JP6761717B2 - Information processing equipment and programs - Google Patents

Description

The present invention relates to a technique for supporting evaluation of a sample as a test object.

Patent Document 1 describes a technique for displaying a similar case image having characteristics similar to the image to be read, together with the image to be read obtained by photographing a patient.

Japanese Patent No. 4979334

For example, in the examination of a patient suspected of having a respiratory disease, the sputum of the patient is examined to identify the bacteria contained in the sputum. In that case, it is desirable to proceed with the test after ascertaining the suitability of sputum as a test target, that is, sputum containing a sufficient amount of the causative bacteria of the disease.
Therefore, an object of the present invention is to provide information that supports evaluation of suitability of a sample as a test target.

In the present invention, as an evaluation target image of sputum , which is a sample to be evaluated for which suitability as an inspection target is evaluated, an acquisition unit that acquires an image of the sputum to be evaluated in an unstained state, and the acquired sputum image. An extraction unit that extracts a region of color representing purulent sputum as a specific color from the image to be evaluated, and based on the extracted region, the suitability of the specimen as an inspection target based on the region of the color of the specimen. It is a classification unit that classifies the sample to be evaluated into one of a plurality of categories in which the degree is classified, and among the plurality of categories classified by the Miller & Jones classification based on the size of the extracted region. A classification unit that classifies sputum to be evaluated into any of the above, a sample image of a sample that is classified into the same category as the category classified by the classification unit, and the same category and the degree of suitability among the plurality of categories. Provided is an information processing apparatus including a display control unit that displays a sample image of a sample classified into the closest category together with the evaluation target image.

Further, in the present invention, as an evaluation target image of sputum, which is an evaluation target sample whose suitability as a test target is evaluated, the sputum to be evaluated can be Gram-stained and leukocytes and squamous epithelial cells can be observed. An acquisition unit that acquires an image enlarged at 1 magnification, an extraction unit that extracts a color region representing white blood cells and squamous epithelial cells that have been Gram-stained as a specific color from the acquired image to be evaluated, and an extraction unit that has been extracted. An extraction unit that classifies the sample to be evaluated into one of a plurality of categories that classify the degree of suitability of the sample as an inspection target based on the region of the color of the sample. The sputum to be evaluated is classified into one of a plurality of categories classified by the Geckler classification based on the number of regions representing leukocytes and the number of regions representing the number of squamous epithelial cells among the above-mentioned regions. A sample image of a sample classified into the same category as the category classified by the classification unit, and a sample image of a sample classified into the same category and the category having the closest suitability among the plurality of categories. Is provided with an information processing apparatus including a display control unit that displays the image together with the evaluation target image .

Further, the present invention obtains an image obtained by Gram-staining the sample to be evaluated as an evaluation target image of the sample to be evaluated whose suitability as an inspection target is evaluated and magnifying the microorganism at a second magnification observable. In addition to the acquisition unit, an extraction unit that extracts a color region representing a Gram-stained microorganism as a specific color from the acquired image to be evaluated, and an extraction unit that extracts the extracted region into the color region of the sample. A classification unit that classifies the sample to be evaluated into one of a plurality of categories that classify the degree of suitability of the sample as a test target based on the above, and a sample that is classified into the same category as the category classified by the classification unit. The display control unit for displaying the sample image of the sample and the sample image of the sample classified into the same category and the category having the closest degree of suitability among the plurality of categories together with the evaluation target image, and the extracted said Provided is an information processing apparatus including an output unit that outputs information that recommends staining by a method other than Gram stain when the shape, size, and number of connections of the region do not satisfy the conditions as bacteria .

Further, the present invention uses a computer as an evaluation target image of sputum, which is an evaluation target sample whose suitability as an inspection target is evaluated, and an acquisition unit that acquires an image of the sputum of the evaluation target in an unstained state. , An extraction unit that extracts a region of a color representing purulent sputum as a specific color from the acquired image to be evaluated, and an inspection of the specimen based on the region of the color of the specimen based on the extracted region. It is a classification unit that classifies the sample to be evaluated into one of a plurality of categories that classify the degree of suitability as a target, and is classified by Miller & Jones classification based on the size of the extracted region. A classification unit that classifies sputum to be evaluated into one of a plurality of categories, a sample image of a sample classified into the same category as the category classified by the classification unit, and the same category among the plurality of categories. Provided is a program for functioning as a display control unit for displaying a sample image of a sample classified into the category having the closest degree of suitability together with the evaluation target image .

Further, in the present invention, the computer is used as an evaluation target image of sputum, which is a sample to be evaluated for which suitability as an examination target is evaluated, and the sputum to be evaluated is Gram-stained and leukocytes and squamous epithelial cells are observed. An acquisition unit that acquires an image magnified at the first possible magnification, an extraction unit that extracts a color region representing white blood cells and squamous epithelial cells that have been Gram-stained as a specific color from the acquired image to be evaluated, and an extraction unit. It is a classification unit that classifies the sample to be evaluated into one of a plurality of categories in which the degree of suitability of the sample as a test target is classified based on the region of the color of the sample. Then, based on the number of regions representing leukocytes and the number of regions representing the number of squamous epithelial cells in the extracted regions, the sputum to be evaluated is assigned to one of a plurality of categories classified by the Geckler classification. A classification unit to be classified, a sample image of a sample classified into the same category as the category classified by the classification unit, and a sample classified into the same category and the category having the closest suitability among the plurality of categories. Provided is a program for functioning the sample image as a display control unit for displaying the sample image together with the evaluation target image .

Further, in the present invention, the computer is Gram-stained with the sample to be evaluated as an evaluation target image of the sample to be evaluated whose suitability as a test target is evaluated , and the microorganism is enlarged at a second magnification observable. An acquisition unit for acquiring an image , an extraction unit for extracting a color region representing a Gram-stained microorganism as a specific color from the acquired image to be evaluated, and the color of a sample based on the extracted region. The classification unit that classifies the sample to be evaluated into one of a plurality of categories that classify the degree of suitability of the sample as a test target based on the area of the above, and the same classification as the classification that the classification unit classified. A display control unit for displaying the sample image of the sample to be evaluated and the sample image of the sample classified into the same category and the category having the closest suitability among the plurality of categories together with the evaluation target image, and extraction. Provided is a program for functioning as an output unit that outputs information recommending staining by a method other than Gram stain when the shape, size and number of linkages of the region do not satisfy the conditions as bacteria .

According to the present invention, it is possible to provide information that supports evaluation of suitability of a sample as a test target.

