red blood cells, white blood cells, non-squamous epithelial cells, squamous epithelial cells, bacteria, crystals, yeast, hyaline casts, other casts, mucus, sperm, leukocyte clumps, and material components other than those listed above, such as combinations of different types of material (hereinafter also referred to as unclassified). Red blood cells are represented by RBC, white blood cells by WBC, non-squamous epithelial cells by NSE, squamous epithelial cells by SQEC, other casts by NHC, and bacteria by BACT. Crystals are represented by CRYS, yeast by YST, hyaline casts by HYST, mucus by MUCS, sperm by SPRM, and leukocyte clumps by WBCC. Material components other than red blood cells, white blood cells, non-squamous epithelial cells, squamous epithelial cells, bacteria, crystals, yeast, hyaline casts, other casts, mucus, sperm, and leukocyte clumps are represented by UNCL (unclassified) or "other material components". That is, the detected components that are classified into a predetermined category by the first classification unit 11B correspond to their material composition and are defined as unclassified categories.

[0143] When classifying the material composition image 3, the first classification unit 11B calculates the applicability based on the image classification method used (e.g., machine learning or pattern matching). The first classification unit 11B classifies the material composition image into, for example, the category with the highest applicability. The applicability described herein refers to the classification probability of the resulting image, and an image is assigned a higher value as the percentage of images in each predetermined category that match the correct image or predetermined feature point increases. The applicability is 100% when an image perfectly matches the correct image or feature point. That is, the material composition image 3 with a relatively low applicability is considered unlikely to be properly classified. The applicability can be expressed as an applicability ratio. In some embodiments, the applicability is used as a predefined criterion based on which to determine whether the classified material composition image (e.g., associated with a specific sample) should be reclassified.

[0144] The applicability value varies depending on how the material components are imaged in the material component image 3. Specifically, in images where the material components are focused, classification-based methods such as machine learning can easily determine the material components. The applicability is high for accurate classification and low for inaccurate classification. However, in images where the material components are not focused, i.e., in images where the material components are blurred, the applicability for accurate classification is low, and the difference between the applicability for accurate classification and the applicability for inaccurate classification is also small. In images where multiple material components overlap, the applicability may have a low value. Specifically, even in a rare sample that should be identified as unclassified and was not trained by the first trained model 15B, the material component will be classified into some category. Therefore, the applicability value is low here.

[0145] The calculation unit 11C calculates the concentration of the material component in the sample based on the number of material component images classified into each predetermined category by the first classification unit 11B. The concentration may be a quantity concentration (e.g., the cardinality of images classified by a particular material component, or as described in further detail below), a percentage per volume of the sample or a portion of the sample, or some other concentration measurement.

[0146] As described below, when it is necessary to remeasure the concentration of material components in the sample, the transmitting unit 11D controls the communication unit 18 to transmit the material composition image 3 to the second processing device 20 via the network N. The material composition image 3 transmitted to the second processing device 20 may be all or part of the classified material composition image 3. The transmitting unit 11D transmits the material composition image 3 together with the classification result of the material composition image 3 classified by the first classification unit 11B.

[0147] The receiving unit 11E controls the communication unit 18 to receive from the second processing device 20 the reclassification result of the material composition image 3 reclassified by the second processing device 20.

[0148] Output unit 11F outputs at least one of a first state, a second state, and a third state for reclassifying the material composition image 3. The output described herein may be a display output from display unit 16 or a printout from a printer (not shown). The first state indicates the state after the first classification unit 11B has classified the material composition image 3 into any of the predetermined categories, and indicates a state awaiting an instruction to send the material composition image 3 to the second processing device 20. The second state indicates a state awaiting receipt of the reclassification result from the second processing device 20. The third state indicates a state receiving the reclassification result from the second processing device 20.

[0149] The receiving unit 11G receives operation input from the user through the operation unit 17.

[0150] Next, we will refer to Figure 5 The functional configuration of the second processing apparatus 20 according to this embodiment is described in detail. As described above, in some embodiments, the second processing apparatus may be configured as a device for reclassifying material composition.

[0151] According to this embodiment, the CPU 21 of the second processing device 20 functions by writing the processing program 25A stored in the storage unit 25 into the RAM 23 and executing the processing program 25A. Figure 5 The function of each of the units shown.

[0152] Figure 5 This is a block diagram illustrating an example of the functional configuration of the second processing apparatus 20 according to this embodiment.

[0153] like Figure 5 As shown, the CPU 21 of the second processing device 20 according to this embodiment is used as an acquisition unit 21A, a second classification unit 21B, a display control unit 21C, a return unit 21D, and a receiving unit 21E.

[0154] Storage unit 25 stores a second trained model 25B. The second trained model 25B is a model used by the second classification unit 21B to classify images, and in some embodiments may have higher classification accuracy than the first trained model 15B.

[0155] The receiving unit 21E controls the communication unit 28 to receive the material composition image 3 from the first processing device 10. The (classified) material composition image 3 received from the first processing device 10 is temporarily stored in the storage unit 25 as a classification target image group.

[0156] The acquisition unit 21A acquires the material composition image 3 to be classified from the classification target image group stored in the storage unit 25.

[0157] The second classification unit 21B (re)classifies the material composition image 3 acquired by the acquisition unit 21A into any predetermined category as a detected component (e.g., the type, size, and shape of the material component, and the presence or absence of a kernel). The material composition image 3 classified into any predetermined category by the second classification unit 21B is sent to the return unit 21D. As a method for classifying the material composition image, for example, a machine learning method is applied. Here, for example, the material composition image 3 is classified using a second trained model 25B. The second trained model 25B is a model generated, for example, by performing machine learning on another set of training data associated with more detected components than the training data of the first trained model 15B using the same machine learning algorithm as the first trained model 15B. The amount of training data trained by the second trained model 25B is greater than the amount of training data trained by the first trained model 15B. That is, the second trained model 25B is trained to achieve a higher classification performance or accuracy than the first trained model 15B.

[0158] The second trained model 25B can be a model generated by using another algorithm with higher classification performance than the first trained model 15B's training data to perform machine learning. As machine learning algorithms, in addition to CNNs mentioned above, various methods can be used, such as linear regression, regularization, decision trees, random forests, k-nearest neighbors (k-NN), logistic regression, or support vector machines (SVMs). For example, when the classification performance of a trained SVM model is higher than that of a CNN, a CNN is used in the first trained model 15B and an SVM is used in the second trained model 25B. Conversely, when the classification performance of a trained CNN model is higher than that of an SVM, an SVM is used in the first trained model 15B and a CNN is used in the second trained model 25B. To compare the classification performance of trained models, a method can be used to calculate and compare metric values ​​(e.g., accuracy or applicability) representing model performance using pre-prepared test data. In some implementations, such metric values ​​can be used as predefined criteria for determining whether a reclassification of the material composition image is necessary.

[0159] The second trained model 25B can be, for example, a model generated by using another algorithm with higher classification performance than the first trained model 15B to perform machine learning on another training data associated with more detected components than the training data of the first trained module 15B.

[0160] When managing the version of the second trained model 25B, it is advantageous that the version of the second trained model 25B is always managed to be the latest.

[0161] Here, the second classification unit 21B can classify the material composition image 3 according to the user's classification operation. That is, the second classification unit 21B performs classification according to the user's instructions. Advantageously, the user described herein is, for example, a laboratory technician proficient in classifying the material composition image 3. In the following text, the user or operator of the second processing device 20 will also be referred to as a "laboratory technician" to distinguish them from the user operating the first processing device 10.

[0162] The display control unit 21C performs control to associate the material composition image 3, which is the object of classification, with the classification result of the first classification unit 11B for display by the display unit 26. The user reclassifies the material composition image 3 displayed by the display unit 26 that was previously classified incorrectly to an appropriate classification. Here, the second classification unit 21B classifies and displays the material composition image 3 based on the classification operation performed by a laboratory technician on the material composition image 3 displayed by the display unit 26.

[0163] <Measurement process of control unit 10>

[0164] Next, we will refer to Figure 6 The operation of the first processing apparatus 10 according to this embodiment is described.

[0165] Figure 6 This is a flowchart illustrating an example of the flow of a measurement process executed by the first processing device 10 when the receiving unit 11G receives an instruction to measure a sample from the user. In some embodiments, the measurement process may be a method for classifying material composition or a part thereof. The CPU 11 of the first processing device 10 reads the processing program 15A stored in the storage unit 15 and executes the measurement process.

