WO2015087524A1 - 抗核抗体画像解析システム、抗核抗体画像解析方法および抗核抗体画像解析プログラム - Google Patents
抗核抗体画像解析システム、抗核抗体画像解析方法および抗核抗体画像解析プログラム Download PDFInfo
- Publication number
- WO2015087524A1 WO2015087524A1 PCT/JP2014/006085 JP2014006085W WO2015087524A1 WO 2015087524 A1 WO2015087524 A1 WO 2015087524A1 JP 2014006085 W JP2014006085 W JP 2014006085W WO 2015087524 A1 WO2015087524 A1 WO 2015087524A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- titer
- luminance
- antinuclear antibody
- dilution factor
- image analysis
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/68—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving proteins, peptides or amino acids
- G01N33/6875—Nucleoproteins
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/693—Acquisition
Definitions
- the present invention relates to an antinuclear antibody image analysis system, an antinuclear antibody image analysis method, and an antinuclear antibody image analysis program for predicting titer by analyzing an antinuclear antibody image.
- Anti-nuclear antibody detection is used for important tests such as diagnosis of collagen disease, which is an autoimmune disease, determination of treatment strategy, and prognosis estimation.
- the most useful method for screening autoantibodies is a fluorescent antibody method. In this method, patient serum diluted to a certain concentration is added to and reacted with human laryngeal cancer-derived epithelial cells called Hep2 cells cultured on a slide glass, and then the presence or absence of antibodies that react with intracellular self-antigens. Is detected using a secondary antibody labeled with a fluorescent dye.
- Fluorescence pattern and antibody titer are obtained as a result of antinuclear antibody test by fluorescent antibody method.
- the determined titer is represented by 40 times positive, 80 times positive, 160 times positive, and the like.
- the 40-fold positive means that the fluorescence pattern is confirmed when the patient serum is diluted 40-fold, but the fluorescence pattern cannot be confirmed when the patient serum is further diluted (for example, 80-fold). ing.
- the determination of antinuclear antibodies by the fluorescent antibody method is performed in the following two steps.
- a qualitative test is performed on a specimen diluted at a certain magnification (for example, 40 times).
- a positive or negative determination is made visually by microscopic observation.
- a specimen determined to be negative for microscopic examination with a fluorescence microscope is considered to be antinuclear antibody negative.
- the second step further processing is performed on the specimen determined to be positive in the qualitative test.
- a slide glass is prepared by doubling the serum, and the antibody titer quantitative test is performed by the dilution factor. At that time, the highest dilution factor showing positive is taken as the antibody titer.
- the fluorescence pattern of the specimen is also determined.
- Patent Document 1 describes a method for measuring a final antibody titer by an indirect immunofluorescence measurement method when measuring antibodies against nuclear antigen and cytoplasmic antigen in human serum.
- the final antibody titer of patient serum is calculated based on the initial antibody titer of patient serum, the exposure time of the camera, and the maximum effective exposure time (final exposure time).
- Patent Document 1 describes a calculation formula for calculating the final antibody titer of serum using the initial antibody titer of patient serum, the exposure time of the camera, and the final exposure time. It is possible to determine a certain titer by using the calculation formula described in.
- the measurement method described in Patent Document 1 has a problem that the accuracy of the calculated antibody titer is low because the formula for calculating the antibody titer is defined in a simple linear format. That is, when the measurement method described in Patent Document 1 is used, there is a problem that the work cost can be reduced, but the prediction accuracy of the titer cannot be increased.
- the present invention provides an antinuclear antibody image analysis system, an antinuclear antibody image analysis method, and an antinuclear antibody that can reduce the work cost of predicting a titer using an antinuclear antibody image while maintaining the prediction accuracy of the titer.
- An object is to provide an image analysis program.
- the antinuclear antibody image analysis system includes at least one luminance calculation means for calculating the luminance of cell nuclei extracted from an antinuclear antibody image at a specified dilution rate, a staining pattern specified by the staining form of the cell nuclei, and And titer predicting means for predicting the titer of the antinuclear antibody using brightness at two dilution ratios.
