Classification of breast cancer grades using physical parameters and K-nearest neighbor method

TELKOMNIKA, Vol.17, No.2, April 2019, pp.637~644
ISSN: 1693-6930, accredited First Grade by Kemenristekdikti, Decree No: 21/E/KPT/2018
DOI: 10.12928/TELKOMNIKA.v17i2.9797  637
Received May 5, 2018; Revised December 1, 2018; Accepted January 27, 2019
Classification of breast cancer grades using physical
parameters and K-nearest neighbor method
Anak Agung Ngurah Gunawan*1
, S. Poniman2
, I. Wayan Supardi3
Physics Department, University of Udayana, Kampus Bukit Jimbaran Bali, Bali, 80361,
tel/fax: 62(0361)704845/62(0361)701954, Indonesia
*Corresponding author, e-mail: a.a.n.gunawan.unud@gmail.com1
,
sponiman@unud.ac.id.supardi@unud.ac.id2
Abstract
Breast cancer is a health problem in the world. To overcome this problem requires early detection
of breast cancer. The purpose of this study is to classify early breast cancer grades. Combination of
physical parameters with k-nearest neighbor Method is proposed to detect early breast cancer grades. The
experiments were performed on 87 mammograms consisting of 12 mammograms of grade
1.41 mammograms of grade 2 and 34 mammogram of grade 3. The proposed method was effective to
classify the grades of breast cancer by an accuracy of 64.36%, 50% sensitivity and 73.5% specitifity.
Physical parameters can be used to classify grades of breast cancer. The results of this study can be used
to complement the diagnosis of breast mammography examination.
Keywords: breast cancer, grade, K-nearest neighbor
Copyright © 2019 Universitas Ahmad Dahlan. All rights reserved.
1. Introduction
Breast cancer is a health problem in the world. To overcome this problem requires early
detection of breast cancer. Discovered microcalsification is a sign of breast cancer. Many
methods have successfully detected the presence of microcalsification [1-6]. However, the
discovery of microcalsification is not enough to classify the breast cancer grades. Nezha H [7]
classified breast cancer using the Quantum Clustering and Wavelet method. Shofwatul U [8]
classified malignant and benign lesions using Feature Selection method. Seyyid A M [9]
classified breast cancer using the K-Nearest Neighbor method with different distances.
Mandeep R [10] classified malignant and benign breast cancer lesions using the Machine
Learning Techniques method. Anggrek C N [11] classified normal and abnormal breast cancer
using the K-Nearest Neighbor method. All the researchers mentioned above, none of them
classifies breast cancer grade
To classify the grades of breast cancer typically used the methods of Tumor Node
Metastase [12] and Scarff Bloom Richardson [13] are used. In this study, we proposed a new
method for classifying breast cancer grades using a combination of physical parameters using
the K-nearest neighbor method. The updated feature of our study is to use the physical
parameters contained in the mammogram as input to the K-nearest neighbor method.
This research needs to be done to improve the prognosis of breast Cancer patient.
The uniqueness of the research is by converting from a mammogram image to a numeric to
determine the grades of breast cancer without a fine needle biopsy. The results of this study are
used as a complement to mammography examination.
2. Materials and Methods
The steps to classify breast cancer grades are as follows: the breast is photographed
using a digital mammography device, then it cuts suspicious mass and is stored using 256 heat
bmp format. Then the image quality is improved to make it brighter. After that, the calculation of
physical parameters using (1) to (13), then statistical tests using anova test to determine the
significant physical parameters to distinguish breast cancer grades, a significant parameter and
then used as an input variable from the K-Nearest Neighbor method using (14), the closest
distance shows the results of grades classification of breast cancer as shown in Figure 1.

