Specimen color tone determining device, automated analysis device, and specimen color tone determining method

Abstract

This specimen color tone determining device comprises: an image acquiring unit 203 that acquires an image of a specimen container 105 accommodating a specimen; a specimen container identifying unit 204 that subjects the image to image processing to acquire container color tone information relating to the color tone of the specimen container 105; an image correcting unit 206; and a specimen color tone determining unit 207 that determines the color tone of the specimen using the container color tone information. The present invention thereby provides a specimen color tone determining device, an automated analysis device, and a specimen color tone determining method with which stable sample color tone determination is achieved regardless of the type of a specimen container.

Description

Specimen Color Tone Determination Device, Automatic Analyzer, and Specimen Color Tone Determination Method

[0001] The present invention relates to a specimen color tone determination device, an automatic analyzer, and a specimen color tone determination method suitable for an automatic analyzer that qualitatively or quantitatively analyzes biological specimens such as blood and urine (hereinafter referred to as specimens).

[0002] Patent Document 1 discloses that, from a plurality of viewpoints, one or more images of a sample container are acquired using a backlight, the one or more images from the plurality of viewpoints are processed, and region classification is determined for each viewpoint to obtain segmentation information for each viewpoint. A semantic map is generated from the segmentation information for each viewpoint, a synthetic viewpoint where serum or plasma components are visible is selected from the semantic map, and for the synthetic viewpoint, front semantic data from the synthetic viewpoint and back semantic data from the back side of the sample container opposite to the synthetic viewpoint are identified. Then, while considering the back semantic data, the HILN of serum or plasma components is determined based on the front semantic data using a HILN classifier.

[0003] Patent No. 6879366

[0004] In the field of clinical examinations including biochemical examinations, automatic analyzers are generally used. An automatic analyzer performs qualitative and quantitative analysis by adding and reacting a reagent that specifically reacts with a specific component contained in a specimen such as blood and urine, and measuring the absorbance or luminescence of the reaction solution.

[0005] In an automatic analyzer, it is desired to early determine whether a specimen is in an appropriate state for being subjected to an examination in order to omit unnecessary examinations, reduce the consumption of consumables and reagents, and improve the reliability of examination results.

[0006] As such techniques, methods have been proposed for detecting the liquid level position of a specimen by image processing and estimating the amount of the specimen based on the detected liquid level position, and methods for estimating the degree of hemolysis or turbidity of the specimen.

[0007] For example, Patent Document 1 describes an automated analysis system that determines the color tone of a sample contained in a sample container using images acquired by a camera. Patent Document 1 states that the color tone level of the sample is determined using images acquired from multiple viewpoints on the side of the sample container.

[0008] Here, the materials used for sample containers in the field include not only transparent polystyrene (PS) but also opaque polypropylene (PP), and specifications such as thickness are not uniform. Therefore, even if the exact same sample is contained in each container, the appearance when viewed from the outside will differ depending on whether the sample container is made of PS or PP. Furthermore, the appearance will also differ depending on the thickness of the sample container wall, even if the material is the same.

[0009] Given these circumstances, when photographing a sample container containing a sample—that is, photographing the sample through the container wall and determining the sample's color from the resulting image—the color of the sample container may significantly affect the reliability of the color determination. This is particularly likely to have a large impact on the turbidity index.

[0010] Our investigation has revealed that the prior art described in Patent Document 1 above has room for improvement, as there is room to avoid the influence of color differences due to the type of sample container in the color determination of the sample.

[0011] This invention has been made in view of the above-mentioned problems, and aims to provide a sample color determination device, an automated analyzer, and a sample color determination method that can achieve stable color determination of a sample regardless of the type of sample container.

[0012] The present invention includes multiple means for solving the above problems, but one example is a specimen color determination device for determining the color tone of a specimen, comprising: an image acquisition unit for acquiring an image of a specimen container containing the specimen; a container color information acquisition unit for acquiring container color information relating to the color tone of the specimen container by image processing the image; and a specimen color determination unit for determining the color tone of a specimen using the container color information.

[0013] According to the present invention, stable color determination of a sample can be achieved regardless of the type of sample container. Other problems, configurations, and effects will be clarified by the following description of the examples.

[0014] This is a top view showing the schematic configuration of an automated analyzer equipped with a sample color determination device according to Example 1. This is a diagram showing the functional block configuration of the sample color determination device according to Example 1. This is a diagram showing an example of reference table data of material and correction values ​​stored in the sample color determination device according to Example 1. This is a diagram showing an example of a GUI (Graphical User Interface) displayed by the sample color determination device according to Example 1. This is a flowchart of a series of processes of the control unit in the sample color determination device according to Example 1. This is a diagram showing the functional block configuration of the sample color determination device according to Example 2. This is a flowchart of a series of processes of the control unit in the sample color determination device according to Example 2.