The figure which shows the whole structure of the microorganism detection support system of an Example Diagram showing the hardware configuration of the sputum image storage device and the microorganism detection work device Diagram showing the functional configuration realized in the microorganism detection support system Diagram showing an example of accumulated sputum images Diagram showing an example of the first division table Diagram showing an example of the second division table Diagram showing an example of the displayed evaluation target image and sample image Diagram showing another example of the displayed evaluation target image and sample image Diagram showing an example of the displayed sputum image and sample image to be inspected The figure which shows an example of the operation procedure of each device in a display process Diagram showing an example of the evaluation target image and sample image displayed in the modified example Diagram showing the functional configuration realized in the modified example microorganism detection support system Diagram showing an example of output recommended information Diagram showing the functional configuration realized in the modified example microorganism detection support system Diagram showing an example of the displayed related information

Hereinafter, the microorganism detection support system which is an embodiment of the present invention will be described. The microorganism detection support system is a system for supporting the detection of microorganisms contained in a patient's sample, and is used by a clinical laboratory technician, a doctor such as a clinician, or the like in, for example, a hospital or a clinical laboratory company. A sample is a material collected from a patient's body and is mainly used for a test for detecting microorganisms in the patient's body.

Microorganisms to be detected are mainly bacteria, but also include fungi and viruses (viruses are indirectly detected by detecting inclusion bodies that are abnormally stained regions in cells). Specimens include, for example, sputum, blood, cerebrospinal fluid, pleural effusion, ascites, pus, body fluid, gastric mucosa biopsy, drain drainage and exudate, as well as body tissue and body fluid adhering to a catheter. In this example, sputum of which is used as a sample. Sputum is mucus (so-called sputum) exhaled from the mouth, and includes mucus and saliva secreted from the respiratory system such as the bronchi.

[1] Example FIG. 1 shows the overall configuration of the microorganism detection support system 1 of the embodiment. The microorganism detection support system 1 includes a sputum image storage device 10 and a microorganism detection work device 20. The sputum image storage device 10 and the microorganism detection work device 20 are connected by a communication line such as a LAN (Local Area Network), and data can be exchanged between the two devices.

The sputum image storage device 10 accumulates images of sputum collected from a patient. The sputum image accumulating device 10 accumulates sputum images magnified at each magnification such as visual (gross observation), 100 times and 1000 times. Further, the sputum image accumulating device 10 accumulates an image of sputum in an unstained state as it is, and an image of sputum stained by a method such as Gram stain. In this embodiment, the sputum image storage device 10 stores the images of these sputum, but a plurality of devices may share and store these images.

The microorganism detection work device 20 is a device used by a clinical laboratory technician when performing work to detect microorganisms from sputum. In addition to the image of sputum to be inspected, the microorganism detection working device 20 displays an image of sputum similar to the image as a sample image. In addition, some sputum is suitable for detecting microorganisms and some are not, and the microorganism detection working device 20 uses an image of sputum suitable for such an inspection target and sputum not suitable for it. The image is also displayed as a sample image. In the microorganism detection support system 1, the microorganism detection working device 20 displays these sample images to support the detection of microorganisms contained in sputum.

FIG. 2 shows the hardware configuration of the sputum image storage device 10 and the microorganism detection work device 20. The sputum image storage device 10 and the microorganism detection work device 20 all include a processor 11, a memory 12, a storage 13, a communication device 14, an input device 15, an output device 16, and a bus 17. It is a computer.

The processor 11 includes, for example, a CPU (Central Processing Unit), and controls the operation of each unit by executing a program. The memory 12 is a recording means such as a RAM (Random Access Memory) and a ROM (Read Only Memory). The RAM is used as a work area when the processor 11 executes a program. The storage 13 is a storage means such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), and a flash memory. The storage 13 is not limited to the one built in the own device, may be an external one, or may be a portable one such as a memory key. The ROMs of the storage 13 and the memory 12 store data, programs, and the like used by the processor 11 for control.

The communication device 14 is a communication means for performing communication between computers. This communication may be performed by either wired communication or wireless communication. The input device 15 is an input device (keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside. The output device 16 is an output device (display, speaker, etc.) that outputs to the outside. The input device 15 and the output device 16 may have an integrated configuration (for example, a touch screen). The devices shown in FIG. 2 are accessible to each other via a bus 17 for communicating information.

The functions described below are realized by each processor 11 of the sputum image storage device 10 and the microorganism detection work device 20 executing a program.
FIG. 3 shows a functional configuration realized in the microorganism detection support system 1. The sputum image storage device 10 includes a sputum image storage unit 101 and a sputum image output unit 102. The microorganism detection working device 20 includes a sputum image acquisition unit 201, a specific region extraction unit 202, a sputum evaluation classification unit 203, a sample image acquisition unit 204, a similarity calculation unit 205, a sputum image display control unit 206, and the sputum image display control unit 206. A classification determination sputum image transmission unit 207 and an inspection result transmission unit 208 are provided.

The sputum image storage unit 101 of the sputum image storage device 10 accumulates sputum images collected from a patient. The sputum image storage unit 101 stores the sputum image file in association with the identification information (for example, patient ID (Identification)) of the patient from whom the sputum was collected and the date and time when the sputum was collected. In this embodiment, the sputum image storage unit 101 stores an image file of sputum taken at three magnifications: visual (without staining), 100 times (with staining), and 1000 times (with staining). Here, "without staining" means that no staining has been performed, and "with staining" means that Gram stain has been performed.

Further, 100 times is a magnification at which leukocytes and squamous epithelial cells can be observed, and is an example of the "first magnification" of the present invention. Further, 1000 times is a magnification at which microorganisms can be observed, and is an example of the "second magnification" of the present invention. The sputum image storage unit 101 stores the inspection results in association with these sputum image files. This test result was input by a clinical laboratory engineer or the like who inspected sputum, and shows findings (name and condition of microorganisms, etc.) about microorganisms contained in sputum.

In addition, the sputum image storage unit 101 stores each sputum in association with an evaluation index for evaluating suitability as an inspection target (whether or not it is suitable for detecting microorganisms). Specifically, the sputum image storage unit 101 stores the indexes classified by the M & J (Miller & Jones) classification and the Geckler classification in association with each other. The M & J classification is an evaluation index based on sputum seen with the naked eye, and is evaluated by the amount of purulent portion mixed in sputum. According to the M & J classification, M1 (completely viscous sputum), M2 (cohesive sputum contains a small amount of purulent sputum), P1 (purulent part is less than 1/3 of the total sputum), P2 (purulent part is Sputum with more than 1/3 of the total and less than 2/3) and P3 (sputum with purulent part of 2/3 or more of the whole) are evaluated higher in this order (P3 has the highest evaluation).

