KR20180039466A - Breast cancer diagnosis apparatus using thermal camera and method thereof - Google Patents
Breast cancer diagnosis apparatus using thermal camera and method thereof Download PDFInfo
- Publication number
- KR20180039466A KR20180039466A KR1020160130805A KR20160130805A KR20180039466A KR 20180039466 A KR20180039466 A KR 20180039466A KR 1020160130805 A KR1020160130805 A KR 1020160130805A KR 20160130805 A KR20160130805 A KR 20160130805A KR 20180039466 A KR20180039466 A KR 20180039466A
- Authority
- KR
- South Korea
- Prior art keywords
- breast cancer
- image
- unit
- thermal image
- contour
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0082—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
-
- 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
- G06T2207/10048—Infrared 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
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
Description
The present invention relates to an apparatus and method for diagnosing breast cancer using a thermal imaging camera, and more particularly, to an apparatus and method for diagnosing breast cancer using a thermal imaging camera, The present invention relates to an apparatus and method for diagnosing breast cancer using a thermal imaging camera that obtains analysis information and compares the obtained breast cancer thermal image analysis information and breast cancer thermal image analysis information with a breast of a normal person to determine whether or not breast cancer is present.
Breast cancer accounts for about 25% of females worldwide and is one of the most fertile cancers with high incidence and mortality. According to the 2012 data for breast cancer from the first stage to the third stage, the one-year survival rate is over 97%, and the survival rate for the fourth stage is 71%. In addition, the 5-year survival rate of the patient drops rapidly from 97% in the first stage diagnosis to 15% in the fourth stage diagnosis.
The survival rate and changes in prognosis of breast cancer patients are highly dependent on initial detection of breast cancer. Therefore, early diagnosis of breast cancer is very important, and various diagnostic methods have been developed for early diagnosis of breast cancer.
Methods of breast cancer diagnosis include self-examination, mammography, breast ultrasound, and magnetic resonance imaging (MRI).
The self-examination method has the disadvantage that it is not costly and there is no risk, but it is inferior in accuracy because it is checking whether there is no lump or other abnormality by touching one's own breast.
The mammography method is to enlarge only a specific part of the breast and to perform an examination to photograph the breast in a compressed state in order to obtain an image necessary for the diagnosis, causing pain during the examination and requiring a high cost of the examination.
The breast ultrasound method is advantageous in that it is relatively inexpensive and does not expose the patient to radiation, but has a problem that it is difficult to find a fine lime material.
Magnetic resonance imaging (MRI) can be used to detect cancerous tumors, but there is a high cost of installing and maintaining the apparatus, which increases the cost of medical care.
Thus, there is a demand for development of a diagnostic apparatus for breast cancer which can be performed more accurately for detecting breast cancer while reducing the installation and maintenance cost of the medical device and lowering the medical water price.
This demand, advanced sensor technology, and chemical treatment technology have been developed, and with the spread of mobile terminals such as a smart phone equipped with a thermal camera, considerable attention has been focused on diagnosis of breast cancer using a small-sized low-cost infrared camera.
It is therefore an object of the present invention to recognize a breast from thermographic images taken through a thermal imaging camera, to obtain breast cancer thermal image analysis information from a breast thermogram for the recognized breast, The present invention provides a diagnostic apparatus and method for diagnosing breast cancer using a thermal imaging camera that determines breast cancer by comparing breast cancer thermal image analysis information of the breast.
According to another aspect of the present invention, there is provided an apparatus for diagnosing breast cancer using a thermal imaging camera, comprising: a thermal imaging camera, wherein a body including a patient's chest is photographed with the thermal imaging camera, An infrared image obtaining unit; An image preprocessing unit for performing an image preprocessing for deleting the background from the thermal image and outputting a left chest radiograph and a right chest radiograph for recognizing the chest in the body whose background is deleted; And analyzing the left and right chest radiograph images of the normal person to extract the feature vectors, classifying the extracted feature vectors by applying an artificial neural network, And a breast cancer determination unit for comparing the breast cancer thermal image analysis information with the breast cancer thermal image analysis information and comparing the breast cancer thermal image analysis information with the normal breast cancer thermal image analysis information to determine the presence or absence of breast cancer in the left and right chest .