[0015] Examples of the sample color determination apparatus, automated analyzer, and sample color determination method of the present invention will be described below with reference to the drawings. In the drawings used herein, the same or corresponding components are denoted by the same or similar reference numerals, and repeated descriptions of these components may be omitted.

[0016] Examples of the automated analyzer of the present invention will be described below with reference to the drawings. It goes without saying that in the following embodiments, the components (including elemental steps, etc.) are not necessarily essential unless specifically indicated or considered fundamentally essential. Furthermore, in the drawings used herein, identical or corresponding components are denoted by the same or similar reference numerals, and repeated explanations of these components may be omitted.

[0017] <Example 1> Example 1 of the sample color determination device, automatic analyzer, and sample color determination method of the present invention will be described with reference to Figures 1 to 5.

[0018] First, the overall configuration of the automated analyzer equipped with a sample color determination device will be explained using Figure 1. Figure 1 is a top view showing an overview of the automated analyzer.

[0019] The automated analyzer 100 shown in Figure 1 is a device for analyzing a sample, and includes a sample supply unit 102 equipped with a sample inlet 102a and an outlet 102b for the sample 101, an analysis module 103 that dispenses a fixed amount of the sample 101 and performs measurement, and a transport unit 104 that transports the sample 101.

[0020] Within the automated analyzer 100, in order to protect the sample 101 and to improve work efficiency, the sample container 105 containing the sample 101 is transported while stored in a sample rack 106. The sample rack 106 may be a multi-rack system or a single-rack system. In Figure 1, arrow D indicates the transport direction of the sample rack 106.

[0021] The transport unit 104 has an input rack transport path 104a for transporting sample racks 106 from the sample supply unit 102 to the analysis module 103, an output rack transport path 104b for transporting sample racks 106 from the analysis module 103 to the sample supply unit 102, and a connecting transport path 104c that connects the input rack transport path 104a and the output rack transport path 104b. Within the input rack transport path 104a, a sample dispensing position 104d is provided in the area for dispensing samples in the analysis module 103.

[0022] Next to the loading rack transport path 104a, a camera 107 focused on the loading rack transport path 104a and a light 108 illuminating the loading rack transport path 104a are fixed near the exit from the sample supply unit 102 to the analysis module 103.

[0023] The control device 109 is connected to each of the devices in the automated analyzer 100 described above by wire or wireless connection, and controls the operation of each device in the automated analyzer 100. The control of the operation of each device by this control device 109 is performed based on various programs recorded in a storage device (not shown). In addition to various programs used for measuring the sample, the storage device stores various parameters input via the input device 201 (see Figure 2), information on the sample to be measured (such as sample type information), and measurement results.

[0024] Although Figure 1 shows the control device 109 as being independent of the sample supply unit 102 and analysis module 103 of the automatic analyzer 100, it may also be located within one of the modules.

[0025] The control processing for the operations performed by this control device 109 may be combined into a single program, divided into multiple programs, or a combination of these. Furthermore, some or all of the programs may be implemented using dedicated hardware or may be modularized.

[0026] The above describes the overall configuration of the automated analyzer 100.

[0027] Next, the details of the functions of the sample color determination device, including the control device 109 in the automated analyzer 100 of this embodiment, will be explained with reference to Figures 2 to 4. Figure 2 is a functional block diagram showing the details of the functions of the sample color determination device.

[0028] As shown in Figure 2, in addition to the input device 201 and the display device 202, the control device 109 is equipped with various functional blocks such as an image acquisition unit 203, a sample container identification unit 204, a storage unit 205, an image correction unit 206, a sample color determination unit 207, and an operation control unit 208 that controls the operation of various mechanisms.

[0029] Of this control device 109, the image acquisition unit 203, sample container identification unit 204, storage unit 205, image correction unit 206, and sample color determination unit 207, excluding the operation control unit 208, correspond to a sample color determination device that determines the color tone of a sample.

[0030] Of this sample color determination device, all except the storage unit 205 may be provided in the form of software within the control unit 109, but they can also be mounted separately from the operation control unit 208, etc., in the form of firmware or the like.

[0031] Furthermore, each function of the sample color determination device can be configured to be processed independently of the automatic analyzer 100, using a server or other means.

