Os efeitos da utilização de atributos perinodulares na classificação de nódulos pulmonares

• José Calheiros UFAL
• Lucas Amorim UFAL
• Lucas Lima UFAL
• Marcelo Oliveira UFAL

DOI: https://doi.org/10.5753/sbcas.2020.11510

Abstract

Currently, most CADx systems have been using only descriptors from the pulmonary nodule region. Recent studies indicate that there is a significant interaction between the pulmonary nodule and its surroundings, the parenchyma, however, this region has been little used for the lung cancer diagnosis process. The objective of this work was to investigate the performance of image descriptors extracted from the regions of the nodule, border and parenchyma (intranodular and perinodular attributes), in the identification of their potential for malignancy. In this work, 897 pulmonary nodules were evaluated with 121 image descriptors extracted from the tumor region. The descriptors were selected by genetic algorithm and the performance evaluation was done through the area under the ROC curve (AUC) with 10 folds cross-validation and 5 repetitions. Our best-evaluated model obtained an average AUC of 0.916, accuracy of 84.26%, sensitivity of 84.45% and specificity of 83.84%. The results obtained sustain that the use of perinodular features effectively improves the classification performance of pulmonary nodules.

References

Aerts, H., Rios Velazquez, E., Leijenaar, R., Parmar, C., Grossmann, P., Cavalho, S., Bussink, J., Monshouwer, R., Haibe-Kains, B., Rietveld, D., Hoebers, F., M Rietbergen, M., Leemans, C., Dekker, A., Quackenbush, J., Gillies, R., and Lambin, P. (2014). Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature communications, 5:4006.

Akgul, C., Rubin, D., Napel, S., Beaulieu, C., Greenspan, H., and Acar, B. (2010).¨ Content-based image retrieval in radiology: Current status and future directions. Journal of digital imaging : the official journal of the Society for Computer Applications in Radiology, 24:208–22.

Armato, S. G., McLennan, G., Bidaut, L., McNitt-Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., et al. (2011). The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans. Medical physics, 38(2):915– 931.

Bannister, N. and Broggio, J. (2016). Cancer survival by stage at diagnosis for england (experimental statistics): Adults diagnosed 2012, 2013, 2014 and followe d up to 2015. Produced in collaboration with Public Health England.

Beig, N., Khorrami, M., Alilou, M., Prasanna, P., Braman, N., Orooji, M., Rakshit, S., Bera, K., Rajiah, P., Ginsberg, J., Donatelli, C., Thawani, R., Yang, M., Jacono, F., Tiwari, P., Velcheti, V., Gilkeson, R., Linden, P., and Madabhushi, A. (2019). Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas. Radiology, 290(3):783–792.

Bray, F., Ferlay, J., Soerjomataram, I., L. Siegel, R., Torre, L., and Jemal, A. (2018). Global cancer statistics 2018: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries: Global cancer statistics 2018. CA: A Cancer Journal for Clinicians, 68.

Chen, C. H., Chang, C. K., Tu, C. Y., Liao, W. C., Wu, B. R., Chou, K. T., Chiou, Y. R., Yang, S. N., Zhang, G., and Huang, T. C. (2018). Radiomic features analysis in computed tomography images of lung nodule classification. PLoS ONE, 13(2).

Coroller, T. P., Grossmann, P., Hou, Y., Rios Velazquez, E., Leijenaar, R. T., Hermann, G., Lambin, P., Haibe-Kains, B., Mak, R. H., and Aerts, H. J. (2015). CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radiotherapy and Oncology, 114(3):345–350.

Dhara, A. K., Mukhopadhyay, S., Dutta, A., Garg, M., and Khandelwal, N. (2016). A Combination of Shape and Texture Features for Classification of Pulmonary Nodules in Lung CT Images. Journal of Digital Imaging, 29(4):466–475.

Dilger, S., Uthoff, J., Judisch, A., Hammond, E., Mott, S., Smith, B., Newell, Jr, J., Hoffman, E., and (de Ryk) Sieren, J. (2015). Improved pulmonary nodule classification utilizing quantitative lung parenchyma features. Journal of Medical Imaging, 2:041004.