The image preprocessing unit may include an image background removal unit that deletes a background from the thermal image and outputs the background image; And a region-of-interest setting unit for recognizing a region of interest, which is a region of interest, from the thermal image from which the background is deleted, and outputting a left chest radiographic image and a right chest radiographic image.
Wherein the image background removal unit comprises: a channel selection unit for selecting and outputting a thermal image of a red (R) channel among the RGB channels of the thermal image output from the thermal image acquisition unit; A Gaussian filtering unit for performing Gaussian filtering on the infrared image of the red channel and outputting the infrared image; An outline detector for detecting a contour of the body from the thermal image of the Gaussian filtered red channel; And a background eraser for erasing the background from the thermal image including all of the RGB channels based on the detected contour.
The image background removal unit may further include an outline enhancement unit for performing Hough transform on the detected outline to enhance the outline more conspicuously.
The ROI setting unit may include a channel selection unit for selecting only the green channel from the thermal image including all of the RGB channels from which the background is removed and outputting the selected channel; A Gaussian filtering unit for performing Gaussian filtering and outputting the thermal image of the green channel; An outline detection unit for detecting an outline of a body including a chest part from an infrared image of the Gaussian-filtered green channel and outputting the detected outline; A contour enhancement unit performing a Hough circle transformation from the body contour detected by the contour detection unit to perform circle detection corresponding to a chest area; And a breast extracting unit for extracting a left chest radiograph image and a right chest radiograph image from an infrared image including all of the RGB channels through image region of interest (ROI) detection based on the circle detected by the contour detecting unit And a detection unit.
The contour enhancement unit determines that the minimum radius value, which is a parameter of the Hough transform, is set to the average radius value of the female chest, and the minimum distance value between the center of the left and right circles that defines the distance between the chests for detecting the chest Is set to 50.
Wherein the breast cancer determination unit extracts feature vectors based on the co-occurrence matrix for the vertical, horizontal, and diagonal lines of the left and right image images subjected to the image preprocessing, and outputs the extracted feature vectors; And an artificial neural network is applied to the extracted feature vectors to generate breast cancer thermal image analysis information. The breast cancer thermal image analysis information is compared with the normal human breast cancer thermographic image analysis information, and the left and right breast image data And a breast cancer analysis unit for determining whether or not the breast cancer is present.
Wherein the breast cancer determination unit further comprises a histogram analysis unit for analyzing and outputting a distribution of histograms measured on the basis of the feature vectors for each of the RGB channels of the left and right chest image images, The histogram of the normal person is compared with the histogram measured based on the characteristic information of each of the RGB channels through the histogram of the normal person and the histogram analyzing unit to determine whether the breast cancer is primarily detected, It is judged that breast cancer is finally present in the corresponding chest if it is judged that both are breast cancer.
Wherein the breast cancer determination unit determines energy, entropy, contrast, correlation, homogeneity, and RGB of the simultaneous occurrence matrix in the vertical, horizontal, and diagonal directions with the feature vector, And includes a mean, variance, skewness, and kurtosis for each channel.
According to another aspect of the present invention, there is provided a method of diagnosing breast cancer using a thermal imaging camera, the method comprising: a thermal image acquisition unit including a thermal imaging camera; An infrared image obtaining step of outputting an infrared image; An image preprocessing step of performing an image preprocessing in which an image preprocessing section deletes a background from the thermal image and outputs a left chest radiograph image and a right chest radiograph image in which the background is recognized in the body deleted from the body; And the breast cancer determination unit analyzes the left and right chest radiograph images subjected to the image preprocessing to extract feature vectors, classifies the extracted feature vectors by applying an artificial neural network, and analyzes the breast cancer thermal image analysis information And a breast cancer determination step of comparing the breast cancer thermal image analysis information with the normal breast cancer thermal image analysis information to determine whether or not the left and right chest breast cancer are present.
Wherein the image preprocessing step includes an image background removal step in which an image background removal unit deletes a background from the thermal image and outputs the background image; And a region-of-interest setting step in which the region-of-interest recognizing unit recognizes the region of interest as the region of interest from the thermal image from which the background is deleted, and outputs the left-side chest radiographic image and the right chest radiographic image.