[0166] First, in step S10, the control unit 10A drives a transfer unit (not shown) to transfer the Spitz tube 84, including the sample positioned at a predetermined location on the transfer unit, to the sample collection location. A barcode reader (not shown) is attached to the sample collection location, and the control unit 10A uses the barcode reader to read a barcode label attached to the side surface of the Spitz tube 84. For example, the barcode label displays a barcode representing a sample ID used to uniquely identify the sample, and the control unit 10A obtains the sample ID of the sample to be tested by reading the barcode label.

[0167] Control unit 10A controls an actuator (not shown) to move the supply tube 80 vertically in the urine material composition analysis device 70, causing the tip of the supply tube 80 (the tip opposite the tip connected to the sample inlet port 42), positioned above the opening of the Spitz tube 84 which is being transported to the sample collection position, to be lowered from the opening into the Spitz tube 84. Control unit 10A drives pump 82 after lowering the tip of the supply tube 80 to the position where the tip of the supply tube 80 reaches the sample. As a result, the sample in the Spitz tube 84 is introduced from the sample inlet port 42 into the flow chamber 40 at a predetermined flow rate, allowing a predetermined volume of sample to flow into the flow chamber 40.

[0168] Simultaneously, the control unit 10A, together with the pump 82, drives the pump 90. As a result, the sheath fluid stored in the tank 92 is introduced into the flow chamber 40 from the sheath fluid inlet port 44 at a predetermined flow rate, so that the sheath fluid binds to the sample in the flow chamber 40.

[0169] Control unit 10A controls camera 74 to acquire sample images of samples in flow chamber 40 and stores the acquired sample images in, for example, storage unit 15. The number of acquired sample images is unlimited, and control unit 10A acquires sample images based on the number of images pre-stored in storage unit 15. The user can change the number of acquired sample images stored in storage unit 15 via operation unit 17.

[0170] The obtained sample images include various types of material components. Therefore, the acquisition unit 11A extracts an image of each of the material components in the sample images, that is, a material component image 3 of each of the material components.

[0171] Figure 7 This is a diagram illustrating an example of a material composition image 3 extracted by the acquisition unit 11A. The material composition image 3 is a rectangular image encompassing the entire material composition. Therefore, the size of the material composition image 3 also varies depending on the size of the material composition.

[0172] The acquisition unit 11A assigns a material composition image ID to each of the material composition images 3 extracted from the sample images. The material composition image ID is an identifier used to uniquely identify each of the material composition images 3 and is used, for example, as the filename of the material composition image 3. The acquisition unit 11A generates a classification list associated with each of the material composition images 3 and the sample ID of the sample from which the material composition image 3 was obtained, and stores this classification list in, for example, the storage unit 15. Table 1 shows an example of the classification list. The material composition images 3 are images obtained from the same sample. Therefore, as shown in Table 1, the same sample ID is associated with the material composition image ID.

[0173] [Table 1]

[0174]

[0175] In step S20, the first classification unit 11B uses the first trained model 15B pre-stored in the storage unit 15 to classify the material composition image 3 into any type of material composition.

[0176] As described above, the first trained model 15B is an example of a classification model for a material composition image 3 generated by machine learning using training data where the input is a known type of material composition image 3 and the output is the type of material composition in the material composition image 3. The number of nodes in the output layer of the first trained model 15B is the number of material composition types that can be classified by the first processing device 10, and each node in the output layer of the first trained model 15B is associated with a type of material composition.

[0177] When the material composition image 3 is input into the first trained model 15B, the first trained model 15B outputs the applicability of each node in the output layer. Since each node in the output layer is associated with the type of material composition, the first classification unit 11B classifies the type of material composition associated with the node of the output layer with the highest applicability as the type of material composition in the material composition image 3 input into the first trained model 15B. Thus, by sequentially inputting all material composition images 3 extracted from the sample images into the first trained model 15B, the first classification unit 11B classifies the material composition images 3 in the sample images as any type of material composition. In other words, it can be said that by classifying the material composition images 3 as material composition images 3 that image the target material composition and material composition images 3 that image the material composition image 3 that image the target material composition, the material composition images 3 can be specified among the material composition images 3.

[0178] The first classification unit 11B associates the types of material components in material composition image 3, classified using the first trained model 15B and represented by material composition image IDs, with the material composition image IDs in the classification list shown in Table 1. Table 2 shows an example of the classification list associated with the types of material components. The values ​​in the classification field of the classification list in Table 2 do not need to be material component names; they can be reference numbers representing material component names. The classification list where the types of material components are associated with the material composition image IDs is an example of the classification results for the material composition images.

[0179] [Table 2]

[0180]

[0181] existFigure 6 In step S30, the calculation unit 11C refers to the classification list shown in Table 2 obtained through the process of step S20, and calculates the concentration of the material component in the sample based on the number of material component images classified as any type of material component. Here, concentration is the quantity concentration of the material component, and refers to an index representing the concentration of the material component in the sample based on the amount of material component in a predetermined unit volume such as 1 microliter.

[0182] Specifically, the calculation unit 11C uses the concentration arithmetic expressions pre-stored in the storage unit 15 to calculate the quantity concentration of each of the material components in the sample. Table 3 shows examples of the concentration arithmetic expressions for each of the material components.

[0183] [Table 3]

[0184]

[0185] In the concentration arithmetic expressions shown in Table 3, the operator "x" represents the multiplication operator. The quantity concentration y in the material composition type is represented by, for example, a linear function of the variable x, which is the number of material composition images 3 of the material composition type. In the concentration arithmetic expressions, "an" (where n represents an integer) represents the slope determined by the material composition type, and "bn" represents the intercept determined by the material composition type. "Xn" represents the number of material composition images 3 in each of the n types of material composition, and "Yn" represents the quantity concentration of each of the n types of material composition. The concentration arithmetic expression for each material composition is an arithmetic expression prepared in advance through experiments or computer simulations to obtain the relationship between the number of material composition images 3 imaged in a sample with a predetermined volume and the quantity concentration of the material composition, and is stored in storage unit 15.

[0186] The concentration arithmetic expressions shown in Table 3 are merely examples, and the concentration arithmetic expression for each of the material components is not limited to a linear function. Table 3 shows the concentration arithmetic expressions corresponding to 13 types of material components, but the number of classifications of material components by the first processing device 10 is only an example.

[0187] exist Figure 6 In step S40, the control unit 10A refers to the quantity concentration of the material component type calculated by the calculation unit 11C in step S30 and determines whether the predetermined items for sample testing (hereinafter referred to as "determined items") meet the review conditions. The review conditions are conditions set by the user through the operation unit 17, serving as a recommendation to recalculate the quantity concentration. The determined items and review conditions are pre-stored, for example, in the storage unit 15, and can be changed by the user through the operation unit 17. Details of the determined items and review conditions will be described below.

[0188] When the review conditions are not met (in the case of a negative determination), it is not necessary to recalculate the quantity concentration of the material components, and the process proceeds to step S50.

[0189] In step S50, the output unit 11F displays the measurement status of the quantity concentration of material components in the sample (hereinafter referred to as "the measurement status of urine material component concentration") on the display unit 16.

[0190] Here, the screen displayed on the display unit 16 by the output unit 11F will be described. The screen displayed on the display unit 16 by the output unit 11F includes, for example, a status screen 61, a work list screen 62, a dashboard screen 63, and an atlas screen 64. One or more screens 61 to 64 can form a graphical user interface (GUI) as a human-machine interface for user operation of the first processing device. At least one of the different screens 61 to 64 can form an element of the GUI. In some embodiments, the following elements can be at least a part of the GUI.

[0191] Figure 8 This is a diagram showing an example of status screen 61. Figure 9 This is an example image showing the work list screen 62. Figure 10 This is an example diagram showing dashboard screen 63. Figure 11 This is an example of a picture in the atlas, screen 64.

[0192] When the user selects status button 2A using a mouse or similar device, output unit 11F displays status screen 61 on display unit 16. When the user selects work list button 2B using a mouse or similar device, output unit 11F displays work list screen 62 on display unit 16. When the user selects dashboard button 2C using a mouse or similar device, output unit 11F displays dashboard screen 63 on display unit 16. When the user selects image gallery button 2D using a mouse or similar device, output unit 11F displays image gallery screen 64 on display unit 16.

[0193] Status screen 61 displays information about the user (i.e., operator) operating the first processing device 10, the connection status of the first processing device 11 to another device, or the status of the first processing device 12, such as the remaining amount of consumables used for sample measurement, as well as the number of sample measurement cases or the calibration results of the first processing device 10. Status screen 61 also displays information about previous periodic maintenance, the cleaning status of components requiring cleaning, such as the supply tube 80, or the shutdown of the first processing device 10, and the startup process when the first processing device 10 is started.