 ISSN: 1693-6930
TELKOMNIKA Vol.17, No.2, April 2019: 637~644
638
Figure 1. Research design
To classify breast cancer levels, 10 physical parameters are needed as follows:
Entropy (E) = − ∑ ∑ [H(yq, yr, d)]log[H(yq, yr, d)]
yt
yr=y1
yt
yq=y1
(1)
Contrast (C) = ∑ ∑ (yq − yr)2yt
yr=y1
yt
yq=y1
H(yt, yr, d) (2)
𝐴𝑛𝑔𝑢𝑙𝑎𝑟 𝑆𝑒𝑐𝑜𝑛𝑑 𝑀𝑜𝑚𝑒𝑛𝑡 (𝑀𝐴) = ∑ ∑ [H(yq, yr, d)]2yt
yr=y1
yt
yq=y1
(3)
Inverse Difference Moment (MD) =
 
 
 
  








yt
yiyq
yt
yiyr yryq
dyryqH
2
1
,,
(4)
for yr ≠ yq
Correlation (Corr) =
∑ ∑ yqyrH(yq,yr,d)−μHm(yq,d)μHm(yr,d)
yt
yr=y1
yt
yq=y1
σHm(yqq,d)σHm(yr,d)
(5)
with
Hm(yq, d) = ∑ H(yq, yr, d)
yt
yr=y1
(6)
Hm(yr, d) = ∑ H(yq, yr, d)
yt
yq=y1
(7)
Mean (MN) = ∑ yqHm(yq, d)
yt
yq=y1
(8)
Deviation (D) = √∑ [yq − ∑ ypHm(yp, d)]2Hm(yq, d)
yt
yp=y1
yt
yq=y1
(9)
Hdiff(i, d) = ∑ ∑ H(yq, yr, d)
yt
yr=y1
yt
yq=|yq−yr|=i
(10)
Entropy of Hdiff (EH) = − ∑ Hdiff(i, d) log Hdiff(i, d)
it
i=i1
(11)
AngularMoment of Hdiff (MAH) = ∑ [Hdiff(i, d)]2it
i=i1
(12)
Mean of Hdiff (MHD) = ∑ i Hdiff(i, d)
it
i=i1
(13)
with H(yq,yr,d), d, y each is the probability of a pair of gray-level, the distance between the pixel
and gray level value, respectively [14]. K-Nearest Neighbor is a method to classify using the
distance of the nearest neighbor [15-20], expressed in (14). Many researchers use the KNN
method to classify breast cancer as has it done by [21-25].

TELKOMNIKA ISSN: 1693-6930 
Classification of breast cancer grades using physical... (Anak Agung Ngurah Gunawan)
639
  



ni
i
UT iiD
1
2
(14)
with D, T and U respectively are the closest neighbors distance, training data, data to be tested.
The study was conducted at the Sanglah central public hospital of Bali, Prima Medika
Bali hospital, and Doctor Soetomo Hospital Surabaya. This research has been approved by the
research ethics committee of medical faculty of Udayana University and Sanglah central public
hospital Denpasar, with approval number: 1204/UN.14.2/KEP/2017. Mammography images
taken from Kodak brand mammography type dry view 6800 laser imager with setting KV=30,
MAS=25, brightness=7, latitude=11, contrast=-4, movie size=18x24 cm. Total trial data of
87 mammograms consisting of 12 mammograms of grade 1,41 mammogram grade 2 and
34 mammogram grade 3. Experimental design that we use is cross section. Annova was used
to find significant physical parameters in differentiating grade 1, 2 and 3. Significant variables
were incorporated into KNN method to classify grading of breast cancer. Physical parameters
are parameters contained in the mammographic image converted into entropy, contrast, angular
second moment, inverse differential moment, mean, deviation, entropy of difference second
order histogram, angular second moment of difference second order histogram and mean of
difference secondorder histogram expressed in (1) through (13).
3. Results and Discussion
3.1. Results
Suspicious mass is shown by arrows such as Figures 2 (a), 3 (a), 4 (a), then it cropped
and stored by the 256 heat bmp format. Graph of the results of the reduction of the background
image with the original image as shown in Figures 2 (b), 3 (b), and 4 (b), it turns out that there
are significant differences in grades 1, 2, and 3. We took grade 1 images from the radiology
installation room database and grade 1 status we got from the medical record of Doctor
Soetomo Hospital Surabaya. In Figure 2 (a) there is a microcalsification.
(a) (b)
Figure 2. (a) Grade 1 (b) Subtract the background image form the original image grade 1 [14]
We took the grade 2 image from the radiology installation room database and the
grade 2 status we got from the medical record of Doctor Soetomo Hospital Surabaya.
In Figure 3 (a) there is shrinking of the skin around the nipples. We took the grade 3 image from
the radiology installation room database and the grade 3 status we got from the medical record
of Doctor Soetomo Hospital Surabaya. In Figure 4 (a) there is a very large density.
To classify grades of breast cancer using 10 physical parameters, not all physical
parameters are significant for classifying grades of breast cancer. Annova statistical test is done
to find a significant variable by looking at significant values smaller than 0.05. From the results
of the study, only contrast variables that have significant values smaller than 0.5, as shown in
Table 1 (see in Appendix). By: d is the distance between pixels; grade 1 (n=12) was taken 12
patients with level one malignancy; garde 2 (n=41) was taken 41 patients with level two
malignancy; grade 3 (n=34) was taken 34 patients with level three malignancy.