The image background removing step may include a channel selecting step of selecting and outputting a red channel among the RGB channels of the thermal image output from the thermal image obtaining unit; A Gaussian filtering step of performing Gaussian filtering and outputting a thermal image of the red channel; An outline detection step of detecting a outline of a body from a thermal image of the red channel by the outline detection unit; And a background erasing step of erasing the background from the thermal image including all of the RGB channels based on the detected contour.
The image background removing step may further include a contour enhancing step of performing a Hough transform on the detected contour so that the contour enhancing part enhances the contour more conspicuously.
The ROI setting step may include a channel selection step of selecting only a green channel from the thermal image including all of the RGB channels whose background is removed, and outputting the selected channel; A Gaussian filtering step of performing Gaussian filtering and outputting the thermal image of the green channel; A contour detection step of detecting and outputting a contour of the body including the chest part from the thermal image of the Gaussian-filtered green channel; A contour enhancement step of performing a Hough circle transformation from the body contour detected by the contour detection unit to perform a circle detection corresponding to a chest part; And a breast detecting step of extracting a left chest radiograph image and a right chest radiograph image from the thermal image including all of the RGB channels through image ROI detection based on the circle detected in the contour detecting unit .
Wherein the contour enhancement step includes a step of enhancing the contour of the contour of the contour of the contour of the contour of the contour of the contour, Is set to 50. The minimum distance value of < RTI ID = 0.0 >
The breast cancer determination step may include a histogram analysis step of analyzing and outputting a histogram of each of the left and right chest radiographic images; A feature information generation step of analyzing the left and right chest radiographic images subjected to the image preprocessing and extracting and outputting feature vectors; And analyzing the breast cancer thermal image analysis information of a normal person, applying artificial neural network to the extracted feature vectors, classifying the extracted feature vectors, generating breast cancer thermal image analysis information using the feature vectors as parameters, And a breast cancer analysis step of comparing the information to determine whether or not the left and right chest breast cancer are present.
Wherein the breast cancer analysis step stores a histogram of the left and right chest radiograph images of the normal person and the histogram of the normal person and the histogram measured by the histogram analyzing unit to determine whether the breast cancer is primarily detected And determining whether the breast cancer is caused by the histogram analysis or the breast cancer based on the breast cancer thermal image analysis information after the breast cancer analysis step, It is judged that there is a presence.
The present invention has the effect of lowering the production cost of the breast cancer diagnostic device by lowering the medical water price by diagnosing the breast cancer using the thermal imaging camera.
Further, since the present invention uses a thermal imaging camera, it has an effect that a patient can be prevented from being exposed to harmful elements such as radiation.
That is, the diagnostic apparatus for breast cancer using the thermal imaging camera of the present invention is faster, economical, and safer than other methods for diagnosing breast cancer, so that the diagnostic apparatus can be used even for sensitive patients such as a female patient.
In addition, since the present invention can diagnose breast cancer directly by a mobile terminal such as a smart phone having one per person and a smart phone equipped with a thermal imaging camera, it is possible to provide a simple and inexpensive primary breast cancer diagnostic means It is possible to diagnose breast cancer early.
1 is a block diagram of a breast cancer diagnosis apparatus using a thermal imaging camera according to the present invention.
2 is a view showing a detailed configuration of an image background removing unit of a breast cancer diagnostic apparatus using a thermal imaging camera according to the present invention.
FIG. 3 is a view showing a detailed configuration of a region-of-interest setting unit of a breast cancer diagnostic apparatus using a thermal imaging camera according to the present invention.
FIG. 4 is a detailed block diagram of a breast cancer determining unit of a breast cancer diagnostic apparatus using the thermal imaging camera according to the present invention.
FIG. 5 is a view showing a thermographic image of a normal person and a breast cancer patient applied according to an embodiment of the present invention. FIG.
6 is a view showing an original image image and an image image in which background is removed according to the present invention.
FIG. 7 is a diagram illustrating a thermal image for each RGB channel according to an exemplary embodiment of the present invention.
8 is a view illustrating contour line images for explaining a contour detection / comparison result according to whether Gaussian filtering is performed according to the present invention.
9 is a diagram illustrating an image of a contour detected during the Hough transform according to the present invention.