The Geckler classification is an evaluation index based on sputum viewed at a magnification of 100 times, and is evaluated by the number of leukocytes and squamous epithelial cells mixed in sputum. According to the Geckler classification, group 1 (white blood cell count is less than 10 and squamous epithelial cell count is more than 25), group 2 (white blood cell count of 10 or more and 25 or less, squamous epithelial cell count is more than 25), and group 3 (white blood cell count is 25). More, more than 25 squamous epithelial cells), group 4 (more than 25 white blood cells, more than 25 squamous epithelial cells), group 5 (more than 25 white blood cells, 10 more squamous epithelial cells) Less than), Group 6 (white blood cell count less than 25, squamous epithelial cell count less than 25).

The higher the number, the higher the evaluation of groups 1 to 5 (group 5 has the highest evaluation). Group 6 represents that it is suitable as a test target depending on the sputum feature (for example, sputum of a patient who tends to have a low white blood cell count). In this embodiment, the evaluation by the M & J classification and the Geckler classification is performed by the sputum evaluation classification unit 203 of the microorganism detection work apparatus 20 described later. The sputum evaluation classification unit 203 will be described in detail later.

FIG. 4 shows an example of the accumulated sputum image. In the example of FIG. 4, the sputum image storage unit 101 has, for example, a patient ID of "ID001", a collection date and time, an M & J classification of "P1", a Geckler classification of "Group 3", and "xxx1.jpg", ". The sputum image files of "yy1.jpg" and "zzz1.jpg", which are visually, 100 times and 1000 times, respectively, are stored in association with each other. In addition, the patient IDs "ID002" and "ID003" are also stored in association with the collection date and time, each evaluation index, and an image file of sputum.

The sputum image acquisition unit 201 of the microorganism detection working device 20 acquires an image of sputum to be evaluated (hereinafter referred to as “evaluation target image”) whose suitability as an inspection target is evaluated. The sputum image acquisition unit 201 is an example of the “acquisition unit” of the present invention. When a storage medium such as a memory key that stores an evaluation target image is connected to its own device, the sputum image acquisition unit 201 reads and acquires the evaluation target image from the storage medium based on the user's operation.

In addition, the sputum image acquisition unit 201 is evaluated from the external device when an operation for accessing an external device (for example, a digital camera or a microscope device that captures the sputum to be evaluated) that stores the evaluation target image is performed. Read and acquire the image. The sputum image acquisition unit 201 acquires, for example, an image of “visually (unstained)” sputum described in the explanation of FIG. 4, that is, an evaluation target image obtained by visually photographing sputum in an undyed state.

In addition, the sputum image acquisition unit 201 has a "100-fold (stained)" sputum image, that is, an evaluation target image in which sputum to be evaluated is Gram-stained and leukocytes and squamous epithelial cells are enlarged at an observable magnification. To get. In addition, the sputum image acquisition unit 201 acquires an image of sputum of "1000 times (with staining)", that is, an evaluation target image in which sputum to be evaluated is Gram-stained and bacteria are enlarged at an observable magnification. Of the evaluation target images thus acquired, the sputum image acquisition unit 201 calculates the evaluation target image of "visually (without staining)" and the evaluation target image of "100 times (with staining)" with the specific area extraction unit 202 and the similarity. It is supplied to the unit 205, and all the evaluation target images are supplied to the sputum image display control unit 206.

The specific area extraction unit 202 extracts a specific color area from the evaluation target image acquired by the sputum image acquisition unit 201. The specific region extraction unit 202 is an example of the "extraction unit" of the present invention. When a visual (unstained) evaluation target image is acquired, the specific region extraction unit 202 changes the color representing purulent sputum (for example, white-yellow, pale yellow, green, yellow, rust) to a specific color. Extract as. In addition, when a 100-fold (stained) evaluation target image is acquired, the specific region extraction unit 202 extracts a color (for example, red) representing Gram-stained leukocytes and squamous epithelial cells as a specific color. Do.

If there are a plurality of regions of a specific color in the evaluation target image, the specific region extraction unit 202 extracts the plurality of regions. The specific area extraction unit 202 generates, for example, information in which a set of coordinates of pixels included in the extracted area and an area ID assigned to each area are associated with each other as area information indicating the extracted area, and the generated area. Information is supplied to the sputum evaluation and classification unit 203.

The sputum evaluation classification unit 203 evaluates the suitability of sputum as an inspection target (that is, evaluation as an inspection target) based on the region extracted by the specific region extraction unit 202 and based on the above-mentioned specific color region of sputum. The higher the evaluation, the more suitable it is as an inspection target.) Classify the sputum to be evaluated into one of the multiple categories. The sputum evaluation classification unit 203 is an example of the “classification unit” of the present invention. As the plurality of categories referred to here, a plurality of categories classified by the above-mentioned M & J classification are used for the visually (unstained) evaluation target image, and the Geckler classification is used for the 100-fold (stained) evaluation target image. Multiple classified categories are used.

More specifically, the sputum evaluation and classification unit 203, when extraction is performed with a color representing purulent sputum as a specific color, a plurality of classifications by M & J classification based on the size of the extracted region. Classify the sputum to be evaluated into one of the categories. The sputum evaluation classification unit 203 performs this classification using the first classification table in which the size of the region and the plurality of classifications of the M & J classification are associated with each other.

FIG. 5 shows an example of the first division table. In the example of FIG. 5, the size of the region is "less than 1%", "1% or more and less than 5%", "5% or more and less than 33%", "33% or more and less than 66%", and "66% or more". , "M1", "M2", "P1", "P2", "P3" are associated with each of the M & J classification categories. The sputum evaluation classification unit 203 calculates a value obtained by dividing the total number of pixels represented by the area information supplied from the specific area extraction unit 202 by the total number of pixels of the entire image, that is, the proportion of the purulent part in the image. The sputum to be evaluated is classified into the categories associated with the size of the area represented by the calculated ratio in the first category table.

In addition, when the sputum evaluation classification unit 203 extracts the Gram-stained leukocytes and the color representing the squamous epithelial cells as a specific color, the number of regions representing leukocytes and the number of squamous epithelial cells in the extracted regions Based on the number of regions representing, the sputum to be evaluated is classified into one of a plurality of categories classified by the Geckler classification. The sputum evaluation classification unit 203 performs this classification using a second classification table in which the number of leukocyte regions, the number of squamous epithelial cell regions, and a plurality of classifications of the Geckler classification are associated with each other.