 ISSN: 1693-6930
640
(a) (b)
Figure 3. (a) Grade 2 (b) subtract the background image form the original image grade 2 [14]
(a) (b)
Figure 4. (a) Grade 3 and (b) subtract the background image form the original
image grade 3 [14]
To determine the value of accuracy, sensitivity and specificity in this study required TP
value means that if the actual grade 1 data turns out to be true grade 1, FNa means that if the
actual grade 1 data turns out to be incorrect grade 1 but grade 2, FNb means the actual data
Grade 1 turns out to be a non-grade 1 class, but grade 3, FP1 means that if the actual grade 2
data turns out to be incorrect grade 2, grade 1. TN1 means that if the actual grade 2 data is true
the grade results actually state grade 2. FN1 means if the data actual grade 2 turns out that the
result of the incorrect classification is not grade 2 but grade 3. FP2 means that if the actual
grade 3 data turns out to be incorrect grade 3 but grade 1, FN2 means that the actual grade 3
data is not grade 3 but grade 2, TN2 means that the actual grade 3 data turns out to be true
grade 3 classification. The formula for determining accuracy, sensitivity and specificity is as
follows:
Accuracy =
212121
21
TNFNFNbFNTNFNaFPFPTP
TNTNTP


Sensitivity =
FNbFNaTP
TP

Specifity =
222
2
FNFPTN
TN

from the results of the study obtained the results of TP, FNa, FNb, FP1, TN1, FN1, FP2, TN2 as
in Table 2.

641
Table 2. Results of K-Nearest Neighbor
Actual Data
Grade 1 (12 mammogram) Grade 2 (41 mammogram) Grade 3 (34 mammogram)
Classification
Results
Grade 1 TP = 6 FP1 = 4 FP2 = 2
Grade 2 FNa = 3 TN1 = 25 FN2 = 7
Grade 3 FNb = 3 FN1 = 12 TN2 = 25
The accuracy, sensitivity and specificity values are as follows:
accuracy = 64.36%,
sensitivity = 50%,
specifity = 73.5%.
Graph Relation of grade 1, 2 and 3 to the value of contrast as Figure 5.
Figure 5. Contrast value of grade 1, 2, and 3
3.2. Discussion
In this paper we presented a new method for breast cancer grades classification based
on a combination of physical parameters using the K-nearest neighbor method. The main
motivation of this research is to develop the concept of early detection of breast cancer grades
with emphasis on physical parameters with K-Nearest Neighbor. The method we propose gives
good results. Evaluation was done by taking new data as many as 87 pictures from Doctor
Soetomo Hospital Surabaya obtained accuracy, sensitivity and specificity are 64.36, 50 and
73.5% respectively. Our method is very stable and reliable. During our classification testing we
have achieved good results regardless of the K factor value in the K-nearest neighbor algorithm.
The test has successfully determined the ac`curacy, sensitivity and specificity of the method we
propose. Tests have shown that the method we propose is sensitive to the type of breast cancer
grades. Analysis Nine physical parameters show that not all physical parameters have a
significant impact on classifying breast cancer grades. Because of this, significant parameters
are needed to improve preprocessing and achieve better results. The combination of physical
parameters and the K-nearest neighbor method has been shown to be a good choice for
classifying breast cancer grades. The method we propose provides the ability to improve the
classification of breast cancer grades.
4. Conclusion
The combination of physical parameters with K-nearest neighbor method is expected to
detect early breast cancer grades. From the experimental results turned out contrast
parameters as input method K-nearest neighbor able to classify the grades of breast cancer
well. Future research prospects were developed using a combination of physical parameters
with adaptive neuro fuzzy method, gynecological algorithm, fuzzy logic, c-mean clustering,

