WO2005121784A1 - 医用画像処理システム - Google Patents
医用画像処理システム Download PDFInfo
- Publication number
- WO2005121784A1 WO2005121784A1 PCT/JP2005/010693 JP2005010693W WO2005121784A1 WO 2005121784 A1 WO2005121784 A1 WO 2005121784A1 JP 2005010693 W JP2005010693 W JP 2005010693W WO 2005121784 A1 WO2005121784 A1 WO 2005121784A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image data
- living body
- image processing
- medical image
- calculated
- Prior art date
Links
Classifications
-
- 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
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/48—Analysis of texture based on statistical description of texture using fractals
-
- 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
- G06V20/695—Preprocessing, e.g. image segmentation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- 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
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Definitions
- the present invention relates to a medical image processing system for processing medical image data related to a living body, and in particular, to a medical image processing system that determines characteristics of the living body based on a fractal dimension of the medical image data related to the living body.
- the present invention relates to a device, a medical image processing method, a medical image processing program, and a computer-readable recording medium that records the medical image processing program.
- a benign tumor cell is a cell clump obtained by strong binding between cells.
- Malignant tumors have a tendency to have a relatively smooth shape, and malignant tumors have a weak binding force, so they take advantage of the fact that cell clumps spread widely and the shape becomes complicated, and judgment based on human subjectiveness and experience
- Amorphous identification methods and devices that identify benign or bad cells by automatically analyzing irregular shapes without discrimination are disclosed (e.g., Patent Document 1 and Non-Patent Documents). See 3.) 0
- Non-Patent Document 4 attempts to numerically express the degree of malignancy of ductal carcinoma using a fractal dimension.
- This study in Non-patent Document 4 discloses the results of using fractal analysis to numerically describe the state of chromatin in mammary gland cytology. Nerve images of breast aspiration aspiration cytology of 19 patients and 22 patients with invasive ductal carcinoma show fractal Minkowski ( Minkowski) dimension and spectral dimension. It was also demonstrated that the appearance of chromatin in the nuclear image of mammary epithelial cells was fractal, indicating that the three-dimensional structure of chromatin in epithelial cells also had fractal properties. Suggest. A statistically significant difference in the average spectral dimension between benign and malignant tumors has been demonstrated, finding a very weak correlation between the two fractal dimensions .
- Patent Document 2 in a blood smear, an image analysis result, which tends to be unstable due to staining or microscope setting conditions, is normalized by using an analysis result of a non-target cell.
- a medical image processing apparatus for providing more useful information for identifying a disease has been disclosed.
- the medical image processing apparatus performs image processing on lymphocyte nuclei in addition to neutrophil cell nuclei to be subjected to image processing, and uses image analysis results obtained from lymphocyte nuclei. By standardizing the image analysis results of neutrophil cell nuclei, image analysis independent of staining and microscope setting conditions is performed.
- the medical image processing apparatus is an apparatus that identifies a target object using image information, and includes an image extracting unit that extracts an area where an object is present from an input image, A luminance information calculation unit that extracts the contour of the object and calculates the luminance of the extracted portion and information analyzed based on the luminance.
- Patent Document 1 Japanese Patent Application Publication No. 1999-120350.
- Patent Document 2 Japanese Patent Application Publication No. 2002 140692.
- Non-Patent Document 2 Simon S. Cross, Fractals In Pathology ", Journal of Pathology, Vol. 182, pp. 1—8, 1997.
- Non-Patent Document 3 Hideyasu Takayasu et al., "Application of Fractal Image Analysis to Cytologic Diagnosis, Medical Imaging Technology, Vol. 15. No. 5, pp. 587—591 , September, 1997.
- Patent Document 4 Andrew J. Einstein, et al., "Fractal Characterization of Chromatin Ap pearance for Diagnosis in Breast Cytology", Journal of Pathology, Vol. 185, pp. 366- 381, 1998.
- Active malignant cells are known to have enhanced transcription of abnormal gene proteins, and in the cell nucleus, tend to be distributed as abnormal aggregation of protein molecules related to transcription factors and the like.
- the distribution is known to be complex.
- these distribution abnormalities are often visually observed by an observer, and are often judged by words based on empirical rules and by vague and subjective judgments.
- the distribution is subjectively determined based on the empirical side of the observer, such as fine granularity and coarse reticulation. It was determined that
- An object of the present invention is to solve the above-mentioned problems, and to provide a medical image processing apparatus and method, a medical image processing program, and a medical image processing method capable of quantitatively determining the characteristics of a living body with higher accuracy and higher accuracy compared to the related art.
- Another object of the present invention is to provide a recording medium on which the medical image processing program is recorded.
- a medical image processing apparatus is a medical image processing apparatus for analyzing characteristics of a living body based on image data of the living body
- a fractal dimension D of the shape image data is calculated based on the obtained shape image data and pattern image data, and a fractal dimension D of the pattern image data is calculated.
- the information of the shape image data is substantially removed.
- C is a predetermined third constant.
- CI dD ZD (where d is a predetermined value)
- the determining means determines the characteristics of the living body by comparing the calculated index value with a predetermined threshold value.
- the threshold value is preferably a predetermined value capable of distinguishing the characteristics of the living body based on image data of a plurality of living bodies whose characteristics of the living body are known.
- the image analysis processing includes at least one of edge processing and binarization processing. Still further, the image analysis processing preferably further includes a conversion processing into color image data and gray scale image data.
- the living body is a cell nucleus
- the image data of the living body is chromatin image data of the cell nucleus
- the pattern image data of the living body is a cell nucleus.
- the image data is chromatin pattern image data
- the determining means determines biological evaluation of the cell nucleus based on the calculated index value.
- the biological evaluation is preferably the malignancy of the cell nucleus cancer.
- the living body is a part of a living body
- the image data of the living body is a medical image that captures the part of the living body using a predetermined signal wave. Obtained by imaging with an imaging device.
- the living body is an organ of an organism
- the shape image data is image data of the shape of the organ
- the pattern image data is a distribution of non-uniformity of a lesion in the organ.
- An image processing method is an image processing method for analyzing characteristics of a living body based on image data of the living body.
- a fractal dimension D of the shape image data is calculated based on the obtained shape image data and pattern image data, and a fractal dimension D of the pattern image data is calculated.
- the information of the shape image data is substantially removed.