FIG. 6 shows an example of the second division table. In the example of FIG. 6, the relationship between the number of leukocytes and the number and classification of squamous epithelial cells in the above-mentioned Geckler classification is represented as the relationship between the number of leukocyte regions and the number and classification of squamous epithelial cell regions. For example, "group 1" is associated with the number of leukocyte regions "less than 10" and the number of squamous epithelial cell regions "more than 25". Regarding "Group 6", the number of leukocyte regions "25 or less" and the number of squamous epithelial cell regions "25 or less" are associated with each other so as to include the case where both numbers are "25". There is.

In the sputum evaluation classification unit 203, since squamous epithelial cells are generally larger than leukocytes, the number of associated pixels among the area IDs represented by the area information supplied from the specific area extraction unit 202 is the threshold value. The above is determined as the region ID of the squamous epithelial cell region, and the one in which the number of associated pixels is less than the threshold value is determined as the region ID of the leukocyte region. In addition, this determination may be made in consideration of not only the size of the region but also the shape (the leukocyte has a shape closer to a circle) and the color of the region. The sputum evaluation classification unit 203 classifies the sputum to be evaluated into the categories in which the number of region IDs of the squamous epithelial cell region thus determined and the number of region IDs of the leukocyte region are associated with each other in the second division table. To do. The sputum evaluation classification unit 203 supplies the classifications classified as described above to the sample image acquisition unit 204.

The sample image acquisition unit 204 acquires a sample image of sputum classified into the same category as the category classified by the sputum evaluation classification unit 203. This category is a category classified by the sputum evaluation classification unit 203, and is not a category judged by humans. In the microorganism detection support system 1, after that, a human being is supposed to finally determine the classification based on the image of sputum to be evaluated. Therefore, the classification classified by the sputum evaluation classification unit 203 is a provisional classification before the final decision, and will be referred to as "provisional classification" below.

In addition to the sputum sample image classified into this provisional category, the sample image acquisition unit 204 has a category having the closest suitability to the provisional category among the plurality of categories classified by the sputum evaluation classification unit 203 (hereinafter referred to as "proximity category"). Acquire a sample image of sputum classified into). There are two types of proximity categories: the category with the highest degree of suitability among the categories with a higher degree of suitability than the provisional category, and the category with the closest degree of suitability among the categories with a lower degree of suitability than the provisional category. Can exist. However, if the degree of suitability of the provisional classification is the highest or the lowest among the plurality of classifications, the proximity classification becomes one. For example, the proximity classification of "M2", which has the second highest degree of suitability from the bottom, is "M1" and "P1", and the proximity classification of "P3", which has the highest degree of suitability, is one of "P2". is there.

Further, in the case of a plurality of divisions of the Geckler classification, if the provisional division is any one of "group 1" to "group 5", it is assumed that the groups having adjacent numbers are the proximity divisions. For example, the proximity divisions of "Group 3" are "Group 2" and "Group 4". When the provisional classification is "Group 6", the sample image acquisition unit 204 is close to each other based on the number of leukocyte regions and the number of squamous epithelial cells regions of the evaluation target image used in the provisional classification. Judge the classification.

The sample image acquisition unit 204 sets the difference between the number of leukocyte regions of the evaluation target image and the number of leukocyte regions that are the thresholds of each division, the number of squamous epithelial cell number regions of the evaluation target image, and the threshold of each division. The difference from the number of squamous epithelial cell number regions is totaled, and the category with the smallest total is judged to be the proximity category. For example, in the second division table shown in FIG. 6, if the number of leukocyte regions (or the number of squamous epithelial cell number regions) is "less than 10", "9" is used as a threshold value, and if it is "more than 25". "26" is used as the threshold value. If it is "10 or more and 25 or less", the number (10 or 25) closer to the number of evaluation target images is used as the threshold value.

For example, when the white blood cell region of the evaluation target image is 8 and the number of squamous epithelial cells is 20, the difference in the leukocyte region (9-8) + the difference in the number of squamous epithelial cells (26-20) in group 1 = 7. In group 2, the difference in leukocyte region (10-8) + difference in the number of squamous epithelial cells (26-20) = 8, and in group 3, the difference in leukocyte region (26-8) + the number of squamous epithelial cells Difference (26-20) = 24, group 4 has white blood cell region difference (26-8) + squamous epithelial cell number region difference (25-20) = 23, group 5 has white blood cell region difference (26- 8) + difference in the number of squamous epithelial cells (20-9) = 29, so group 1 in which the total difference is the smallest “7” is judged to be a proximity category.

The method for determining the proximity classification of "Group 6" is not limited to this, and may be determined in advance, for example. For example, in the case of multiple categories of Geckler classification, "Group 1", "Group 2", "Group 3", "Group 6", "Group 4", and "Group 5" are decided from the one with the smallest degree of suitability. deep. In this case, the sample image acquisition unit 204 determines that "group 3" and "group 4" are proximity divisions if the provisional division is "group 6", and "group 6" if the provisional division is "group 4". And "Group 5" are judged to be proximity categories. The sample image acquisition unit 204 transmits to the sputum image storage device 10 request data requesting a sample image of sputum classified into the proximity category determined in this way and a sample image classified into the provisional category.

When the sputum image output unit 102 of the sputum image storage device 10 receives the transmitted request data, it associates the sputum image associated with the provisional classification indicated by the request data with the proximity division indicated by the request data. The sputum image obtained is read from the sputum image storage unit 101. The sputum image output unit 102 outputs those read images to the requesting microorganism detection working device 20. The sample image acquisition unit 204 acquires the sputum image associated with the provisional division and the sputum image associated with the proximity division, which are output in this way, and supplies the image to the similarity calculation unit 205.

The similarity calculation unit 205 calculates the similarity between the evaluation target image acquired by the sputum image acquisition unit 201 and the sample image acquired by the sample image acquisition unit 204. The similarity calculation unit 205 calculates, for example, the feature amount of the evaluation target image supplied from the sputum image acquisition unit 201 and the feature amount of the sample image supplied from the sample image acquisition unit 204, and those characteristics are calculated. Calculate the similarity based on the quantity.

The similarity calculation unit 205 calculates the feature amount and the similarity by using well-known techniques such as SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features) and ORB (Oriented FAST and Rotated BRIEF). When the similarity calculation unit 205 calculates the similarity for each sample image, the similarity calculation unit 205 supplies the sputum image display control unit 206 with the calculated similarity for each sample image and the sample image.

