KLASIFIKASI CITRA ULTRASONOGRAFI UNTUK DETEKSI NODUL TIROID BERDASARKAN ECHOGENICITY

Wirawan Setyo Prakoso; Alva Rischa  Qhisthana Pratika

doi:10.36761/hexagon.v6i1.5052

Authors

Wirawan Setyo Prakoso Politeknik Industri Petrokimia Banten
Alva Rischa Qhisthana Pratika

DOI:

https://doi.org/10.36761/hexagon.v6i1.5052

Keywords:

Ultrasound, Thyroid nodules, Classification, Early detection of disease, Feature extraction, Machine learning techniques, SVM echogenicity classification.

Abstract

One of the important features for diagnosing malignant thyroid nodules is based on their echogenicity characteristics, namely the grey intensity of each nodule. Therefore, computer-aided diagnosis (CADx) is required to select important features and classify nodules that are more likely to be malignant or benign and the form of treatment is known. This study proposes classifying thyroid nodules based on texture features from histogram, GLCM and GLRLM into 4 classes: anechoic, hyperechoic, hypoechoic and very hypoechoic. Ultrasound is the best way to filter information about the characteristics of the degree of malignancy of thyroid nodules used by doctors. The doctor's decision takes a long time. Early detection is necessary, so that doctors can provide treatment and prevention quickly. This study uses machine learning for early detection of the level of malignancy of thyroid nodules using ultrasound images with a dataset obtained from Sardjito Hospital, Yogyakarta Radiology Department. The results showed that the Linear SVM method is the best method to classify the level of malignancy of thyroid nodules based on the dataset which has been divided into 4 classes with 64 features resulting in an accuracy of 68.3%, a positive predictive value of 70% and a sensitivity value of 68%.

Keywords: Ultrasound, Thyroid nodules, Classification, Early detection of disease, Feature extraction, Machine learning techniques, SVM echogenicity classification.

References

Inman et al., “Completeness of ultrasound reporting impacts time to biopsy for benign and malignant thyroid nodules,” Am. J. Surg., vol. 213, no. 5, hal. 931–935, 2017.

J. H. Shin et al., “Ultrasonography diagnosis and imaging-based management of thyroid nodules: Revised Korean society of thyroid radiology consensus statement and recommendations,” Korean J. Radiol., vol. 17, no. 3, hal. 370–395, 2016.

G. Russ, “Risk stratification of thyroid nodules on ultrasonography with the French TI-RADS: Description and reflections,” Ultrasonography, vol. 35, no. 1, hal. 25–38, 2015.

N. C. Institute, “Cancer Stat Facts: Thyroid Cancer.” [Daring]. Tersedia pada: https://seer.cancer.gov/statfacts/html/thyro.html.

M. Rahmawaty, H. A. Nugroho, Y. Triyani, I. Ardiyanto, dan I. Soesanti, “Classification of breast ultrasound images based on texture analysis,” Proc. 2016 1st Int. Conf. Biomed. Eng. Empower. Biomed. Technol. Better Futur. IBIOMED 2016, hal. 1–6, 2017.

N. Ponraj, L. Saviour, Poongodi, dan M. Mercy, “Segmentation of thyroid nodules using watershed segmentation,” 2nd Int. Conf. Electron. Commun. Syst. ICECS 2015, no. Icecs, hal. 1098–1102, 2015.

D. Selvathi dan V. S. Sharnitha, “Thyroid classification and segmentation in ultrasound images using machine learning algorithms,” 2011 - Int. Conf. Signal Process. Commun. Comput. Netw. Technol. ICSCCN-2011, no. Icsccn, hal. 836–841, 2011.

R. Suganya dan S. Rajaram, “Feature extraction and classification of ultrasound liver images using haralick texture-primitive features: Application of SVM classifier,” 2013 Int. Conf. Recent Trends Inf. Technol. ICRTIT 2013, hal. 596–602, 2013.

M. Singh, S. Singh, dan S. Gupta, “A new measure of echogenicity of ultrasound images for liver classification,” Can. Conf. Electr. Comput. Eng., hal. 000317–000320, 2011.

G. Wang dan F. Chen, “Texture features for classification of ultrasonic liver images based on neural network,” J. Comput. Inf. Syst., vol. 1, no. 4, hal. 749–755, 2005.

A. S. M. Sohail, P. Bhattacharya, S. P. Mudur, dan S. Krishnamurthy, “Local relative glrlm-based texture feature extraction for classifying ultrasound medical images,” Can. Conf. Electr. Comput. Eng., no. 1, hal. 001092–001095, 2011.

M. Owjimehr, H. Danyali, dan M. S. Helfroush, “Fully automatic segmentation and classification of liver ultrasound images using completed LBP texture features,” 22nd Iran. Conf. Electr. Eng. ICEE 2014, no. Icee, hal. 1956–1960, 2014.

A. Nugroho, H. A. Nugroho, N. A. Setiawan, dan L. Choridah, “Internal content classification of ultrasound thyroid nodules based on textural features,” Commun. Sci. Technol., vol. 1, no. 2, hal. 61–69, 2016.

M. A. Savelonas, D. E. Maroulis, D. K. Iakovidis, dan N. Dimitropoulos, “Computer-aided malignancy risk assessment of nodules in thyroid US images utilizing boundary descriptors,” Proc. - 12th Pan-Hellenic Conf. Informatics, PCI 2008, hal. 157–160, 2008.

F. L, Neural Network In Computer Intelligence. Singapura: Mc Graw Hill, 1994.

G. Mak dan G. M. M. Montreal, “the Implementation of Support Vector Machines Using the Sequential Minimal Optimization Algorithm,” 2000.