Feasibility Study of MRI and Multimodality CT/MRI Radiomics for Lung Nodule Classification
Resumo
O câncer de pulmão é o tipo mais frequente e letal de câncer e o seu diagnóstico precoce é crucial para a sobrevivência do paciente. A tomografia computadorizada (TC) é o padrão-ouro para o rastreio da doença; no entanto, apresenta a desvantagem de expor o paciente à radiação. Estudos recentes têm demonstrado o potencial da ressonância magnética (RM) no diagnóstico de nódulos pulmonares. Este trabalho busca avaliar a aplicação de características radiômicas de RM para a caracterização de nódulos pulmonares e se a combinação de atributos de TC e RM podem levar a melhores resultados que as modalidades individuais. Para tal, foram segmentados nódulos pulmonares em imagens de TC e RM de 33 pacientes com nódulos pulmonares; a partir de cada modalidade foram extraídos 89 características radiômicas, que foram combinadas em um conjunto de características multimodalidade. Estas características foram usadas para classificar os nódulos entre benignos e malignos por meio de algoritmos de aprendizagem de máquina, calculando a AUC em 30 iterações. Os resultados indicam que características radiômicas de RM são adequadas para a caracterização de lesões pulmonares, com valores de AUC até 17% maiores que seus equivalentes em TC e evidenciando RM enquanto modalidade de imagem para sistemas de suporte à decisão. No entanto, a abordagem multimodalidade não apresentou ganhos em desempenho, sugerindo que a concatenação de características pode não ser uma estratégia adequada para lidar com imagens médicas multimodalidade.
Referências
Beckett, K. R., Moriarity, A. K., and Langer, J. M. (2015). Safe use of contrast media: what the radiologist needs to know. Radiographics, 35(6):1738–1750.
Blandin Knight, S., Crosbie, P. A., Balata, H., Chudziak, J., Hussell, T., and Dive, C. (2017). Progress and prospects of early detection in lung cancer. Open biology, 7(9):170070.
Cawley, G. C. and Talbot, N. L. (2010). On over-tting in model selection and subsequent selection bias in performance evaluation. The Journal of Machine Learning Research, 11:2079–2107.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of articial intelligence research, 16:321–357.
Claesen, M. and De Moor, B. (2015). Hyperparameter search in machine learning. arXiv preprint arXiv:1502.02127.
Demsar, J. (2006). Statistical comparisons of classiers over multiple data sets. Journal of Machine Learning Research, 7:1–30.
Fawcett, T. (2006). An introduction to roc analysis. Pattern recognition letters, 27(8):861–874.
Ferreira, J. R., Oliveira, M. C., and de Azevedo-Marques, P. M. (2018). Characterization of pulmonary nodules based on features of margin sharpness and texture. Journal of digital imaging, 31(4):451–463.
Francisco, V., Koenigkam-Santos, M., Wada, D. T., Junior, J. R. F., Fabro, A. T., Cipriano, F. E. G., Quatrina, S. G., and de Azevedo-Marques, P. M. (2019). Computer-aided In XXVI Brazilian diagnosis of lung cancer in magnetic resonance imaging exams. Congress on Biomedical Engineering, pages 121–127. Springer.
Gillies, R. J., Kinahan, P. E., and Hricak, H. (2016). Radiomics: images are more than pictures, they are data. Radiology, 278(2):563–577.
Guo, Z., Li, X., Huang, H., Guo, N., and Li, Q. (2019). Deep Learning-Based Image Segmentation on Multimodal Medical Imaging. IEEE Transactions on Radiation and Plasma Medical Sciences, 3(2):162–169.
Hatt, M., Tixier, F., Visvikis, D., and Le Rest, C. C. (2017). Radiomics in pet/ct: more than meets the eye? Journal of Nuclear Medicine, 58(3):365–366.
Jatobá, A., Lima, L., Amorim, L., and Oliveira, M. (2020). Cnn hyperparameter optimization for pulmonary nodule classication. In Anais do XX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 25–36, Porto Alegre, RS, Brasil. SBC.
Knight, S. B., Crosbie, P. A., Balata, H., Chudziak, J., Hussell, T., and Dive, C. (2017). Progress and prospects of early detection in lung cancer. Open Biology, 7(9).
Li, L., Zhao, X., Lu, W., and Tan, S. (2019a). Deep learning for variational multimodality tumor segmentation in pet/ct. Neurocomputing.
Li, S., Xu, P., Li, B., Chen, L., Zhou, Z., Hao, H., Duan, Y., Folkert, M., Ma, J., Huang, S., et al. (2019b). Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features. Physics in Medicine & Biology, 64(17):175012.
Mu, W., Qi, J., Lu, H., Schabath, M., Balagurunathan, Y., Tunali, I., and Gillies, R. J. (2018). Radiomic biomarkers from pet/ct multi-modality fusion images for the prediction of immunotherapy response in advanced non-small cell lung cancer patients. In Medical Imaging 2018: Computer-Aided Diagnosis, volume 10575, page 105753S. International Society for Optics and Photonics.
Ohno, Y., Kauczor, H.-U., Hatabu, H., Seo, J. B., van Beek, E. J., and for Pulmonary Functional Imaging (IWPFI), I. W. (2018). Mri for solitary pulmonary nodule and mass assessment: current state of the art. Journal of Magnetic Resonance Imaging, 47(6):1437–1458.
Parekh, V. S. and Jacobs, M. A. (2019). Deep learning and radiomics in precision medicine. Expert review of precision medicine and drug development, 4(2):59–72.
Pastorino, U., Rossi, M., Rosato, V., Marchianò, A., Sverzellati, N., Morosi, C., Fabbri, A., Galeone, C., Negri, E., Sozzi, G., et al. (2012). Annual or biennial ct screening versus observation in heavy smokers: 5-year results of the mild trial. European Journal of Cancer Prevention, 21(3):308–315.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Rampinelli, C., De Marco, P., Origgi, D., Maisonneuve, P., Casiraghi, M., Veronesi, G., Spaggiari, L., and Bellomi, M. (2017). Exposure to low dose computed tomography for lung cancer screening and risk of cancer: secondary analysis of trial data and riskbenet analysis. bmj, 356:j347.
Ribeiro, M. X., Balan, A. G., Felipe, J. C., Traina, A. J., and Traina, C. (2009). Mining statistical association rules to select the most relevant medical image features. In Mining complex data, pages 113–131. Springer.
Siegel, R. L., Miller, K. D., and Jemal, A. (2018). Cancer statistics, 2018. CA: A Cancer Journal for Clinicians, 68(1):7–30.
Sieren, J. C., Ohno, Y., Koyama, H., Sugimura, K., and McLennan, G. (2010). Recent technological and application developments in computed tomography and magnetic resonance imaging for improved pulmonary nodule detection and lung cancer staging. Journal of Magnetic Resonance Imaging, 32(6):1353–1369.
Vaidya, M., Creach, K. M., Frye, J., Dehdashti, F., Bradley, J. D., and El Naqa, I. (2012). Combined PET/CT image characteristics for radiotherapy tumor response in lung cancer. Radiotherapy and Oncology, 102(2):239–245.
Valliéres, M., Freeman, C. R., Skamene, S. R., and El Naqa, I. (2015). A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Physics in Medicine and Biology, 60(14):5471– 5496.
Van Griethuysen, J. J., Fedorov, A., Parmar, C., Hosny, A., Aucoin, N., Narayan, V., Beets-Tan, R. G., Fillion-Robin, J.-C., Pieper, S., and Aerts, H. J. (2017). Computational radiomics system to decode the radiographic phenotype. Cancer research, 77(21):e104–e107.
Wei, L., Osman, S., Hatt, M., and El Naqa, I. (2019). Machine learning for radiomicsbased multimodality and multiparametric modeling. The quarterly journal of nuclear medicine and molecular imaging : ofcial publication of the Italian Association of Nuclear Medicine (AIMN) [and] the International Association of Radiopharmacology (IAR), [and] Section of the Society of.., 63(4):323–338.
Wild, C. P., Weiderpass, E., and Stewart, B. W. (2020). WORLD CANCER REPORT: cancer research for cancer development. International Agency for Research on Cancer.
Yang, Y., Feng, X., Chi, W., Li, Z., Duan, W., Liu, H., Liang, W., Wang, W., Chen, P., He, J., and Liu, B. (2018). Deep learning aided decision support for pulmonary nodules diagnosing: A review. Journal of Thoracic Disease, 10(Suppl 7):S867–S875.
Yi, C. A., Shin, K. M., Lee, K. S., Kim, B.-T., Kim, H., Kwon, O. J., Choi, J. Y., and Chung, M. J. (2008). Non–small cell lung cancer staging: efcacy comparison of integrated pet/ct versus 3.0-t whole-body mr imaging. Radiology, 248(2):632–642.
Zhu, L., Kolesov, I., Gao, Y., Kikinis, R., and Tannenbaum, A. (2014). An effective interactive medical image segmentation method using fast growcut. In MICCAI workshop on interactive medical image computing.
Blandin Knight, S., Crosbie, P. A., Balata, H., Chudziak, J., Hussell, T., and Dive, C. (2017). Progress and prospects of early detection in lung cancer. Open biology, 7(9):170070.
Cawley, G. C. and Talbot, N. L. (2010). On over-tting in model selection and subsequent selection bias in performance evaluation. The Journal of Machine Learning Research, 11:2079–2107.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of articial intelligence research, 16:321–357.
Claesen, M. and De Moor, B. (2015). Hyperparameter search in machine learning. arXiv preprint arXiv:1502.02127.
Demsar, J. (2006). Statistical comparisons of classiers over multiple data sets. Journal of Machine Learning Research, 7:1–30.
Fawcett, T. (2006). An introduction to roc analysis. Pattern recognition letters, 27(8):861–874.
Ferreira, J. R., Oliveira, M. C., and de Azevedo-Marques, P. M. (2018). Characterization of pulmonary nodules based on features of margin sharpness and texture. Journal of digital imaging, 31(4):451–463.
Francisco, V., Koenigkam-Santos, M., Wada, D. T., Junior, J. R. F., Fabro, A. T., Cipriano, F. E. G., Quatrina, S. G., and de Azevedo-Marques, P. M. (2019). Computer-aided In XXVI Brazilian diagnosis of lung cancer in magnetic resonance imaging exams. Congress on Biomedical Engineering, pages 121–127. Springer.
Gillies, R. J., Kinahan, P. E., and Hricak, H. (2016). Radiomics: images are more than pictures, they are data. Radiology, 278(2):563–577.
Guo, Z., Li, X., Huang, H., Guo, N., and Li, Q. (2019). Deep Learning-Based Image Segmentation on Multimodal Medical Imaging. IEEE Transactions on Radiation and Plasma Medical Sciences, 3(2):162–169.
Hatt, M., Tixier, F., Visvikis, D., and Le Rest, C. C. (2017). Radiomics in pet/ct: more than meets the eye? Journal of Nuclear Medicine, 58(3):365–366.
Jatobá, A., Lima, L., Amorim, L., and Oliveira, M. (2020). Cnn hyperparameter optimization for pulmonary nodule classication. In Anais do XX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 25–36, Porto Alegre, RS, Brasil. SBC.
Knight, S. B., Crosbie, P. A., Balata, H., Chudziak, J., Hussell, T., and Dive, C. (2017). Progress and prospects of early detection in lung cancer. Open Biology, 7(9).
Li, L., Zhao, X., Lu, W., and Tan, S. (2019a). Deep learning for variational multimodality tumor segmentation in pet/ct. Neurocomputing.
Li, S., Xu, P., Li, B., Chen, L., Zhou, Z., Hao, H., Duan, Y., Folkert, M., Ma, J., Huang, S., et al. (2019b). Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features. Physics in Medicine & Biology, 64(17):175012.
Mu, W., Qi, J., Lu, H., Schabath, M., Balagurunathan, Y., Tunali, I., and Gillies, R. J. (2018). Radiomic biomarkers from pet/ct multi-modality fusion images for the prediction of immunotherapy response in advanced non-small cell lung cancer patients. In Medical Imaging 2018: Computer-Aided Diagnosis, volume 10575, page 105753S. International Society for Optics and Photonics.
Ohno, Y., Kauczor, H.-U., Hatabu, H., Seo, J. B., van Beek, E. J., and for Pulmonary Functional Imaging (IWPFI), I. W. (2018). Mri for solitary pulmonary nodule and mass assessment: current state of the art. Journal of Magnetic Resonance Imaging, 47(6):1437–1458.
Parekh, V. S. and Jacobs, M. A. (2019). Deep learning and radiomics in precision medicine. Expert review of precision medicine and drug development, 4(2):59–72.
Pastorino, U., Rossi, M., Rosato, V., Marchianò, A., Sverzellati, N., Morosi, C., Fabbri, A., Galeone, C., Negri, E., Sozzi, G., et al. (2012). Annual or biennial ct screening versus observation in heavy smokers: 5-year results of the mild trial. European Journal of Cancer Prevention, 21(3):308–315.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Rampinelli, C., De Marco, P., Origgi, D., Maisonneuve, P., Casiraghi, M., Veronesi, G., Spaggiari, L., and Bellomi, M. (2017). Exposure to low dose computed tomography for lung cancer screening and risk of cancer: secondary analysis of trial data and riskbenet analysis. bmj, 356:j347.
Ribeiro, M. X., Balan, A. G., Felipe, J. C., Traina, A. J., and Traina, C. (2009). Mining statistical association rules to select the most relevant medical image features. In Mining complex data, pages 113–131. Springer.
Siegel, R. L., Miller, K. D., and Jemal, A. (2018). Cancer statistics, 2018. CA: A Cancer Journal for Clinicians, 68(1):7–30.
Sieren, J. C., Ohno, Y., Koyama, H., Sugimura, K., and McLennan, G. (2010). Recent technological and application developments in computed tomography and magnetic resonance imaging for improved pulmonary nodule detection and lung cancer staging. Journal of Magnetic Resonance Imaging, 32(6):1353–1369.
Vaidya, M., Creach, K. M., Frye, J., Dehdashti, F., Bradley, J. D., and El Naqa, I. (2012). Combined PET/CT image characteristics for radiotherapy tumor response in lung cancer. Radiotherapy and Oncology, 102(2):239–245.
Valliéres, M., Freeman, C. R., Skamene, S. R., and El Naqa, I. (2015). A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Physics in Medicine and Biology, 60(14):5471– 5496.
Van Griethuysen, J. J., Fedorov, A., Parmar, C., Hosny, A., Aucoin, N., Narayan, V., Beets-Tan, R. G., Fillion-Robin, J.-C., Pieper, S., and Aerts, H. J. (2017). Computational radiomics system to decode the radiographic phenotype. Cancer research, 77(21):e104–e107.
Wei, L., Osman, S., Hatt, M., and El Naqa, I. (2019). Machine learning for radiomicsbased multimodality and multiparametric modeling. The quarterly journal of nuclear medicine and molecular imaging : ofcial publication of the Italian Association of Nuclear Medicine (AIMN) [and] the International Association of Radiopharmacology (IAR), [and] Section of the Society of.., 63(4):323–338.
Wild, C. P., Weiderpass, E., and Stewart, B. W. (2020). WORLD CANCER REPORT: cancer research for cancer development. International Agency for Research on Cancer.
Yang, Y., Feng, X., Chi, W., Li, Z., Duan, W., Liu, H., Liang, W., Wang, W., Chen, P., He, J., and Liu, B. (2018). Deep learning aided decision support for pulmonary nodules diagnosing: A review. Journal of Thoracic Disease, 10(Suppl 7):S867–S875.
Yi, C. A., Shin, K. M., Lee, K. S., Kim, B.-T., Kim, H., Kwon, O. J., Choi, J. Y., and Chung, M. J. (2008). Non–small cell lung cancer staging: efcacy comparison of integrated pet/ct versus 3.0-t whole-body mr imaging. Radiology, 248(2):632–642.
Zhu, L., Kolesov, I., Gao, Y., Kikinis, R., and Tannenbaum, A. (2014). An effective interactive medical image segmentation method using fast growcut. In MICCAI workshop on interactive medical image computing.
Publicado
15/06/2021
Como Citar
JATOBÁ, Anthony E. A.; OLIVEIRA, Marcelo C.; KOENIGKAM-SANTOS, Marcel; AZEVEDO-MARQUES, Paulo de.
Feasibility Study of MRI and Multimodality CT/MRI Radiomics for Lung Nodule Classification. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 21. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 200-211.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2021.16065.