- the determining may include the calculated index value. Is compared with a predetermined threshold value to determine the characteristics of the living body.
- the threshold value is preferably a predetermined value based on image data of a plurality of living bodies whose characteristics of the living body are known.
- the image analysis processing includes at least one of an edge processing and a binary processing. Furthermore, the image analysis processing preferably further includes a conversion processing into color image data power gray scale image data.
- the living body is a cell nucleus
- the image data of the living body is chromatin image data of the cell nucleus
- the pattern image data of the living body is a chromatin pattern of the cell nucleus.
- Image data, wherein the determining step determines biological evaluation of the cell nucleus based on the calculated index value.
- the biological evaluation is preferably the degree of malignancy of the cell nucleus cancer.
- the living body is a part of a living body, and the image data of the living body is imaged by a medical imaging device that images the part using a predetermined signal wave. Is obtained.
- the living body is an organ of an organism
- the shape image data is image data of the shape of the organ
- the pattern image data is a distribution of non-uniformity of a lesion in the organ.
- the judgment step judges a biological evaluation of a lesion in the organ based on the calculated index value.
- An image processing program according to a third invention is characterized by including the steps of the image processing method.
- a computer-readable recording medium is characterized by recording the above-mentioned image processing program.
- the medical image processing apparatus and method by performing a predetermined image analysis process on image data of a living body, the shape image data obtained by extracting the contour of the living body can be obtained. And pattern image data obtained by extracting a pattern in the outline of the living body. Next, a fractal dimension D of the shape image data is calculated based on the obtained shape image data and pattern image data, and the fractal dimension D of the pattern image data is calculated. After calculating the fractal dimension D, the fractal dimension D
- An index value CI is calculated which substantially removes and substantially contains information on the pattern of the pattern image data. Further, the characteristic of the living body is determined based on the calculated index value. Therefore, the index value CI that substantially removes the information of the image data related to the shape of the living body and substantially includes the pattern information of the pattern image data is calculated, and the calculated index value is calculated as the index value CI. Since the characteristics of the living body are determined based on the above, it is possible to quantitatively determine the characteristics of the living body with a very simple processing method and with higher accuracy than in the related art.
- FIG. 1 is a block diagram showing a configuration of a medical image processing system including a medical image processing apparatus 10 for executing analysis and evaluation processing of biological cell nucleus chromatin pattern image data according to an embodiment of the present invention. .
- FIG. 2 is a flowchart of a main flow showing a process of analyzing and evaluating biological cell nucleus chromatin pattern image data performed by the medical image processing apparatus 10 of FIG. 1.
- FIG. 3 is a subroutine of FIG. 2, and is a flowchart showing a judgment process (step S5-1) according to a first embodiment of the processing example.
- FIG. 4 is a subroutine of FIG. 2, and is a flowchart showing a judgment process (step S5-2) according to a second embodiment processing example.
- FIG. 5 is a flowchart showing a subroutine of FIG. 2 and showing a judgment process (step S5-3) according to a third embodiment of the present invention.
- FIG. 6 is a schematic analysis diagram showing the principle of fractal dimension analysis processing by a box counting method used in the fractal calculation processing of FIG. 2.
- FIG. 7 A graph showing the logarithmic value LogN (r) of the number of cells with respect to the logarithmic value Log (r) of the length r of one side of the divided square, which is an example of the result of the fractal dimension analysis processing by the box counting method of FIG. is there.
- FIG. 8 is a table showing cases according to Example 1.
- FIG. 9 is a graph showing the results of analysis and evaluation of cell nuclei in cases according to Example 1.
- the chromatin index CI value of relapsed and non-relapsed cases was statistically significant (P ⁇ 0.001).
- FIG. 1 A first figure.
- FIG. 10 is a table showing an estimation result of recurrence, which is an analysis and evaluation processing result on a cell nucleus of a case according to Example 2.
- FIG. 11 is a table showing a change in accuracy due to a threshold change, which is a result of analysis and evaluation processing on cell nuclei in cases according to Example 2.
- FIG. 12 is a photograph showing an example of image data including a plurality of cell nuclei stored by the image input processing of FIG. 2.
- FIG. 13 is a photograph showing an example of image data for each cell nucleus extracted from the image data in FIG. 11 by the first image analysis processing in FIG. 2.
- FIG. 14 Image data of a single cell nucleus extracted by the first image analysis processing in Figure 2 (the original image data is a color image data of 10.64 million colors. In Figure 14, the image data was converted to grayscale image data. 12 shows image data.) FIG.
- FIG. 15 is a photograph showing an example of image data of each of the RGB colors for the image data in FIG.
- FIG. 16 is a photograph showing an example of image data of each RGB color after binarization processing and edge processing by the first image analysis processing of FIG. 2 with respect to the image data of each RGB color of FIG. 15;
- FIG. 17 A is a photograph of the chromatin image data after the first image analysis processing of FIG. 2 on the cell nucleus image data of the first experimental example, and the fractal dimension calculated by the fractal calculation processing of FIG. D is shown, and B is the nuclear shape image after the second image analysis processing in FIG.
- FIG. 2 shows a photograph showing an example of data image data and a fractal dimension D calculated by the fractal operation processing of FIG. 2, and C represents chromatin after the first image analysis processing of FIG. 2.
- FIG. 3 is a diagram showing a photograph of image data and a chromatin index CI value calculated by the fractal calculation process of FIG. 2 relating to the photograph.
- FIG. 18 A is a photograph of the chromatin image data of the cell nucleus image data of the second experimental example after the first image analysis processing of FIG. 2 and the fractal dimension calculated by the fractal calculation processing of FIG. D is shown, and B is the nuclear shape image after the second image analysis processing in FIG.
- the calculated fractal dimension D is shown, and C is the chromatin after the first image analysis processing in FIG.
- FIG. 3 is a diagram showing a photograph of image data and a chromatin index CI value calculated by the fractal calculation process of FIG. 2 relating to the photograph.
- FIG. 20 is a photograph showing a plurality of chromatin pattern image data of four malignant cases A, B, C, and D according to Example 1, and a photograph showing an average value of a chromatin index CI value of each malignant case.
- Fig. 21 is an ultrasonic image of a typical breast cancer according to Example 3, which is a photograph showing an irregular shape of the breast cancer and a nonuniform internal lowness.
- FIG. 22 is an ultrasonic image of a typical breast cancer according to Example 3, which is a photograph showing internal unevenness and calcification of the breast cancer.