 ISSN: 1693-6930
642
neural network and support vector machine. The best results of these methods can be applied
to digital mammography tools. So that digital mammography tool is able to detect early and
predict the type of breast cancer before the biopsy.
Acknowledgment
Thanks to DPRM Ristekdikti who has funded this research, thanks also to Udayana
University, Doctor Soetomo Hospital Surabaya, Sanglah central public hospital of Bali, and
Prima Medika hospital that has provided facilities for this research.
References
[1] Henrot P, Leroux A, Barlier C. Breast microcalcifications: The lesions in anatomical pathology.
Diagnostic and Interventional Imaging. 2014; 95(1); 141-152.
[2] Boisserie-Lacroix M, Bullier B, Hurtevent-Labrot G, Ferron S, Lippa N, Mac Grogan G. Correlation
between imaging and prognostic factors: Molecular classification of breast cancers. Diagnostic and
Interventional Imaging. 2014; 95(1); 227-233.
[3] Naseem M, Murray J, Hilton F. Mammographic microcalcifications and breast cancer tumorigenesis:
a radiologic-pathologic analysis. BioMed Central Cancer. 2015; 15(1); 307-315.
[4] Scimeca M, Giannini E, Antonacci C. Microcalcifications in breast cancer: an active phenomenon
mediated by epithelial cells with mesenchymal characteristics. BioMed Central Cancer. 2014; 14(1);
286-294.
[5] Dheeba J, Jiji W. Detection of Microcalcification Clusters in Mammograms using Neural Network,
International Journal of Advanced Science and Technology. 2010; 19(1); 13-22.
[6] Eddaoudi F, Regragui F. Microcalcifications detection in mammographic images using texture coding.
Applied Mathematical Sciences. 2011; 5(8); 381-393.
[7] Hamdi N, Auhmani K, Hassani MM. A New Approach Based on Quantum Clustering and Wavelet
Transform for Breast Cancer Classification: Comparative Study. International Journal of Electrical
and Computer Engineering. 2015: 5(5): 1027-1034.
[8] Uyun S, Choridah L. Feature Selection Mammogram based on Breast Cancer Mining. International
Journal of Electrical and Computer Engineering. 2018: 8(1): 60-69.
[9] Medjahed SA, Saadi TA, Benyettou A. Breast Cancer Diagnosis by using k-Nearest Neighbor with
Different Distances and Classification Rules. International Journal of Computer Applications. 2013:
62(1): 1-5.
[10] Rana M, Chandorkar P, Dsouza A, Kazi N. Breast Cancer Diagnosis and Recurrence Prediction
Using Machine Learning Techniques. International Journal of Research in Engineering and
Technology. 2015; 4(4); 372-376.
[11] Nusantara AC, Purwanti E, Soelistiono S. Classification of Digital Mammogram based on Nearest-
Neighbor Method for Breast Cancer Detection. International Journal of Technology. 2016: 7(1); 71-77.
[12] McKenna RJ, Murphy GP. Cancer Surgery. Philadelphia: JB Lippincott Company. 1994: 209-254.
[13] Sternberg SS, Antonioli DA, et al. Diagnostic Surgical Pathology. Third Edition. Lippincott Williams
and Wilkins. 1999: 319-379.
[14] Gunawan AA. A Novel Model Determination of Breast Cancer Stage Using Physical Parameter. Far
East Journal of Matematical. 2014; 87(1); 23-35.
[15] Trstenjak B, Mikac S, Donko D. KNN with TF-IDF Based Framework for Text Categorization.
Procedia Engineering. 2014; 69(1); 1356–1364.
[16] Krati Saxena D, Khan Z, Singh S. Diagnosis of Diabetes Mellitus Using K Nearest Neighbor
Algorithm. International Journal of Computer Science Trends and Technology (IJCST). 2014; 2(4);
36-43.
[17] Imandoust S, Bolandraftar M. Application of K-Nearest Neighbor (KNN) Approach for Predicting
Economic Events: Theoretical Background. International Journal of Engineering Research and
Applications. 2013; 3(5); 605-610.
[18] Kataria A, Singh M. A Review of Data Classification Using K-Nearest Neighbour Algorithm.
International Journal of Emerging Technology and Advanced Engineering. 2013; 3(6); 354-360.
[19] Chitupe A, Joshi S. Data Classification Algorithm Using K-Nearest Neighbour Method Applied to ECG
Data. IOSR Journal of Computer Engineering. 2013; 14(4); 13-21.
[20] Khamis HS, Cheruiyot KW, Kimani S. Application of k- Nearest Neighbour Classification in Medical
Data Mining. International Journal of Information and Communication Technology Research. 2014;
4(4); 121-128.
[21] Gunawan AA, Supardi IW, Poniman S, Dharmawan BG. The Utilization of Physical Parameter to
Classify Histopathology Types of Invasive Ductal Carcinoma (IDC) and Invasive Lobular Carcinoma
(ILC) by using K-Nearest Neighbourhood (KNN) Method. International Journal of Electrical and
Computer Engineering (IJECE). 2018: 8(4): 2442-2450.

