Methodology and tools for creating training samples for artificial intelligence systems for recognizing lung cancer on CT images

Nikolay S. Kulberg; Кульберг Николай Сергеевич; Maxim A. Gusev; Гусев М. А.; Roman V. Reshetnikov; Решетников Р. В.; Alexey B. Elizarov; Елизаров А. Б.; Vladimir P. Novik; Новик В. П.; Sergey B. Prokudaylo; Прокудайло С. Б.; Yuriy N. Philippovich; Филиппович Ю. Н.; Victor A. Gobmolevsky; Гомболевский В. А.; Anton V. Vladzymyrskyy; Владзимирский А. В.; Natalya N. Kamynina; Камынина Н. Н.; Sergey P. Morozov; Морозов С. П.

doi:10.46563/0044-197X-2020-64-6-343-350

Methodology and tools for creating training samples for artificial intelligence systems for recognizing lung cancer on CT images

Autores: Kulberg N.S.¹^,2, Gusev M.A.¹^,3, Reshetnikov R.V.¹^,4, Elizarov A.B.¹, Novik V.P.¹, Prokudaylo S.B.¹, Philippovich Y.N.³, Gobmolevsky V.A.¹, Vladzymyrskyy A.V.¹, Kamynina N.N.⁵, Morozov S.P.¹
Afiliações:
1. Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department
2. Federal Research Center «Computer Science and Control» of Russian Academy of Sciences
3. Moscow Polytechnic Uniersity
4. Institute of Molecular Medicine, Sechenov First Moscow State Medical University
5. Research Institute for Healthcare Organization and Medical Management of Moscow Healthcare Department
Edição: Volume 64, Nº 6 (2020)
Páginas: 343-350
Seção: PROBLEMS OF SOCIALLY SIGNIFICANT DISEASES
##submission.dateSubmitted##: 25.10.2024
URL: https://rjonco.com/0044-197X/article/view/637940
DOI: https://doi.org/10.46563/0044-197X-2020-64-6-343-350
ID: 637940

Citar

Texto integral

Resumo

Introduction. Medical imaging techniques can diagnose many diseases at the early stages of their development, improving the patient survival. Artificial intelligence (AI) systems, requiring the high-quality annotated and marked-up sets of medical images, are a suitable and promising means of improving the diagnostics’ quality.

The purpose of the study was to develop a methodology and software for creating AIS training sets.

Material and methods. We compared the main annotation methods’ performance and accuracy and based the information system on the most efficient method in both domains to develop an optimal approach. To markup objects of interest, we used the cluster model of lesions localization previously developed by the authors. We used C++ and Kotlin programming languages for software development.

Results. A structured annotation template with delivered a glossary of terms became the basis of the information system. The latter consists of three interacting modules, two of which are executed on a remote server’s capacities and one on a personal computer or mobile device of the end-user. The first module is a web service responsible for the workflow logic. The second module, a web server, is responsible for interacting with client applications. Its role is to identify users and manage the database and Picture Archiving and Communication System (PACS) connections. The front-end module is a web application with a graphical interface that assists the end-user in images’ markup and annotation.

Conclusions. An algorithmic basis and a software package have been created for annotation and markup of CT images. The resulting information system was used in a large-scale lung cancer screening project for the creation of medical imaging datasets.

Palavras-chave

artificial intelligence systems, training sample, computed tomography, computer diagnostics, medical artificial intelligence, medical imaging

Sobre autores

Nikolay Kulberg

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department; Federal Research Center «Computer Science and Control» of Russian Academy of Sciences

Autor responsável pela correspondência
Email: kulberg@npcmr.ru
ORCID ID: 0000-0001-7046-7157

MD, Ph.D., head of the Department, Scientific and Practical Clinical Center for Diagnostics and Telemedicine Technologies, Moscow, 109029, Russia.

e-mail: kulberg@npcmr.ru

Rússia

Bibliografia

Riquelme D., Akhloufi M.A. Deep learning for lung cancer nodules detection and classification in CT scans. AI. 2020; 1(1): 28–67. https://doi.org/10.3390/ai1010003
Bell D.J., Morgan M.A. Lung-RADS. National Cancer Institute (NCI). Available at: https://radiopaedia.org/articles/lung-rads
Morozov S.P., Kul’berg N.S., Gombolevskiy V.A., Ledikhova N.A., Sokolina I.A., Vladzimirskiy A.V., et al. Tagged Chest Computed Tomography (CT) Images. Patent RU № 2018620500; 2018. (in Russian)
Morozov S.P., Kul’berg N.S., Gombolevskiy V.A., Ledikhova N.A., Sokolina I.A., Vladzimirskiy A.V., et al. Chest Computer Tomography (CT) set for Machine Learning. Patent RU № 2018620427; 2018. (in Russian)
Li Z., Wang C., Han M., Xue Y., Wei W., Li L.J., et al. Thoracic Disease Identification and Localization with Limited Supervision. Available at: https://arxiv.org/abs/1711.06373
Armato S.G., McLennan G., Bidaut L., McNitt-Gray M.F., Meyer C.R., Reeves A.P., et al. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans. Med. Phys. 2011; 38(2): 915–31. https://doi.org/10.1118/1.3528204
Kan S.H. Metrics and Models in Software Quality Engineering. Boston: Addison-Wesley Professional; 2003.
Kovalev V.A., Levchuk V.A., Kalinovskiy A.A., Fridman M.V. Tumor segmentation in whole-slide histology images using deep learning. Informatika. 2019; 16(2): 18–26. (in Russian)
Xu R., Zhou X., Hirano Y., Tachibana R., Hara T., Kido S., et al. Particle system based adaptive sampling on spherical parameter space to improve the MDL method for construction of statistical shape models. Comput. Math. Methods Med. 2013; 2013: 196259. https://doi.org/10.1155/2013/196259
Armato S.G., Meyer C.R., Mcnitt-Gray M.F., McLennan G., Reeves A.P., Croft B.Y., et al. The Reference Image Database to Evaluate Response to therapy in lung cancer (RIDER) project: A resource for the development of change analysis software. Clin. Pharmacol. Ther. 2008; 84(4): 448–56. https://doi.org/10.1038/clpt.2008.161
Bakr S., Gevaert O., Echegaray S., Ayers K., Zhou M., Shafiq M., et al. A radiogenomic dataset of non-small cell lung cancer. Sci. Data. 2018; 5: 180202. https://doi.org/10.1038/sdata.2018.202

Arquivos suplementares

Ação

1. JATS XML

Baixar

Nome de usuário
Senha
Lembrar usuário

Esqueceu a senha?	Cadastro

Nome de usuário
Senha
Lembrar usuário

Esqueceu a senha?	Cadastro

Methodology and tools for creating training samples for artificial intelligence systems for recognizing lung cancer on CT images

Texto integral

Resumo

Palavras-chave

Sobre autores

Nikolay Kulberg

Maxim Gusev

Roman Reshetnikov

Alexey Elizarov

Vladimir Novik

Sergey Prokudaylo

Yuriy Philippovich

Victor Gobmolevsky

Anton Vladzymyrskyy

Natalya Kamynina

Sergey Morozov

Bibliografia

Arquivos suplementares