A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification

Ergin, Semih; Topuz, Bengisu; Cinar, Ali

doi:10.35860/iarej.857579

A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification

Ali ÇINAR, (Kastamonu Üniversitesi, Elektrik ve Elektronik Mühendisliği Bölümü, Kastamonu, Türkiye)

Bengisu TOPUZ, (Hacettepe Üniversitesi, Fen Bilimleri Enstitüsü, Biyomühendislik Anabilim Dalı, Ankara, Türkiye)

Semih ERGİN (Eskişehir Osmangazi Üniversitesi, Elektrik ve Elektronik Mühendisliği Bölümü, Eskişehir, Türkiye)

International Advanced Researches and Engineering Journal

4 1

Yıl: 2021 Cilt: 5 Sayı: 2 Sayfa Aralığı: 281 - 291 Metin Dili: İngilizce DOI: 10.35860/iarej.857579 İndeks Tarihi: 29-07-2022

A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification

Öz:

Suspicious regions in chest x-rays are detected automatically, and these regions are classified intothree types, including “malignant nodule”, “benign nodule”, and “no nodule” in this study. Firstly,the areas except the lung tissues are removed in each chest x-ray using the thresholding method.Then, Poisson noise was removed from the images by applying the gradient filter. Ribs mayoverlap onto nodules. Since this circumstance will make the detection of a nodule difficult, it isnecessary to distinguish and suppress the ribs. The location of the rib bones is determined by atemplate matching method, and then the corresponding bones are suppressed by applying theGabor filter. After this stage, suspicious tissues in the chest x-rays are specified using the ChanVese active contour without edges. Then, some features are extracted from these suspiciousregions. Six different features are extracted: Statistical, Histogram of Oriented Gradients (HOG)-based, Local Binary Pattern (LBP)-based, Geometrical, Gray Level Co-Occurrence Matrix(GLCM) Texture-based and Dense Scale Invariant Feature Transform (DSIFT)-based. Then, theclassification stage is achieved using these features. The best classification result is obtained usingstatistical, LBP-based, and HOG-Based features. The classification results are evaluated withsensitivity, accuracy, and specificity analyses. K-Nearest Neighbour (KNN), Decision Tree (DT),Random Forest (RF), Logistic Linear Classifier (LLC), Support Vector Machines (SVM), Fisher’sLinear Discriminant Analysis (FLDA), and Naive Bayes (NB) methods are used for theclassification purpose separately. The random forest classifier gives the best results with 57%sensitivity, 66% accuracy, 81% specificity values.

Anahtar Kelime: Nodule classification Rib detection ROI detection Chest x-ray classification Rib suppression Nodule detection

