Arcabouço para Classificação, Recuperação por Conteúdo e Radiômica de Imagens Médicas: uma investigação de biomarcadores quantitativos para o câncer de pulmão

• José Raniery Ferreira Junior USP
• Marcel Koenigkam Santos USP
• Paulo Mazzoncini Azevedo-Marques USP

DOI: https://doi.org/10.5753/sbcas.2020.11551

Abstract

This work aimed to decrease the feature (inefficient numeric representation of images) and performance (low quality of integration) gaps that clinical decision support systems may have. Some medical image datasets were produced during the development of this research. Semiautomatic models of pattern recognition, content-based retrieval, image classification, and prognosis evaluation were developed to build a framework for medical image analysis. The framework disclosed the potential to integrate with health information systems and identified several biomarkers, potentially supporting decision making. Finally, this thesis contributed to the identification of a radiomics signature to assess lung cancer diagnosis and prognosis for patient risk stratification.

References

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

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

Digumarthy, S., Padole, A., Gullo, R., Sequist, L., and Kalra, M. (2019). Can CT radiomic analysis in nsclc predict histology and EGFR mutation status? Medicine, 98:e13963.

Ferreira, J., Santos, M., Cipriano, F., Fabro, A., and Marques, P. (2018). Radiomicsbased features for pattern recognition of lung cancer histopathology and metastases. Computer Methods and Programs in Biomedicine, 159:23–30.

Ferreira, J., Santos, M., Hironaka, T., Cipriano, F., Fabro, A., Yoshida, H., and Marques, P. (2019a). Deep learning-based radiomics of primary lung tumors in CT images for prediction of distant metastasis. Sup Int J Comput Assist Radiol Surg, page S79.

Ferreira, J., Santos, M., Kikuchi, Y., Faleiros, M., Cipriano, F., Fabro, A., Yoshida, H., and Marques, P. (2019b). A radiomics approach for differentiation of pseudocavitation from cavitation on lung cancer tumors. Sup Int J Comput Assist Radiol Surg, page S78.

Ferreira, J., Santos, M., Tenório, A., Faleiros, M., Cipriano, F., Fabro, A., Näppi, J.,

Yoshida, H., and Marques, P. (2020). CT-based radiomics for prediction of histologic subtype and metastatic disease in primary malignant lung neoplasms. Int J Comput Assist Radiol Surg, 15:163–172.

Ferreira, J. R., Oliveira, M. C., and 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.

Ferreira, J. R., Oliveira, M. C., and Azevedo-Marques, P. M. (2017). Integrating 3D image descriptors of margin sharpness and texture on a GPU-optimized similar pulmonary nodule retrieval engine. The Journal of Supercomputing, 73(8):3451–3467.

Ferreira, Junior, J. R. and Oliveira, M. C. (2015). Evaluating margin sharpness analysis on similar pulmonary nodule retrieval. In Proceedings of 28th IEEE International Symposium on Computer-Based Medical Systems, pages 60–65.

Ferreira, Junior, J. R. and Oliveira, M. C. (2017). Unidade de processamento gráfico no diagnóstico auxiliado por computador. Journal of Health Informatics, 9(3):103–108.

Ferreira Jr, J., Santos, M., Machado, C., Faleiros, M., Correia, N., Cipriano, F., Fabro, A., and Marques, P. (2020). Análise radiômica do câncer de pulm˜ao para avaliação prognóstica do paciente e da heterogeneidade intratumoral. Radiol Bras, Ahead.

Ferreira Junior, J. R., Azevedo-Marques, P. M., and Oliveira, M. C. (2017). Selecting relevant 3D image features of margin sharpness and texture for lung nodule retrieval. Int J Comput Assist Radiol Surg, 12(3):509–517.

Ferreira Junior, J. R., Oliveira, M. C., and 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.

Gillies, R., Kinahan, P., and Hricak, H. (2016). Radiomics: Images are more than pictures, they are data. Radiology, 278(2):563–577.

Sacconi, B., Anzidei, M., Leonardi, A., Boni, F., Saba, L., Scipione, R., Anile, M., Rengo, M., Longo, F., Bezzi, M., Venuta, F., Napoli, A., Laghi, A., and Catalano, C. (2017).

Analysis of ct features and quantitative texture analysis in patients with lung adenocarcinoma: a correlation with egfr mutations and survival rates. Clin Radiol, 72:443–50.

Santos, M., Ferreira, J.,Wada, D., Tenório, A., Barbosa, M., and Marques, P. (2019). Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine. Radiologia Brasileira, 52(6):387–396.

Wu, J., Shultz, D., Gudur, M., Rubin, D., Loo, B., Diehn, M., and Li, R. (2016). Earlystage non–small cell lung cancer: Quantitative imaging characteristics of 18f fluorodeoxyglucose pet/ct allow prediction of distant metastasis. Radiology, 281:270–78.

Zhou, H., Dong, D., Chen, B., Fang, M., Cheng, Y., Gan, Y., Zhang, R., Zhang, L., Zang, Y., Liu, Z., et al. (2018). Diagnosis of distant metastasis of lung cancer: Based on clinical and radiomic features. Translational Oncology, 11(1):31–36.

Zhu, X., Dong, D., Chen, Z., Fang, M., Zhang, L., Song, J., Yu, D., Zang, Y., Liu, Z., Shi, J., et al. (2018). Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. European Radiology, 28(7):2772–2778.