- the antinuclear antibody image analysis method calculates the brightness of cell nuclei extracted from an antinuclear antibody image at a designated dilution factor, and a staining pattern specified by the staining form of the cell nucleus and at least one dilution factor.
- the anti-nuclear antibody titer is predicted using luminance.
- the anti-nuclear antibody image analysis program is a computer that calculates a luminance calculation process for calculating the luminance of cell nuclei extracted from an anti-nuclear antibody image at a specified dilution ratio, and a staining pattern specified by a staining form of cell nuclei. And a titer prediction process for predicting the titer of the antinuclear antibody using at least one luminance at a dilution ratio.
- the present invention it is possible to reduce the operation cost for predicting the titer using the antinuclear antibody image while maintaining the prediction accuracy of the titer.
- FIG. 1 is a block diagram showing an embodiment of an antinuclear antibody image analysis system according to the present invention.
- the antinuclear antibody image analysis system of this embodiment includes an image input unit 11, a cell nucleus extraction unit 12, a staining pattern determination unit 13, a luminance calculation unit 14, a titer prediction unit 15, and a prediction result output unit 16. It has.
- the image input means 11 inputs an antinuclear antibody image.
- the input antinuclear antibody image is an image of an antinuclear antibody diluted to a specific magnification. If the magnification of the input antinuclear antibody image is specified, for example, 40 times dilution, 80 times dilution, 160 times dilution, etc., the magnification is arbitrary. In this embodiment, an image obtained by photographing a secondary antibody labeled by the fluorescent antibody method is used as an antinuclear antibody image.
- the input antinuclear antibody image is not limited to an image generated using the fluorescent antibody method.
- the image input means 11 may read an antinuclear antibody image from a storage means (not shown) for storing an image, and receives an image transmitted from another device via a communication network (not shown). May be.
- the cell nucleus extraction means 12 extracts cell nuclei from the input antinuclear antibody image. At this time, the cell nucleus extraction means 12 may extract interphase and mitotic cell nuclei from the antinuclear antibody image based on the brightness and shape of the cell nuclei. This is because the accuracy of specifying a staining pattern, which will be described later, can be improved by extracting cell nuclei at the division stage.
- the method for extracting the cell nucleus from the antinuclear antibody image is arbitrary, and the cell nucleus extracting means 12 may extract the cell nucleus from the antinuclear antibody image using a widely known method.
- the staining pattern determination means 13 determines an antinuclear antibody pattern from the extracted cell nucleus.
- the fluorescent antibody method using a fluorescent dye can be classified mainly into a mottle type, a homogeneous type, a marginal type, a discrete mottle type, a nucleolus type, and a cytoplasm type according to the staining form. Therefore, the staining pattern determination unit 13 determines whether the antinuclear antibody can be classified into any one of these patterns based on the extracted staining form of the cell nucleus.
- this pattern of the antinuclear antibody is specified based on the staining form of the cell nucleus, this pattern is hereinafter referred to as a staining pattern.
- the staining pattern determination means 13 may determine that the antinuclear antibody is a homogeneous staining pattern.
- the staining pattern determination unit 13 may determine the staining pattern of the antinuclear antibody using another widely known method.
- the staining pattern determination means 13 may determine that the target antinuclear antibody has a plurality of staining patterns. That is, the staining pattern determination unit 13 may specify not only one staining pattern but also a plurality of staining patterns from the staining form of the cell nucleus.
- the luminance calculation means 14 calculates the luminance of the stained region of the cell nucleus.
- the luminance calculation unit 14 selects an interphase cell nucleus from the extracted cell nuclei.
- the luminance calculation means 14 calculates the average value of the Green values among the RGB values for each selected interphase cell nucleus. That is, here, the average value of the Green values is calculated by the number of cell nuclei.
- the luminance calculation means 14 calculates the average value of the green values of each cell nucleus in order to calculate one luminance value for the entire image. That is, the luminance can be calculated by the following formula 1.
- Luminance Average sum of Green values of each cell nucleus / Number of cell nuclei (Equation 1)
- the luminance calculation means 14 calculates the average value of the predetermined green value from each cell nucleus, and calculates the average value of the green value of the entire image calculated using the calculated average value of each cell nucleus. It is good.
