G.V. Danilov
Burdenko Neurosurgical Center
T.A. Konakova
Burdenko National Medical Scientific Center for Neurosurgery
E.L. Pogosbekyan
Burdenko Neurosurgical Center;
Institute of Higher Nervous Activity and Neurophysiology
S.V. Shugai
Burdenko Neurosurgical Center
A.I. Batalov
Burdenko Neurosurgical Center
N.B. Vikhrova
Burdenko Neurosurgical Center;
Scientific Practical Clinical Center for Diagnosis and Telemedicine Technologies
I.N. Pronin
Burdenko Neurosurgical Center
Non-invasive diagnosis of brain gliomas by histological type using neuroradiomics in standardized regions of interest: towards digital biopsy
Journal: Burdenko's Journal of Neurosurgery. 2023;87(6): 59‑66
Views: 808
Downloaded: 14
To cite this article:
Danilov GV, Shevchenko AM, Konakova TA, Pogosbekyan EL, Shugai SV, Tsukanova TV, Zakharova NE, Batalov AI, Agrba SB, Vikhrova NB, Pronin IN. Non-invasive diagnosis of brain gliomas by histological type using neuroradiomics in standardized regions of interest: towards digital biopsy. Burdenko's Journal of Neurosurgery.
2023;87(6):59‑66. (In Russ., In Engl.)
https://doi.org/10.17116/neiro20238706159
The future of contemporary neuroimaging does not solely lie in novel image-capturing technologies, but also in better methods for extraction of useful information from these images. Scientists see great promise in radiomics, i.e. the methodology for analysis of multiple features in medical image. However, there are certain issues in this field impairing reproducibility of results. One such issue is no standards in establishing the regions of interest.
To introduce a standardized method for identification of regions of interest when analyzing MR images using radiomics; to test the hypothesis that this approach is effective for distinguishing different histological types of gliomas.
We analyzed preoperative MR data in 83 adults with various gliomas (WHO classification, 2016), i.e. oligodendroglioma, anaplastic oligodendroglioma, anaplastic astrocytoma, and glioblastoma. Radiomic features were computed for T1, T1-enhanced, T2 and T2-FLAIR modalities in four standardized volumetric regions of interest by 356 voxels (46.93 mm3): 1) contrast enhancement; 2) edema-infiltration; 3) area adjacent to edema-infiltration; 4) reference area in contralateral hemisphere. Subsequently, mathematical models were trained to classify MR-images of glioma depending on histological type and quantitative features.
Mean accuracy of differential diagnosis of 4 histological types of gliomas in experiments with machine learning was 81.6%, mean accuracy of identification of tumor types — from 94.1% to 99.5%. The best results were obtained using support vector machines and random forest model.
In a pilot study, the proposed standardization of regions of interest demonstrated high effectiveness for MR-based differential diagnosis of oligodendroglioma, anaplastic oligodendroglioma, anaplastic astrocytoma and glioblastoma. There are grounds for applying and improving this methodology in further studies.
Authors:
G.V. Danilov
Burdenko Neurosurgical Center
T.A. Konakova
Burdenko National Medical Scientific Center for Neurosurgery
E.L. Pogosbekyan
Burdenko Neurosurgical Center;
Institute of Higher Nervous Activity and Neurophysiology
S.V. Shugai
Burdenko Neurosurgical Center
A.I. Batalov
Burdenko Neurosurgical Center
N.B. Vikhrova
Burdenko Neurosurgical Center;
Scientific Practical Clinical Center for Diagnosis and Telemedicine Technologies
I.N. Pronin
Burdenko Neurosurgical Center
Received:
10.09.2023
Accepted:
14.09.2023
List of references:
Close metadata
Email Confirmation
An email was sent to test@gmail.com with a confirmation link. Follow the link from the letter to complete the registration on the site.
Email Confirmation
Log in to the site using your account in one of the services
We use cооkies to improve the performance of the site. By staying on our site, you agree to the terms of use of cооkies. To view our Privacy and Cookie Policy, please. click here.