- FIG. 23 is an X-ray image of a typical breast cancer according to Example 4, which is a photograph showing calcification of the breast cancer.
- Lymph node metastasis, estrogen receptor expression, Her-2 overexpression, and histological grade are known as predictors of breast cancer prognosis, and recurrence risk items are regarded as important in treatment strategies.
- Breast aspiration aspiration cytology is reliable for preoperative benign and malignant diagnosis Power has not been evaluated as a prognostic factor.
- the present inventors performed a fractal analysis in order to clarify whether or not the nuclear chromatin pattern of the cancer cells of the breast aspiration material can be a prognostic factor for recurrence.
- FIG. 1 is a block diagram showing a configuration of a medical image processing system including a medical image processing apparatus 10 for performing analysis and evaluation processing of biological cell nucleus chromatin pattern image data according to an embodiment of the present invention. It is.
- FIG. 2 is a flowchart of a main flow showing the analysis and evaluation processing of the biological cell nucleus chromatin pattern image data executed by the medical image processing apparatus 10 of FIG.
- the medical image processing apparatus 10 according to the present embodiment performs analysis and evaluation of the biological cell nucleus chromatin pattern image data of FIG.
- Step SI Image input processing
- Step S2 first image analysis processing
- Step S3 second image analysis processing
- Step S4 fractal dimension calculation processing
- Step S5 judgment processing
- the communication interface 2a in the CCD digital camera 2 of the imaging device 60 and the communication interface 52 of the medical image processing device 10 are connected via a communication cable 50.
- These communication interfaces 2a and 51 are, for example, a USB (Universal Serial Bus) interface or a LAN (Local Area Network) interface.
- image data including, for example, cell nuclei of breast cancer, captured by the CCD digital camera 2 using the microscope 1 is transmitted from the imaging device 60 to the medical image processing device 10 and received by the medical image processing device 10 to perform image processing. Is done.
- the medical image processing apparatus 10 First, the configuration of the medical image processing apparatus 10 will be described with reference to FIG.
- the medical image processing device 10
- a computer CPU (central processing unit) 20 for calculating and controlling the operation and processing of the medical image processing apparatus 10;
- a ROM (read only memory) 21 for storing a basic program such as an operation program and data necessary for executing the program
- a RAM (random access memory) 22 that operates as a working memory of the CPU 20 and temporarily stores parameters and data necessary for image processing;
- MRI image data which is composed of, for example, a node disk memory and is received from the MRI apparatus 1
- An image memory 23 for storing image data during image processing and image data after image processing;
- a program memory 24 which is constituted by, for example, a node disk memory and stores the image processing program of FIG. 2 read using the CD-ROM drive device 45;
- a printer that is connected to a printer 44 that prints image data processed by the CPU 20 and a predetermined analysis result, performs predetermined signal conversion of print data to be printed, and outputs to the printer 44 for printing.
- Interface 34
- (k) Read the program data of the image processing program from the CD-ROM 45a in which the image processing program is stored.
- the program data of the read image processing program is connected to the CD-ROM drive device 45 and converted into a predetermined signal. And a drive device interface 35 for transferring the data to the program memory 24.
- circuits 20-24, 31-34 and 51 are connected via a bus 30.
- image data of a living cell nucleus generated by the CCD digital camera 2 of the imaging device 60 is transmitted from the communication interface 2a of the CCD digital camera 2 to the communication interface 51 of the medical image processing device 10 via the communication cable 60. After being transmitted and received, it is temporarily stored in the image memory 23 for image processing (step in FIG. 2). Sl).
- a cytological specimen of breast cancer is subjected to a known staining method using, for example, hematoxylin (a dark blue basic dye) (for example, the original method of Papanicolaou).
- hematoxylin a dark blue basic dye
- the chromatin image data is obtained by a CCD digital camera. 2 is transmitted from the communication interface 2 a to the communication interface 51 of the medical image processing apparatus 10 via the communication cable 60.
- step S1 of Fig. 2 an image input process is executed. That is, the biological cell nucleus chromatin image data is received from the CCD digital camera 2 and temporarily stored in the image memory 23.
- the power using the imaging device 60 composed of the microscope 1 and the CCD digital camera 2 is not limited to this, and the imaging device such as a CCD camera, a scanner, or a digital camera may be directly used. You can use it for imaging.
- a first image analysis process is performed. That is, the image data of each cell nucleus was extracted from the biological cell nucleus chromatin image data, and a binary thresholding process was performed on the image data for each cell nucleus after the extraction using a predetermined threshold and value.
- an analysis process is executed by executing the edge extraction process to identify the chromatin pattern distribution, and the processed image data is converted into the chromatin pattern image data after the first image analysis process (256 gradations for each RGB color). ) Is stored in the image memory 23.
- Non-Patent Document 1 A known method can be used.
- image data of each cell nucleus may be extracted by manually specifying the outer contour of each cell nucleus.
- the binarization process and the edge extraction process may execute at least one process.
- at least one process may be performed on the color image data.
- RGB Image conversion processing for converting into grayscale image data of each color may be further executed. In this case, preferably, after performing the edge extraction processing on the image data of the cell nucleus, the image conversion processing is performed, and an arbitrary density of the staining density gradation of the cell nucleus is determined.
- V ⁇ value Executes binarization processing.
- step S3 a second image analysis process is performed. That is, image data of a cell nucleus shape in which the outer contour line of the image data for each cell nucleus after the extraction is solid black is generated, and the processed image data is processed into the nuclear shape image data after the second image analysis process.
- the image data is stored in the image memory 23 as (256 gradations for each color of RGB).
- step S4 a fractal dimension calculation process is performed. That is, for each cell nucleus, based on the chromatin pattern image data and the nucleus shape image data, each fractal dimension D, D is calculated using, for example, a box counting method.
- the fractal dimension of the image data is calculated by the box counting method for the image data after the image analysis processing.
- the box counting method is a general method for obtaining the fractal dimension of digital image power.
- N (r) be the number of.
- the logarithm of the length of one side of the divided square (the size of the divided square) is plotted on the horizontal axis, and the logarithm of the number of squares overlapping the figure is plotted on the vertical axis.
- a straight line with a slope of is obtained, and this slope becomes the fractal dimension. Fluctuations occur when analyzing actual image data, so the slope of the graph is determined by the least squares method or the like.