The sputum image display control unit 206 controls the display means of its own device to display the evaluation target image acquired by the sputum image acquisition unit 201, and the sample image supplied from the similarity calculation unit 205, that is, provisional A sample image of sputum classified into a category and a sample image of sputum classified into a proximity category are displayed. The sputum image display control unit 206 is an example of the "display control unit" of the present invention.

The sputum image display control unit 206 sets the sputum sample image classified into the provisional category and the sputum sample image classified into the proximity category into the evaluation target image based on the similarity supplied from the similarity calculation unit 205. Display each in the order according to the degree of similarity.
FIG. 7 shows an example of the displayed evaluation target image and sample image. In the example of FIG. 7, the sputum image display control unit 206 displays the M & J classification support screen A1.

The sputum image display control unit 206 displays the evaluation target image B1 whose provisional division is classified into P3, and the sample images C11, C12, and C13 of the same division P3 as the provisional division (similarity is 97% and 91%, respectively). 86%) are displayed side by side in the order of the left side as the degree of similarity is higher. Further, the sputum image display control unit 206 displays the sample images C21, C22, and C23 (similarities of 78%, 66%, and 62%, respectively) of the division P2, which is a proximity division of the provisional division, to the left as the similarity is higher. They are displayed side by side in the following order. The sputum image display control unit 206 displays the value of their similarity in the vicinity of each sample image (below in this example). These sample images are a part, and by operating the scroll bar, sample images having a lower similarity than these sample images are also displayed.

The sputum image display control unit 206 displays the classification determination buttons D1 and D2 for determining the classification of the evaluation target image B1 in the M & J classification. The division determination button D1 is a button for determining the division P3, and the division determination button D2 is a button for determining the division P2. By comparing the displayed evaluation target image B1 and each sample image, the clinical laboratory technician decides whether the classification of the evaluation target image B1 in the M & J classification is the same as the provisional classification P3 or the proximity classification P2. To judge.

For example, if the sample image of the category P3 is considered to be more similar to the evaluation target image B1 than the sample image of the category P2, the clinical laboratory technician presses the category determination button D1 to determine the category of the evaluation target image B1. Determined in category P3. On the contrary, if the sample image of the category P2 is considered to be more similar to the evaluation target image B1 than the sample image of the category P3, the clinical laboratory technician performs an operation of pressing the category determination button D2 to obtain the evaluation target image B1. The category is determined to be category P2.

FIG. 8 shows another example of the displayed evaluation target image and the sample image. In the example of FIG. 8, the sputum image display control unit 206 displays the Geckler classification support screen A2. The sputum image display control unit 206 displays the evaluation target image B2 whose provisional classification is classified into group 4, and the sample images C41, C42, and C43 of the same group 4 as the provisional classification (similarity is 84% and 72%, respectively). , 68%) are displayed side by side in the order of the left side as the degree of similarity is higher.

Further, the sputum image display control unit 206 is the same as the sample images C31, C32, and C33 of Group 3, which are the proximity divisions of the provisional division (similarity is 56%, 47%, 39%, respectively), and the proximity division of the provisional division. Sample images C51, C52, and C53 of a certain group 5 (similarity is 92%, 87%, and 76%, respectively) are displayed side by side in the order of the left side as the degree of similarity is higher.

The sputum image display control unit 206 displays the classification determination buttons D3, D4 and D5 (buttons for determining the classification in groups 3, 4 and 5, respectively) for determining the classification in the Geckler classification of the evaluation target image B2. By comparing the displayed evaluation target image B2 and each sample image, the clinical laboratory technician sets the classification of the evaluation target image B2 in the Geckler classification into the same group 4 as the provisional classification, or into the proximity classification group 3 or 5. Decide if you want to. The clinical laboratory technician presses the enter button indicating the category determined to be most similar to the evaluation target image B2, and determines the category of the evaluation target image B2 into any of groups 3, 4, and 5.

When the user performs an operation to determine the classification of the image to be evaluated, the classification determination sputum image transmission unit 207 includes the sputum image whose classification is determined by this operation, the determined division, and the sputum reflected in the sputum image. The sputum image data representing the patient ID of the patient from whom the sputum was collected and the date and time when the sputum was collected is transmitted to the sputum image storage device 10. When the sputum image storage unit 101 of the sputum image storage device 10 receives the transmitted sputum image data, it receives each information (patient ID, collection date and time, determined classification, sputum image file) represented by the received sputum image data. They are associated with each other and stored as shown in FIG. The sputum image storage unit 101 accumulates a new sputum image whose classification is determined in this way.

Further, in the present embodiment, the sputum image display control unit 206 considers that the evaluation target image whose classification in the Geckler classification is determined by the user to the groups 4, 5 and 6 is suitable as the inspection target, and sets the evaluation target image. An image 1000 times (with staining) of the sputum in the image is displayed as a sputum image to be inspected. In this case, the sample image acquisition unit 204 acquires all 1000 times (stained) images of sputum accumulated in the sputum image storage device 10 as sample images, and the similarity calculation unit 205 acquires those sample images. And the degree of similarity with the sputum image to be inspected is calculated.

The sputum image display control unit 206 displays the sputum image to be inspected, and displays the sample images in order from the one with the highest degree of similarity.
FIG. 9 shows an example of the displayed sputum image and sample image to be inspected. In the example of FIG. 9, the sputum image display control unit 206 displays sample images C61, C62, C63, C64, C65, which have a high degree of similarity between the sputum image B3 to be inspected and the sputum image B3 on the sputum internal biological screen A3. C66 (similarity is 94%, 90%, 84%, 83%, 79%, 75%, respectively) is displayed in order from the one with the highest similarity.

Further, the sputum image display control unit 206 displays the inspection result input field E1. When a clinical laboratory technician or the like compares the sputum image B3 to be inspected and each sample image and inputs the test result in the input field E1, the test result transmission unit 208 is reflected in the input test result and, for example, the sputum image B3. The test result data representing the patient ID of the patient who collected the sputum and the date and time of collection is transmitted to the sputum image storage device 10. When the sputum image storage unit 101 of the sputum image storage device 10 receives the transmitted test result data, the test result represented by the test result data is shown in association with the patient ID and the collection date and time represented by the received test result data. Store as shown in 4.