10 is a view for explaining a method of extracting left and right chest regions separated by breast recognition and ROI detection using Hough transform according to the present invention.
11 is a histogram of a normal person and a breast cancer patient to explain a breast cancer detection method according to the present invention.
12 is a view for explaining a method of generating a co-occurrence matrix for explaining a method of detecting breast cancer according to the present invention.
13 is a diagram showing intensity levels of concurrent matrices generated according to the present invention in different colors.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the configuration and operation of a breast cancer diagnostic apparatus using the thermal imaging camera according to the present invention will be described with reference to the accompanying drawings, and a method for diagnosing breast cancer in the apparatus will be described.
FIG. 1 is a view showing a configuration of a breast cancer diagnostic apparatus using the thermal imaging camera according to the present invention, FIG. 5 is a view showing a thermographic image of a normal person and a breast cancer patient applied according to an embodiment of the present invention, Fig. 7 is a view showing an original image image and an image image in which a background is removed according to the present invention. FIG. 5A is an RGB thermal image of a normal person, and FIG. 5B is an RGB thermal image of a cancer patient. 1, 5, and 6. FIG.
The apparatus for diagnosing breast cancer using the thermal imaging camera according to the present invention includes a thermal
A thermal image acquisition unit (10) includes a thermal imaging camera (not shown) to photograph a part of a body including a part of the body of a patient and to radiate an RGB thermal image of the body including the part to an image preprocessing unit 100). The RGB thermal image refers to a thermal image including both red (R), green (G), and blue (B) as shown in FIG. Hereinafter, a thermal image including only red is referred to as a red channel thermal image, and a thermal image including only green is referred to as a green channel thermal image. In addition, the RGB thermal image may further include a gray channel in addition to a red channel, a green channel, and a blue channel.
As shown in Fig. 5, the thermal
The
The breast
The breast
FIG. 2 is a view showing a detailed configuration of an image background removing unit of a breast cancer diagnostic apparatus using the thermal imaging camera according to the present invention, FIG. 7 is a view showing a thermal image for each RGB channel according to an embodiment of the present invention, FIG. 8 is a view illustrating contour line images for explaining contour detection and comparison results according to whether Gaussian filtering is performed according to the present invention, and FIG. 9 is a diagram illustrating contour images detected during Hough transformation according to the present invention. This will be described below with reference to Fig. 2 and Figs. 7 to 9. Fig.
The image
The
This is because the average and standard deviation of the infrared image of the red channel is less than the mean and standard deviation of the other channels as shown in FIG. 7 and Table 1 below, which makes it easier to detect the body contour including the patient's chest area to be.
The
The
In the image
Therefore, it is preferable to perform the Gaussian filtering through the
The
The
FIG. 3 is a diagram illustrating a detailed configuration of a region-of-interest setting unit of the apparatus for diagnosing breast cancer using the thermal imaging camera according to the present invention. Fig. This will be described below with reference to Figs. 3 and 10. Fig.
The region of
The
The
The
The
The
FIG. 4 is a view showing a detailed configuration of a breast cancer determination unit of a breast cancer diagnosis apparatus using the thermal imaging camera according to the present invention, and FIG. 11 is a histogram of a normal person and a breast cancer patient to explain a breast cancer detection method according to the present invention. FIG. 12 is a view for explaining a simultaneous occurrence matrix generation method for explaining a breast cancer detection method according to the present invention. FIG. 13 is a view for explaining a method of generating a concurrent occurrence matrix according to the present invention. Fig. This will be described below with reference to Figs. 4 and 11 to 13. Fig.
The breast
The
The histogram represents the existence probability distribution function of the color intensity in a given left and right chest radiographic image, and can be expressed by the following equation (1).
Where p is the pixel value of the thermal image, and m and n are the width and height of the image.
11 is a histogram generated by Equation (1), wherein (a) is a histogram of a normal person, and (b) is a histogram of a patient having a high possibility of breast cancer.
The feature vectors that can be applied to the histogram may be Mean, Standard Deviation, Skewness, Kurtosis, and the like.
The average is the average pixel value of the RGB channels of the RGB channel thermal image. The standard deviation is a value obtained by calculating the square root of the variance of the image. The asymmetry rate is a value indicating the degree of symmetry with respect to the color distribution. Is a value obtained by measuring the distribution.