- the method of calculating the luminance is not limited to the method of calculating using Equation 1.
- the titer predicting means 15 predicts the titer of the antinuclear antibody represented in the image using the identified staining pattern and the calculated brightness of the cell nucleus. At this time, the titer predicting means 15 predicts the titer by using the luminance calculated for the antinuclear antibody image at one specific dilution factor. Therefore, the anti-nuclear antibody image input to the image input means 11 may be only an image having a specific dilution ratio for one anti-nuclear antibody.
- the titer predicting means 15 of the present embodiment uses the luminance calculated from the anti-nuclear antibody image at a specific dilution factor to determine the luminance of the anti-nuclear antibody image at other dilution factors according to the characteristics of each staining pattern. Predict. Specifically, the titer predicting means 15 calculates a function indicating the relationship between the dilution factor and the brightness for each staining pattern. In general, the higher the dilution factor, the lower the luminance. Therefore, the function indicated by the luminance factor and the luminance is a monotonically decreasing function.
- a curve represented by this function may be referred to as a titer prediction curve. That is, it can be said that the titer prediction curve is a curve indicating the relationship between the dilution factor and the luminance.
- the titer predicting means 15 specifies the dilution factor at which the luminance is lower than a predetermined determination threshold based on the calculated function, and specifies the titer from the specified dilution factor.
- the determination threshold value is a threshold value for determining whether or not the staining pattern is visible, and is determined in advance for each staining pattern according to an empirical rule by an engineer or the like.
- variable representing the dilution factor is x and the luminance is y
- the titer prediction curve is expressed by the following equation 2.
- a is a constant determined for each staining pattern, and is determined in advance according to an empirical rule or the like.
- B ' is a value determined according to the calculated luminance.
- FIG. 2 is an explanatory diagram showing an example of a method for predicting the titer.
- the staining pattern determination unit 13 determines that the staining pattern is a homogeneous saddle type (homogeneous type).
- the horizontal axis represents a variable representing the dilution factor
- the vertical axis represents luminance.
- the dilution factor on the horizontal axis is indicated by a hole number (variable indicating the dilution factor).
- the dilution factor is 40, 80, 160, 320, 640, 1280, 2560, 5120, respectively. Assigned to Nos. 1-8.
- a determination threshold is set for the homogeneous type (homogeneous type) that is a staining pattern.
- the dilution factor at which the titer prediction curve is lower than the determination threshold is between 5th and 6th. Therefore, the titer predicting means 15 predicts the highest dilution factor No. 5 (640 times) among the dilution factors to be determined as the titer as the titer.
- the third (160 times) dilution ratio is selected, but the selection ratio is not limited to the third (160 times), and any dilution ratio may be selected. . Since the titer predicting means 15 of this embodiment calculates a titer prediction curve in a range before and after the dilution factor, for example, even when the third dilution factor is selected, only the luminance of the fourth and subsequent dilution factors is obtained. In addition, the luminance of the dilution factor before the second can be predicted in the same manner.
- the titer predicting means 15 calculates the titer prediction curve from the specified staining pattern and the luminance of the specific dilution factor, and specifies the dilution factor lower than the determination threshold. Therefore, it is not necessary to calculate the luminance of a plurality of dilution factors, and the cost for calculating the titer can be reduced.
- the titer since the titer is determined by gradually diluting the diluted serum, prepare multiple dilutions of serum, and negative or positive for each dilution of serum. It is necessary to judge whether. However, in this embodiment, it is only necessary to prepare and image a serum with a specific dilution factor, and it is not necessary to prepare serum with another dilution factor. Therefore, it is possible to reduce the cost of preparing a slide glass in which serum is diluted twice, and further, it is possible to save labor for observing each of the serum diluted twice.
- the titer prediction curve is represented by a relationship indicating exponential decay, and the function is determined according to a constant a determined for each staining pattern. Therefore, by using this titer prediction curve, the relationship between the dilution factor and the brightness can be expressed more appropriately, so that the prediction accuracy of the titer can be increased.
- the titer prediction unit 15 calculates a titer prediction curve for each possible staining pattern. May be calculated to predict the titer.