[0194] The work list screen 62 displays, in a list format, general information about sample measurements, such as the measurement time for each sample.

[0195] The dashboard screen 63 displays the measurement status of the urine material component concentration for each sample in the form of a panel. Sample panel 5 is associated with each sample and displays, for example, the sample ID of the sample associated with sample panel 5. For example, the dashboard screen 63 provides each of the following display areas: ordered, not approved, under review, awaiting approval, microscopic examination, and requiring confirmation, and the measurement status of the urine material component concentration in the sample associated with sample panel 5 is displayed in the display area showing sample panel 5. In some embodiments, the element "not approved" is a first status element of the graphical user interface, the element "under review" is a second status element of the graphical user interface, and "awaiting approval" is a third status element of the graphical user interface.

[0196] Image 4 in the atlas is displayed on screen 64. Image 4 is a standard composition image of a material composition type. That is, image 4 is an exemplary image of a material composition type.

[0197] The operation bar 7, located below the status screen 61, the work list screen 62, the dashboard screen 63, and the atlas screen 64, displays various buttons corresponding to each screen.

[0198] When the process proceeds to Figure 6 In step S50, the concentration of urine material components is not approved. Therefore, the control unit 10A sets the measurement status of urine material component concentration to "unapproved". Therefore, the output unit 11F displays the sample panel 5 corresponding to the sample to be measured on the display unit 16, which is displayed in the "unapproved" area of ​​the dashboard screen 63.

[0199] In step S60, the receiving unit 11G determines whether a selection by the user on any of the sample panels 5 displayed on the dashboard screen 63 has been received. When no selection for sample panel 5 is received (in the case of negative confirmation), the determination process of step S60 is repeated until sample panel 5 is selected, thus monitoring the user's selection status for sample panel 4. Meanwhile, when a selection for sample panel 5 is received (in the case of positive confirmation), the process proceeds to step S70.

[0200] In step S70, the control unit 10A determines whether the urine qualitative test results of the sample associated with the selected sample panel 5 are stored in the server 35. Specifically, the control unit 10A determines whether the urine qualitative test results associated with a sample ID that is the same as the sample ID associated with the selected sample panel 5 are stored in the server 35. When the urine qualitative test results are stored in the server 35 (in the case of affirmative determination), the process proceeds to step S80. For ease of description, the sample associated with the selected sample panel 5 will be referred to as the "selected sample".

[0201] In step S80, the control unit 10A obtains the qualitative test results of the urine of the selected sample from the server 35 and proceeds to step S90.

[0202] During the determination process in step S70, when the control unit 10A determines that the urine qualitative test result of the selected sample is not stored in the server 35 (in the case of negative determination), the process proceeds to step S90 without executing the process in step S80.

[0203] In step S90, the output unit 11F displays an approval screen 65 on the display unit 16 indicating that the concentration of urine material components of the selected sample has been approved.

[0204] When the urine qualitative test results of the selected sample are obtained through step S80, the output unit 11F displays the urine material component concentration and the urine qualitative test results of the selected sample on the approval screen 65. Simultaneously, when the urine qualitative test results of the selected sample are not stored in the server 35, the output unit 11F only displays the urine material component concentration of the selected sample on the approval screen 65.

[0205] Figure 12 This is an example diagram of an approved screen 65 displaying the concentration of urine material components and the results of qualitative urine tests. Figure 12 In the approval screen 65, the left table displays the qualitative test results of urine, and the right table displays the concentration of urine material components. The approval screen 65 is a pop-up screen overlaid on the dashboard screen 63.

[0206] On the approval screen 65, selection buttons 6 are displayed, including an approval button 6A, a review button 6B, a display button 6C, and a close button 6D.

[0207] The approval button 6A is used to approve the urine material component concentration displayed on the approval screen 65 (i.e., the measurement result of the urine material component concentration in the selected sample). By approving the urine material component concentration, the measurement result of the urine material component concentration in the selected sample is confirmed.

[0208] The Review button 6B is used to recalculate the concentration of urine material components in the selected sample. The user selects the Review button 6B when the urine material component concentration displayed on the Approval screen 65 differs from the trend estimated based on urine qualitative test results, or when the user wants a more detailed calculation of the urine material component concentration.

[0209] The Display button 6C is used to display the material composition image 3 of the selected sample used to calculate the concentration of urine material components. The user selects the Display button 6C when they want to confirm the material composition of the selected sample.

[0210] The close button 6D is used to close the approval screen 65 and display the dashboard screen 63.

[0211] exist Figure 6 In step S100, the receiving unit 11G determines whether an instruction from the user has been received by the operation unit 17 selecting the selection button 6. When no instruction from the user is received (in the case of negative confirmation), the determination process of step S100 is repeated until any selection button 6 is selected, thereby monitoring the user's selection status of the selection button 6. When an instruction from the user is received (in the case of positive confirmation), the receiving unit 11G notifies the control unit 10A of the received instruction content, and the process proceeds to step S110.

[0212] In step S110, the control unit 10A determines whether a review instruction has been received via selecting the review button 6B. If no review instruction has been received (in the case of a negative determination), the process proceeds to step S120.

[0213] In step S120, the control unit 10A determines whether it has received a display command for the material composition image 3, which was communicated via the selection of the display button 6C. If no display command for the material composition image 3 is received (in the case of a negative determination), the process proceeds to step S130.

[0214] In step S130, the control unit 10A determines whether an approval instruction has been received via selecting the approval button 6A. If no approval instruction has been received (in the case of a negative determination), it is assumed that the user selected the close button 6D. When the close button 6D is selected, a close instruction is displayed. Therefore, according to the instruction from the control unit 10A, the output unit 11F closes the approval screen 65, and the process proceeds to step S50. As a result, through the process of step S50, the dashboard screen 63 is displayed on the display unit 16, showing the measurement status of the urine material component concentration for each sample.

[0215] Meanwhile, when the control unit 10A determines during the determination process in step S130 that it has received an approval instruction (in the case of a positive determination), the process proceeds to step S140.

[0216] Here, it is assumed that the measurement results of the urine material component concentration in the selected sample have been approved by the user. Therefore, in step S140, the control unit 10A sends the measurement results of the urine material component concentration associated with the sample ID of the selected sample to the server 35 via the sending unit 11D. As a result, the urine material component concentration of the sample measured by the urine material component analysis device 70 is registered in the server 35, and Figure 6 The measurement process shown is now complete. Once the urine material composition concentration is registered in server 35, output unit 11F removes the sample panel 5 associated with the approved urine material composition concentration from dashboard screen 63.

[0217] Meanwhile, when the control unit 10A determines during the determination process in step S120 that it has received a display instruction for the material composition image 3 (in the case of certainty), the process proceeds to step S150.

[0218] Here, the user wants to confirm the shape or size of the material components in the selected sample. Therefore, in step S150, the output unit 11F displays the material composition display screen 66 on the display unit 16.

[0219] Figure 13 This is a diagram illustrating an example of a material composition display screen 66. On the material composition display screen 66, a material composition image 3 of the selected sample is displayed, categorized by the type of material composition. In area 60A of the material composition display screen 66, the material composition image 3 of the selected sample is displayed. In area 60B of the material composition display screen 66, an atlas image 4 of the same type as the material composition image 3 displayed in area 60A is displayed.

[0220] The material composition display screen 66 includes a first item button group 52 and a second item button group 53. The first item button group 52 includes buttons for each type of material composition in the selected sample. The second item button group 53 includes buttons for each type of all material composition that can be classified in the first processing device 10.

[0221] Output unit 11F displays a material composition image 3 in area 60A, which corresponds to the material composition type selected by the user in the first item button group 52. Conversely, when any button in the second item button group 53 is selected, output unit 11F displays a reclassification operation screen (not shown) on display unit 16. The reclassification operation screen provides the user with an interface for reclassifying the material composition image 3 selected from the material composition image 3 displayed in area 60A of the material composition display screen 66 into the material composition type corresponding to any button selected from the second item button group 53.

[0222] The output unit 11F can display the urine qualitative test results of the selected sample in area 66A of the material composition display screen 66. When the urine sediment measurement results of the selected sample are stored in the server 35, the control unit 10A can obtain the urine sediment measurement results of the selected sample from the server 35, and the output unit 11F can display the urine sediment measurement results and urine qualitative test results obtained by the control unit 10A in area 66A.