643
[22] Palaniammal V, Chandrasekaran RM. Analysis for breast cancer diagnosis using KNN classification.
International Journal of Applied Engineering Research. 2014: 9(22): 14233-14241.
[23] Pawlovsky AP, Nagahashi M. A method to select a good setting for the kNN algorithm when using it
for breast cancer prognosis. IEEE-EMBS International Conference on Biomedical and Health
Informatics (BHI). 2014: 189–192.
[24] Odajima K, Pawlovsky AP. A detailed description of the use of the kNN method for breast cancer
diagnosis. International Conference on Biomedical Engineering and Informatics. 2014: 688–692.
[25] Rashmi GD, Lekha A, Bawane N. Analysis of Efficiency of Classification and Prediction Algorithms
(KNN) for Breast Cancer Dataset. Information Systems Design and Intelligent Applications. 2016;
187-197.
Appendix
Table 1. Average Physical Parameter Values of Grades 1, 2 and 3 with Varying Distances
between Pixels from Doctor Soetomo Surabaya Hospital in 2018 [21]
d
Grade 1 (n=12) Grade 2 (n=41) Grade 3 (n=34)
Significant
Average
Standard
deviation
Average
Standartd
deviation
Average
Standard
deviation
Entropy
1 3.6685417 0.0881638 3.6319412 0.1573514 3.6208618 0.1525623 0.633
2 3.7247925 0.0847231 3.672801 0.1604696 3.666451 0.1541859 0.496
3 3.7517792 0.0857836 3.694687 0.159785 3.687972 0.156853 0.435
4 3.7661092 0.0850587 3.706679 0.1579018 3.69521 0.1541363 0.361
5 3.7728242 0.0836522 3.713076 0.1552709 3.699073 0.1532215 0.328
6 3.7758875 0.0824338 3.716717 0.1533973 3.704095 0.1529091 0.34
7 3.7757117 0.0782974 3.71747 0.1502065 3.701108 0.1508396 0.303
8 3.7719675 0.0771117 3.717147 0.1475737 3.699568 0.1500894 0.317
9 3.7692092 0.0742788 3.713742 0.1448325 3.696645 0.1483907 0.304
10 3.7638058 0.0735703 3.711725 0.142265 3.692972 0.1468494 0.312
Contrast
1 265.48121 62.20458 350.38306 196.50348 189.0247 174.32289 0.001
2 483.93363 174.75801 538.94056 293.14921 310.7809 293.39607 0.003
3 701.66646 318.23153 695.89709 330.71914 423.77046 411.87455 0.004
4 914.4501 474.53675 846.3778 382.35455 528.4305 527.18974 0.005
5 1116.8115 625.24631 964.79304 464.09323 623.12277 632.24398 0.008
6 1304.2279 763.96169 1133.7382 523.70389 707.48815 723.9107 0.005
7 1469.4238 884.45686 1271.2085 606.08567 784.85087 807.73648 0.004