- the dilution ratio of serum used for the quantitative test is arbitrary. Therefore, the present invention can be similarly applied to other than the above-described dilution factors such as 40 times, 80 times, and 160 times (for example, 10 times, 100 times, etc.).
- the method for predicting the titer using an antinuclear antibody image having a specific dilution factor is described.
- the dilution factor used is not limited to one.
- the prediction result output means 16 outputs the prediction result by the titer prediction means 15.
- the output method of the prediction result is arbitrary.
- the prediction result output unit 16 may output only the titer of the input antinuclear antibody image.
- the prediction result output unit 16 may display the function calculated by the titer prediction unit 15 and the determination threshold in a graph.
- the prediction result output unit 16 is realized by, for example, a display device.
- the cell nucleus extraction means 12, the staining pattern determination means 13, the luminance calculation means 14, and the titer prediction means 15 are realized by a CPU of a computer that operates according to a program (antinuclear antibody image analysis program). For example, it is stored in a storage unit (not shown) provided in the antinuclear antibody image analysis system, and the CPU reads the program, and in accordance with the program, the cell nucleus extraction means 12, the staining pattern determination means 13, the luminance calculation means 14, and the titer.
- the prediction unit 15 may be operated.
- the cell nucleus extraction means 12, the staining pattern determination means 13, the luminance calculation means 14, and the titer prediction means 15 may each be realized by dedicated hardware.
- FIG. 3 is a flowchart showing an operation example of the antinuclear antibody image analysis system of the present embodiment.
- the cell nucleus extraction means 12 extracts cell nuclei from the antinuclear antibody image (step S22).
- the staining pattern determination unit 13 specifies the staining pattern of the antinuclear antibody based on the extracted staining form of the cell nucleus (step S23).
- the luminance calculation means 14 calculates the luminance of the extracted cell nucleus (step S24).
- the titer prediction means 15 calculates a titer prediction curve based on the specified staining pattern and the calculated brightness of the specific dilution factor (step S25). Then, the titer predicting means 15 predicts the titer by specifying the dilution factor smaller than the determination threshold value from the titer predicting curve (step S26).
- the luminance calculation unit 14 calculates the luminance in the stained region of the cell nucleus extracted from the antinuclear antibody image at the designated dilution factor, and the titer prediction unit 15 specifies the specific value.
- the anti-nuclear antibody titer is predicted using the stained pattern and the brightness at the specified dilution factor. Therefore, the work cost for predicting the titer using the antinuclear antibody image can be reduced while maintaining the prediction accuracy of the titer.
- the present embodiment it is possible to reduce the cost of creating a slide glass in which serum is diluted twice, and to save the trouble of observing each slide glass diluted in double. In other words, it is possible to perform the determination at the same time as the number of holes provided in the slide glass.
- slide glasses were prepared by diluting sera for 4 cases in which each staining pattern was specified, respectively, and images were obtained by staining each specimen at each dilution rate.
- a serum with a titer of 40 times was diluted to a maximum titer of 5120 times, and images of each titer were collected.
- the luminance calculated from the image is used as the luminance.
- the luminance illustrated in FIG. 4 was calculated.
- the luminance calculated from the image may be referred to as a measured value.
- FIG. 4 is an explanatory diagram showing the luminance at each titer.
- the values shown in FIG. 4 (a), FIG. 4 (b), FIG. 4 (c) and FIG. 4 (d) are calculated from the images of the staining patterns of the mottle type, homogeneous type, nucleolus type and discrete mottle type, respectively. Brightness.
- Equation 2 the brightness at 160 times the titer was substituted into Equation 2 or Equation 3 shown above to calculate the value of the constant b ', and the titer prediction curve was calculated.
- a value predetermined for each staining pattern is used for the constant a in Expression 2 or Expression 3.
- FIG. 5 to 8 are explanatory diagrams showing the relationship between the titer prediction curve calculated for each staining pattern and the measured values calculated from the collected images.
- the graph illustrated in FIG. 5 shows the relationship between the mottled titer and luminance
- the graph illustrated in FIG. 6 shows the relationship between the homogeneous titer and luminance.
- the graph illustrated in FIG. 7 shows the relationship between the titer of the nucleolus type and the luminance
- FIG. 8 shows the relationship between the titer of the discrete mottle type and the luminance.