[0032] The image acquisition unit 203 acquires an image of the specimen container 105 containing the specimen, which was captured by the camera 107.

[0033] The memory unit 205 stores various parameters for the operation of each mechanism of the automatic analyzer 100, information about the sample, and various information necessary for the analysis of the sample, as well as correction value information for the image of the sample container 105 corresponding to the type of sample container 105.

[0034] This correction value information includes information to compensate for the influence of color (transparency) due to differences in the material and wall thickness of the sample container 105. For example, as shown in Figure 3, the R, G, and B values ​​for each material constituting the sample container 105 are pre-set and stored in the form of reference table data 300.

[0035] The specimen container identification unit 204 determines the type of specimen container 105 containing the specimen from the image of the specimen container 105 acquired by the image acquisition unit 203.

[0036] The image correction unit 206 corrects the image information of the sample container 105 by applying correction value information stored in the storage unit 205 that corresponds to the type of sample container 105 determined by the sample container identification unit 204.

[0037] These sample container identification unit 204 and image correction unit 206 constitute a container color information acquisition unit that processes the image to acquire container color information related to the color tone of the sample container 105. In this embodiment, the correction value information stored in the storage unit 205 is acquired as container color information.

[0038] The sample color determination unit 207 uses the image of the sample container 105 corrected by the image correction unit 206 to determine the color level (e.g., turbidity, hemolysis, yellowness) of the sample 101 contained within. For example, the sample color determination unit 207 corrects the RGB values ​​of the pixel values ​​in the area where the sample is located in the image using correction value information corresponding to the material associated with the identified sample container 105, and uses the corrected image to determine the color of the sample. The sample color determination unit 207 determines the color level by comparing it with a threshold value stored in the storage unit 205, and if it exceeds the threshold value, it cancels the dispensing of the sample or corrects the measurement results in the analysis module 103.

[0039] In addition, when the color tone level exceeds the threshold value, it is desirable that the specimen color tone determination unit 207 issue an alarm notifying the fact and display it on the display device 202.

[0040] Among the functions of the control device 109, the specimen container identification unit 204, the image correction unit 206, and the specimen color tone determination unit 207 can be configured to update the processing by, for example, providing a learned model obtained by machine learning of types and the like from a partial image or the entire image of various specimen containers 105.

[0041] It is also possible to display the above determination result on the display device 202 and present it to the user.

[0042] FIG. 4 shows an example of a GUI (Graphical User Interface) presented to the user. On the determination result display screen 620 of each specimen shown in FIG. 4, for example, a detection result display area 621, a specimen information display area 622, and an operation area 623 are displayed.

[0043] In the detection result display area 621, in addition to the image of the specimen container 105 captured by the camera 107, the determination result of the color tone of the specimen is superimposed and displayed. In FIG. 4, as an example, the upper end 501 and the lower end 502 of the specimen area, and the area 602 where the specimen can be acquired are displayed. In addition, when an object or a label is detected, the detection position of the object or the label may be displayed. Further, in addition to the method of showing the detection result by a rectangle as in the example of FIG. 4, for example, the specimen acquisition possible area may be shown by the upper end / lower end, or the specimen acquisition possible area may be shown for each pixel or small area.

[0044] In the specimen information display area 622, for example, the ID of the sample, information on whether it has been normally processed, the identification result of the container type by the specimen container identification unit 204, the amount of liquid that can be acquired, etc. are displayed. In addition, for example, the detection position of the specimen area such as the position of the upper end and the lower end of the specimen may be displayed numerically (not shown).

[0045] In the operation area 623, buttons for receiving user operations are displayed, and it is possible to switch the samples displayed in the detection result display area 621 and the specimen information display area 622.

[0046] Next, the processing content according to this embodiment that is preferably executed in the above-described automatic analyzer 100 will be described with reference to FIG. 5. FIG. 5 is a flowchart of a series of processes of the control unit in the automatic analyzer according to this embodiment, and the control main body of the operation is preferably the control device 109.

[0047] First, when the image acquisition unit 203 of the control device 109 is instructed to start analysis from the input device 201 by a user's operation, the operation control unit 208 causes the specimen rack 106 to be transported and acquires the image information of the specimen container 105 photographed by the camera 107 (step S1).

[0048] Next, the specimen container identification unit 204 of the control device 109 determines the type of the specimen container 105 based on the image information acquired in step S1 (step S2).

[0049] Next, the image correction unit 206 of the control device 109 corrects the image information of the specimen container 10 obtained in step S1 using the correction value information corresponding to the type of the specimen container 105 determined in step S2 and stored in the storage unit 205 (step S3).