The mean, standard deviation, asymmetry rate, and kurtosis can be obtained by the following equation (2).
The simultaneous occurrence matrix
The feature vectors applied to the co-occurrence matrix may be Energy, Contrast, Homogeneity and Correlation.
The energy means the uniformity of the sum of the squared elements of the coincidence matrix, the entropy is a measure of statistical randomness, i.e., the uncertainty, the contrast can measure the local variability in the image, Direction, and the correlation shows the relationship between the pixels, which can be calculated by the following equation (3).
Each of the feature vectors in Equation (3) is a technique well known to those skilled in the art, and thus a detailed description thereof will be omitted.
The simultaneous occurrence matrix
The breast
The breast
In addition, the breast
While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. It will be easily understood. It is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, it is intended to cover various modifications within the scope of the appended claims.
10: thermal image acquisition unit 100: image preprocessing unit
200: image background removal unit 210: channel selection unit (red)
220: Gaussian filtering unit 230: Outline detection unit
240: contour enhancement unit 250: background deletion unit
300: ROI setting unit 310: Channel selection unit (green)
320: Gaussian filtering unit 330: Outline detection unit
340: contour enhancement unit 350: breast detection unit
400: Breast cancer determination unit 410: Histogram analysis unit
420: Simultaneous occurrence matrix characteristic generation unit 430: Breast cancer analysis unit
Claims (18)
An image preprocessing unit for performing an image preprocessing for deleting the background from the thermal image and outputting a left chest radiograph and a right chest radiograph for recognizing the chest in the body whose background is deleted; And
And analyzing the left and right chest radiograph images of the normal person to extract feature vectors, classifying the extracted feature vectors by applying an artificial neural network, And a breast cancer determination unit for comparing the breast cancer thermal image analysis information with the breast cancer thermal image analysis information to determine whether or not the left and right breast are present in the breast cancer A breast cancer diagnosis apparatus using a thermal imaging camera.
The image pre-
An image background removing unit that deletes the background from the thermal image and outputs the background image; And
And a region-of-interest setting unit for outputting the left chest radiographic image and the right chest radiographic image by recognizing the chest as the region of interest from the thermal image from which the background is deleted.
Wherein the image background removal unit comprises:
A channel selection unit for selecting and outputting a thermal image of a red (R) channel among the RGB channels of the thermal image output from the thermal image acquisition unit;
A Gaussian filtering unit for performing Gaussian filtering on the infrared image of the red channel and outputting the infrared image;
An outline detector for detecting a contour of the body from the thermal image of the Gaussian filtered red channel; And
And a background erasing unit for erasing the background from the thermal image including all of the RGB channels based on the detected contour.
Wherein the image background removal unit comprises:
And a contour enhancing unit for enhancing the contour more clearly by performing a Hough transform on the detected contour.
The region-
A channel selector for selecting only a green channel from the thermal image including all the RGB channels from which the background is removed and outputting the selected channel;
A Gaussian filtering unit for performing Gaussian filtering and outputting the thermal image of the green channel;
An outline detection unit for detecting an outline of a body including a chest part from an infrared image of the Gaussian-filtered green channel and outputting the detected outline;
A contour enhancement unit performing a Hough circle transformation from the body contour detected by the contour detection unit to perform circle detection corresponding to a chest area; And
A breast detecting unit for extracting a left chest radiograph image and a right chest radiograph image from an infrared image including all of the RGB channels through image region of interest (ROI) detection based on the circle detected by the contour detecting unit; And a diagnostic device for diagnosing breast cancer using the thermal imaging camera.
Wherein the contour enhancing unit comprises:
The minimum radius value which is a parameter of the Hough transform is set to the average radius value of the female chest and the minimum distance value between the center of the left and right circles which defines the distance between the chests for detecting the chest is set to 50 Wherein the breast cancer diagnosis apparatus comprises:
The breast cancer judgment unit,
Extracting feature vectors based on a co-occurrence matrix for vertical, horizontal, and two diagonal lines of the image preprocessed left and right image images, and outputting the extracted feature vectors; And
The breast cancer thermal image analysis information is stored by applying the artificial neural network to the extracted feature vectors and the breast cancer thermal image analysis information is generated by comparing the breast cancer thermal image analysis information with the normal person's breast cancer thermal image analysis information, And a breast cancer analysis unit for determining the presence or absence of the breast cancer.