- the points indicated by black crosses, cross marks, black squares, and white squares indicate the luminances of the respective titers calculated from the images of the cases of the respective staining patterns, and are indicated by solid lines.
- the curve shown shows the calculated titer prediction curve.
- a straight line drawn in parallel with the horizontal axis between luminance 0 and 50 indicates a determination threshold value for each staining pattern.
- each titer prediction curve In the estimation of each titer prediction curve, a measurement value of 160 times the titer is used. Therefore, as shown in FIG. 5 to FIG. Matches. 5 to 8 show that the calculated titer prediction curve approaches the measured value at each titer. In particular, as the titer increases, each measured value becomes a titer predicted curve. Asymptotically shown.
- the measured value of case 1 and the luminance of the titer prediction curve are both 5120 times the titer and below the determination threshold. Therefore, the titer of case 1 is determined to be 2560 times the titer both when the titer prediction curve is used and when the measured value is used. Similarly, the measured values of Case 3 and Case 4 are below the determination threshold at a titer of 2560 times. Therefore, the titer of case 3 and case 4 is determined to be 1280 times the titer both when the titer prediction curve is used and when the measured value is used.
- the titer cannot be determined as it is.
- the titer prediction curve of the present invention it is understood that the luminance is lower than the determination threshold by 640 times the titer. That is, the titer of case 2 can be determined to be 320 times the titer by using the titer prediction curve.
- the titer can be determined in the same manner as the staining pattern shown in FIG.
- the luminance adjustment function of the microscope works because the luminance is too high, and the luminance of the measured value is distorted.
- a gap is observed between the brightness indicated by the prediction curve (for example, cases 1, 3, and 4 at a titer of 40 times in FIG. 5).
- FIG. 9 is a block diagram showing an outline of an antinuclear antibody image analysis system according to the present invention.
- the antinuclear antibody image analysis system according to the present invention includes a luminance calculating unit 81 (for example, luminance calculating unit 14) that calculates the luminance of cell nuclei extracted from an antinuclear antibody image at a specified dilution factor, and a staining form of cell nuclei.
- luminance calculating unit 81 for example, luminance calculating unit 14
- titer predicting means 82 for example, titer predicting means 15 for predicting the titer of the antinuclear antibody using the identified staining pattern and the luminance at at least one dilution factor.
- Such a configuration can reduce the work cost of predicting the titer using the antinuclear antibody image.
- the titer predicting means 82 is based on the identified staining pattern and the calculated brightness of the specific dilution rate, and shows a titer prediction curve (for example, Formula 2 or Formula 3) showing the relationship between the dilution rate and the brightness.
- the titer of the antinuclear antibody may be predicted by calculating from the titer prediction curve a dilution factor that is smaller than a predetermined determination threshold according to the staining pattern.
- the luminance of each titer can be complemented, so that it is not necessary to prepare antinuclear antibodies having a plurality of dilution ratios, so that the work cost for predicting the titer can be reduced.
- the titer predicting means 82 may predict the maximum dilution factor as the titer of the antinuclear antibody among the dilution factors to be determined as the titer among the dilution factors smaller than the specified dilution factor. Good.
- the luminance calculation means 81 calculates an average value of predetermined color values (for example, Green values in RGB) from each cell nucleus, and calculates the entire image calculated using the calculated average value of each cell nucleus.
- the average value of the color values may be the luminance.
- the titer predicting means 82 may predict the titer of the antinuclear antibody for each of one or more staining patterns specified from one antinuclear antibody image.
- the work cost for predicting the titer can be further reduced by predicting the titers of a plurality of possible staining patterns from one antinuclear antibody image.
- the present invention is suitably applied to, for example, a system that analyzes a stained specimen of an antinuclear antibody by a fluorescent antibody method with image data and evaluates a fluorescent pattern and an antibody titer.