[0050] Next, the specimen color tone determination unit 207 of the control device 109 compares the color tone level of the specimen 101 contained in the specimen container 105 with a threshold value stored in the storage unit 205 using the image information of the specimen container 105 corrected in S3, and makes a determination (step S4).

[0051] Next, the effects of this embodiment will be described.

[0052] The specimen color tone determination device according to the first embodiment of the present invention described above is a device that determines the color tone of a specimen, and includes an image acquisition unit 203 that acquires an image of a specimen container 105 that houses the specimen, a specimen container identification unit 204, an image correction unit 206 that performs image processing on the image to acquire container color tone information regarding the color tone of the specimen container 105, and a specimen color tone determination unit 207 that determines the color tone of the specimen using the container color tone information.

[0053] This configuration solves a problem in conventional technology where, when photographing the sample container 105 containing the sample, that is, photographing the sample through the sample container 105 and determining the color tone of the sample from the resulting image, there is a concern that the reliability of the determination result may decrease due to the influence of the color of the sample container 105. In other words, it becomes possible to determine the color tone of the sample regardless of the type of sample container 105, and highly reliable sample information can be obtained, thereby improving the reliability of the test results and the efficiency of the system compared to conventional methods.

[0054] Furthermore, the system includes a storage unit 205 that stores image correction value information corresponding to the type of sample container 105. The sample container identification unit 204 and the image correction unit 206 acquire the correction value information stored in the storage unit 205 as container color information. In particular, the sample color determination unit 207 determines the color by correcting the image using the correction value information, thereby identifying the type of sample container 105 and acquiring container color information. This allows for very high-speed color determination and improves sample processing.

[0055] Furthermore, since the correction value information stored in the memory unit 205 is information for correcting the influence of the color of the sample container 105, even faster judgment processing can be achieved.

[0056] <Example 2> The sample color determination device, automatic analyzer, and sample color determination method of Example 2 of the present invention will be described with reference to Figures 6 and 7. Figure 6 is a functional block diagram showing the details of the sample color determination device according to Example 2, and Figure 7 is a flowchart of a series of processes of the control unit in the automatic analyzer according to Example 2.

[0057] In the above-described embodiment 1, image processing was performed by applying correction value information corresponding to the type of sample container 105 that was stored in advance. In contrast, in the sample color determination device of embodiment 2, the pixel information acquisition unit 401 and the image correction unit 206A acquire first pixel information in a first region where no sample is present and second pixel information in a second region where a sample is present in the sample container 105 within the target image, and perform a process of subtracting the first pixel information from the second pixel information.

[0058] The configuration of the automated analyzer in Example 2 is equivalent to that of the automated analyzer 100 in Example 1, so illustrations and detailed descriptions are omitted.

[0059] The differences between the functional block diagram of the control device 109A in Embodiment 2 shown in Figure 6 and the functional block diagram of the control device 109 in Embodiment 1 shown in Figure 2 are that the configuration of the storage unit 205A and the image correction unit 206A are partially different, the pixel information acquisition unit 401 has been added, and the sample container identification unit 204 has been removed.

[0060] As described above, the pixel information acquisition unit 401 in the control device 109A shown in Figure 6 acquires, from the region of the sample container 105 in the image acquired by the image acquisition unit 203, first pixel information in the first region where no sample is present and second pixel information in the second region where a sample is present. The image correction unit 206A performs a process of subtracting the first pixel information from the second pixel information acquired by the pixel information acquisition unit 401. Then, the sample color determination unit 207 uses the second pixel information, from which the first pixel information has been subtracted, as sample-derived data to determine hemolysis, jaundice, etc.

[0061] The first region where no sample is present can be the region on the upper side of the sample container 105 where no sample is present, excluding the upper end and its vicinity, as well as the label, etc. More preferably, the region where not only the front side but also the back side and the background wall of the sample container 105 are visible from the camera 107, and even more preferably, the region where the difference in pixel value information with respect to the surrounding region is below a predetermined reference value (this can also be the average of multiple regions).

[0062] Next, the processing details related to this embodiment, which are suitably executed in the above-described automatic analyzer 100, will be explained with reference to Figure 7.

[0063] Step S11 in Figure 7 is the same as step S1 shown in Figure 5.

[0064] Next, the pixel information acquisition unit 401 of the control device 109A acquires, in the image acquired in step S1, first pixel information in the first region where no sample is present and second pixel information in the second region where a sample is present (step S12).

