Email this article 
Software for brain tumor diagnosis on magnetic resonance imaging
- Authors: Tuchinov B.N.1, Letyagin A.Y.1,2, Amelina E.V.1, Amelin M.E.3, Pavlovskiy E.N.1, Golushko S.K.1
-
Affiliations:
- Novosibirsk State University
- Research Institute of Clinical and Experimental Lymphology — Branch of the Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of Sciences
- Federal Neurosurgical Center
- Issue: Vol 4, No 1S (2023)
- Pages: 138-140
- Section: Conference proceedings
- URL: https://jdigitaldiagnostics.com/DD/article/view/430372
- DOI: https://doi.org/10.17816/DD430372
- ID: 430372
Cite item
Full Text
Abstract
BACKGROUND: The main reason for the development and implementation of artificial intelligence (AI) technologies in neuro-oncology is the high prevalence of brain tumors reaching up to 200 cases per 100,000 population. The incidence of a primary focus in the brain is 5%–10%; however, 60%–70% of those who die from malignant neoplasms have metastases in the brain. Magnetic resonance imaging (MRI) is the most common method for primary non-invasive diagnosis of brain tumors and monitoring disease progression. One of the challenges is the classification of tumor types and determination of clinical parameters (size and volume) for the conduct, diagnosis, and treatment procedures, including surgery.
AIM: To develope a software module for the differential diagnosis of brain neoplasms on MRI images.
METHODS: The software module is based on the developed Siberian Brain Tumor Dataset (SBT), which contains information on over 1000 neurosurgical patients with fully verified (histologically and immunohistochemically) postoperative diagnoses. The data for research and development was presented by the Federal Neurosurgical Center (Novosibirsk). The module uses two- and three-dimensional computer vision models with pre-processed MRI sequence data included in the following packages: pre-contrast T1-weighted image (WI), post-contrast T1-WI, T2-WI, and T2-WI with fluid-attenuated inversion-recovery technique. The models allow to detect and recognize with high accuracy 4 types of neoplasms, such as meningioma, neurinoma, glioblastoma, and astrocytoma, and segment and distinguish components and sizes: ET (tumor core absorbing Gd-containing contrast), TC (tumor core) = ET + Necr (necrosis) + NenTu, and WT (whole tumor) = TC + Ed (peritumoral edema).
RESULTS: The developed software module shows high segmentation results on SBT by Dice metric for ET 0.846, TC 0.867, WT 0.9174, Sens 0.881, and Spec 1.000 areas. The testing and validation were done at the international BraTS Challenge 2021 competition. The test dataset yielded DiceET 0.86588, DiceTC 0.86932, and DiceWT 0.921 values, placing the developed software module in the top ten. According to the classification, the results demonstrate high accuracy rates of up to 92% in patient analysis (up to 89% in slice analysis), a very high potential, and a perspective for future research in this area.
CONCLUSIONS: The developed software module may be used for training specialists and in clinical diagnostics.
Full Text
BACKGROUND: The main reason for the development and implementation of artificial intelligence (AI) technologies in neuro-oncology is the high prevalence of brain tumors reaching up to 200 cases per 100,000 population. The incidence of a primary focus in the brain is 5%–10%; however, 60%–70% of those who die from malignant neoplasms have metastases in the brain. Magnetic resonance imaging (MRI) is the most common method for primary non-invasive diagnosis of brain tumors and monitoring disease progression. One of the challenges is the classification of tumor types and determination of clinical parameters (size and volume) for the conduct, diagnosis, and treatment procedures, including surgery.
AIM: To develope a software module for the differential diagnosis of brain neoplasms on MRI images.
METHODS: The software module is based on the developed Siberian Brain Tumor Dataset (SBT), which contains information on over 1000 neurosurgical patients with fully verified (histologically and immunohistochemically) postoperative diagnoses. The data for research and development was presented by the Federal Neurosurgical Center (Novosibirsk). The module uses two- and three-dimensional computer vision models with pre-processed MRI sequence data included in the following packages: pre-contrast T1-weighted image (WI), post-contrast T1-WI, T2-WI, and T2-WI with fluid-attenuated inversion-recovery technique. The models allow to detect and recognize with high accuracy 4 types of neoplasms, such as meningioma, neurinoma, glioblastoma, and astrocytoma, and segment and distinguish components and sizes: ET (tumor core absorbing Gd-containing contrast), TC (tumor core) = ET + Necr (necrosis) + NenTu, and WT (whole tumor) = TC + Ed (peritumoral edema).