8 1607.5084 981.88602 1403.0164 695.40234 857.93327 890.80103 0.005
9 1746.3309 1077.6346 1528.2417 786.31147 928.13054 972.88746 0.005
10 1757.9529 1133.6373 1647.1759 877.54774 995.00783 1051.5562 0.009
Anguler
second
moment
1 0.0002742 6.331E-05 0.00258 0.0121617 0.000996 0.0031795 0.615
2 0.000235 5.368E-05 0.002369 0.0114941 0.000741 0.0023154 0.588
3 0.00022 5.135E-05 0.002203 0.010853 0.00062 0.001843 0.579
4 0.0002092 4.814E-05 0.00204 0.0101715 0.00054 0.0014655 0.577
5 0.000205 4.523E-05 0.001894 0.0094979 0.000491 0.0012406 0.578
6 0.0002025 4.615E-05 0.001754 0.008829 0.000457 0.001081 0.583
7 0.0002008 4.441E-05 0.001623 0.0081787 0.000429 0.0009476 0.587
8 0.0002033 4.418E-05 0.001497 0.0075266 0.000421 0.0009219 0.598
9 0.0002042 4.231E-05 0.001379 0.0068739 0.000405 0.0008366 0.603
10 0.0002042 4.078E-05 0.001276 0.0062613 0.000398 0.0007989 0.607
Invers
differensial
moment
1 0.0550017 0.0080398 0.050305 0.0112195 0.050863 0.0102625 0.388
2 0.0435583 0.006599 0.041152 0.0088032 0.041908 0.0088899 0.691
3 0.0366325 0.0056583 0.036585 0.0083152 0.03753 0.0086837 0.873
4 0.03318 0.0052641 0.033432 0.0079717 0.034597 0.0091464 0.79
5 0.030095 0.0052241 0.031184 0.0079358 0.032842 0.0091317 0.525
6 0.0286042 0.0051924 0.029318 0.0077564 0.031019 0.0088928 0.548
7 0.0265842 0.0056255 0.028046 0.0075968 0.029592 0.0088625 0.479
8 0.02498 0.0051824 0.026452 0.0073192 0.028509 0.0088071 0.317
9 0.0238067 0.0050711 0.025359 0.0068792 0.027285 0.0086237 0.313
10 0.0234283 0.0048346 0.024368 0.0069794 0.026728 0.0085537 0.272
Mean of
Hm(y,d)
1 131.62967 28.959467 145.02607 27.714486 148.54017 30.619119 0.226
2 132.11067 29.12184 145.40824 27.738119 149.17381 30.691868 0.223
3 132.5816 29.273948 145.74163 27.759487 149.69002 30.676374 0.222
4 133.00409 29.415246 146.047 27.757742 150.13301 30.664421 0.222
5 133.39093 29.545445 146.31024 27.740678 150.52887 30.66877 0.222
6 133.75322 29.674278 146.35145 27.646034 150.86479 30.674152 0.223
7 134.08084 29.820181 146.76085 27.663767 151.1448 30.66699 0.225
8 134.34956 29.978102 146.95661 27.593481 151.37044 30.662581 0.226
9 134.56753 30.137103 147.12655 27.523106 151.56755 30.652291 0.227
10 134.73142 30.286683 147.26316 27.449828 151.7134 30.638789 0.227