[0223] In step S160, the receiving unit 11G determines whether a display off command has been received from the material composition display screen 66. If no display off command is received (in the case of a negative determination), the determination process of step S160 is repeated until a display off command is received, and thus it is detected whether a display off command has been given. On the other hand, if a display off command is received (in the case of a positive determination), the process proceeds to step S50. Therefore, through the processing of step S50, the dashboard screen 63 is displayed on the display unit 16, and the measurement status of the urine material composition concentration of each sample is displayed.

[0224] On the other hand, when the control unit 10A determines during the determination process in step S110 that it has received a review instruction (in the case of a positive determination), the process proceeds to step S180.

[0225] Here, the user wishes to recalculate the concentration of urine material components in the selected sample. Therefore, in step S180, the control unit 10A sends the material component image 3 obtained from the selected sample, along with the sample ID, to the second processing device 20, which provides the classification service for the material component image 3, via the sending unit 11D. The control unit 10A also sends information other than the sample ID and the material component image 3 to the second processing device 20 according to instructions from the user. For example, the control unit 10A sends the sample ID and material component image 3 of the selected sample, a classification list (see Table 2) that associates the types of material components with the material component image 3 in the selected sample, and the measurement results of the urine material component concentration for each type of material component in the selected sample to the second processing device 20.

[0226] The material composition images 3 sent by the control unit 10A to the second processing device 20 are preferably all material composition images 3 obtained from the selected sample, but may also be a part (or a set or subset) of the obtained material composition images 3. The user can select the material composition images 3 to be sent to the second processing device 20.

[0227] When the urine qualitative test results of the selected sample can be obtained from the server 35, the control unit 10A can also send the urine qualitative test results of the selected sample to the second processing device 20.

[0228] Therefore, the request to reclassify the material composition image 3 to the second processing device 20 is completed. Therefore, the operation of transmitting the material composition image 3 to the second processing device 20 to allow the second processing device 20 to reclassify the material composition image 3 is referred to as "review".

[0229] The second processing unit 20 is requested to reclassify the material composition image 3 obtained from the selected sample. Therefore, in step S190, the control unit 10A sets the measurement status of the urine material composition concentration of the selected sample to "under review". The measurement status of the urine material composition concentration of each sample is managed by a measurement status list. The measurement status list is, for example, a list stored in the storage unit 15. Table 4 shows an example of a measurement status list.

[0230] [Table 4]

[0231]

[0232] In the example of the measurement status list shown in Table 4, the measurement status of urine material component concentration is set for each of the 16 samples whose sample IDs are represented by "#A0001" to "#A0016".

[0233] Based on the measurement settings for the concentration of urine material components, the output unit 11F displays the result on the display unit 16. Figure 10 The dashboard screen 63 shown displays the sample panel 5 associated with the selected sample in a display area that matches the measurement status of the urine material component concentration. Here, since the measurement status of the urine material component concentration is "under review," the sample panel 5 associated with the selected sample is displayed in the "under review" area of ​​the dashboard screen 63. Therefore, Figure 6 The measurement process shown has ended.

[0234] On the other hand, when the control unit 10A determines Figure 6 When the determined item in step S40 meets the review conditions (in the case of affirmative determination), the process proceeds to step S170.

[0235] Here, the control unit 10A determines that the concentration of urine material components needs to be recalculated.

[0236] Therefore, in step S170, the control unit 10A determines whether the automatic transfer setting has been performed on the second processing device 20. When the automatic transfer setting has not been performed (in the case of a negative determination), the control unit 10A cannot transfer the material composition image 3 obtained from the sample to the second processing device 20, and cannot request the reclassification of the material composition image 3 without the user's permission. Therefore, the process proceeds to step S50. That is, the control unit 10A displays the dashboard screen 63 on the display unit 16 and delegates the determination of whether the urine material composition concentration needs to be recalculated to the user. Here, the control unit 10A sets the measurement status of the urine material composition concentration of the sample to "awaiting approval". Therefore, the sample panel 5 of the sample to be tested is displayed in the "awaiting approval" area of ​​the dashboard screen 63.

[0237] Simultaneously, when automatic transmission is set (in a positive state), the process proceeds to step S180. As described above, in step S180, the control unit 10A transmits the material composition image 3 obtained from the sample to be measured to the second processing device 20 via the transmission unit 11D. Therefore, when the review conditions in the determination item are met, the material composition image 3 of the sample is automatically transmitted from the first processing device 10 to the second processing device 20 without the user instructing the first processing device 10 to conduct a review. Whether automatic transmission is allowed can be set by the user.

[0238] <Second processing device 20 reclassifies material composition image 3>

[0239] Next, the operation of the second processing device 20 will be described. Figure 14 This is a flowchart illustrating an example of the reclassification process performed by the second processing unit 20 when a material composition image 3 of a sample represented by a sample ID is received from the first processing unit 10. The CPU 21 of the second processing unit 20 reads the processing program 25A stored in the storage unit 25 and executes the reclassification process. Hereinafter, an example will be described of the second processing unit 20 receiving the material composition image 3 and a classification list of samples represented by sample IDs (i.e., the classification results of the first classification unit 11B) from the first processing unit 10.

[0240] For example, in the second processing device 20, a professional laboratory technician who examines the material composition image 3 and determines the type of material composition in the material composition image 3 operates the second processing device 20 to reclassify the material composition image.

[0241] First, in step S200, the display control unit 21C displays on the display unit 26. Figure 13The material composition display screen 66 is shown. On the material composition display screen 66, the material composition image 3 received from the first processing device 10 is displayed based on the classification of the classification list also received from the first processing device 10.

[0242] In step S210, the control unit 20A determines whether any button in the first item button group 52 of the material composition display screen 66 has been selected by the operation unit 27. When no button in the first item button group 52 is selected (in the case of negative confirmation), the determination process of step S210 is repeated until any button in the first item button group 52 is selected, thereby monitoring the selection status of the first item button group 52 by the laboratory technician. On the other hand, when any button in the first item button group 52 is selected (in the case of positive confirmation), the process proceeds to step S220.

[0243] In step S220, the display control unit 21C displays a material composition image 3 of the material composition type associated with the selected button in area 60A of the material composition display screen 66.

[0244] In step S230, the control unit 20A determines whether any button in the second item button group 53 of the material composition display screen 66 has been selected by the operation unit 27. When no button in the second item button group 53 is selected (in the case of negative confirmation), the determination process of step S230 is repeated until any button in the second item button group 53 is selected, thereby monitoring the selection status of the second item button group 53 by the laboratory technician. On the other hand, when any button in the second item button group 53 is selected (in the case of positive confirmation), the process proceeds to step S240.

[0245] In step S240, the display control unit 21C displays a reclassification operation screen on the display unit 26. Through the reclassification operation screen, laboratory technicians reclassify the material composition image 3, which was incorrectly identified in the classification, as a specified type of material composition. When the urine qualitative test results of the sample are sent from the first processing device 10, laboratory technicians can refer to the urine qualitative test results to reclassify the material composition image 3.

[0246] In step S250, the control unit 20A determines whether any instruction has been received from the laboratory technician. If no instruction is received (in the case of a negative determination), the determination process of step S250 is repeated until any instruction is received; therefore, the control unit 20A waits until an instruction is received from the laboratory technician. Conversely, if any instruction is received (in the case of a positive determination), the process proceeds to step S260.

[0247] In the following text, control unit 20A receives instructions from laboratory technicians. First, in step S260, control unit 20A determines whether a reclassification instruction has been received from the laboratory technicians. When a reclassification instruction is received (in the affirmative case), the process proceeds to step S270.

[0248] In step S270, the second classification unit 21B, as an example of a reclassification unit, reclassifies the type of material component in material composition image 3 selected by the laboratory technician to any type of material component specified by the laboratory technician, and the process proceeds to step S280. Specifically, the control unit 20A updates the classification field of the classification list received from the second processing device 20. Table 5 shows an example of the classification list, where material composition image 3, represented by material composition image ID "#B00001", is reclassified from red blood cells to yeast relative to the classification list shown in Table 2. The updated classification list is an example of the reclassification result of material composition image 3 by the second classification unit 21B.

[0249] [Table 5]

[0250]

[0251] When no classification list is received from the first processing device 10, the control unit 20A can generate a classification list in which the type of material component in the material composition image 3 selected by the laboratory technician is associated with the material composition image ID.

[0252] Meanwhile, if no reclassification instruction is received during the determination process in step S260 (in the case of negative determination), the process proceeds to step S280 without executing the process in step S270.