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Biomedical Technology (AREA)
- Hematology (AREA)
- Immunology (AREA)
- Molecular Biology (AREA)
- Urology & Nephrology (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Microbiology (AREA)
- Cell Biology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Biotechnology (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Pathology (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
Description
x=log2x’-C (ただし、Cは定数)
12 細胞核抽出手段
13 染色パターン判定手段
14 輝度算出手段
15 力価予測手段
16 予測結果出力手段
Claims (9)
- 指定された希釈倍率の抗核抗体画像から抽出される細胞核の輝度を算出する輝度算出手段と、
前記細胞核の染色形態により特定される染色パターンと、少なくとも1つの希釈倍率における前記輝度とを用いて、抗核抗体の力価を予測する力価予測手段とを備えた
ことを特徴とする抗核抗体画像解析システム。 - 力価予測手段は、特定された染色パターンと、算出された特定の希釈倍率の輝度に基づいて、希釈倍率と輝度との関係を示す力価予測曲線を算出し、染色パターンに応じて予め定められる判定閾値よりも小さくなる希釈倍率を力価予測曲線から特定することにより、抗核抗体の力価を予測する
請求項1記載の抗核抗体画像解析システム。 - 力価予測手段は、特定された希釈倍率よりも小さい希釈倍率のうち、力価として判定すべき希釈倍率の中で、最大の希釈倍率を抗核抗体の力価と予測する
請求項2記載の抗核抗体画像解析システム。 - 輝度算出手段は、各細胞核から予め定められた色の値の平均値を算出し、算出された各細胞核の平均値を用いて算出される画像全体の前記色の値の平均値を輝度とする
請求項1から請求項3のうちのいずれか1項に記載の抗核抗体画像解析システム。 - 力価予測手段は、1つの抗核抗体画像から特定される1つ以上の染色パターンのそれぞれについて、抗核抗体の力価を予測する
請求項1から請求項4のうちのいずれか1項に記載の抗核抗体画像解析システム。 - 指定された希釈倍率の抗核抗体画像から抽出される細胞核の輝度を算出し、
前記細胞核の染色形態により特定される染色パターンと、少なくとも1つの希釈倍率における前記輝度とを用いて、抗核抗体の力価を予測する
ことを特徴とする抗核抗体画像解析方法。 - 特定された染色パターンと、算出された特定の希釈倍率の輝度に基づいて、希釈倍率と輝度との関係を示す力価予測曲線を算出し、
染色パターンに応じて予め定められる判定閾値よりも小さくなる希釈倍率を力価予測曲線から特定することにより、抗核抗体の力価を予測する
請求項6記載の抗核抗体画像解析方法。 - コンピュータに、
指定された希釈倍率の抗核抗体画像から抽出される細胞核の輝度を算出する輝度算出処理、および、
前記細胞核の染色形態により特定される染色パターンと、少なくとも1つの希釈倍率における前記輝度とを用いて、抗核抗体の力価を予測する力価予測処理
を実行させるための抗核抗体画像解析プログラム。 - コンピュータに、
力価予測処理で、特定された染色パターンと、算出された特定の希釈倍率の輝度に基づいて、希釈倍率と輝度との関係を示す力価予測曲線を算出させ、染色パターンに応じて予め定められる判定閾値よりも小さくなる希釈倍率を力価予測曲線から特定させることにより、抗核抗体の力価を予測させる
請求項8記載の抗核抗体画像解析プログラム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/100,898 US9972085B2 (en) | 2013-12-11 | 2014-12-05 | Antinuclear antibody image analysis system, antinuclear antibody image analysis method, and antinuclear antibody image analysis program |
CN201480066893.8A CN105814441B (zh) | 2013-12-11 | 2014-12-05 | 抗核抗体图像分析系统、抗核抗体图像分析方法和抗核抗体图像分析程序 |
JP2015552326A JP6176752B2 (ja) | 2013-12-11 | 2014-12-05 | 抗核抗体画像解析システム、抗核抗体画像解析方法および抗核抗体画像解析プログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013-255558 | 2013-12-11 | ||
JP2013255558 | 2013-12-11 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015087524A1 true WO2015087524A1 (ja) | 2015-06-18 |
Family
ID=53370853
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/006085 WO2015087524A1 (ja) | 2013-12-11 | 2014-12-05 | 抗核抗体画像解析システム、抗核抗体画像解析方法および抗核抗体画像解析プログラム |
Country Status (4)
Country | Link |
---|---|
US (1) | US9972085B2 (ja) |
JP (1) | JP6176752B2 (ja) |
CN (1) | CN105814441B (ja) |
WO (1) | WO2015087524A1 (ja) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111512383B (zh) * | 2017-08-04 | 2023-09-19 | 文塔纳医疗系统公司 | 用于图像处理的自动测定评估和归一化 |