Wherein the breast cancer judgment unit
And a histogram analyzing unit for analyzing and outputting a distribution of histograms measured on the basis of the feature vectors for each of the RGB channels of the left and right chest image images
Wherein the breast cancer analyzing unit comprises:
The histogram of the left and right image images of the normal person is further stored and the histogram of the normal person is compared with the histogram measured based on the characteristic information of each of the RGB channels through the histogram analyzing unit, And determining whether or not the second breast cancer is caused by the breast cancer thermal image analysis information. If both of the breast cancer cases are judged to be breast cancer, it is determined that the breast cancer is finally present in the breast cancer.
Wherein the breast cancer judgment unit
Energy, entropy, contrast, correlation, homogeneity, and mean (RGB) of the co-occurrence matrices in the vertical, horizontal, ), A variance, an asymmetric rate (Skewness), and a kurtosis.
An image preprocessing step of performing an image preprocessing in which an image preprocessing section deletes a background from the thermal image and outputs a left chest radiograph image and a right chest radiograph image in which the background is recognized in the body deleted from the body; And
The breast cancer determination unit analyzes the left and right chest radiograph images, extracts the feature vectors, classifies the extracted feature vectors by applying an artificial neural network, and analyzes the breast cancer thermal image analysis information using the feature vectors as parameters And a breast cancer determination step of comparing the generated breast cancer thermal image analysis information with the breast cancer thermal image analysis information of the normal person to determine whether or not the left and right breast are present in the breast cancer. Methods of diagnosing breast cancer.
Wherein the image preprocessing step comprises:
An image background removal step of removing an image background from the thermal image and outputting the background image; And
And a region-of-interest setting step of outputting the left chest radiographic image and the right chest radiographic image by recognizing the chest as the region of interest from the thermal image from which the background region has been deleted, Methods of diagnosing breast cancer.
Wherein the image background removal step comprises:
A channel selecting step of selecting and outputting a red (R) channel among the RGB channels of the thermal image output from the thermal image obtaining unit;
A Gaussian filtering step of performing Gaussian filtering and outputting a thermal image of the red channel;
An outline detection step of detecting a outline of a body from a thermal image of the red channel by the outline detection unit; And
And a background erasing step of erasing the background from the thermal image including all of the RGB channels on the basis of the detected contour.
Wherein the image background removal step comprises:
Further comprising a contour enhancing step of performing a Hough transform on the detected contour so that the contour enhances the contour more conspicuously.
The region of interest setting includes:
A channel selecting step of selecting and outputting only a green channel from the thermal image including all of the RGB channels whose background is removed;
A Gaussian filtering step of performing Gaussian filtering and outputting the thermal image of the green channel;
A contour detection step of detecting and outputting a contour of the body including the chest part from the thermal image of the Gaussian-filtered green channel;
A contour enhancement step of performing a Hough circle transformation from the body contour detected by the contour detection unit to perform a circle detection corresponding to a chest part; And
And a breast detecting step of extracting a left chest radiograph image and a right chest radiograph image from an infrared image including all of the RGB channels through image region of interest (ROI) detection based on the circle detected by the contour detecting unit A method for diagnosing breast cancer using a thermal imaging camera.
Wherein the contour enhancing step comprises:
The contour enhancement unit sets the minimum radius value that is a parameter of the Hough circle transformation to the average radius value of the female chest and the minimum distance value between the center of the left and right circles that defines the distance between the chests for detecting the chest is 50 Of the breast cancer. ≪ RTI ID = 0.0 > 11. < / RTI >
In the breast cancer determination step,
A histogram analysis step of analyzing and outputting a histogram of each of the left and right chest radiographic images;
A feature information generation step of analyzing the left and right chest radiographic images subjected to the image preprocessing and extracting and outputting feature vectors; And
The breast cancer thermal image analysis information is stored, and the artificial neural network is applied to the extracted feature vectors to generate breast cancer thermal image analysis information having the feature vectors as parameters, and the breast cancer thermal image analysis information And determining a presence or absence of a breast cancer in the left and right chest based on the comparison result.
