Lung nodules classification in CT images using texture descriptors




lung nodules, CT, CAD, Haralick, texture


In lung cancer, early diagnosis can improve potentially the prognosis. Accurate interpretation of computed tomography (CT) scans demands significant efforts by radiologists due to the extensive number of slices analyzed in each examination, for each patient. Computer-aided diagnosis (CAD) systems have been applied in several medical fields, but mostly in lung nodules detection and classification. CAD systems for lung lesions classification usually extract different types of features from lesions, such as texture feature, shape and intensity. This exploratory study aims to investigate the performance of lung nodules classification in 2D and 3D CT lesions images using Haralick texture features analysis and binary logistic regression.  Expert radiologists manually segmented from a CT dataset of 17 benign and 20 malignant nodules, which have their anatomopathological results. Haralick features were extracted from 2D lesions images, using the largest cross-section nodule area, and from all nodule volume (3D). Principal Component Analysis (PCA) was applied to reduce texture features dimensionality, showing two and three principal components (PC) can explain 85.8% and 96.25% of data variance for 2D lesions, and 72.4% and 91.7% for 3D lesions, respectively. Binary logistic regression using leave-one-out cross-validation for training and test datasets showed no differences in accuracy (63% - 68%), using two or three PC. The higher sensitivity (75%) was acquired using 2D images with two or three PC, while the higher specificity (65%) was obtained using 3D images with two or three PC. Binary logistic regression using a small number of Haralick texture features showed better accuracy in lung nodules classification than visual evaluation by radiologists, although the limited dataset. Further studies are needed to generalize and improve these results.


Não há dados estatísticos.


Doi K, MacMahon H, Giger ML, Hoffmann KR. Computer-aided diagnosis and its potential impact on diagnostic radiology. Comput Diagnosis Med imaging Amsterdam, Netherlands Elsevier Sci. 1999;11–20.

Giger ML, Suzuki K. Computer-Aided Diagnosis. Biomed Inf Technol [Internet]. 2008 Jan 1 [cited 2019 Mar 18];359–XXII. Available from:

Zia ur Rehman M, Javaid M, Shah SIA, Gilani SO, Jamil M, Butt SI. An appraisal of nodules detection techniques for lung cancer in CT images. Biomed Signal Process Control [Internet]. 2018 Mar 1 [cited 2019 Mar 18];41:140–51. Available from:

Rubin GD. Lung nodule and cancer detection in computed tomography screening. In: Journal of Thoracic Imaging [Internet]. 2015 [cited 2019 Mar 18]. p. 130–8. Available from:

Froner APP. Caracterização de nódulos pulmonares em imagens de tomografia computadorizada para fins de auxílio ao diagnóstico [Internet]. Pontifícia Universidade Católica do Rio Grande do Sul; 2015 [cited 2019 Apr 10]. Available from:

Madero Orozco H, Vergara Villegas OO, Cruz Sánchez VG, Ochoa Domínguez H de J, Nandayapa Alfaro M de J. Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine. Biomed Eng Online [Internet]. 2015 Dec 12 [cited 2019 Mar 18];14(1):9. Available from:

Zayed N, Elnemr HA. Statistical Analysis of Haralick Texture Features to Discriminate Lung Abnormalities. Int J Biomed Imaging [Internet]. 2015 Oct 8 [cited 2019 Apr 3];2015:1–7. Available from:

Haralick RM, Shanmugam K, Dinstein I. Textural Features for Image Classification. IEEE Trans Syst Man Cybern [Internet]. 1973 Nov [cited 2019 Apr 10];SMC-3(6):610–21. Available from:

Han F, Wang H, Zhang G, Han H, Song B, Li L, et al. Texture Feature Analysis for Computer-Aided Diagnosis on Pulmonary Nodules. J Digit Imaging [Internet]. 2014 [cited 2019 Mar 22];28(1):99–115. Available from:

Wei G, Cao H, Ma H, Qi S, Qian W, Ma Z. Content-based image retrieval for Lung Nodule Classification Using Texture Features and Learned Distance Metric. J Med Syst [Internet]. 2018 [cited 2019 Apr 15];42(1). Available from:

Franco MLN, Nunes LM, Froner APP, Silva AMM, Patrocínio AC. REDES NEURAIS ARTIFICIAIS APLICADAS NA CLASSIFICAÇÃO DE TUMORES PULMONARES [Internet]. [cited 2019 Apr 15]. Available from:

Kavitha MS, Shanthini J, Sabitha R. ECM-CSD: An Efficient Classification Model for Cancer Stage Diagnosis in CT Lung Images Using FCM and SVM Techniques. J Med Syst [Internet]. 2019 Mar 12 [cited 2019 Apr 15];43(3):73. Available from:

Dhara AK, Mukhopadhyay S, Khandelwal N. 3D texture analysis of solitary pulmonary nodules using co-occurrence matrix from volumetric lung CT images. In: Novak CL, Aylward S, editors. International Society for Optics and Photonics; 2013 [cited 2019 Apr 15]. p. 867039. Available from:

Xujiong Ye, Xinyu Lin, Dehmeshki J, Slabaugh G, Beddoe G. Shape-Based Computer-Aided Detection of Lung Nodules in Thoracic CT Images. IEEE Trans Biomed Eng [Internet]. 2009 Jul [cited 2019 Apr 15];56(7):1810–20. Available from:

Ramteke RJ, Y KM. Automatic Medical Image Classification and Abnormality Detection Using K- Nearest Neighbour. Int J Adv Comput Res [Internet]. 2012 [cited 2019 Apr 3];2(4):190–6. Available from:




Como Citar

de Moura, L. V., Dartora, C. M., & Marques da Silva, A. M. (2019). Lung nodules classification in CT images using texture descriptors. Revista Brasileira De Física Médica, 13(3), 38–42.



Artigo Original

Artigos mais lidos pelo mesmo(s) autor(es)

1 2 3 > >>