Tecnologias da informação e métodos computacionais para gerenciamento, otimização e medicina de precisão em departamentos de imagens médicas

Autores

  • Marcos Machado Radtec

Palavras-chave:

Tecnologia médica, Padronização, Protocolos, Biomarcadores, Inteligência artificial, Radiologia

Resumo

A área da saúde demanda por tecnologias da informação e métodos computacionais para melhorar a produtividade dos serviços e oferecer assistência personalizada aos pacientes. Este trabalho buscou desenvolver e explorar sistemas e métodos computacionais para implementar melhorarias no gerenciamento, otimizar os exames, e acessar novos biomarcadores e assinaturas com inteligência artificial para apoio à decisão. Foram desenvolvidos e implementados softwares com o conceito Workflow Based Approach (WBA) e métodos computacionais escritos em linguagem Python para melhorar a gestão e otimizar os protocolos de exames. Um workflow para acesso a novos biomarcadores e assinaturas IA foi desenvolvido e validado em pacientes com CT de COVID-19, 18F-FDG-PET/CT de câncer de colo do útero e 18F-FDG-PET/CT de linfoma Hodgkin. O workflow demonstrou-se válido em análises de robustez: repetitividade (erro < 5%), reprodutibilidade (coeficiente de correlação intraclasse, ICC > 90%) e correlação clínica (p < 0,05). Os modelos preditivos para 18F-FDG-PET/CT de câncer de colo do útero e 18F-FDG-PET/CT de linfoma Hodgkin apresentaram desempenho geral de AUC=0,74 e AUC=0,96, respectivamente. Um novo software que utiliza métodos de IA para apoio ao diagnóstico da COVID-19 em CT de tórax de pacientes com pneumonia foi disponibilizado e validado em um PACS/Viewer. Sem apoio do software, os médicos tiveram desempenho médio de 83,4% de sensibilidade, e 64,3% de especificidade. Com o apoio do software, o desempenho melhorou para 87,1% de sensibilidade, e 91,1% de especificidade. Adicionalmente, o software melhorou a concordância entre observadores, de moderado para substancial, em uma escala construída a partir do coeficiente de concordância Cohen’s Kappa.

Downloads

Não há dados estatísticos.

Referências

ACR accreditation. Disponível em: . Acesso em: 19/09/2022.

ALMEIDA, M.; PEREIRA, L.; Ren, T.; CAVALCANTI, C.; SIJBERS, J. The Gated Recurrent Conditional Generative Adversarial Network (GRC-GAN): application to denoising of lowdose CT images. In: 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE, 2021. p. 129-135. ISSN 0278-0062

ARMSTRONG, I.; PARTHIBAN, A.; JAMES, J.; TONGE, C.; LAWSON, R. Reduced-count myocardial perfusion SPECT with resolution recovery. Nuclear Medicine Communications, v. 33, n. 2, p. 121-129, 2012. ISSN 1473-5628.

ASH, J. and BATES, D. Factors and forces affecting EHR system adoption: report of a 2004 ACMI discussion. Journal of the American Medical Informatics Association, v. 12, n. 1, p. 8-12, 2005. ISSN 1067-5027.

AYAL, M. and SEIDMAN, A. An empirical investigation of the value of integrating enterprise information systems: the case of medical imaging informatics. Journal of Management Information Systems, v. 26, n. 2, p. 43-68, 2009. ISSN 0742-1222.

BARBOSA PNVP, BITENCOURT AGV, MIRANDA GD, et al. Chest CT accuracy in the diagnosis of SARS-CoV-2 infection: initial experience in a cancer center. Radiologia Brasileira, v. 53, p. 211-215, 2020. ISSN 0100-3984

BLAZONA, B and KONCAR, M. HL7 and DICOM based integration of radiology departments with healthcare enterprise information systems. International Journal of Medical Informatics, v. 76, n.3, p. 425-432, 2007. ISSN 1386-5056.

BRAY F, FERLAY J, SOERJOMATARAM I, SIEGEL R, TORRE L, JEMAL A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. (2018) 68: 394–424. doi: 10.3322/caac.21492. ISSN 1542-4863

Buvat I & Orlhac F. The TRUE Checklist for Identifying Impactful Artificial Intelligence–Based Findings in Nuclear Medicine: Is It True? Is It Reproducible? Is It Useful? Is It Explainable? J Nuc Med. 2021; 62(6): 752-54. ISSN 2159-662X

CBOK, BPM. Guide to the business process management common body of knowledge. Versão, v. 2, p. 2009, 2009.

COOK, G.; SIDDIQUE, M.; TAYLOR, B.; YIP, C.; CHICKLORE, S.; GOH, V. Radiomics in PET: principles and applications. Clinical and Translational Imaging, v. 2, n. 3, p. 269-276, 2014. ISSN 2281-7565

COTTEREAU AS, VERSARI A, LOFT A, et al. Prognostic value of baseline metabolic tumor volume in early-stage Hodgkin lymphoma in the standard arm of the H10 trial. Blood. 2018;131(13):1456-1463. ISSN: 0006-4971

CRANDALL, J.; FRAUM, T.; LEE, M.; JIANG, L.; GRIGSBY, P.; WAHL, R. Repeatability of 18F-FDG PET radiomic features in cervical cancer. Journal of Nuclear Medicine, v. 62, n. 5, p. 707-715, 2021. ISSN 2159-662X

DA CUNHA JÚNIOR, Ademar Dantas et al. Adipose tissue radiodensity: A new prognostic biomarker in people with multiple myeloma. Nutrition, v. 86, p. 111141, 2021. ISSN 0899-9007

DESHMANE, A.; GULANI, V.; GRISWOLD, M.; SEIBERLICH, N. Parallel MR imaging. Journal of Magnetic Resonance Imaging, v. 36, n. 1, p. 55-72, 2012. ISSN 1522-2586.

EBADI, Maryam et al. Visceral adipose tissue radiodensity is linked to prognosis in hepatocellular carcinoma patients treated with selective internal radiation therapy. Cancers, v. 12, n. 2, p. 356, 2020. ISSN 2072-6694

FANNY O.; BOUGHDAD, S.; PHILIPPE, C.; et al. A postreconstruction harmonization method for multicenter radiomic studies in PET. Journal of Nuclear Medicine, v. 59, n. 8, p. 1321-1328, 2018. ISSN 2159-662X

FERLAY J, SOERJOMATARAM I, DIKSHIT R, ESER S, MATHERS C, REBELO M, et al. Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012. International journal of cancer, v. 136, n. 5, p. E359-E386, 2015. ISSN 1097-0215

FIOCRUZ. Estudo analisa registro de óbitos por Covid-19 em 2020. Disponível em <https://portal.fiocruz.br/noticia/estudo-analisa-registro-de-obitos-por-covid-19-em-2020> Acessado em 19.11.2022

HOEKSTRA, C. J.; PRUIM, J.; WILLEMSEN, A.; ARENDS, B.; KOTZERKE, J.; BOCKISCH, A.; BEYER, T.; CHITI, A.; KRAUSE, B. J. FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. European journal of nuclear medicine and molecular imaging, p. 1-26, 2014. ISSN 1619-7070.

HUANG, Y.; WEI, L.; HU, Y.; SHAO, N.; LIN, Y.; HE, S.; SHI, H.; ZHANG, X.; LIN, Y. Multi-parametric MRI-based radiomics models for predicting molecular subtype and androgen receptor expression in breast cancer. Frontiers in Oncology, v. 11, 2021. ISSN 2234-943X

IM HJ, BRADSHAW T, SOLAIYAPPAN M, CHO SY. Current methods to define metabolic tumor volume in positron emission tomography: which one is better?. Nuclear medicine and molecular imaging, v. 52, n. 1, p. 5-15, 2018. ISSN 1619-7089

IROJU, O.; SORIYAN, A.; GAMBO, I; OLALEKE, J. Interoperability in healthcare: benefits, challenges and resolutions. International Journal of Innovation and Applied Studies, v. 3, n. 1, p. 262-270, 2013. ISSN 2028-9324

ISO/FDIS 16290:2013(E) Space systems - Definition of the Technology Readiness Levels (TRLs) and their criteria of assessment. International Organization for Standardization, Switzerland, 2013. 12p.

JAMBOR, I. Optimization of prostate MRI acquisition and post-processing protocol: a pictorial review with access to acquisition protocols. Acta Radiologica Open, v. 6, n. 12, p. 1-14, 2017. ISSN 2058-4601.

KAALEP, A,; SERA, T.; OYEN, W.; KRAUSE, B.; CHITI, A.; LIU, Y.; BOELLAARD, R. EANM/EARL FDG-PET/CT accreditation-summary results from the first 200 accredited imaging systems. European journal of nuclear medicine and molecular imaging, v. 45, n. 3, p. 412-422, 2018. ISSN 1619-7070.

KANOUN, Salim et al. Influence of software tool and methodological aspects of total metabolic tumor volume calculation on baseline [18F] FDG PET to predict survival in Hodgkin lymphoma. PloS one, v. 10, n. 10, p. e0140830, 2015. ISSN 1932-6203.

KAPLAN, S. and ZHU, Y. Full-dose PET image estimation from low-dose PET image using deep learning: a pilot study. Journal of digital imaging, v. 32, n. 5, p. 773-778, 2019. ISSN 1618-727X

KHIEWVAN B, TORIGIAN DA, EMAMZADEHFARD S, PAYDARY K, SALAVATI A, HOUSHMAND S, et al. Update of the role of PET/CT and PET/MRI in the management of patients with cervical cancer. Hellenic journal of nuclear medicine, v. 19, n. 3, p. 254-268, 2016. ISSN 1790-5427

KOENIG, Inke R. et al. What is precision medicine? European respiratory journal, v. 50, n. 4, 2017.

KOOPEMAN, D.; van OSCH, J. A.; JAGER, P. L.; TENBERGEN, C. J.; KNOLLEMA, S.; SLUMP, C. H.; van DALEN, J. A. Technical note: how to determine the FDG activity for tumor PET imaging that satisfies European guidelines. European journal of nuclear medicine and molecular imaging physics, v. 3, n. 1, p. 22, 2016. ISSN 2197-7364 (Online).

KWEE TC and KWEE RM. Chest CT in COVID-19: what the radiologist needs to know. Radiographics, v. 40, n. 7, p. 1848, 2020. ISSN 1527-1323

LECCHI, M.; MARTINELLI, I.; ZOCCARATO, O.; MAIOLI, C.; LUCIGNANI, G.; DEL SOLE, A. Comparative analysis of full-time, half-time, and quarter-time myocardial ECGgated SPECT quantification in normal-weight and overweight patients. Journal of Nuclear Cardiology, v. 24, n. 3, p. 876-887, 2017. ISSN 1532-6551.

MACHADO, M.; MENEZES, V.; NAMÍAS, M.; VIEIRA, N.; QUEIROZ, C.; MATHEOUD, R.; ALESSIO, A.; OLIVEIRA, M. Protocols for harmonized quantification and noise reduction in low-dose oncologic 18F-FDG PET/CT imaging. Journal of Nuclear Medicine Technology, v. 47, n. 1, p. 47-54, 2019. ISSN 0091-4916.

MACHADO, M. A. D.; MENEZES, V. O.; NAMIAS, M; VIEIRA, N. S.; QUEIROZ, C. C.; OLIVEIRA, M. L. Technology Innovation Based on Specific Nuclear Medicine Software for PET/CT Protocol Standardization and Quality Assurance Management. International Symposium – Quantification in Medical and Preclinical Imaging: state of the art and future developments. Groningen, Holanda, 2016.

MACHADO, M.; PITA, J.; NETTO, E. M. PET Radiomic Features Variability: A Phantom Study on the Influence of Reconstruction and Discretization Method. Revista Brasileira de Física Médica. v.15, 2021. ISSN 1984-9001.

MACHADO, M. A. D., QUEIROZ, C. C, PITA, J. L. P, et al. Prediction of Treatment Failure in Hodgkin Lymphoma: A Machine Learning Approach in Baseline 18F-FDG PET/CT. Revista Brasileira De Física Médica, 17, 680. https://doi.org/10.29384/rbfm.2023.v17.19849001680. ISSN 1984-9001.

Machado, M.A.D., Silva, R.R.E., Namias, M. et al. Multi-center Integrating Radiomics, Structured Reports, and Machine Learning Algorithms for Assisted Classification of COVID-19 in Lung Computed Tomography. J. Med. Biol. Eng. 43, 156–162 (2023). https://doi.org/10.1007/s40846-023-00781-4. ISSN 16090985, 21994757

MACHADO, M. Metodologia para otimização de protocolo PET/CT harmonizado de baixa dose em tumores sólidos com reconstrução Point Spread Function. Orientador: Mércia Liane. 2017. 79f. Dissertação (Mestrado). Programa de Pós-Graduação em Tecnologias

Energéticas e Nucleares. Centro Regional de Ciências Nucleares do Nordeste, Departamento de Energia Nuclear, Universidade Federal de Pernambuco. Disponível em <https://repositorio.ufpe.br/handle/123456789/25171>

MANSOORI, B.; ERHARD, K.; SUNSHINE, J. Picture Archiving and Communication System (PACS) implementation, integration & benefits in an integrated health system. Academic radiology, v. 19, n. 2, p. 229-235, 2012. ISSN 1076-6332.

MARTIN, C. and SOOKPENG, S. Setting up computed tomography automatic tube current modulation systems. Journal of Radiological Protection, v. 36, n. 3, p. R74, 2016. ISSN 0952-4746.

MILGROM SA, ELHALAWANI H, LEE J, et al. A PET Radiomics Model to Predict Refractory Mediastinal Hodgkin Lymphoma. Scientific reports, v. 9, n. 1, p. 1-8, 2019. ISSN: 2045-2322

MENEZES, V.; MACHADO, M.; QUEIROZ, C.; SOUZA, O. S.; d’ERRICO, F.; NAMIAS, M.; LAROCCA, T. F.; SOARES, M. B. P. Optimization of oncological 18F-FDG PET/CT imaging based on a multiparameter analysis. Medical physics, v. 43, n. 2, p. 930-938, 2016. ISSN 0094-2405.

MENEZES, V.; MACHADO, M.; QUEIROZ, C.; REINANDE, I.; VIEIRA, L.; GAMA, J. How does Lean Six Sigma method improve healthcare practice in nuclear medicine departments? A successful case of dedicated software applications in oncological PET/CT. Journal of Nuclear Medicine v.59 (supplement 1) 1013, 2018. ISSN 0161-5505

METTLER J, MÜLLER H, VOLTIN CA, BAUES C, KLAESER B, MOCCIA A, BORCHMANN P, ENGERT A, KUHNERT G, DRZEZGA AE, DIETLEIN M, KOBE C. Metabolic Tumour Volume for Response Prediction in Advanced-Stage Hodgkin Lymphoma. J Nucl Med. 2018 Jun 7;60(2):207–11. ISSN: 0161-5505

NAMÍAS, M.; BRADSHAW, T.; MENEZES, V.; MACHADO, M.; JERAJ, R. A novel approach for quantitative harmonization in PET. Physics in Medicine & Biology, v. 63, n. 9, p. 095019, 2018. ISSN 1361-6560

NANCE, J.; MEENAN, C.; NAGY, P. The future of the radiology information system. American Journal of Roentgenology, v. 200, n. 5, p. 1064-1070, 2013. ISSN 1546-3141.

NIOCHE, Christophe et al. LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer research, v. 78, n. 16, p. 4786-4789, 2018. ISSN 1538-7445.

OLIA, N.; KAMALI-ASL, A.; TABRIZI, S.; GERAMIFAR, P.; SHEIKHZADEH, P.; FARZANEFAR, S.; ARABI, H.; ZAIDI, H. Deep learning–based denoising of low-dose SPECT myocardial perfusion images: quantitative assessment and clinical performance. European journal of nuclear medicine and molecular imaging, v. 49, n. 5, p. 1508-1522, 2022. ISSN 1619-7070

PADHANI, A. and OLLIVIER, L. The RECIST criteria: implications for diagnostic radiologists. The British journal of radiology, v. 74, n. 887, p. 983-986, 2001. ISSN 2053-1303

PARK, J.; KIM, H.; KIM, D.; PARK, S.; KIM, J.; CHO, S.; KIM, J. A systematic review reporting quality of radiomics research in neuro-oncology: toward clinical utility and quality improvement using high-dimensional imaging features. BMC cancer, v. 20, n. 1, p. 1-11, 2020. ISSN 1471-2407

PFAEHLER, Elisabeth et al. Repeatability of 18F‐FDG PET radiomic features: A phantom study to explore sensitivity to image econstruction settings, noise, and delineation method. Medical physics, v. 46, n. 2, p. 665-678, 2019. ISSN 2473-4209

PFAEHLER, E.; MESOTTEN, L.; ZHOVANNIK, I.; PIEPLENBOSCH, S.; THOMEER, M.; VANHOVE, K.; ADRIAENSENS, P.; BOELLAARD, R. Plausibility and redundancy analysis to select FDG‐PET textural features in non‐small cell lung cancer. Medical physics, v. 48, n. 3, p. 1226-1238, 2021. ISSN 2473-4209

PONCE, D.; MACHADO, M.; MENEZES, M.; QUEIROZ, Q.; ALCANTARA, A.; SENA, T.; MARTINIANO, M.; VIGÁRIO, V. Plataforma para Gerenciamento de Filas e Rastreabilidade de Processos para Aumentar a Produtividade e a Segurança do Paciente. Anais do XVII Congresso Brasileiro de Informática em Saúde, p. 54-55, 2020. ISSN-2178-2857.

QUEIROZ, C.; MACHADO, M.; XIMENES, A.; PINO, A.; NETTO, E. Technical note: Partitioning of gated single photon emission computed tomography raw data for protocols optimization. J Appl Clin Med Phys, 23:e13508. 2022. ISSN 1526-9914.

SACHS, Peter B. et al. CT and MR protocol standardization across a large health system: providing a consistent radiologist, patient, and referring provider experience. Journal of digital imaging, v. 30, n. 1, p. 11-16, 2017. ISSN 1718-727X

SANAAT, A.; SHIRI, I.; ARABI, H.; MAINTA, I.; NKOULOU, R.; ZAIDI, H. Deep learningassisted ultra-fast/low-dose whole-body PET/CT imaging. European journal of nuclear medicine and molecular imaging, v. 48, n. 8, p. 2405-2415, 2021. ISSN 1619-7070

SYEDA HB, SYED M, SEXTON KW, et al. Role of machine learning techniques to tackle the COVID-19 crisis: systematic review. JMIR medical informatics, v. 9, n. 1, p. e23811, 2021. ISSN 2291-9694

STRIMBU, Kyle; TAVEL, Jorge A. What are biomarkers?. Current Opinion in HIV and AIDS, v. 5, n. 6, p. 463, 2010. ISSN 1746-6318

SUI, H.; LIU, L.; LI, X.; ZUO, P.; CUI, J.; MO, Z. CT-based radiomics features analysis for predicting the risk of anterior mediastinal lesions. Journal of Thoracic Disease, v. 11, n. 5, p. 1809, 2019. ISSN 2072-1439

SUNG H, FERLAY J, SIEGEL RL, LAVERSANNE M, SOERJOMATARAM I, JEMAL A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians, v. 71, n. 3, p. 209-249, 2021. ISSN 1542-4863

TIXIER, F.; Le REST, C.; HATT, M.; ALBARGHACH, N.; PRADIER, O.; METGES, J.; CORCOS, L.; VISVIKIS, D. et al. Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in

esophageal cancer. Journal of Nuclear Medicine, v. 52, n. 3, p. 369-378, 2011. ISSN 0161-5505

VALENTA, I.; TREYER, V.; HUSMANN, L.; GAEMPERLI, O.; SCHINDLER, M.; HERZOG, B.; VEIT-HEIBACH, P.; BUECHEL, R.; NKOULOU, R.; PAZHENKOTTIL, A.; KAUFMANN, P. New reconstruction algorithm allows shortened acquisition time for myocardial perfusion SPECT.

European journal of nuclear medicine and molecular imaging, v. 37, n. 4, p. 750-757, 2010. ISSN 1619-70789.

VALLIÈRES, M.; ZWANENBURG, A.; BADIC, B.; Le REST, C.; VISVIKIS, D.; HATT, M.. Responsible radiomics research for faster clinical translation. Journal of Nuclear Medicine, v. 59, n. 2, p. 189-193, 2018. ISSN 0161-5505

VAN GRIETHUYSEN, Joost JM et al. Computational radiomics system to decode the radiographic phenotype. Cancer research, v. 77, n. 21, p. e104-e107, 2017. ISSN 1538-7445.

VANROSSUM, G. Python reference manual. Department of Computer Science [CS], n. R 9525, 1995.

WAHL, R. L.; JACENE, H.; KASAMON, Y.; LODGE, M. A. From RECIST to PERSIST: evolving considerations for PET response criteria in solid tumors. Journal of Nuclear Medicine. v. 50, n. suppl 1 , p. 122S-150S, 2009. ISSN 0161-5505.

YANG, G.; YU, S.; DONG, H.; SLABAUGH, G.; DRAGOTTI, P.; YE, X.; LIU, F.; ARRIDGE, S.; KEEGAN, J.; GUO, Y.; FIRMIN, D. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE transactions on medical imaging, v. 37, n. 6, p. 1310-1321, 2017. ISSN 0278-0062

ZANG, J.; LU, X.; NIE, H; HUANG, Z.; van der Aalst, P.; Radiology information system: a workflow-based approach. International Journal of Computer Assisted Radiology and Surgery, v.4, p. 509-516, 2009. ISSN 1861-6429.

ZWANENBURG, A et al. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology, v. 295, n. 2, p. 328-338, 2020. ISSN 1527-1315

Downloads

Publicado

2023-04-24

Como Citar

Machado, M. (2023). Tecnologias da informação e métodos computacionais para gerenciamento, otimização e medicina de precisão em departamentos de imagens médicas. Revista Brasileira De Física Médica, 17, 723. Recuperado de https://rbfm.emnuvens.com.br/rbfm/article/view/723

Edição

Seção

Resenha de Tese ou Dissertação

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