Each device included in the microorganism detection support system 1 performs a display process for displaying a sputum evaluation support screen as shown in FIGS. 7 and 8 based on the above configuration.
FIG. 10 shows an example of the operation procedure of each device in the display process. This operation procedure is started when the user performs an operation of causing the microorganism detection working device 20 to acquire an image to be evaluated. First, the microorganism detection working device 20 (sputum image acquisition unit 201) acquires an image (evaluation target image) of sputum to be evaluated whose suitability as an inspection target is evaluated (step S11).

Next, the microorganism detection working device 20 (specific region extraction unit 202) extracts a region of a specific color from the acquired image to be evaluated (step S12). Subsequently, the microorganism detection working device 20 (sputum evaluation and classification unit 203) was classified by a plurality of categories (M & J classification or Geckler classification) that classified the degree of suitability of sputum as an inspection target based on the extracted region. The sputum to be evaluated is classified into one of the plurality of categories) (step S13). Next, the microorganism detection working device 20 (sample image acquisition unit 204) determines the classification (proximity classification) that is closest to the classification (provisional classification) classified in step S13 (step S14).

Subsequently, the microorganism detection working device 20 (sample image acquisition unit 204) requests the sputum image storage device 10 for the sample image of the provisional classification and the sample image of the proximity classification (step S15). The sputum image storage device 10 (sputum image output unit 102) reads out the requested sample image of the provisional division and the sample image of the proximity division (step S21), and outputs the sample image to the microorganism detection working device 20 (step S22). .. The microorganism detection working device 20 (sample image acquisition unit 204) acquires the output sample image of the provisional division and the sample image of the proximity division (step S23).

Next, the microorganism detection working device 20 (similarity calculation unit 205) calculates the similarity between the output sample image and the evaluation target image (step S24). Subsequently, the microorganism detection working device 20 (sputum image display control unit 206) displays the evaluation target image, and displays the sample images acquired in step S23 in the order corresponding to the similarity calculated in step S24. (Step S25).

Then, when the user performs the operation of determining the classification of the evaluation target image, the microorganism detection working device 20 (classification determination sputum image transmission unit 207) accepts this operation as the classification determination operation (step S31), and is described above. The sputum image data (data representing the sputum image, the determined category, the patient ID and the collection date and time) is transmitted to the sputum image storage device 10 (step S32). The sputum image storage device 10 (sputum image storage unit 101) stores each information (patient ID, collection date and time, determined classification, sputum image file) represented by the received sputum image data (step S33).

In this embodiment, the microorganism detection working device 20 (sputum evaluation classification unit 203) classifies sputum classifications based on the image to be evaluated, but the provisional classifications classified in this way do not necessarily match the classifications judged by humans. Is not always. On the other hand, even if the human judgment is not the provisional classification, if the provisional classification captures the features of the image to be evaluated to some extent, it is judged to be the classification closest to the provisional classification, that is, the proximity classification. Probability is high.

Therefore, the microorganism detection working device 20 (sputum image display control unit 206) displays a sample image as shown in the examples of FIGS. 7 and 8, so that when a human sees the image to be evaluated, it is classified as a temporary category. By comparing both of the two types of sample images, the sputum sample image to be classified and the sputum sample image to be classified into the proximity classification, with the evaluation target image, it is possible to determine the more appropriate classification. As described above, according to this embodiment, information supporting the evaluation (that is, the above two types of sample images) is provided to a worker (for example, a clinical laboratory technician) who evaluates the suitability of sputum as an examination target. Can be provided.

Specifically, it is possible to provide information that supports evaluation by M & J classification and information that supports evaluation by Geckler classification. Further, in this embodiment, the sample images are displayed in an order according to the degree of similarity with the evaluation target image. As a result, compared to the case where the sample images are displayed in an order irrelevant to the similarity, a more reference image among the sample images, that is, an image more similar to the evaluation target image is easily compared with the evaluation target image. be able to.

[2] Modifications The above-described embodiment is merely an example of the embodiment of the present invention, and may be modified as follows. In addition, the above-described embodiment and each modification may be combined and implemented as necessary.

[2-1] Aspects according to the degree of similarity In the embodiment, the sputum image display control unit 206 displays the sample images in the order according to the degree of similarity with the image to be evaluated, but the present invention is not limited to this, and for example, the same. It may be displayed in a mode according to the degree.
FIG. 11 shows an example of the evaluation target image and the sample image displayed in this modified example. In the example of FIG. 11, the sputum image display control unit 206 displays the evaluation target image B1 and the sample images C11, C12, C13, C21, C22, and C23 shown in FIG. 7 on the M & J classification support screen A4.

The sputum image display control unit 206 displays these sample images in a size corresponding to the similarity calculated by the similarity calculation unit 205. Specifically, the sputum image display control unit 206 displays the sample image in a larger size as the degree of similarity increases. In this example, the size of the reference is multiplied by the degree of similarity to be displayed. ing. The sputum image display control unit 206 displays, for example, the sample image C11 having a similarity of 97% in a size of 97% of the reference size, and the sample image C23 having a similarity of 62% has a reference size of 62. It is displayed in% size. In this case, the degree of similarity can be grasped from the size of the sample image.

Not limited to this, the sputum image display control unit 206 may display sample images in sizes of 100%, 90%, 80%, ... Of the reference size in order from the one with the highest similarity. .. Further, the sputum image display control unit 206 may change not only the size but also the brightness and contrast of the sample image according to the degree of similarity. In any case, it is desirable that the magnitude and order of the similarity of the sample images can be grasped from the difference in the display mode of the sample images.

[2-2] Output of recommended information When identifying microorganisms from sputum images stained with gram at an observable magnification as shown in Fig. 9, depending on the state of sputum, even non-microorganisms are stained. It may be difficult to find microorganisms among them. In that case, other staining methods may be recommended.

FIG. 12 shows a functional configuration realized in the microorganism detection support system 1a of this modified example. The microorganism detection support system 1a includes a microorganism detection work device 20a, and the microorganism detection work device 20a includes a recommended information output unit 209 in addition to the parts shown in FIG. The sputum image acquisition unit 201 of this modification also supplies the evaluation target image of "1000 times (with staining)" to the specific region extraction unit 202. The specific region extraction unit 202 extracts regions from the supplied evaluation target image using colors representing Gram-stained microorganisms (for example, red and purple) as specific colors. When the specific area extraction unit 202 extracts the area, the specific area extraction unit 202 supplies the above-mentioned area information to the recommended information output unit 209.