[0253] In step S280, the control unit 20A determines whether a microscopic examination instruction has been received from a laboratory technician. A microscopic examination instruction is an instruction to perform a detailed examination of the sample, for example, using a microscopic method that tests the type or quantity of material components in the sample by visually examining a person with a laboratory microscope. When a microscopic examination instruction is received (in the affirmative case), the process proceeds to step S290.

[0254] In step S290, the control unit 20A adds the microscopic examination status, indicating that a microscopic examination instruction has been received from the laboratory technician, to the sample ID, and the process proceeds to step S300. Meanwhile, if no microscopic examination instruction is received during the determination process in step S280 (in the case of a negative determination), the process proceeds to step S300 without executing step S290.

[0255] In step S300, the control unit 20A returns a classification list reflecting the sample ID and reclassification results to the first processing device 10 via the return unit 21D. When a microscopic examination command is received, the microscopic examination status is added to the sample ID returned to the first processing device 10. Therefore, Figure 14 The reclassification process shown has ended.

[0256] The example of reclassifying material composition image 3 into a specified type of material composition based on reclassification instructions from a laboratory technician has been described above. However, even without reclassification instructions from a laboratory technician, the second processing device 20 can reclassify material composition image 3. Specifically, the second classification unit 21B can use a second trained model 25B pre-stored in storage unit 25 to classify material composition image 3 as a type of material composition specified by the laboratory technician.

[0257] As described above, the second trained model 25B is a classification model with higher classification performance than the first trained model 15B. Therefore, the second trained model 25B classifies the material composition image 3 more accurately than the first trained model 15B, and thus the first trained model 15B can be used to correct the classification errors of the material composition image 2.

[0258] When the second trained model 25B is used to classify the material composition image 3, even if the laboratory technician does not specify the material composition image 3 to be reclassified, the control unit 20A will reclassify all material composition images received from the first processing device 10 into any type of material composition.

[0259] <Re-measurement of urine material component concentration by control unit 10>

[0260] Next, the operation of the first processing unit 10, which receives a classification list reflecting the reclassification results of the sample ID and material composition image 3 from the second processing unit 20, will be described.

[0261] Figure 15 This is a flowchart illustrating an example of the remeasurement process performed by the first processing unit 10 when a classification list reflecting the reclassification results of the sample ID and material composition image 3 is received from the second processing unit 20. The CPU 11 of the first processing unit 10 reads the processing program 15A stored in the storage unit 15 and executes the remeasurement process.

[0262] Figure 15 The flowchart shown is Figure 6The difference in the flowchart of the measurement process shown is that steps S10 to S40 and step S170 have been deleted, and step S45 has been added. Step S50 has been replaced by step S50A. Because the other processes are... Figure 6 The process is the same, so the process of steps S45 and S50 will be mainly described to illustrate the remeasurement process of the first processing device 10.

[0263] When the second processing device 20 receives a classification list reflecting the reclassification results of the sample ID and material composition image 3, step S45 is executed.

[0264] In step S45, the calculation unit 11C refers to the classification list received from the second processing device 20 to recalculate the number of material component images 3 for the type of material component, and substitutes the recalculated number into the concentration arithmetic expression shown in Table 3 to recalculate the concentration of urine material component in the material component type.

[0265] In step S50A, the control unit 10A references the sample ID received from the data management device, and when a microscopic examination status is added to the sample ID, the control unit 10A sets the measurement status of the concentration of urine material components in the sample represented by the sample ID to "awaiting microscopic examination" for use in the measurement status list shown in Table 4. When a microscopic examination status is not added to the sample ID, the control unit 10A sets the measurement status of the concentration of urine material components in the sample represented by the sample ID to "awaiting approval" for use in the measurement status list shown in Table 4.

[0266] The output unit 11F displays on the display unit 16 that each sample panel 5 associated with a sample is displayed in a dashboard screen 63 in a display area that matches the measurement status of the urine material component concentration set in the measurement status list. Therefore, the display position of the sample panel 5 in the dashboard screen 63 is updated according to the latest measurement status of the urine material component concentration.

[0267] Next, the user selects any sample panel 5 from the updated dashboard screen 63 to perform the process described in and after step S60 above. That is, for the sample corresponding to the selected sample panel 5, the approval of the measurement results of the urine material component concentration, the review of the measurement results of the urine material component concentration, and the display of the material component image 3 are repeated. Therefore, Figure 15 The remeasurement process shown is now complete.

[0268] <Review Conditions>

[0269] The procedure for measuring the concentration of urine material components in the material composition processing system 100 has been described above. Specifically, in... Figure 6In step S40, during the determination process, the control unit 10A of the first processing device 10 determines whether the predetermined determination item meets the review criteria. The control unit 10A will be described in detail below. Figure 6 The determination process in step S40 refers to the determined items and review conditions.

[0270] When selected by the user Figure 8 When the setting button 7A is pressed in the operation bar 7 of the status screen 61 shown, the output unit 11F displays the setting screen 55 on the display unit 16.

[0271] Figure 16 This is a diagram showing an example of a setup screen 55. Setup screen 55 is a screen for setting up various functions in the urine material composition analyzer 70. For example, setup screen 55 includes buttons for registering and deleting user operator accounts in the first processing unit 10. When the user selects the automatic review request confirmation button 55A on setup screen 55, output unit 11F displays the automatic review request confirmation screen 56 on display unit 16.

[0272] Figure 17 This is a diagram illustrating an example of an automatic review request determination screen 56 (graphical user interface), which is, or may be, part of some implementations of a condition setting element in a graphical user interface. Automatic review request determination screen 56 is a screen for selecting the type of determination item referenced by control unit 10A to execute an automatic review request. An automatic review request is a review request executed by the first processing unit 10 when the determination item meets review conditions, regardless of the user's intent.

[0273] like Figure 17 As shown, the types of projects include marking, material composition projects, and qualitative testing projects.

[0274] A marker refers to an event that occurs during the testing of a sample and is to be monitored. The occurrence status of an event is represented by a marker indicating whether it has occurred or not. In some implementations, this can be a predefined condition, on which it is determined whether the material composition image needs to be reclassified. Therefore, the event to be monitored is referred to as a "marker," and the occurrence of the event to be monitored is referred to as a "generated marker." In this case, in some implementations, it is determined that the material composition image needs to be reclassified.

[0275] Material composition items refer to the types of material components that can be analyzed in the urine material composition analyzer 70.

[0276] Qualitative test items refer to each of the qualitative test items that can be analyzed in the urine qualitative analysis device 30.

[0277] Within the defined project, there are selection lists 56A, 56B, and 56C for setting whether to set the corresponding defined project as a defined target for each type of review condition. Each of selection lists 56A, 56B, and 56C includes an option "OK" for setting the corresponding defined project as a defined target for review conditions and an option "Uncertain" for not setting the corresponding defined project as a defined target for inspection conditions. The user sets the options in selection lists 56A, 56B, and 56C through operation unit 17. Figure 17 In the example of the automatic review request determination screen 56 shown, all determination items, including labels, material composition items, and qualitative test items, are set as the determination targets of the review conditions, such that at least one of the labels, material composition items, and qualitative test items can be a predefined condition, and the material composition image is automatically reclassified based on the predefined condition.

[0278] In the automatic review request determination screen 56, setting buttons are provided for each type of the determined item to set the review conditions for the determined item. The flag setting button 56D is used to set the review conditions for flags. The threshold setting button 56E is used to set the review conditions for material composition items. The threshold setting button 56F is used to set the review conditions for qualitative testing items.

[0279] When the user selects the setting button corresponding to the item for which the review criteria are defined, the user generates review criteria via the review criteria setting screen 57 displayed on the display unit 16. After generating the review criteria, the user selects the apply button 56G and then the save button 56H. The control unit 10A updates the review criteria by selecting the apply button 56G, and stores the updated review criteria in the storage unit 15 by selecting the save button 56H.

[0280] When the user selects the close button 561, the output unit 11F closes the automatic review request confirmation screen 56 and displays the settings screen 55 on the display unit 16.

[0281] Figure 18 This is an example diagram showing the logo condition setting screen 57A, which is the logo review condition setting screen 57. (See diagram for reference.) Figure 18 As shown, on the labeling condition setting screen 57A, for example, a list of possible error items in the urine qualitative analysis device 30 is displayed. When the list of error items cannot be fully displayed on the labeling condition setting screen 57A, the user moves the scroll bar 57X vertically to scroll the labeling condition setting screen 57A, and all error items are displayed on the labeling condition setting screen 57A.

[0282] Each erroneous item is associated with a validity field 57D. In validity field 57D, the user sets it to "valid" or "invalid." By setting validity field 57D to "valid," review criteria are generated that must be met when the corresponding erroneous item occurs. When validity field 57D is set to "invalid," no review criteria are generated for the corresponding erroneous item. In other words, the user edits validity field 57D to set the review criteria to be determined.