 ISSN: 1693-6930
644
Table 1. Average Physical Parameter Values of Grades 1, 2 and 3 with Varying Distances
between Pixels from Doctor Soetomo Surabaya Hospital in 2018 [21] (continue)
d
Grade 1 (n=12) Grade 2 (n=41) Grade 3 (n=34)
Significant
Average
Standard
deviation
Average
Standartd
deviation
Average
Standard
deviation
Deviation
1 34.260554 9.7619133 34.312329 11.739118 34.201961 10.784648 0.999
2 34.063222 9.6913602 34.191907 11.747045 34.178546 10.497243 0.999
3 33.87281 9.6183372 34.104492 11.766145 34.037906 10.491743 0.998
4 33.718329 9.5646835 34.029315 11.792871 33.940052 10.525177 0.996
5 33.59901 9.5004278 33.986836 11.803124 33.773723 10.663739 0.993
6 33.49073 9.4028597 33.972137 11.809241 33.7171 10.70515 0.99
7 33.376675 9.2914793 33.966377 11.819327 33.776023 10.655739 0.987
8 33.241699 9.1846679 33.967365 11.831127 33.754651 10.701706 0.98
9 33.132857 9.1244331 33.976051 11.835557 33.743379 10.759438 0.973
10 33.067677 9.1209389 33.99897 11.844682 33.751424 10.812589 0.968
Entropy of
of
difference
second
order
histogram
1 1.5207192 0.051969 1.544523 0.0937383 1.547077 0.0883259 0.651
2 1.6403642 0.0628206 1.63932 0.0873686 1.643583 0.0996902 0.979
3 1.7141417 0.0744286 1.698631 0.0893982 1.702241 0.1102782 0.887
4 1.7665917 0.0828595 1.742473 0.0939141 1.742984 0.1194766 0.76
5 1.8067333 0.0885038 1.776767 0.0980366 1.774627 0.1270087 0.66
6 1.8386942 0.0924841 1.805169 0.1032635 1.800483 0.1318185 0.596
7 1.8637192 0.0956349 1.828137 0.1076612 1.821602 0.1358604 0.563
8 1.8797392 0.0996391 1.849734 0.1119991 1.839526 0.1396573 0.62
9 1.9006017 0.1008531 1.867021 0.115691 1.852449 0.1419445 0.519
10 1.9146375 0.1021066 1.881975 0.1189006 1.868959 0.1445945 0.569
Anguler
second
moment of
difference
second
order
histogram
1 0.03668 0.0051556 0.0341868 0.0085414 0.0353732 0.0076225 0.586
2 0.0282383 0.0039959 0.0297332 0.0117903 0.0286021 0.0066021 0.821
3 0.0239925 0.0037562 0.0261732 0.0110877 0.0251809 0.0065281 0.727
4 0.021315 0.003611 0.0237566 0.010287 0.0230621 0.0065961 0.67
5 0.0194033 0.0034894 0.0219956 0.0096175 0.0215512 0.0066765 0.61
6 0.0180183 0.0034022 0.0206161 0.0090624 0.0203379 0.0065739 0.573
7 0.0169567 0.003318 0.0194468 0.0083957 0.0193909 0.0065425 0.547
8 0.0161233 0.0032688 0.0184744 0.0078957 0.0186097 0.0064878 0.532
9 0.0154375 0.0032256 0.0176859 0.0074144 0.0179182 0.0063886 0.515
10 0.0148642 0.0031297 0.016971 0.006786 0.01735 0.0063198 0.487
Mean of
difference
second
order
histogram
1 12.471971 1.437844 13.61416 3.055367 13.57642 2.740966 0.429
2 16.497296 2.330525 16.91747 3.296786 17.10418 3.79908 0.868
3 19.660166 3.426158 19.40229 3.708941 19.62252 4.608733 0.965
4 22.319414 4.424387 21.49979 4.243049 21.63089 5.370358 0.869
5 24.645164 5.302194 23.35188 4.84364 23.33268 6.035107 0.741
6 26.637238 6.112734 25.03549 5.50095 24.83297 6.606327 0.66
7 28.368256 6.793837 26.56531 6.134323 26.15693 7.135861 0.608
8 29.839518 7.442675 28.00049 6.796493 27.37054 7.655554 0.598
9 31.144367 8.017093 29.28278 7.442864 28.49279 8.115047 0.599
10 32.271235 8.5010159 30.47403 8.063936 29.53199 8.580728 0.616

Classification of breast cancer grades using physical parameters and K-nearest neighbor method

More Related Content

What's hot (20)

Similar to Classification of breast cancer grades using physical parameters and K-nearest neighbor method (20)

More from TELKOMNIKA JOURNAL (20)

Recently uploaded (20)

Classification of breast cancer grades using physical parameters and K-nearest neighbor method