- the force using the box counting method is not limited to this, and other methods such as the Hausdorff dimension method may be used.
- step S5 a determination process is performed. That is, for each cell nucleus, the fractal dimension D of chromatin pattern image data and the fractal dimension of nuclear shape image data
- the chromatin index CI is a characteristic of cell nuclei.
- the chromatin index CI may be displayed to indicate the degree of sex.
- the characteristics of the cell nucleus may be interpreted to include the meaning of the degree.
- a is a predetermined first constant
- b is a predetermined second constant.
- the threshold for binarization processing for the three color RGB image data was obtained by shifting the /! Value, for example, from 80 to 150 gradations by 10 gradations.
- one fractal dimension D can be calculated by setting, for example, 130 gradations as one threshold value.
- the value of the chromatin index CI substantially eliminates the information of the nuclear shape image data and substantially replaces the information of the pattern of the pattern image data. Will be included.
- the fractal dimension D of the chromatin pattern image data indicates the complexity of the chromatin distribution
- the fractal dimension D of the data indicates the complexity of the nuclear shape only, hence the chromatin index CI
- the chromatin index is an index to which the “self-morphological difference method” is applied, and it has become possible to provide morphological information in which a morphological error or a shape error is reduced from a plurality of pieces of information of a cell morphology.
- these chromatin indices are based on the fact that the cell and nuclear morphology originally have a unique shape (nuclear shape) and a plurality of morphological information such as intranuclear proteins distributed inside them. Therefore, their relationship with the nuclear shape and the characteristic shape of chromatin cannot be ignored.
- the form or shape
- the idea is to extract the different characteristics of each and eliminate the influence between the parameters.
- These are called the self-morphological difference methods.
- the chromatin index CI using the self-morphological difference method
- Evaluation of the distribution of romatin became possible.
- the same morphological power Since multiple parameters obtained affect each parameter, the morphological parameters are subtracted, and the evaluation is performed using the dimensional difference.
- Non-Patent Document 4 was previously disclosed as a report example of the prior art, but this paper only discloses that fractal dimension analysis was used to evaluate nuclear chromatin for benign / malignant discriminant diagnosis. .
- the effects of nuclear shape were not considered when assessing nuclear chromatin.
- the shape of the cell nucleus in malignant cases shows an irregular shape, and it is necessary to remove the influence of the nuclear shape when evaluating nuclear chromatin.
- benign cases do not show nuclear irregularities, and nuclear shapes often show circular shapes composed of smooth lines.Malignant cases often show irregular shapes with coarse lines. It is. Therefore, it is desirable to correct the outer shape including the chromatin distribution at the time of evaluation.
- the embodiment according to the present invention uses a fractal dimension analysis as an evaluation of the degree of malignancy, and eliminates the influence of irregularities in the nuclear shape when evaluating the nuclear chromatin shape (self-morphological difference method).
- the evaluation of malignancy became possible.
- Estimation of recurrence and lymph node metastasis were shown as indicators of malignancy, and it became possible to evaluate nuclear chromatin distribution as such indicators.
- Non-Patent Document 4 analyzes the distribution of nuclear chromatin without discriminating the nucleus shape, for the purpose of discriminating only benign and malignant.
- the analysis of nuclear chromatin distribution e.g., self-morphological Method.
- the chromatin index CI is calculated using the equation (1).
- the chromatin index CI is calculated using any of the following equations (2) to (4). You may. That is, by using any of the following equations (2) to (4), information of the nuclear shape image data is substantially removed and chromatin substantially including the information of the pattern of the pattern image data is used.
- the indicator CI can be calculated.
- a is a predetermined first constant
- b is a predetermined second constant
- c is a predetermined third constant. Is a constant.
- a l
- b l
- c l are set.
- e is a predetermined fifth constant.
- e l.
- FIG. 3 is a subroutine of FIG. 2, and is a flowchart showing a judgment process (step S5-1) according to the first embodiment.
- step S11 first, for each cell nucleus, a fractal dimension D of chromatin pattern image data and Based on the fractal dimension D of the core shape image data and the above equation (1),
- step S12 it is determined whether or not CI ⁇ CIthr.
- step S13 it is determined that there is a high possibility that the breast cancer will recur, and the process proceeds to step S15.
- step S14 it is determined that the possibility of breast cancer recurrence is low, and the process proceeds to step S15. Further, in step S15, the judgment result is displayed and output on the CRT display 43, and the process returns to the main routine.
- FIG. 4 is a subroutine of FIG. 2, which is a determination process according to the second embodiment (step S5
- step S21 first, for each cell nucleus, based on the fractal dimension D of the chromatin pattern image data and the fractal dimension D of the nuclear shape image data,
- FIG. 5 is a subroutine of FIG. 2, which is a judgment process according to the third embodiment (step S5
- step S31 first, for each cell nucleus, the fractal dimension D of the chromatin pattern image data and the fractal dimension D of the nucleus shape image data are used.
- step S33 it is determined that the malignancy of the breast cancer is high, and the process proceeds to step S35.
- step S34 it is determined that the malignancy of the breast cancer is low, and the process proceeds to step S35. Further, in step S35, the judgment result is displayed and output on the CRT display 43, and the process returns to the main routine.
- the chromatin index threshold, value CIthr (threshold of recurrence! /, Value), CItht (threshold for metastasis to lymph node), and CIthm (threshold for malignancy) are, for example, as described above. Based on image data of a plurality of breast cancer cell nuclei for which the characteristics of breast cancer are known, their average value, maximum value, and the like are calculated (for example, see Examples 1 and 2 described later). It can be decided empirically in advance.
- the information of the image data relating to the shape of the living body is substantially removed, and the information of the pattern of the pattern image data is substantially eliminated. Since the index value CI is calculated based on the calculated index value and the characteristic or the degree of the living body is determined based on the calculated index value, a very simple processing method can be used with higher accuracy than the conventional technology. Quantitatively the characteristics of the living body or its degree, Can be determined.
- an index capable of quantitatively estimating the prognosis of cancer recurrence, cancer metastasis, and cancer malignancy can be obtained by calculating and analyzing a plurality of fractal dimensions having different recurrence cases and tumor diameters in advance.
- the chromatin index CI of a certain organism with a predetermined cancer malignancy threshold and value, it is possible to objectively and quantitatively determine whether the cancer malignancy is high or low. .