CN107545153B (zh) * | 2017-10-25 | 2021-06-11 | 桂林电子科技大学 | 一种基于卷积神经网络的核小体分类预测方法 |
CN113837255B (zh) * | 2021-09-15 | 2023-06-13 | 中国科学院心理研究所 | 预测以细胞为基质的抗体核型类别的方法、设备和介质 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08304284A (ja) * | 1995-05-09 | 1996-11-22 | Suzuki Motor Corp | 抗核抗体反応判定装置 |
JPH09218202A (ja) * | 1995-12-08 | 1997-08-19 | B M L:Kk | 抗核抗体の検出方法及び検出用キット |
US20080016015A1 (en) * | 2004-04-08 | 2008-01-17 | Petra Perner | Methods For Acquiring Shapes From Hep-2 Cell Selections And The Case-Based Recognition Of Hep-2 Cells |
JP2010210290A (ja) * | 2009-03-06 | 2010-09-24 | Olympus Corp | Dnaが断片化されたアポトーシス細胞の検出方法、細胞画像解析装置、プログラム、及びアポトーシスのステージの評価方法 |
JP2011503586A (ja) * | 2007-11-13 | 2011-01-27 | メディパン・ゲーエムベーハー | 間接免疫蛍光測定法による最終抗体価の測定方法およびその評価方法 |
JP2011043350A (ja) * | 2009-08-19 | 2011-03-03 | Olympus Corp | 細胞画像解析装置、細胞画像解析方法、及びコンピュータープログラム |
JP2011075278A (ja) * | 2009-09-29 | 2011-04-14 | Olympus Corp | 細胞核を構成する構造体の解析方法、及び細胞核の形態の解析方法 |
JP2013520664A (ja) * | 2010-02-22 | 2013-06-06 | メディパン・ゲーエムベーハー | 合成基材及び細胞基材に結合した抗体の同時検出による疾病診断のための方法及びシステム |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SE9900875D0 (sv) | 1999-03-11 | 1999-03-11 | Eurodiagnostica Ab | Antinuclear antibody assay utilizing stress-treated cells or cell extracts |
DE10127572A1 (de) * | 2001-05-30 | 2002-12-05 | Pathoarray Gmbh | Werkzeuge zur Diagnostik, molekularen Definition und Therapieentwicklung chronischer entzündlicher Gelenkerkrankungen |
ES2226549B1 (es) * | 2002-12-18 | 2006-07-16 | One Way Liver Genomics, S.L. | Metodo para el diagnostico de esteatohepatitis no alcoholica (nash) mediante el empleo de marcadores moleculares. |
-
2014
- 2014-12-05 WO PCT/JP2014/006085 patent/WO2015087524A1/ja active Application Filing
- 2014-12-05 JP JP2015552326A patent/JP6176752B2/ja active Active
- 2014-12-05 CN CN201480066893.8A patent/CN105814441B/zh active Active
- 2014-12-05 US US15/100,898 patent/US9972085B2/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08304284A (ja) * | 1995-05-09 | 1996-11-22 | Suzuki Motor Corp | 抗核抗体反応判定装置 |
JPH09218202A (ja) * | 1995-12-08 | 1997-08-19 | B M L:Kk | 抗核抗体の検出方法及び検出用キット |
US20080016015A1 (en) * | 2004-04-08 | 2008-01-17 | Petra Perner | Methods For Acquiring Shapes From Hep-2 Cell Selections And The Case-Based Recognition Of Hep-2 Cells |
JP2011503586A (ja) * | 2007-11-13 | 2011-01-27 | メディパン・ゲーエムベーハー | 間接免疫蛍光測定法による最終抗体価の測定方法およびその評価方法 |
JP2010210290A (ja) * | 2009-03-06 | 2010-09-24 | Olympus Corp | Dnaが断片化されたアポトーシス細胞の検出方法、細胞画像解析装置、プログラム、及びアポトーシスのステージの評価方法 |
JP2011043350A (ja) * | 2009-08-19 | 2011-03-03 | Olympus Corp | 細胞画像解析装置、細胞画像解析方法、及びコンピュータープログラム |
JP2011075278A (ja) * | 2009-09-29 | 2011-04-14 | Olympus Corp | 細胞核を構成する構造体の解析方法、及び細胞核の形態の解析方法 |
JP2013520664A (ja) * | 2010-02-22 | 2013-06-06 | メディパン・ゲーエムベーハー | 合成基材及び細胞基材に結合した抗体の同時検出による疾病診断のための方法及びシステム |
Non-Patent Citations (2)
Title |
---|