[0283] For example, when the validity field 57D in the error item “Qualitative item anomaly: abnormal coloring” is set to “valid”, a satisfactory review condition will be generated when the urine qualitative test results of the sample include test results that identify abnormal coloring.

[0284] When the confirmation button 57Y is selected, the control unit 10A temporarily stores the review conditions generated in the flag condition setting screen 57A in the RAM 13. When the close button 57Z is selected, the output unit 11F closes the flag condition setting screen 57A and displays the automatic review request confirmation screen 56 on the display unit 16.

[0285] When the urine qualitative analysis device 30 is in Figure 6 During the qualitative analysis of the sample in step S40, the control unit 10A retrieves error information from the server 35 related to the urine qualitative analysis device 30, which has the same sample ID as the sample ID retrieved in step S10. The server 35 stores error information that records anomalies occurring in the urine qualitative analysis device 30 and associates these anomalies with the sample ID of the sample. When the retrieved error information includes information indicating that at least one of the error items is set to "valid" in the validity field 57D of the flag condition setting screen 57A, the control unit 10A determines that the review conditions are met.

[0286] The output unit 11F can display a list of errors that may occur in each of the devices in the material composition processing system 100 on the review condition setting screen 57. Specifically, the output unit 11F displays a list of possible errors in each of the first processing device 10, the urine qualitative analysis device 30, the server 35, and the urine material composition analysis device 70 on the flag condition setting screen 57A. Here, based on the user's settings in the flag condition setting screen 57A, the control unit 10A generates review conditions for flags for at least one of the first processing device 10, the urine qualitative analysis device 30, the server 35, and the urine material composition analysis device 70.

[0287] exist Figure 6In step S40, the control unit 10A retrieves error information from the server 35, which stores error information for each of the devices linked to the same sample ID as the sample ID retrieved in step S10, including the first processing device 10, the urine qualitative analysis device 30, the server 35, and the urine material composition analysis device 70. When the retrieved error information includes information indicating that at least one of the error items is set to "valid" in the validity field 57D of the flag condition setting screen 57A, the control unit 10A determines that the review conditions are met.

[0288] When an error occurs on the review condition setting screen 57 where the validity field 57D is set to "valid", it is recommended to recalculate the calculated concentration of urine material components. Therefore, when at least one of the review conditions of the first processing device 10, the urine qualitative analysis device 30, the server 35, and the urine material component analysis device 70 is met, the control unit 10A sends the material component image 3 of the sample to the second processing device 20 to request review.

[0289] It should be understood that the control unit 10A can directly acquire error information generated from each of the first processing device 10, the urine qualitative analysis device 30, the server 35, and the urine material composition analysis device 70.

[0290] Figure 19 This is a diagram showing an example of the material composition condition setting screen 57B, which is the review condition setting screen 57 for the material composition item.

[0291] like Figure 19 As shown, the validity field 57D, the project field 57E, the threshold field 57F, the grade field 57G, and the display value field 57H are displayed on the material composition condition setting screen 57B.

[0292] For example, in field 57E, all types of material components that can be analyzed by the urine material composition analyzer 70 are displayed.

[0293] In the threshold field 57F, the user sets a threshold for the quantity concentration of the material composition type corresponding to the row direction. The threshold field 57F is user-editable, allowing the setting of thresholds for the quantity concentration of different material composition types. The quantity concentration threshold also includes comparison information. This comparison information indicates the magnitude relationship between the quantity concentration and the threshold, such as indicating that the quantity concentration is "matches the threshold," "threshold or higher," "threshold or lower," "below the threshold," or "above the threshold." The threshold setting is displayed in the display value field 57H.

[0294] In the grade field 57G, the user sets the interval information for the quantity concentration of the material component type corresponding to the row direction. The grade field 57G can be edited by the user, setting the interval information for the quantity concentration of the material component type. The interval information refers to the situation for each group when dividing the quantity concentration into a predetermined number of groups, for example, starting from the lowest quantity concentration and sequentially designated as "Level 1," "Level 2," and "Level 3." The user sets values ​​for the same type of material component in either the threshold field 57F or the grade field 57G.

[0295] For example, when the RBC threshold is set to "1.0 µL or greater" and the RBC validity field 57D is set to "valid", a review condition is generated that is met when the RBC concentration in the sample is 1.0 µL or more. Similarly, when the RBC level is set to "Level 1" and the RBC validity field 57D is set to "valid", a review condition is generated that is met when the RBC concentration in the sample is within the Level 1 range.

[0296] When the confirmation button 57Y is selected, the control unit 10A temporarily stores the review conditions generated in the material composition condition setting screen 57B in the RAM 13. When the close button 57Z is selected, the output unit 11F closes the material composition condition setting screen 57B and displays the automatic review request confirmation screen 56 on the display unit 16.

[0297] When the validity field 57D is set to "invalid", review criteria based on the quantity concentration in the corresponding material composition type will not be generated.

[0298] exist Figure 6 In step S40, the control unit 10A refers to the quantity concentration of the material component type calculated by the calculation unit 11C in step S30. When the quantity concentration of at least one type of material component is set to "valid" in the validity field 57D of the material component condition setting screen 57B, the control unit 10A determines that the review conditions are met.

[0299] Figure 20 This is an example of a qualitative condition setting screen 57C, which is the review condition setting screen 57 for a qualitative test item.

[0300] like Figure 20 As shown, the qualitative condition setting screen 57C displays the validity field 57D, the item field 57J, and the grade field 57K.

[0301] For example, in item field 57J, all qualitative items that can be analyzed by urine qualitative analysis device 30 are displayed.

[0302] In the Rank field 57K, the user sets the threshold or interval information for qualitative items corresponding to the row direction. The user can edit the Rank field 57K and set the threshold or interval information for the corresponding qualitative items.

[0303] For example, when the URO level is set to "NORMAL" and the URO validity field 57D is set to "Valid", a review condition is generated that is met when the URO value in the sample is within the range associated with "NORMAL". Similarly, when the creatinine threshold, i.e., CRE, is set to "10 mg / dL or higher" and the CRE validity field 57D is set to "Valid", a review condition is generated that is met when the CRE value in the sample is 1.0 mg / dL or higher.

[0304] On the qualitative condition setting screen 57C, the name of the grade field 57K corresponding to the type of the qualitative item can be replaced with a name such as "hue" or "concentration," which allows users to intuitively understand the setting content.

[0305] When the confirmation button 57Y is selected, the control unit 10A temporarily stores the review conditions generated in the qualitative condition setting screen 57C in the RAM 13. When the close button 57Z is selected, the output unit 11F closes the qualitative condition setting screen 57C and displays the automatic review request confirmation screen 56 on the display unit 16.

[0306] When the validity field 57D is set to "invalid", no review criteria based on the corresponding qualitative item value are generated.

[0307] exist Figure 6 In step S40, the control unit 10A refers to the sample ID stored in the server 35 and the urine qualitative test results linked to the sample ID, which are the same as the sample ID obtained in step S10. When the value of at least one qualitative item in the validity field 57D of the qualitative condition setting screen 57C is set to "valid" meets the conditions set in the grade field 57K, the control unit 10A determines that the review conditions are met.

[0308] Therefore, when it is determined that the project meets the review conditions received by the receiving unit 11G through the flag condition setting screen 57A, the material composition condition setting screen 57B, and the qualitative condition setting screen 57C, the control unit 10A transmits the material composition image 3 of the sample to the second processing device 20 and sends a review request to the second processing device 20.

[0309] exist Figure 6In step S40, when at least one determined item meets the review conditions, the control unit 10A can proceed to step S170. However, when all of the multiple predetermined determined items meet their respective review conditions, the control unit 10A can proceed to step S170. For example, when Figure 19 When the concentrations of RBCs and DRBCs (deformed red blood cells) in the material composition setting screen 57B meet the review conditions, the control unit 10A can proceed to step S170. A combination of multiple determined items can be any combination of types within the same determined item, or a combination of different types from different determined items.

[0310] When review conditions are generated for a determined item in each of the flag condition setting screen 57A, material composition condition setting screen 57B, and qualitative condition setting screen 57C, if the determined item meets the review conditions but is set to "not determined" by the selection lists 56A, 56B, and 56C of the automatic review request determination screen 56, that is, the automatic transmission setting is not performed on the determined item that meets the review conditions, and the control unit 10A does not send the review request to the second processing device 20. That is, the process proceeds to step S50 without proceeding to step S180. Therefore, the user can easily invalidate the determination target of each type of review condition in the determined item type by setting the selection lists 56A, 56B, and 56C without setting the validity field 57D, which has been set to "valid", back to "invalid".