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

1. Stewart, B., C.P. Wild, World Cancer Report 2014. 2015, WHO Press.
2. Garfinkel, L., G. Murphy, W.J. Lawrence, R.J. Lenhard, American Cancer Society Textbook of Clinical Oncology. 1995, The Society Press.
3. Abbas, W., K.B. Khan, M. Aqeel, M.A. Azam, M.H. Ghouri, F.H. Jaskani, Lungs Nodule Cancer Detection Using Statistical Techniques. IEEE 23rd International Multitopic Conference, 2020, Pakistan. p. 1-6.
4. Parveen, S., K.B. Khan, Detection and classification of pneumonia in chest X-ray images by supervised learning. IEEE 23rd International Multitopic Conference, 2020, Pakistan, p. 1-5.
5. Gonzalez, E.R., V. Ponomaryov, Automatic Lung nodule segmentation and classification in CT images based on SVM. 9th International Kharkiv Symposium on Physics and Engineering of Microwaves, Millimeter and Submillimeter Waves, 2016, Ukraine. p. 1-4.
6. Tun, K.M.M, A.S. Khaing, Feature Extraction and Classification of Lung Cancer Nodule using Image Processing Techniques. International Journal of Engineering Research & Technology, 2014. 3(3): p. 2204- 2210.
7. Shiraishi, J., S. Katsuragawa, J. Ikezoe, T. Matsumoto, T. Kobayashi , K. Komatsu, M. Matsui, H. Fujita, Y. Kodera, K. Doi, Development of a digital image database for chest radiographs with and without a lung nodule: Receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. AJR, 2000. 174(1): p. 71-74.
8. Khan, K.B., A.A. Khaliq, M. Shadid, J.A. Shah, A new approach of weighted gradient filter for denoising of medical images in the presence of Poisson noise. Tehnički vjesnik, 2016. 23 (6): p. 1755-62.
9. Gallagher, N., G. Wise, A theoretical analysis of the properties of median filters. IEEE Transaction on Acoustic Speech Signal Processing, 1981. 29 (6): p. 1135–1141.
10. Wang, C., A. Elazab, J. Wu, Q. Hua, Lung nodule classification using deep feature fusion in chest radiography. Computerized Medical Imaging and Graphics, 2017. 57: p. 10-18.
11. Gabor, D., Theory of communication. Journal of the Institution of Electrical Engineers- Part III: Radio and Communication Engineering, 1946. 93(26): p. 429–457.
12. Soleymanpour, E., H.R. Pourreza, E. Ansariour, M. Sadooghi, Fully Automatic Lung Segmentation and Rib Suppression Methods to Improve Nodule Detection in Chest Radiographs. Journal of Medical Signals and Sensors, 2011. 1(3): p. 191-199.
13. Haddad, R.A., A.N. Akansu, A, Class of Fast Gaussian Binomial Filters for Speech and Image Processing, IEEE Transactions on Acoustics, Speech and Signal Processing, 1991. 39(3): p. 723-727.
14. Chan, T.F., L.A. Vese, Active contours without edges. IEEE Transactions on Image Processing, 2001. 10(2): p. 266‐277.
15. Esener, I.I., S. Ergin, T. Yuksel, A New Feature Ensemble with a Multistage Classification Scheme for Breast Cancer Diagnosis. Journal of Healthcare Engineering, 2017. 2017: p. 1-15.
16. Ahonen, T., A. Hadid, M. Pietkäinen, Face description with local binary patterns: Application to face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006. 28(12): p. 2037-2041.
17. Song, L., X. Liu, L. Ma, C. Zhou, X. Zhao, Y. Zhao, Using HOG-LBP features and MMP learning to recognize imaging signs of lung lesions. 25.International Symposium On Computer-Based Medical Systems, 2012, Italy. p. 1-4.
18. Wang, L., D.C. He,Texture Classification Using Texture Spectrum, Pattern Recognition, 1990. 23(8): p. 905-910.
19. Esener, I.I., The Identification of Suspicious Regions on Mammography Images for Breast Cancer and the Classification of Breast Cancer Type. PhD Thesis, Eskisehir Osmangazi University, 2017.
20. Haralick, R.M., K. Shanmugam, I. Dinstein, Textural features of image classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973. SMC-3(6): p. 610- 621.
21. Soh. L., C. Tsatsoulis, Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Transactions on Geoscience and Remote Sensing, 1999. 37(2): p. 780-795.
22. Clausi, D.A., An analysis of co-occurrence texture statistics as a function of grey level quantization. Canadian Journal of Remore Sensing, 2002. 28(1): p. 45-62.
23. Esener. I.I, S. Ergin, T. Yuksel, A Genuine GLCM-based Feature Extraction for Breast Tissue Classification on Mammograms. International Journal of Intelligent Systems and Applications in Engineering, 2016. 4(Special Issue): p. 124-129.
24. Ergin. S., O. Kilinc, Using DSIFT and LCP features for detecting breast lesions. ISCSE, 2013. International Symposium on Computing in Science & Engineering. Proceedings: Izmir. p. 216-220.
25. Kim. J., B.S. Kim, S. Savarese, Comparing image classification methods:K-nearest-neighbor and supportvector-machines. 6. WSEAS International Conference on Computer Engineering and Applications, 2012, World Scientific and Engineering Academy and Society: USA. p. 133-138.
26. Akar. O, O. Gungor, Classification of multispectral images using Random Forest Algorithm. Journal of Geodesy and Geoinformation, 2012. 1(2): p. 105-112.
27. Safavian, S.R., D. Landgrebe, A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 1991. 21(3): p. 660-674.
28. Rish, I., An empirical study of the naive Bayes classifier. IJCAI Workshop on Empirical Methods in artificial intelligence, 2001, IBM New York: USA. p. 41-46.
29. Webb, A.R., Linear discriminant analysis in Statistical Pattern Recognition. 2002, John Wiley & Sons.
30. Ozkan, K., S. Ergin, S. Isik, I. Isikli, A new classification scheme of plastic wastes based upon recycling labels, Waste Management, 2015. 35: p. 29-35. 291
31. Fisher, R.A., The use of multiple measurements in taxonomic problems. Annals of Eugenics, 1936. 7(2): p. 179-188.

APA	Cinar A, Topuz B, Ergin S (2021). A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. , 281 - 291. 10.35860/iarej.857579
Chicago	Cinar Ali,Topuz Bengisu,Ergin Semih A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. (2021): 281 - 291. 10.35860/iarej.857579
MLA	Cinar Ali,Topuz Bengisu,Ergin Semih A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. , 2021, ss.281 - 291. 10.35860/iarej.857579
AMA	Cinar A,Topuz B,Ergin S A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. . 2021; 281 - 291. 10.35860/iarej.857579
Vancouver	Cinar A,Topuz B,Ergin S A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. . 2021; 281 - 291. 10.35860/iarej.857579
IEEE	Cinar A,Topuz B,Ergin S "A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification." , ss.281 - 291, 2021. 10.35860/iarej.857579
ISNAD	Cinar, Ali vd. "A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification". (2021), 281-291. https://doi.org/10.35860/iarej.857579

APA	Cinar A, Topuz B, Ergin S (2021). A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. International Advanced Researches and Engineering Journal, 5(2), 281 - 291. 10.35860/iarej.857579
Chicago	Cinar Ali,Topuz Bengisu,Ergin Semih A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. International Advanced Researches and Engineering Journal 5, no.2 (2021): 281 - 291. 10.35860/iarej.857579
MLA	Cinar Ali,Topuz Bengisu,Ergin Semih A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. International Advanced Researches and Engineering Journal, vol.5, no.2, 2021, ss.281 - 291. 10.35860/iarej.857579
AMA	Cinar A,Topuz B,Ergin S A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. International Advanced Researches and Engineering Journal. 2021; 5(2): 281 - 291. 10.35860/iarej.857579
Vancouver	Cinar A,Topuz B,Ergin S A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. International Advanced Researches and Engineering Journal. 2021; 5(2): 281 - 291. 10.35860/iarej.857579
IEEE	Cinar A,Topuz B,Ergin S "A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification." International Advanced Researches and Engineering Journal, 5, ss.281 - 291, 2021. 10.35860/iarej.857579
ISNAD	Cinar, Ali vd. "A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification". International Advanced Researches and Engineering Journal 5/2 (2021), 281-291. https://doi.org/10.35860/iarej.857579