KAZUTO NAKAMURA ET AL.: "Image Titer Workstation (Keiko Gazo Kaiseki Sochi) o Mochiita Kokakukotai Sokutei no Kisoteki Kento", JAPANESE JOURNAL OF CLINICAL LABORATORY AUTOMATION, vol. 25, no. 4, 1 August 2000 (2000-08-01), pages 412 * |
TETSUO NAKABAYASHI ET AL.: "Simplification of antinuclear antibody determination by fluorescent image analysis equipment 'Image titer", THE JOURNAL OF CLINICAL LABORATORY INSTRUMENTS AND REAGENTS, vol. 22, no. 1, 1999, pages 69 - 72 * |
Also Published As
Publication number | Publication date |
---|---|
JPWO2015087524A1 (ja) | 2017-03-16 |
CN105814441B (zh) | 2017-10-03 |
US20160300345A1 (en) | 2016-10-13 |
US9972085B2 (en) | 2018-05-15 |
JP6176752B2 (ja) | 2017-08-09 |
CN105814441A (zh) | 2016-07-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bizzaro et al. | Automated antinuclear immunofluorescence antibody screening: a comparative study of six computer-aided diagnostic systems | |
US10169861B2 (en) | Image processing apparatus, non-transitory computer readable medium, and image processing method | |
EP3005293B1 (en) | Image adaptive physiologically plausible color separation | |
JP2019195304A (ja) | 画像解析方法、装置、コンピュータプログラム、及び深層学習アルゴリズムの生成方法 | |
JP2023065352A (ja) | 画像解析方法、画像解析装置、プログラム、学習済み深層学習アルゴリズムの製造方法および学習済み深層学習アルゴリズム | |
US20130026391A1 (en) | Information processing apparatus, information processing method, program, and method of correcting intensity of fluorescence spectrum | |
US11854196B2 (en) | System and method for real time assay monitoring | |
JP6176752B2 (ja) | 抗核抗体画像解析システム、抗核抗体画像解析方法および抗核抗体画像解析プログラム | |
US9424640B2 (en) | Pathological diagnosis support apparatus and pathological diagnosis support method | |
CN115902227B (zh) | 一种免疫荧光试剂盒的检测评估方法及系统 | |
CN111656393A (zh) | 组织学图像分析 | |
JP2014235033A (ja) | 画像処理装置及びプログラム | |
JP7393769B2 (ja) | 生物学的サンプルの画像に対するコンピュータ実装プロセス | |
US20220404283A2 (en) | Method and apparatus for detecting a presence of a fluorescence pattern type on an organ section by means of immunofluorescence microscopy | |
Bertin et al. | ICARE improves antinuclear antibody detection by overcoming the barriers preventing accreditation | |
JP5860738B2 (ja) | 尿検査装置、データ処理装置、データ処理方法、及びプログラム | |
US11985415B2 (en) | Microscopy system and method for generating an overview image | |
WO2023188803A1 (ja) | 自動欠陥分類装置 | |
CN116735598A (zh) | 一种面板检测方法、装置、设备及存储介质 | |
JP2023100357A (ja) | 情報処理装置及びプログラム | |
Lopez | Characterization and Colocalization of Tissue-Based Biomarker Expression by Quantitative Image Analysis: Development and Extraction of Novel Features |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14869779 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015552326 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15100898 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14869779 Country of ref document: EP Kind code of ref document: A1 |