[0311] In this embodiment, step S40 determines whether the selected item meets the review criteria, and step S170 determines whether to automatically transmit the selected item to the second processing device 20 for the selected item that meets the review criteria. In another embodiment, it can be determined after step S30 whether there are selected items for which automatic transmission settings are applied to the second processing device 20. When such items exist, the review criteria can be determined only for those selected items, and if the review criteria are met, the process proceeds to step S180. Here, only the review criteria for the selected items for which automatic transmission settings are applied need to be checked. Therefore, the necessity of automatic transmission can be effectively determined.

[0312] In each of the embodiments, processor (or circuitry) refers to a processor in a broad sense and includes general-purpose processors (such as central processing units (CPUs)) or special-purpose processors (such as graphics processing units (GPUs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or programmable logic devices).

[0313] In each of the embodiments, the operation of the processor (or circuitry) can be implemented by a single processor or in collaboration with multiple processors located in physically separate locations. The order of processor operation is not limited to the order described in each of the embodiments and can be changed as appropriate.

[0314] The first processing apparatus 10 according to an embodiment has been described above. The embodiment may be in the form of a program for causing a computer to perform the functions of each unit in the first processing apparatus 10. The embodiment may be in the form of a computer-readable non-transitory storage medium storing the program.

[0315] The configuration of the first processing device 10 described in the above embodiments is exemplary and can be changed depending on the situation without departing from the scope of this disclosure. The display of the material composition image 3 is not limited to the above embodiments, and the material composition image 3 can be displayed horizontally side-by-side. The display position of each of the buttons can be appropriately changed.

[0316] The processing flow of the program described in the above embodiments is exemplary, and unnecessary steps can be deleted, new steps can be added, or the processing order can be changed without departing from the scope of this disclosure.

[0317] In the above embodiments, it has been described that the process according to the embodiments is implemented by software configuration through computer execution of a program. However, this disclosure is not limited thereto. For example, the embodiments can be implemented by hardware configuration or by a combination of hardware and software configuration.

[0318] The aspects of this disclosure will be described below.

[0319] The information processing apparatus according to a first aspect includes: an acquisition unit configured to acquire a material composition image obtained by imaging a material composition in a sample; a first classification unit configured to classify the material composition image acquired by the acquisition unit into any one of a predetermined category corresponding to the material composition; a transmission unit configured to transmit the material composition image to a data management device via a network line; a receiving unit configured to receive from the data management device a classification result of the material composition image classified by the data management device; and an output unit configured to output at least one of a first state, a second state, and a third state regarding the reclassification of the material composition image, wherein the first state indicates a state after the first classification unit has classified the material composition image into the predetermined category and indicates a state awaiting an instruction to send the material composition image to the data management device, the second state indicates a state awaiting the receipt of the classification result from the data management device, and the third state indicates a state receiving the classification result from the data management device.

[0320] According to the second aspect, in the information processing apparatus according to the first aspect, the third state includes a fourth state indicating that a classification result has been received from the data management device and the classification result does not include an instruction for a predetermined test, and a fifth state indicating that the classification result has been received from the data management device and the classification result includes an instruction for a predetermined test.

[0321] According to a third aspect, in an information processing apparatus according to the first or second aspect, the output unit is configured to display at least one of the first state, the second state, and the third state on a display unit.

[0322] According to the fourth aspect, in the information processing apparatus according to the first or second aspect, the output unit is configured to display on the display unit any one of the first state, the second state, and the third state for each sample.

[0323] According to the fifth aspect, the information processing apparatus according to any one of the first to fourth aspects further includes a calculation unit configured to calculate the quantity concentration of material components in a sample based on the number of material component images classified into a predetermined category by the first classification unit.

[0324] According to the sixth aspect, in the information processing apparatus according to the fifth aspect, the first state represents the state after the quantity concentration has been calculated by the calculation unit.

[0325] The information processing system according to the seventh aspect includes: an information processing apparatus according to any one of the first to sixth aspects; and a data management apparatus connected to the information processing apparatus via a network line, the data management apparatus including: a second classification unit configured to classify material composition images received from the information processing apparatus; and a return unit configured to return the classification result of the second classification unit to the information processing apparatus.

[0326] The information processing method of the information processing apparatus according to the eighth aspect includes the following steps: acquiring a material composition image obtained by imaging a material composition in a sample; classifying the material composition image into any one of a predetermined category corresponding to the material composition; transmitting the material composition image to a data management device via a network line; receiving from the data management device a classification result of the material composition image being classified by the data management device; and outputting at least one of a first state, a second state, and a third state regarding the reclassification of the material composition image, wherein the first state indicates a state after classifying the material composition image into the predetermined category and indicates a state awaiting an instruction to send the material composition image to the data management device, the second state indicates a state awaiting the receipt of the classification result from the data management device, and the third state indicates a state receiving the classification result from the data management device.

[0327] The information processing procedure according to the ninth aspect causes a computer to perform a process comprising the following steps: acquiring a material composition image obtained by imaging the material composition in a sample; classifying the material composition image into any one of a predetermined category corresponding to the material composition; transmitting the material composition image to a data management device via a network line; receiving from the data management device a classification result of the material composition image classified by the data management device; and outputting at least one of a first state, a second state, and a third state regarding the reclassification of the material composition image, wherein the first state indicates a state after classifying the material composition image into the predetermined category and indicates a state awaiting an instruction to send the material composition image to the data management device, the second state indicates a state awaiting the receipt of the classification result from the data management device, and the third state indicates a state receiving the classification result from the data management device.

[0328] Furthermore, this disclosure relates to the following aspects, which may be combined with any aspect disclosed herein:

[0329] B1. An apparatus for classifying the composition of materials, said apparatus comprising a circuit configured to:

[0330] Acquire a material composition image, wherein the material composition image presents the material composition of the sample;

[0331] The material composition images are classified into material composition types by associating each one of them with a material composition type; and

[0332] Displaying a graphical user interface, wherein the graphical user interface includes a first state element and a second state element, wherein the first state element indicates an unapproved state as a result obtained based on the classification of the material composition image, and wherein the second state element indicates a review status of the classified material composition image, and wherein the classified material composition image is associated with either the first state element or the second state element based on the corresponding classification result of classifying the material composition image.

[0333] B2. The device according to B1, wherein the graphical user interface includes an approval element displayed when the user operates the first state element, wherein the approval element is configured to display information associated with the classified material composition image based on the classified material composition image.

[0334] B3. The device according to B2, wherein the information of the associated classified material composition image includes at least one of material composition concentration and qualitative test results.

[0335] B4. The device according to B2 or B3, wherein the approval element is configured to receive user input, and wherein the circuitry is further configured to transmit an associated, classified material composition image to a remote processing device for reclassification based on the received user input.

[0336] B5. The device according to any one of B2 to B4, wherein the circuitry is further configured to determine the concentration of a certain type of material component in a sample based on the number of material component images classified as such material components.

[0337] B6. The device according to any one of B1 to B5, wherein the second state element indicates the state of review of a reclassified material composition image that is undergoing reclassification.

[0338] B7. The device according to any one of B1 to B6, wherein the graphical user interface includes a third status element indicating the pending approval status of the reclassified component image.

[0339] B8. The device according to B7, wherein when a user operates the third state element, the associated reclassified component image is approved.

[0340] B9. The apparatus according to any one of B1 to B8, wherein the circuitry is further configured to automatically determine, based on predefined conditions, a reclassification of the classified material composition image, wherein

[0341] Reclassification is performed with higher classification accuracy than that of the material composition image.

[0342] B10. The device according to B9, wherein the predefined conditions can be configured by the user.

[0343] B11. The device according to B10, wherein the graphical user interface includes a condition setting element configured to set the predefined conditions based on user input.

[0344] B12. The device according to B11, wherein the condition setting element includes at least one of material composition condition setting and qualitative condition setting.

[0345] B13. A system for classifying material composition, the system comprising: a device according to any one of B1 to B13 as a first processing unit; and a remote processing unit as a second processing unit, wherein the first processing unit and the second processing unit are each configured to communicate with each other via a network, wherein the second processing unit includes circuitry configured to:

[0346] The classified material composition image is obtained from the first processing device;

[0347] The system receives operator input based on a graphical user interface; and

[0348] Based on the received operator input, the material composition image in the obtained classified material composition image is reclassified, and the reclassification is performed with a higher classification accuracy than the classification of the classified material composition image.

[0349] B14. A method for classifying the composition of materials, the method comprising the following steps:

[0350] Acquire a material composition image, wherein the material composition image presents the material composition of the sample;

[0351] The material composition images are classified into material composition types by associating each one of them with a material composition type; and

[0352] Displaying a graphical user interface, wherein the graphical user interface includes a first state element and a second state element, wherein the first state element indicates an unapproved state of the result obtained based on a classified material composition image, and wherein the second state element indicates a review status of the classified material composition image, and wherein the classified material composition image is associated with the first state element or the second state element based on a corresponding classification result of classifying the material composition image.

[0353] B15. A computer program for classifying the composition of materials, the computer program comprising instructions that, when executed by a processor, cause the processor to perform the method according to B14.

[0354] Furthermore, this disclosure relates to the following aspects, which may be combined with any aspect disclosed herein:

[0355] A1. An apparatus for classifying the composition of materials, the apparatus comprising a circuit configured to:

[0356] Acquire a material composition image, wherein the material composition image presents the material composition of the sample;

[0357] The material composition images are classified into material composition types by associating each one of them with a material composition type; and

[0358] Based on predefined conditions, the material composition image is automatically reclassified from the classified material composition image, wherein the reclassification is performed with a higher classification accuracy than the classification of the material composition image.

[0359] A2. The device according to A1, wherein the predefined conditions are associated with the concentration of a material component of the sample.

[0360] A3. The device according to A2, wherein the circuitry is further configured to determine the concentration of a certain type of material component in a sample based on the number of material component images classified as such material components.

[0361] A4. The device according to any one of A1 to A3, wherein the predefined conditions are associated with the classification accuracy of the material composition classification.

[0362] A5. The device according to A4, wherein the classification accuracy is specific to classifying material composition images into a specific type of material composition.

[0363] A6. The device according to any one of A1 to A5, wherein the predefined conditions are associated with a quality value.

[0364] A7. The apparatus according to A6, wherein the quality value is obtained by measuring the quality of the sample.

[0365] A8. The device according to any one of A6 or A7, wherein the circuitry is further configured to measure the mass of the sample to obtain the mass value.

[0366] A9. The device according to A7 or A8, wherein the predefined conditions are further associated with error information indicating an anomaly associated with a quality measurement of the sample.

[0367] A10. The device according to any one of A1 to A9, wherein the predefined conditions can be configured by the user.

[0368] A11. The device according to any one of A1 to A10, wherein the circuitry is further configured to transmit a classified material composition image for reclassification to a remote processing device.

[0369] A12. The device according to A11, wherein the circuitry is further configured to determine a set of classified material composition images, and to perform reclassification based on the set.

[0370] A13. The device according to A12, wherein the determined set of classified material composition images is sent to the remote processing device.

[0371] A14. The device according to any one of A11 to A13, wherein the circuitry is configured to further transmit classification information associated with the classified material composition image to the remote processing device.

[0372] A15. The device according to any one of A1 to A14, wherein the circuit is further configured to determine whether the predefined condition is satisfied.

[0373] A16. The device according to A15, wherein the step of determining whether a predefined condition is met includes determining at least one of the following: the magnitude relationship between the concentration of a material component of a user-specified type and a user-specified threshold; the magnitude relationship between a quality value representing a qualitative test result of a sample and a threshold; and the occurrence status of a user-specified error item among error items in an error message.

[0374] A17. The device according to any one of A1 to A16, wherein the sample is urine.

[0375] A18. An apparatus for reclassifying the composition of materials, the apparatus comprising a circuit configured to:

[0376] By associating each of the material composition images with a material composition type, the classified material composition images are classified into the type of material composition, wherein reclassification is performed with a higher classification accuracy than the classification of the classified material composition images.

[0377] A19. A system for classifying the composition of materials, the system comprising:

[0378] The device according to any one of A1 to A17 is the first processing apparatus;

[0379] As a remote processing device, the first processing device and the second processing device are each configured to communicate with each other via a network, wherein the second processing device includes circuitry configured to:

[0380] The classified material composition image is obtained from the first processing device; operator input is received based on the graphical user interface; and

[0381] Based on the received operator input, the material composition image in the obtained classified material composition image is reclassified, and the reclassification is performed with a higher classification accuracy than the classification of the classified material composition image.

[0382] A20. The system according to A19, wherein the operator input includes at least one of the following: selecting a material composition image, selecting a classification of the material composition, and selecting a reclassification method.

[0383] A21. The system according to A19 or A20, wherein the circuitry of the second processing device is further configured as follows:

[0384] The reclassification results of the material composition image are transmitted to the first processing device.

[0385] A21. A method for classifying the composition of materials, the method comprising the following steps:

[0386] Acquire a material composition image, wherein the material composition image presents the material composition of the sample;

[0387] The material composition images are classified into material composition types by associating each one of them with a material composition type; and

[0388] Based on predefined conditions, the material composition image is automatically reclassified from the classified material composition image, wherein the reclassification is performed with a higher classification accuracy than the classification of the material composition image.

[0389] A22. A computer program for classifying material composition, the computer program comprising instructions that, when executed by a processor, cause the processor to perform the method according to A21.

[0390] Industry Applicability

[0391] According to this disclosure, an apparatus and method for classifying the composition of materials can be provided.

Claims

1. An apparatus for classifying the composition of materials, the apparatus comprising a circuit configured to: Obtain material composition images, where, The material composition image presents the material composition of the sample; The material composition images are classified into material composition types by associating each image with a material composition type; and Displaying a graphical user interface, wherein the graphical user interface includes a first state element and a second state element, wherein the first state element indicates an unapproved state as a result obtained based on the classification of the material composition image, and wherein the second state element indicates a review status of the classified material composition image, and wherein the classified material composition image is associated with either the first state element or the second state element based on the corresponding classification result of classifying the material composition image.

2. The device according to claim 1, wherein, The graphical user interface includes an approval element displayed when the user interacts with the first status element, wherein the approval element is configured to display information associated with the classified material composition image based on the classified material composition image.

3. The device according to claim 2, wherein, The information in the associated classified material composition image includes at least one of the material composition concentration and qualitative test results.

4. The device according to claim 2 or 3, wherein, The approval element is configured to receive user input, wherein the circuitry is further configured to transmit an associated, classified image of material composition to a remote processing device for reclassification based on the received user input.

5. The device according to any one of claims 2 to 4, wherein, The circuit is further configured to determine the concentration of a material component of a certain type in the sample based on the number of material component images classified as such.

6. The device according to any one of the preceding claims, wherein, The second status element indicates the status of the reclassified material composition image under review.

7. The device according to any one of the preceding claims, wherein, The graphical user interface includes a third status element indicating the pending approval status of the reclassified component images.

8. The device according to claim 7, wherein, When the user interacts with the third state element, the associated reclassified component image is approved.

9. The device according to any one of the preceding claims, wherein, The circuit is further configured to automatically determine, based on predefined conditions, to reclassify the material composition image of the classified material composition image, wherein the reclassification is performed with a higher classification accuracy than the classification of the material composition image.

10. The device according to claim 9, wherein, The predefined conditions are configurable by the user.

11. The device according to claim 10, wherein, The graphical user interface includes a condition setting element configured to set the predefined conditions based on user input.

12. The device according to claim 11, wherein, The condition setting elements include at least one of material composition condition settings and qualitative condition settings.

13. A system for classifying the composition of materials, the system comprising: The apparatus as a first processing device according to any one of claims 1 to 13; as well as As a remote processing device, the first processing device and the second processing device are each configured to communicate with each other via a network, wherein the second processing device includes circuitry configured to: The classified material composition image is obtained from the first processing device; The system receives operator input based on a graphical user interface; and Based on the received operator input, the material composition image in the obtained classified material composition image is reclassified, and the reclassification is performed with a higher classification accuracy than the classification of the classified material composition image.

14. A method for classifying the composition of materials, the method comprising the following steps: Acquire a material composition image, wherein the material composition image presents the material composition of the sample; The material composition images are classified into material composition types by associating each one of them with a material composition type; and Displaying a graphical user interface, wherein the graphical user interface includes a first state element and a second state element, wherein the first state element indicates an unapproved state of the result obtained based on a classified material composition image, and wherein the second state element indicates a review status of the classified material composition image, and wherein the classified material composition image is associated with the first state element or the second state element based on a corresponding classification result of classifying the material composition image.

15. A computer program for classifying material composition, the computer program comprising instructions that, when executed by a processor, cause the processor to perform the method according to claim 14.

Images