The recommended information output unit 209 outputs recommended information that recommends staining by a method other than Gram stain when the shape, size, and number of connections of the region extracted by the specific region extraction unit 202 do not satisfy the conditions as a bacterium. To do. The recommended information output unit 209 is an example of the "output unit" of the present invention. The recommended information output unit 209 has, for example, an extraction region having a circular shape (coccus), an elongated rod shape or an elongated cylindrical shape (bacillus), a thread shape, a curved shape, or a spiral shape. If the size is 0.1 μm or more and 10 μm or less and the regions are connected, the number of connections is even or the number of connections is equal to or more than the threshold (the number of connections is large, so it looks like a grape). If the condition is not satisfied, it is determined that the extraction area does not represent a microorganism, and recommended information is output.

FIG. 13 shows an example of the output recommended information. In the example of FIG. 13, the recommended information output unit 209 has a sputum image B4 that has been stained with Gram and magnified 1000 times, and a character string "No microorganisms can be found by Gram stain. We recommend Ziehl-Neelsen staining." The recommended information F1 including and is output. The recommended information output unit 209 outputs the recommended information F1 to, for example, the display means of the own device and displays it. Staining sputum with Thiel-Neelsen staining can stain microorganisms that have a large amount of fatty acids and are difficult to color with Gram stain (such as Mycobacterium and some bacteria of Nocardia).

In this modification, by outputting the recommended information, it is possible to make it less likely that those microorganisms are not detected without staining by the recommended method, as compared with the case where the recommended information is not output. it can. The staining method recommended by the recommended information is not limited to Thiel-Nelsen staining, but may be other anti-acid bacterium staining such as Kinyon staining or Trant staining, Gimenez staining, Nisel staining, or Hiss staining. It may be a dyeing method such as. In either case, it is possible to make it easier to find microorganisms according to the characteristics of the recommended staining method as compared with the case where the recommended information is not output.

[2-3] Display of Related Information In addition to the evaluation target image and the sample image, the microorganism detection working apparatus may display related information about the patient who collected the sputum shown by the sputum image.
FIG. 14 shows a functional configuration realized in the microorganism detection support system 1b of this modified example. The microorganism detection support system 1b includes a sputum image storage device 10b and a microorganism detection work device 20b.

The sputum image storage device 10b includes a sputum image output unit 102, a sputum image / related information storage unit 103, and a related information output unit 104. The microorganism detection working device 20a includes a sputum image / related information display control unit 210 in place of the sputum image display control unit 206 shown in FIG. 3, and additionally includes a related information acquisition unit 211. In addition to the above-mentioned test results, patient ID, and collection date and time, the test result transmission unit 208 of this modified example has a WBC (White Blood Cell) value, a CRP (C Reactive Protein) value, and a patient's test result transmission unit 208. Body temperature, pulse rate, redness, pain, etc. are transmitted as related information. These related information are information used as a reference when determining whether or not microorganisms such as bacteria and viruses that cause infectious diseases are growing in the patient's body.

The sputum image / related information storage unit 103 stores the related information transmitted in this way together with the inspection result in association with the evaluation target image. When the sputum image output unit 102 reads the sputum image from the sputum image / related information storage unit 103 in the same manner as in the embodiment, the sputum image output unit 102 outputs the read sputum image to the requesting microorganism detection working device 20 and the related information output unit. Supply to 104. The related information output unit 104 outputs the related information accumulated in association with the supplied sputum image to the microorganism detection working device 20. The related information acquisition unit 211 acquires the output related information and supplies it to the sputum image / related information display control unit 210.

The sputum image / related information display control unit 210 displays the supplied related information together with the corresponding sputum image (sample image).
FIG. 15 shows an example of the displayed related information. In the example of FIG. 15, the sputum image / related information display control unit 210 evaluates the sample images C11, C12, and C13 of the same division P3 as the provisional classification, and each sample image on the M & J classification support screen shown in the example of FIG. The degree of similarity with the target image and the related information G1 corresponding to each sample image are displayed.

Related information G1 includes WBC value, CRP value, body temperature and pulse. When a clinical laboratory technician or the like looks at this M & J classification support screen, it is possible to confirm the related information G1 indicating the state of the patient from which a sample image similar to the evaluation target image was collected. Thus, for example, sample image C11 is sputum collected from a patient whose WBC and CRP are higher than the standard range and there is a high suspicion of bacterial infection, whereas sample image C13 is based on WBC and CRP. Accuracy of evaluation as a sample of sputum shown in the sample image compared to the case where related information is not displayed, such as sputum collected from a patient who is within the range of and has a low suspicion of bacterial infection. Can be raised.

The sputum image / related information display control unit 210 may display the sputum sample image classified into the provisional category and the sputum sample image classified into the proximity category in the order corresponding to the corresponding related information. Good. For example, the sputum image / related information display control unit 210 displays the sample image in order from the one with the larger WBC value, or displays the sample image in order from the one with the larger CRP value. Thereby, it is possible to grasp the tendency of sputum in those patients by arranging the sample images of sputum collected from patients having similar values of specific related information side by side.

[2-4] Specimens Specimens other than sputum may be used in the sample microorganism detection support system. For specimens other than sputum, there may be no widely used classification method such as M & J classification method or Geckler classification, but in that case, for example, in hospitals and clinical laboratory companies, the color of the sample taken and the color of the sample. It suffices to establish a method for classifying the degree of suitability of the sample as an inspection target from the size and shape by image processing.

If a classification method by image processing is established, a function (classification unit) for evaluating and classifying samples can be realized as in the sputum evaluation classification unit 203 shown in FIG. In addition, if a classification method that is widely used for samples other than sputum is created in the future, a function that realizes the classification method by image processing may be provided as a classification unit. In each case, as in the example, the sample image of the sample classified into the same category as the category classified by the classification unit and the sample image of the sample classified into the category closest to the category and the degree of suitability are obtained. , Can be displayed together with the image to be evaluated.

[2-5] Devices for Realizing Each Part The devices for realizing each part shown in FIGS. 3 and the like are not limited to the devices shown in those figures. For example, one device may realize each part included in the sputum image storage device 10 and the microorganism detection work device 20. Further, two or more devices may realize each part included in the microorganism detection working device 20. For example, the first device is realized from the sputum image acquisition unit 201 to the sputum evaluation classification unit 203, and the second device is realized from the sample image acquisition unit 204 to the sputum image display control unit 206. In this case, the information processing system (system forming a part of the microorganism detection support system) including the first device and the second device realizes each part included in the microorganism detection work device 20. In short, it is sufficient that these functions are realized as a whole microorganism detection support system.