- the program when the image processing program data of FIG. 2 is stored and executed in the CD-ROM 45a, the program is loaded into the program memory 24 and executed.
- the present invention is not limited to this. It may be stored in various recording media such as a recording medium of an optical disk such as CD-RW, DVD, and MO, or a recording medium of a magneto-optical disk, or a recording medium of a magnetic disk such as a floppy (registered trademark) disk. These recording media are computer-readable recording media.
- the data of the image processing program of FIG. 2 may be stored in the program memory 24 in advance and the image processing may be executed.
- Example 1 the analysis is performed by fractal analysis and morphological examination of the nuclear chromatin pattern as a prognostic factor for breast cancer.
- the target was 69 invasive ductal carcinomas (14 recurrence cases, non-recurrence cases (nl. 24 cases, ⁇ . 31 cases). The details are shown in Fig. 8.
- the non-recurrence cases nl ⁇ is a lymph node metastasis case
- non-recurrence case ⁇ is a lymph node non-metastasis case
- the above-mentioned fractal dimension analysis was performed using the chromatin index CI indicating the complexity of chromatin distribution.
- FIG. 12 is a photograph showing an example of image data including a plurality of cell nuclei stored in the image input processing of FIG. 2 in the first embodiment.
- images of 1577 nuclei of 69 specimens obtained were photographed with Olympus BX51 microscope 1 and -kon CCD digital camera 2 (magnification: X600), and image data of only the target cell nuclei was obtained.
- the image data file has a bitmap file format of an arbitrary size.
- the photograph of the drawing attached in this application has the format of the grayscale JPEG file due to restrictions in online application.
- the photographing conditions were all the same.
- Figure 23 shows an example of extracting an analysis image.
- FIG. 13 is a photograph showing an example of image data for each cell nucleus extracted from the image data of FIG. 11 by the first image analysis processing of FIG. 2, and FIG. 14 is a full-color image of one cell nucleus.
- the image of the image data is shown.
- the image data of FIG. 12 was input to the medical image processing apparatus 10 of FIG. 2, and a predetermined image analysis process was performed on the input image data to obtain image data for identifying a chromatin distribution.
- edge extraction processing for extracting the contour shape of the cell nucleus chromatin was performed.
- the measurement target image data is RGB image data, and 21 gradations out of 80-150 gradations of 256 gradations of each color image (the gradations in 10 gradation steps, that is, 80 gradations, 90 gradations) , 100 gradations,..., 150 gradations were used as threshold values.)
- FIG. 15 shows the RGB image data before the edge extraction processing for the cell nucleus chromatin image data in FIG. 14, and
- FIG. 16 shows the RGB image data after the edge extraction processing.
- the outer contour shape is extracted based on the RGB image data after the edge extraction processing, and the fractal dimension D of the chromatin pattern image data in the contour and the solid in the contour are defined as black.
- A is a photograph of the chromatin image data after the first image analysis processing of FIG. 2 on the cell nucleus image data of the first experimental example, and is calculated by the fractal calculation processing of FIG. Fractal dimension D
- B is the nucleus after the second image analysis processing in FIG.
- Shape image data A photograph showing an example of image data, and the fractal operation shown in Fig. 2 2 shows the fractal dimension D calculated by the processing, and C shows the fractal dimension after the first image analysis processing in FIG.
- FIG. 3 is a diagram showing a photograph of chromatin image data and a chromatin index CI value calculated by the fractal calculation process of FIG. 2 for the photograph. Further, in FIG. 18, A is calculated by the photograph of the chromatin image data after the first image analysis processing of FIG. 2 for the cell nucleus image data of the second experimental example and the fractal calculation processing of FIG. Fractal dimension D
- FIG. B shows a photograph showing an example of the nuclear shape image data image data after the second image analysis processing of FIG. 2 and the fractal dimension D calculated by the fractal operation processing of FIG.
- 3C is a diagram showing a photograph of the chromatin image data after the first image analysis processing in FIG. 2 and a chromatin index CI value calculated by the fractal calculation processing in FIG.
- FIG. 19 shows the chromatin pattern image data when a plurality of cell nuclei of the case according to Example 1 were classified into a non-recurrent case (A) and a recurrent case (B), and the analysis in FIG. 14 is a photograph showing the chromatin index CI value as an average of the evaluation results.
- the chromatin index CI value was higher in the relapsed case than in the non-relapsed case, and the chromatin staining increased in calorie, indicating irregular crude chromatin properties.
- FIG. 9 is a graph showing the results of analysis and evaluation of the cell nuclei of the case according to Example 1, wherein the chromatin index CI value between the relapsed case and the non-relapsed case is statistically significant ( FIG. As is clear from FIG. 9, the chromatin index CI value (P ⁇ 0.001) of the relapsed case and the non-relapsed case has a statistically significant difference.
- FIG. 20 is a photograph showing a plurality of chromatin pattern image data for the four malignant cases A, B, C, and D according to Example 1, and a photograph showing the average value of the chromatin index CI value of each malignant case. . As is evident from Fig.
- the appearance of nucleoli and irregular distribution of chromatin can be visually recognized from the chromatin images, but it is difficult to distinguish between cases and to predict malignancy and recurrence. I understand.
- the mean power of the chromatin index CI has a significant difference.
- the nuclear chromatin images of A, B, C, and D shown in Fig. 20 all morphologically satisfy the malignant findings, the evaluation of the degree of malignancy is inaccurate by visual observation of the morphological chromatin pattern according to the conventional technology. Lack of reproducibility.
- the chromatin index CI was high in 85% (12Z14 cases) of recurrent breast cancer, and a significant difference was observed between the recurrent breast cancer cases and the non-breast cancer cases (P ⁇ 0 001), suggesting irregular chromatin distribution. 84% (21Z25 cases) of non-relapsed cases (n 0) with a tumor diameter of less than 2.5 cm had a relatively low chromatin index CI value. In non-relapsed cases (nl), a relatively high chromatin index CI value was found frequently in cases with a tumor diameter of 2.5 cm or more, and a correlation with the tumor diameter was observed (P ⁇ 0.001).