[0065] Next, the image correction unit 206A performs a process of subtracting the first pixel information from the second pixel information acquired by the pixel information acquisition unit 401 (step S13). Then, the sample color tone determination unit 207 of the control device 109 uses the image information of the sample container 105 corrected in S13 to compare the color tone level of the sample 101 in the sample container 105 with a threshold stored in the storage unit 205 and makes a determination (step S14).

[0066] The other configurations and operations are substantially the same as those of the sample color determination device, automatic analyzer, and sample color determination method described in Example 1 above, and details are omitted.

[0067] In the sample color determination device, automatic analyzer, and sample color determination method of Example 2 of the present invention, substantially the same effects as those of the sample color determination device, automatic analyzer, and sample color determination method of Example 1 described above can be obtained.

[0068] Furthermore, the pixel information acquisition unit 401 and the image correction unit 206A acquire, as container color information, first pixel information in a first region where no sample is present and second pixel information in a second region where a sample is present in the sample container 105 within the image. In particular, the pixel information acquisition unit 401 and the image correction unit 206A determine the color tone by subtracting the first pixel information from the second pixel information, thereby extracting image information of the sample container 105 from the image, and thus obtaining a more accurate color tone derived from the sample.

[0069] <Other> The present invention is not limited to the above embodiments, and various modifications are included. The above embodiments are described in detail for the purpose of clearly illustrating the present invention, and are not necessarily limited to those having all the configurations described.

[0070] Furthermore, it is possible to replace parts of the configuration of one embodiment with parts of the configuration of another embodiment, and it is also possible to add parts of the configuration of another embodiment to the configuration of one embodiment. In addition, it is possible to add, delete, or replace parts of the configuration of each embodiment with parts of other configurations.

[0071] 100...Automatic analyzer 101...Sample 102...Sample supply unit 102a...Inlet 102b...Outlet 103...Analysis module 104...Transport unit 104a...Inlet rack transport path 104b...Outlet rack transport path 104c...Connecting transport path 104d...Sample dispensing position 105...Sample container 106...Sample rack 107...Camera 108...Illumination 109, 109A...Control device 201...Input device 202...Display device 203...Image acquisition unit 204...Sample container identification unit (container color information acquisition unit) 205, 205A...Storage unit 206, 206A...Image correction unit (container color information acquisition unit) 207...Sample color determination unit 208...Operation control unit 300...Reference table data 401...Pixel information acquisition unit (container color information acquisition unit) 501...Upper edge 502...Lower edge 602...Area 620...Judgment result display screen 621...Detection result display area 622...Sample information display area 623...Operation area

Claims

1. A specimen color determination device for determining the color tone of a specimen, comprising: an image acquisition unit for acquiring an image of a specimen container containing the specimen; a container color information acquisition unit for acquiring container color information relating to the color tone of the specimen container by image processing the image; and a specimen color determination unit for determining the color tone of a specimen using the container color information.

2. A specimen color determination device according to claim 1, further comprising a storage unit for storing correction value information of the image corresponding to the type of specimen container, wherein the container color information acquisition unit acquires the correction value information stored in the storage unit as the container color information, and the specimen color determination unit determines the color by correcting the image using the correction value information.

3. A specimen color determination device according to claim 2, wherein the correction value information stored in the storage unit is information for correcting the influence of the color of the specimen container.

4. A sample color determination device according to claim 3, wherein the sample color determination unit determines the color by subtracting the correction value information from the image.

5. A sample color determination device according to claim 1, wherein the container color information acquisition unit acquires, as container color information, first pixel information in a first region where the sample is not present and second pixel information in a second region where the sample is present in the sample container in the image.

6. A sample color determination device according to claim 5, wherein the sample color determination unit determines the color by performing a process of subtracting the first pixel information from the second pixel information.

7. An automated analyzer comprising a sample color determination device according to any one of claims 1 to 6, for analyzing the sample.

8. A method for determining the color tone of a specimen, comprising: an image acquisition step of acquiring an image of a specimen container containing the specimen; a container color tone information acquisition step of acquiring container color tone information relating to the color tone of the specimen container by image processing the image; and a specimen color tone determination step of determining the color tone of the specimen using the container color tone information.

9. A sample color determination method according to claim 8, wherein the container color information acquisition step involves acquiring correction value information for the image corresponding to the type of sample container that has been previously acquired as container color information.

10. A sample color determination method according to claim 8, wherein the container color information acquisition step includes acquiring, as container color information, first pixel information in a first region where the sample is not present and second pixel information in a second region where the sample is present in the sample container in the image.

Images