[2-6] Category of Invention The present invention can be regarded as an information processing system such as a microorganism detection support system including a sputum image storage device and a microorganism detection work device, in addition to an information processing device such as a microorganism detection work device. .. Further, the present invention can be regarded as an information processing method for realizing the processing performed by each device, and also as a program for operating a computer that controls each device. This program may be provided in the form of a recording medium such as an optical disc that stores it, or may be provided in the form of being downloaded to a computer via a network such as the Internet and installed and made available. May be done.

1 ... Sputum detection support system, 10 ... Sputum image storage device, 20 ... Sputum detection work device, 101 ... Sputum image storage unit, 102 ... Sputum image output unit, 201 ... Sputum image acquisition unit, 202 ... Specific area extraction unit, 203 ... sputum evaluation classification unit, 204 ... sample image acquisition unit, 205 ... similarity calculation unit, 206 ... sputum image display control unit, 207 ... classification determination sputum image transmission unit, 208 ... inspection result transmission unit, 209 ... recommended information output unit ..

Claims (6)

As an evaluation target image of sputum , which is a sample to be evaluated whose suitability as an inspection target is evaluated, an acquisition unit that acquires an image of the sputum to be evaluated in an unstained state, and an acquisition unit.
An extraction unit that extracts a color region representing purulent sputum as a specific color from the acquired image to be evaluated, and an extraction unit.
Based on the extracted said regions, the classification unit for classifying a sample of the evaluation object to one of a plurality of segments classified the degree of appropriateness of the inspected specimen on the basis of the color of the area of the sample There is a classification unit that classifies sputum to be evaluated into one of a plurality of categories classified by Miller & Jones classification based on the size of the extracted region .
A sample image of a sample classified into the same category as the category classified by the classification unit and a sample image of a sample classified into the same category and the category closest to the degree of suitability among the plurality of categories are described. An information processing device equipped with a display control unit that displays an image to be evaluated. As an evaluation target image of sputum , which is a sample to be evaluated whose suitability as a test target is evaluated, an image in which the sputum to be evaluated is glam-stained and leukocytes and squamous epithelial cells are enlarged at an observable first magnification. And the acquisition department to acquire
An extraction unit that extracts a color region representing leukocytes and squamous epithelial cells that have been Gram-stained as a specific color from the acquired image to be evaluated, and an extraction unit.
Based on the extracted said regions, the classification unit for classifying a sample of the evaluation object to one of a plurality of segments classified the degree of appropriateness of the inspected specimen on the basis of the color of the area of the sample The sputum to be evaluated is classified into one of a plurality of categories classified by the Geckler classification based on the number of regions representing leukocytes and the number of regions representing the number of squamous epithelial cells in the extracted regions. And the classification department that classifies
A sample image of a sample classified into the same category as the category classified by the classification unit and a sample image of a sample classified into the same category and the category closest to the degree of suitability among the plurality of categories are described. An information processing device equipped with a display control unit that displays an image to be evaluated. An acquisition unit that Gram stains the evaluation target sample as an evaluation target image of the evaluation target sample whose suitability as an inspection target is evaluated , and acquires an image magnified at a second magnification in which microorganisms can be observed .
An extraction unit that extracts a color region representing a microorganism Gram-stained as a specific color from the acquired image to be evaluated, and an extraction unit.
A classification unit that classifies the sample to be evaluated into one of a plurality of categories that classify the degree of suitability of the sample as a test target based on the extracted region of the color of the sample. ,
The sample image of the sample classified into the same category as the category classified by the classification unit and the sample image of the sample classified into the same category and the category having the closest degree of suitability among the plurality of categories are described. A display control unit that displays with the image to be evaluated,
An information processing apparatus including an output unit that outputs information recommending staining by a method other than Gram stain when the shape, size, and number of links of the extracted regions do not satisfy the conditions as bacteria . Computer,
As an evaluation target image of sputum , which is a sample to be evaluated whose suitability as an inspection target is evaluated, an acquisition unit that acquires an image of the sputum to be evaluated in an unstained state, and an acquisition unit.
An extraction unit that extracts a color region representing purulent sputum as a specific color from the acquired image to be evaluated, and an extraction unit.
Based on the extracted said regions, the classification unit for classifying a sample of the evaluation object to one of a plurality of segments classified the degree of appropriateness of the inspected specimen on the basis of the color of the area of the sample There is a classification unit that classifies sputum to be evaluated into one of a plurality of categories classified by Miller & Jones classification based on the size of the extracted region .
The sample image of the sample classified into the same category as the category classified by the classification unit and the sample image of the sample classified into the same category and the category having the closest degree of suitability among the plurality of categories are described. A program to function as a display control unit to be displayed together with the image to be evaluated. Computer,
As an evaluation target image of sputum , which is a sample to be evaluated whose suitability as a test target is evaluated, an image in which the sputum to be evaluated is glam-stained and leukocytes and squamous epithelial cells are enlarged at an observable first magnification. And the acquisition department to acquire
An extraction unit that extracts a color region representing leukocytes and squamous epithelial cells that have been Gram-stained as a specific color from the acquired image to be evaluated, and an extraction unit.
Based on the extracted said regions, the classification unit for classifying a sample of the evaluation object to one of a plurality of segments classified the degree of appropriateness of the inspected specimen on the basis of the color of the area of the sample The sputum to be evaluated is classified into one of a plurality of categories classified by the Geckler classification based on the number of regions representing leukocytes and the number of regions representing the number of squamous epithelial cells in the extracted regions. And the classification department that classifies
The sample image of the sample classified into the same category as the category classified by the classification unit and the sample image of the sample classified into the same category and the category having the closest degree of suitability among the plurality of categories are described. A program to function as a display control unit to be displayed together with the image to be evaluated. Computer,
An acquisition unit that Gram stains the evaluation target sample as an evaluation target image of the evaluation target sample whose suitability as an inspection target is evaluated , and acquires an image magnified at a second magnification in which microorganisms can be observed .
An extraction unit that extracts a color region representing a microorganism Gram-stained as a specific color from the acquired image to be evaluated, and an extraction unit.
A classification unit that classifies the sample to be evaluated into one of a plurality of categories that classify the degree of suitability of the sample as a test target based on the extracted region of the color of the sample. ,
The sample image of the sample classified into the same category as the category classified by the classification unit and the sample image of the sample classified into the same category and the category having the closest degree of suitability among the plurality of categories are described. A display control unit that displays with the image to be evaluated,
A program for functioning as an output unit that outputs information recommending staining by a method other than Gram stain when the shape, size, and number of links of the extracted region do not satisfy the conditions as a bacterium .

Images