- Example 1 From the results of Example 1, it was inferred that nuclear chromatin of recurrent breast cancer cases had certain morphological characteristics. Chromatin in patients with recurrent breast cancer had multiple coarse aggregates around the nucleoli and was irregularly distributed. Aggregated chromatin was observed in the vicinity of the nuclear membrane of cells showing bright and fine aggregated chromatin in the nucleus. Then, fractal dimension analysis is performed on these nuclear chromatin patterns, and the chromatin index CI is calculated. The irregularities of the chromatin pattern could be quantitatively reduced. The quantification (quantification) of these patterns enables prediction of recurrence and quantitative evaluation of malignancy, and can provide clinical information useful for initial treatment.
- Example 1 A method of determining a recurrence case, a lymph node transfer case, and a biological malignancy of a test sample based on the fractal dimension calculated in Example 1 will be described below.
- the obtained cell nucleus specimen is photographed with a Olympus BX51 microscope 1 and a Nikon CCD digital camera 2 (magnification: X600) to create image data (bitmap file) of the cell nucleus specimen.
- the photographing conditions are the same as those in the first embodiment.
- the image data was input to the medical image processing apparatus in FIG. 1, and the analysis and evaluation processing in FIG. 2 was performed.
- the purpose-specific determination processing in FIGS. 3 to 5 was performed. That is, in the judgment processing for each purpose (relapse cases and lymph node metastasis cases, biological malignancy) shown in FIGS. 3 to 5, the calculated chromatin index CI is determined by the threshold values CIthr, CItht set for each purpose.
- the biological malignancy refers to a superordinate concept of the degree of recurrence and the degree of metastasis to lymph nodes, and these are hereinafter referred to as “malignancy and the like”.
- the principles of the present invention have applicability to medical image evaluation methods.
- the observation image has an irregular shape force, it is important to take into account the shape of the outline that is a collection of those patterns.
- medical images include many types of images having various shapes and fractal properties.
- X-ray photography, mammography (mammography), MRI (Magnetic Resonance Imaging) are known.
- XCT X-ray Computed Tomography
- PET Positron-emission Tomography
- imaging findings such as ultrasound echo are useful for daily observation and evaluation of lesions in clinical medicine.
- Fig. 21 is an ultrasonic echo image of a typical breast cancer according to Example 3, and is a photograph showing the irregular low-equal internal low echo of the breast cancer.
- Fig. 21 is an image obtained by scanning at intervals of 2.5 mm. A tumor image 2.5 cm in size is observed at the center. It is nodular with irregular edges and uneven low echo inside, with a strong border echo image in front of the mass.
- FIG. 22 is an ultrasonic echo image of a typical breast cancer according to Example 3, and is a photograph showing internal unevenness and calcification of the breast cancer.
- Figure 22 shows an example of a tumor with irregular and smooth margins that is somewhat difficult to distinguish from fibroadenoma. However, a strong point-like echo image is observed inside the tumor. Cancer with calcification.
- Figs. 21 and 22 show the ultrasound image of the mammary gland.
- the dimensions of the outline and the fractal dimensions that are indicators of internal echo non-uniformity were obtained. It is possible to mathematically formulate image information from the same tumor lesion and calculate the index value using the same formula as the chromatin index CI to judge the degree of malignancy of the lesion.
- FIG. 23 is an X-ray image of a typical breast cancer according to Example 4, and is a photograph showing calcification of the breast cancer.
- FIG. 23 no apparent mass shadow is observed, but a moderate amount of calcified image is observed on the right side of the breast.
- the calcified image is clearly depicted, and each calcified image has a variety of images such as circular, V-shaped, rod-shaped, and comma-shaped. Further, the calcified images are linearly arranged in the direction of the nipple.
- Fig. 23 is an X-ray image (mammography image) of breast cancer.
- the outline dimension and the fractal dimension that is an index of internal calcification are obtained. It is also possible to mathematically formulate the image information of those tumor lesions and calculate the index value using the same formula as the chromatin index CI to judge the degree of malignancy of the lesion.
- the shape of the calcification nest is scattered, uniform size.
- the shape of the calcification foci has characteristics such as denseness, irregularity in size, and abnormal shape. Therefore, these calcification patterns are evaluated using fractal dimension D, and information on fractal dimension D related to the shape of the lesion is removed.
- the chromatin index CI of the present invention is applied to organs such as breast cancer and epithelial lesions.
- the indicator CI may be applied to non-epithelial cancers such as muscle.
- the power code CI using the code CI as the chromatin index does not mean only the index of chromatin.
- the contour of the living body is extracted by executing a predetermined image analysis process on the image data of the living body. And image data obtained by extracting a pattern in the contour of the living body. Next, based on the obtained shape image data and pattern image data, the fractal dimension D of the shape image data is calculated, and the pattern
- An index value CI substantially including information of the image data and substantially including the pattern information of the pattern image data is calculated. Further, the characteristic or the degree of the living body is determined based on the calculated index value. Therefore, the index value CI that substantially removes the information of the image data related to the shape of the living body and substantially includes the information of the pattern of the pattern image data is calculated, and based on the calculated index value. Since the characteristics of the living body or the degree thereof are determined, the characteristics of the living body can be quantitatively determined with a very simple processing method with higher accuracy than the conventional technology.
- the image processing apparatus and method according to the present invention which provide a quantitative index of the distribution form of chromatin in cell nuclei, are useful as an objective index for an observer, and are used as preoperative and postoperative treatment selection as an index of malignancy. Can give information.
- it can be applied to, for example, basic medicine, applied medicine, biology, and basic science that require cell nucleus evaluation. It is used in all fields that handle cells, such as evaluation of test cell nuclei and cultured cell nuclei.
- the medical image processing apparatus and method according to the present invention are not limited to cell nucleus evaluation, but can be widely applied to evaluation of some internal organs and lesions of a living body.
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP05750443A EP1775585A4 (en) | 2004-06-10 | 2005-06-10 | SYSTEM FOR PROCESSING MEDICAL IMAGES |
JP2006514587A JP4748059B2 (ja) | 2004-06-10 | 2005-06-10 | 医用画像処理システム |
US11/628,955 US7865000B2 (en) | 2004-06-10 | 2005-06-10 | Medical image processing apparatus for analyzing properties of living body based on image data thereof |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2004-172669 | 2004-06-10 | ||
JP2004172669 | 2004-06-10 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2005121784A1 true WO2005121784A1 (ja) | 2005-12-22 |
Family
ID=35503201
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2005/010693 WO2005121784A1 (ja) | 2004-06-10 | 2005-06-10 | 医用画像処理システム |
Country Status (4)
Country | Link |
---|---|
US (1) | US7865000B2 (ja) |
EP (1) | EP1775585A4 (ja) |
JP (1) | JP4748059B2 (ja) |
WO (1) | WO2005121784A1 (ja) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009213555A (ja) * | 2008-03-07 | 2009-09-24 | Okayama Saiseikai General Hospital | 超音波エコー画像処理装置及び方法 |
CN101859383A (zh) * | 2010-06-08 | 2010-10-13 | 河海大学 | 基于时间序列重要点分析的高光谱遥感图像波段选择方法 |
JP2014094067A (ja) * | 2012-11-08 | 2014-05-22 | Fujifilm Ri Pharma Co Ltd | X線画像診断支援のためのコンピュータプログラム、装置及び方法 |
JP2014522532A (ja) * | 2011-06-06 | 2014-09-04 | コーニンクレッカ フィリップス エヌ ヴェ | 表現型を示す組み合わせサインのクロスモーダル適用 |
JP2015125609A (ja) * | 2013-12-26 | 2015-07-06 | 株式会社ケンシュー | 画像処理方法、画像処理プログラム、画像処理装置及び工業製品 |
JP2015194394A (ja) * | 2014-03-31 | 2015-11-05 | 富士フイルムRiファーマ株式会社 | 肺疾患判別プログラム、記録媒体及び肺疾患判別方法 |
JP2017029549A (ja) * | 2015-08-04 | 2017-02-09 | 国立大学法人佐賀大学 | 内視鏡画像処理装置、内視鏡画像処理方法及び内視鏡画像処理プログラム |
WO2020195258A1 (ja) * | 2019-03-26 | 2020-10-01 | 国立大学法人大阪大学 | 画像解析方法、画像解析プログラム、記録媒体、画像解析装置、画像解析システム |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9290010B2 (en) * | 2011-10-06 | 2016-03-22 | AI Cure Technologies, Inc. | Method and apparatus for fractal identification |
US20130215146A1 (en) * | 2012-02-17 | 2013-08-22 | Canon Kabushiki Kaisha | Image-drawing-data generation apparatus, method for generating image drawing data, and program |
US8942444B2 (en) * | 2012-08-17 | 2015-01-27 | General Electric Company | System and method for image compression in X-ray imaging systems |
CN103488997B (zh) * | 2013-09-09 | 2018-03-30 | 南京小网科技有限责任公司 | 基于各类重要波段提取的高光谱图像波段选择方法 |
CN111667467B (zh) * | 2020-05-28 | 2021-01-26 | 江苏大学附属医院 | 基于聚类算法的下肢血管钙化指数多参数累积计算方法 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11120350A (ja) | 1997-10-14 | 1999-04-30 | Sony Corp | 不定形の識別方法及び不定形の識別装置 |
US6026174A (en) | 1992-10-14 | 2000-02-15 | Accumed International, Inc. | System and method for automatically detecting malignant cells and cells having malignancy-associated changes |
JP2002140692A (ja) | 2000-10-30 | 2002-05-17 | Sysmex Corp | 画像解析装置 |
WO2003071468A1 (en) | 2002-02-22 | 2003-08-28 | Istituto Clinico Humanitas | Method and apparatus for analyizing biological tissue specimens |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU6654394A (en) * | 1992-12-14 | 1994-07-04 | University Of Washington | Order-based analyses of cell and tissue structure |
US5787201A (en) * | 1996-04-09 | 1998-07-28 | The United States Of America As Represented By The Secretary Of The Navy | High order fractal feature extraction for classification of objects in images |
AUPR647801A0 (en) * | 2001-07-19 | 2001-08-09 | Cea Technologies Inc. | Chromatin segmentation |
US7062079B2 (en) * | 2003-02-14 | 2006-06-13 | Ikonisys, Inc. | Method and system for image segmentation |
US6993187B2 (en) * | 2003-02-14 | 2006-01-31 | Ikonisys, Inc. | Method and system for object recognition using fractal maps |
AU2003249106A1 (en) * | 2003-07-09 | 2005-01-28 | Fondaione "Michele Roriguez" - Istituto Scientifico Per Le Misure Quantitative in Medicina | Method and apparatus for analyzing biological tissues |
-
2005
- 2005-06-10 WO PCT/JP2005/010693 patent/WO2005121784A1/ja active Application Filing
- 2005-06-10 JP JP2006514587A patent/JP4748059B2/ja not_active Expired - Fee Related
- 2005-06-10 US US11/628,955 patent/US7865000B2/en not_active Expired - Fee Related
- 2005-06-10 EP EP05750443A patent/EP1775585A4/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6026174A (en) | 1992-10-14 | 2000-02-15 | Accumed International, Inc. | System and method for automatically detecting malignant cells and cells having malignancy-associated changes |
JPH11120350A (ja) | 1997-10-14 | 1999-04-30 | Sony Corp | 不定形の識別方法及び不定形の識別装置 |
JP2002140692A (ja) | 2000-10-30 | 2002-05-17 | Sysmex Corp | 画像解析装置 |
WO2003071468A1 (en) | 2002-02-22 | 2003-08-28 | Istituto Clinico Humanitas | Method and apparatus for analyizing biological tissue specimens |
Non-Patent Citations (10)
Title |
---|
ANDREW J. EINSTEIN ET AL.: "Fractal Characterization of Chromatin Appearance for Diagnosis in Breast Cytology", JOURNAL OF PATHOLOGY, vol. 185, 1998, pages 366 - 381 |
BACKMAN V ET AL: "Measuring Cellular Structure at Submicrometer Scale With Light Scattering Spectroscopy.", vol. 7, no. 6, 2001, pages 887 - 893, XP001124015 * |
HARA T ET AL: "Nyubo X-sen Shashin ni okeru Shuryu In'ei no Ryoakusei Kanbetsu System no Kaihatsu.", MEDICAL IMAGING TECHNOLOGY., vol. 17, no. 5, September 1999 (1999-09-01), pages 577 - 584, XP002995841 * |
HIDEKI TAKAYASU ET AL.: "Application of Fractal Image Analysis to Cytologic Diagnosis", MEDICAL IMAGING TECHNOLOGY, vol. 15, no. 5, September 1997 (1997-09-01), pages 587 - 591 |
NIWA Y ET AL: "Digital Gazo o Mochiita Lymphocyte Kaku Kozo no Fractal Jigen no Sokutei.", vol. 50, no. 7, 2002, pages 702 - 705, XP002995842 * |
See also references of EP1775585A4 |
SIMON S. CROSS: "Fractals In Pathology", JOURNAL OF PATHOLOGY, vol. 182, 1997, pages 1 - 8 |
TOKOYAMA T.: "Nyugan Yogo Inshi to shite no Kaku Chromatin pattern no Fractal Kaiseki oyobi Keitaigakuteki Kento.", 22 May 2004 (2004-05-22), pages 140, XP002995840 * |
WILLIAM H. WOLBERG ET AL.: "Breast Cytology Diagnosis with Digital Image Analysis", BREAST CYTOLOGY DIAGNOSIS, vol. 15, no. 6, December 1993 (1993-12-01) |
WU H S ET AL: "Region Growing Segmentation of Chromatin Clumps of Ovarian Cells Using Adaptive Gradients.", JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY., vol. 48, no. 1, 23 March 2004 (2004-03-23), pages 22 - 27, XP002995843 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009213555A (ja) * | 2008-03-07 | 2009-09-24 | Okayama Saiseikai General Hospital | 超音波エコー画像処理装置及び方法 |
CN101859383A (zh) * | 2010-06-08 | 2010-10-13 | 河海大学 | 基于时间序列重要点分析的高光谱遥感图像波段选择方法 |
JP2014522532A (ja) * | 2011-06-06 | 2014-09-04 | コーニンクレッカ フィリップス エヌ ヴェ | 表現型を示す組み合わせサインのクロスモーダル適用 |
JP2014094067A (ja) * | 2012-11-08 | 2014-05-22 | Fujifilm Ri Pharma Co Ltd | X線画像診断支援のためのコンピュータプログラム、装置及び方法 |
JP2015125609A (ja) * | 2013-12-26 | 2015-07-06 | 株式会社ケンシュー | 画像処理方法、画像処理プログラム、画像処理装置及び工業製品 |
JP2015194394A (ja) * | 2014-03-31 | 2015-11-05 | 富士フイルムRiファーマ株式会社 | 肺疾患判別プログラム、記録媒体及び肺疾患判別方法 |
JP2017029549A (ja) * | 2015-08-04 | 2017-02-09 | 国立大学法人佐賀大学 | 内視鏡画像処理装置、内視鏡画像処理方法及び内視鏡画像処理プログラム |
WO2020195258A1 (ja) * | 2019-03-26 | 2020-10-01 | 国立大学法人大阪大学 | 画像解析方法、画像解析プログラム、記録媒体、画像解析装置、画像解析システム |
JP7450942B2 (ja) | 2019-03-26 | 2024-03-18 | 国立大学法人大阪大学 | 画像解析方法、画像解析プログラム、記録媒体、画像解析装置、画像解析システム |
Also Published As
Publication number | Publication date |
---|---|
EP1775585A4 (en) | 2010-08-04 |
US20080267485A1 (en) | 2008-10-30 |
EP1775585A1 (en) | 2007-04-18 |
JPWO2005121784A1 (ja) | 2008-04-10 |
US7865000B2 (en) | 2011-01-04 |
JP4748059B2 (ja) | 2011-08-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4748059B2 (ja) | 医用画像処理システム | |
JP4504203B2 (ja) | 画像分析に基づいたエストロゲン及びプロゲステロン表現のスコアリング | |
EP2745111B1 (en) | System and method for the detection of precancer or cancer cells in a biological sample | |
Keenan et al. | An automated machine vision system for the histological grading of cervical intraepithelial neoplasia (CIN) | |
RIBER‐HANSEN et al. | Digital image analysis: a review of reproducibility, stability and basic requirements for optimal results | |
US11232565B2 (en) | Examining device for processing and analyzing an image | |
Fan et al. | Computed tomography-based texture analysis of bladder cancer: differentiating urothelial carcinoma from micropapillary carcinoma | |
Sahni et al. | Breast cancer detection using image processing techniques | |
JP2016507229A (ja) | 細胞レベルfishドットカウントのための方法及びシステム | |
CN107567631B (zh) | 组织样品分析技术 | |
Guillaud et al. | Exploratory analysis of quantitative histopathology of cervical intraepithelial neoplasia: Objectivity, reproducibility, malignancy‐associated changes, and human papillomavirus | |
Pham et al. | Correlation of ultra-high field MRI with histopathology for evaluation of rectal cancer heterogeneity | |
Wang et al. | Application of digital mammography-based radiomics in the differentiation of benign and malignant round-like breast tumors and the prediction of molecular subtypes | |
Reljin et al. | Multifractal-based nuclei segmentation in fish images | |
Yoshioka et al. | Fractal analysis method for the complexity of cell cluster staining on breast FNAB | |
Dreyfuss et al. | Comparison of CT Texture Analysis Software Platforms in Renal Cell Carcinoma: Reproducibility of Numerical Values and Association With Histologic Subtype Across Platforms | |
RU2321859C2 (ru) | Способ дифференциальной диагностики гиперплазии, интраэпителиальных неоплазий и рака шейки матки | |
Lee et al. | Evaluation of nuclear chromatin using grayscale intensity and thresholded percentage area in liquid‐based cervical cytology | |
Golatta et al. | LECANDUS study (LEsion CANdidate Detection in UltraSound Data): evaluation of image analysis algorithms for breast lesion detection in volume ultrasound data | |
Roshan et al. | Accuracy of digital image analysis (DIA) of borderline human epidermal growth factor receptor (HER2) immunohistochemistry in invasive ductal carcinoma | |
RU2450790C2 (ru) | Способ проведения исследования для диагностики злокачественного новообразования | |
Ballerini et al. | Fractal analysis of microscopic images of breast tissue | |
Li et al. | An investigation into the consistency in mammographic density identification by radiologists: effect of radiologist expertise and mammographic appearance | |
Dzulkifli et al. | A Computer-Aided Diagnosis (CAD) System for Automatic Counting of Ki67 Cells in Meningioma | |
Khozeymeh et al. | Comparison of FNA-based conventional cytology specimens and digital image analysis in assessment of pancreatic lesions |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KM KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2005750443 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2006514587 Country of ref document: JP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWW | Wipo information: withdrawn in national office |
Country of ref document: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 11628955 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 2005750443 Country of ref document: EP |