Wherein the breast cancer analyzing step comprises:
A histogram analysis step of determining whether a breast cancer is primarily detected by comparing the histogram of the normal person and the histogram measured by the histogram analyzing unit, wherein the histogram of the left and right chest radiograph images of the normal person is further stored, Including,
Wherein, when it is determined that both of the breast cancer by the histogram analysis and the breast cancer by the breast cancer thermal image analysis information are judged to be breast after the breast cancer analysis step, it is determined that the breast cancer is finally present in the corresponding breast Diagnostic method for breast cancer using thermal imaging camera.
The feature vector,
Energy, Entropy, Contrast, Correlation, Homogeneity, Mean, Dispersion by RGB Channels in the Vertical, Horizontal and Two Diagonal Direction Wherein the method comprises diagnosing a breast cancer using a thermal imaging camera.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160130805A KR101887760B1 (en) | 2016-10-10 | 2016-10-10 | Breast cancer diagnosis apparatus using thermal camera and method thereof |
PCT/KR2017/011134 WO2018070760A1 (en) | 2016-10-10 | 2017-10-10 | Device and method for diagnosing breast cancer by using thermal imaging camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160130805A KR101887760B1 (en) | 2016-10-10 | 2016-10-10 | Breast cancer diagnosis apparatus using thermal camera and method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20180039466A true KR20180039466A (en) | 2018-04-18 |
KR101887760B1 KR101887760B1 (en) | 2018-08-10 |
Family
ID=61905646
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020160130805A KR101887760B1 (en) | 2016-10-10 | 2016-10-10 | Breast cancer diagnosis apparatus using thermal camera and method thereof |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR101887760B1 (en) |
WO (1) | WO2018070760A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20200029345A (en) * | 2018-09-10 | 2020-03-18 | 엑시스 에이비 | Method and system for filtering thermal image data |
KR102108050B1 (en) * | 2019-10-21 | 2020-05-07 | 가천대학교 산학협력단 | Method for classifying breast cancer histology images through incremental boosting convolution networks and apparatus thereof |
CN112673394A (en) * | 2018-07-16 | 2021-04-16 | Npl管理有限公司 | System and method for acquiring thermal image data of body part and thermal imager |
KR20220059887A (en) * | 2020-11-03 | 2022-05-10 | 한국 한의학 연구원 | Method and device for constructing deep learning model for detecting abdominal cold sensation area |
KR20220075002A (en) * | 2020-11-26 | 2022-06-07 | 네오컨버전스 주식회사 | Method and appararus of generating numerical data for deep learning using diagnosing beat of futus using artificail intelligence |
KR102543555B1 (en) * | 2022-07-11 | 2023-06-14 | 성균관대학교산학협력단 | Ai breast cancer diagnosis apparatus, and breast cancer self-diagnosis method using the same |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020060046A1 (en) * | 2018-09-20 | 2020-03-26 | 아주대학교 산학협력단 | Convolutional neural network-based mammogram image analysis method using four-channel input, and system therefor |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100804809B1 (en) | 2005-07-04 | 2008-02-20 | 김영창 | Breast cancer check system |
KR20110039897A (en) * | 2009-10-12 | 2011-04-20 | 서울대학교산학협력단 | Method for detection of clustered microcalcifications on digital mammogram |
KR20160017927A (en) * | 2014-08-07 | 2016-02-17 | 박영훈 | diagnosis system and method of breast cancer |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5657362A (en) * | 1995-02-24 | 1997-08-12 | Arch Development Corporation | Automated method and system for computerized detection of masses and parenchymal distortions in medical images |
JP4430937B2 (en) * | 2001-12-07 | 2010-03-10 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | Medical viewing system and method for spatial enhancement of structures in noisy images |
KR100719350B1 (en) * | 2005-09-08 | 2007-05-17 | 건국대학교 산학협력단 | System for diagnosing breast cancer and method therefor |
-
2016
- 2016-10-10 KR KR1020160130805A patent/KR101887760B1/en active IP Right Grant
-
2017
- 2017-10-10 WO PCT/KR2017/011134 patent/WO2018070760A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100804809B1 (en) | 2005-07-04 | 2008-02-20 | 김영창 | Breast cancer check system |