RESULTS: The developed software module shows high segmentation results on SBT by Dice metric for ET 0.846, TC 0.867, WT 0.9174, Sens 0.881, and Spec 1.000 areas. The testing and validation were done at the international BraTS Challenge 2021 competition. The test dataset yielded DiceET 0.86588, DiceTC 0.86932, and DiceWT 0.921 values, placing the developed software module in the top ten. According to the classification, the results demonstrate high accuracy rates of up to 92% in patient analysis (up to 89% in slice analysis), a very high potential, and a perspective for future research in this area.
CONCLUSIONS: The developed software module may be used for training specialists and in clinical diagnostics.
About the authors
Bair N. Tuchinov
Novosibirsk State University
Author for correspondence.
Email: bairt@nsu.ru
ORCID iD: 0000-0002-8931-9848
SPIN-code: 2224-5343
Russian Federation, Novosibirsk
Andrey Yu. Letyagin
Novosibirsk State University; Research Institute of Clinical and Experimental Lymphology — Branch of the Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of Sciences
Email: letyagin-andrey@yandex.ru
ORCID iD: 0000-0002-9293-4083
SPIN-code: 5660-5059
Russian Federation, Novosibirsk; Novosibirsk
Evgeniya V. Amelina
Novosibirsk State University
Email: amelina.evgenia@gmail.com
ORCID iD: 0000-0001-7537-3846
SPIN-code: 8814-0913
Russian Federation, Novosibirsk
Mihail E. Amelin
Federal Neurosurgical Center
Email: amelin81@gmail.com
ORCID iD: 0000-0002-5933-6479
SPIN-code: 7657-9571
Russian Federation, Novosibirsk
Evgeniy N. Pavlovskiy
Novosibirsk State University
Email: pavlovskiy@post.nsu.ru
ORCID iD: 0000-0001-6976-1885
Russian Federation, Novosibirsk
Sergey K. Golushko
Novosibirsk State University
Email: s.k.golushko@gmail.com
ORCID iD: 0000-0002-0207-7648
SPIN-code: 8826-8439
Russian Federation, Novosibirsk
References
- Amelina EV, Letyagin AYu, Tuchinov BN, et al. Specific features of designing a database for neuro-oncological 3D MRI images to be used in training artificial intelligence. Sibirskii nauchnyi meditsinskii zhurnal. 2022;42(6):51–59. (In Russ). doi: 10.18699/SSMJ20220606
- Pnev S, Groza V, Tuchinov B, et al. Multi-Class Brain Tumor Segmentation via 3d and 2d Neural Networks. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI). IEEE; 2022. P. 1–5.
- Sao Khue LM, Pavlovskiy E. Binary Brain Tumor Classification With Semantic Features Using Convolutional Neural Network. In: 2022 Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT). IEEE; 2022. P. 044–047.
- Pnev S, Groza V, Tuchinov B, et al. Brain Tumor Segmentation with Self-supervised Enhance Region Post-processing. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Virtual Event, Sep 27, 2021, Revised Selected Papers, Part II. Cham: Springer International Publishing; 2022. P. 267–275.
- Menze BH, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging. 2015;34(10):1993–2024. doi: 10.1109/TMI.2014.2377694
- Bakas S, Akbari H, Sotiras A, et al. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data. 2017;4:170117. doi: 10.1038/sdata.2017.117
- Baid U, Ghodasara S, Mohan S, et al. The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain tumor segmentation and radiogenomic classification. Computer Vision and Pattern Recognition. 2021:2107.02314. doi: 10.48550/arXiv.2107.02314
- Louis DN, Perry A, Wesseling P, et al. The 2021 WHO classification of tumors of the central nervous system: a summary. Neuro Oncol. 2021;23(8);1231–1251. doi: 10.1093/neuonc/noab106
Supplementary files