Dilger, S. K. N. (2013). The use of surrounding lung parenchyma for the automated classification of pulmonary nodules.

Felix, A., Oliveira, M., Machado, A., and Raniery, J. Using 3D Texture and Margin Sharpness Features on Classification of Small Pulmonary Nodules. Technical report.

Ferreira, J. R., de Azevedo-Marques, P. M., and Oliveira, M. C. (2017). Selecting relevant 3d image features of margin sharpness and texture for lung nodule retrieval. International Journal of Computer Assisted Radiology and Surgery, 12(3):509–517.

Firmino, M., Angelo, G., Morais, H., Dantas, M. R., and Valentim, R. (2016). Computeraided detection (CADe) and diagnosis (CADx) system for lung cancer with likelihood of malignancy. BioMedical Engineering OnLine, 15(1):2.

Haralick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6):610– 621.

Huang, P., Park, S., Yan, R., Lee, J., Chu, L. C., Lin, C. T., Hussien, A., Rathmell, J., Thomas, B., Chen, C., HalS, R., Ettinger, D. S., Brock, M., Hu, P., Fishman, E. K., Gabrielson, E., and Lam, S. (2018). Added value of computer-aided CT image features for early lung cancer diagnosis with small pulmonary nodules: A matched case-control study. Radiology, 286(1):286–295.

Junior, J. R. F., Oliveira, M. C., and de Azevedo-Marques, P. M. (2016). Cloud-based nosql open database of pulmonary nodules for computer-aided lung cancer diagnosis and reproducible research. Journal of digital imaging, 29(6):716–729.

Knight, S., Crosbie, P., Balata, H., Chudziak, J., Hussell, T., and Dive, C. (2017). Progress and prospects of early detection in lung cancer. Open Biology, 7:170070.

Paul, R., Hawkins, S. H., Schabath, M. B., Gillies, R. J., Hall, L. O., and Goldgof, D. B. (2018). Predicting malignant nodules by fusing deep features with classical radiomics features. Journal of Medical Imaging, 5(01):1.

Stec, N., Arje, D., Moody, A. R., Krupinski, E. A., and Tyrrell, P. N. (2018). A systematic review of fatigue in radiology: Is it a problem?

Uthoff, J., Stephens, M. J., Newell, J. D., Hoffman, E. A., Larson, J., Koehn, N., De Stefano, F. A., Lusk, C. M., Wenzlaff, A. S., Watza, D., Neslund-Dudas, C., Carr, L. L., Lynch, D. A., Schwartz, A. G., and Sieren, J. C. (2019). Machine learning approach for distinguishing malignant and benign lung nodules utilizing standardized perinodular parenchymal features from CT. Medical Physics, page mp.13592.

Way, T. W., Sahiner, B., Chan, H.-P., Hadjiiski, L., Cascade, P. N., Chughtai, A., Bogot, N., and Kazerooni, E. (2009). Computer-aided diagnosis of pulmonary nodules on ct scans: Improvement of classification performance with nodule surface features. Medical Physics, 36(7):3086–3098.

Wei, G., Cao, H., Ma, H., Qi, S., Qian, W., and Ma, Z. (2018). Content-based image retrieval for Lung Nodule Classification Using Texture Features and Learned Distance Metric. Journal of Medical Systems, 42(1).

World Health Organisation (2019). Cancer. http://www.who.int/ mediacentre/factsheets/fs282/fr/, Last accessed on 2019-08-22.

Xu, J., Napel, S., Greenspan, H., Beaulieu, C., Agrawal, N., and Rubin, D. (2012). Quantifying the margin sharpness of lesions on radiological images for content-based image retrieval. Medical physics, 39:5405–18.

Zhou, H., Dong, D., Chen, B., Fang, M., Cheng, Y., Gan, Y., Zhang, R., Zhang, L., Zang, Y., Liu, Z., Zheng, H., Li, W., and Tian, J. (2018). Diagnosis of Distant Metastasis of Lung Cancer: Based on Clinical and Radiomic Features. Translational Oncology, 11(1):31–36.