KR20110039897A (en) * | 2009-10-12 | 2011-04-20 | 서울대학교산학협력단 | Method for detection of clustered microcalcifications on digital mammogram |
KR20160017927A (en) * | 2014-08-07 | 2016-02-17 | 박영훈 | diagnosis system and method of breast cancer |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112673394A (en) * | 2018-07-16 | 2021-04-16 | Npl管理有限公司 | System and method for acquiring thermal image data of body part and thermal imager |
KR20200029345A (en) * | 2018-09-10 | 2020-03-18 | 엑시스 에이비 | Method and system for filtering thermal image data |
KR102108050B1 (en) * | 2019-10-21 | 2020-05-07 | 가천대학교 산학협력단 | Method for classifying breast cancer histology images through incremental boosting convolution networks and apparatus thereof |
KR20220059887A (en) * | 2020-11-03 | 2022-05-10 | 한국 한의학 연구원 | Method and device for constructing deep learning model for detecting abdominal cold sensation area |
WO2022097815A1 (en) * | 2020-11-03 | 2022-05-12 | 한국 한의학 연구원 | Diagnostic model development technology using thermal imaging camera for reproducing cold sensation area based on abdominal palpation by doctor of traditional medicine |
KR20220075002A (en) * | 2020-11-26 | 2022-06-07 | 네오컨버전스 주식회사 | Method and appararus of generating numerical data for deep learning using diagnosing beat of futus using artificail intelligence |
KR102543555B1 (en) * | 2022-07-11 | 2023-06-14 | 성균관대학교산학협력단 | Ai breast cancer diagnosis apparatus, and breast cancer self-diagnosis method using the same |
Also Published As
Publication number | Publication date |
---|---|
WO2018070760A1 (en) | 2018-04-19 |
KR101887760B1 (en) | 2018-08-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101887760B1 (en) | Breast cancer diagnosis apparatus using thermal camera and method thereof | |
Navarro et al. | Accurate segmentation and registration of skin lesion images to evaluate lesion change | |
US5133020A (en) | Automated method and system for the detection and classification of abnormal lesions and parenchymal distortions in digital medical images | |
US5452367A (en) | Automated method and system for the segmentation of medical images | |
US8340388B2 (en) | Systems, computer-readable media, methods, and medical imaging apparatus for the automated detection of suspicious regions of interest in noise normalized X-ray medical imagery | |
US20140018681A1 (en) | Ultrasound imaging breast tumor detection and diagnostic system and method | |
US20120014505A1 (en) | Radiation image processing apparatus, radiation image processing method, and radiation image processing program | |
JP2007007440A (en) | Automated method and apparatus to detect phyma and parenchyma deformation in medical image using computer | |
JP4604451B2 (en) | Medical image processing apparatus and malignancy determination method | |
TWI482102B (en) | Methods for processing enhancement of target pattern, method for generating classification system of target patterns and classifying detected target patterns | |
ITRM20060213A1 (en) | METHOD OF PROCESSING BIOMEDICAL IMAGES | |
JP2003334183A (en) | Abnormal shadow-detecting device | |
JP4729188B2 (en) | Gaze detection device | |
KR102095730B1 (en) | Method for detecting lesion of large intestine disease based on deep learning | |
Guzman-Cabrera et al. | Digital processing of thermographic images for medical applications | |
US20170367677A1 (en) | Analysis method for breast image and electronic apparatus using the same | |
JPH09251535A (en) | Method and device for detecting pattern in two-dimensional multi-contrast image | |
US20160100789A1 (en) | Computer-aided diagnosis system and computer-aided diagnosis method | |
Negied | Infrared thermography-based breast cancer detection—comprehensive investigation | |
Nurhayati et al. | Stroke identification system on the mobile based CT scan image | |
KR20190113351A (en) | Analysis apparatus for medical image using machine learning algorithm | |
González et al. | On image registration for study of thyroid disorders by infrared exams | |
Hankare | Breast abnormality based early diagnosis of breast cancer using non-invasive digital infrared thermal imaging | |
Gomathy et al. | Automated segmentation using PCA and area estimation of thyroid gland using ultrasound images | |
Heriana et al. | Tumor size classification of breast thermal image using fuzzy C-Means algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant |