[Non-invasive diagnosis of brain gliomas by histological type using neuroradiomics in standardized regions of interest: towards digital biopsy]. / Neinvazivnaya diagnostika gliom golovnogo mozga po gistologicheskomu tipu s pomoshch'yu neiroradiomiki v standartizirovannykh zonakh interesa: na puti k tsifrovoi biopsii.

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. OBJECTIVE: 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. MATERIAL AND METHODS: 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. RESULTS: 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. CONCLUSION: 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.

Radiomics in Determining Tumor-to-Normal Brain SUV Ratio Based on 11C-Methionine PET/CT in Glioblastoma.

Modern methodology of PET/CT quantitative analysis in patients with glioblastomas is not strictly standardized in clinic settings and does not exclude the influence of the human factor. Methods of radiomics may facilitate unification, and improve objectivity and efficiency of the medical image analysis. The aim of the study is to evaluate the potential of radiomics in the analysis of PET/CT glioblastoma images identifying the relationship between the radiomic features and the 11С-methionine tumor-to-normal brain uptake ratio (TNR) determined by an expert in routine. Materials and Methods: PET/CT data (2018-2020) from 40 patients (average age was 55±12 years; 77.5% were males) with a histologically confirmed diagnosis of "glioblastoma" were included in the analysis. TNR was calculated as a ratio of the standardized uptake value of 11C-methionine measured in the tumor and intact tissue. Calculation of radiomic features for each PET was performed in the specified volumetric region of interest, capturing the tumor with the surrounding tissues. The relationship between TNR and the radiomic features was determined using the linear regression model. Predictors were included in the model following correlation analysis and LASSO regularization. The experiment with machine learning was repeated 300 times, splitting the training (70%) and test (30%) subsets randomly. The model quality metrics and predictor significance obtained in 300 tests were summarized. Results: Of 412 PET/CT radiomic parameters significantly correlated with TNR (p<0.05), the regularization procedure left no more than 30 in each model (the median number of predictors was 9 [7; 13]). The experiment has demonstrated a non-random linear correlation (the Spearman correlation coefficient was 0.58 [0.43; 0.74]) between TNR and separate radiomic features, primarily fractal dimensions, characterizing the geometrical properties of the image. Conclusion: Radiomics enabled an objective determination of PET/CT image texture features reflecting the biological activity of glioblastomas. Despite the existing limitations in the application, the first results provide a good perspective of these methods in neurooncology.

[MR-guided non-invasive typing of brain gliomas using machine learning]. / Pervye rezul'taty neinvazivnogo tipirovaniya gliom golovnogo mozga po dannym magnitno-rezonansnoi tomografii s pomoshch'yu mashinnogo obucheniya.

Gliomas are the most common neuroepithelial brain tumors. The modern classification of tumors of central nervous system and treatment approaches are based on tissue and molecular features of a particular neoplasm. Today, histological and molecular genetic typing of tumors can only be carried out through invasive procedures. In this regard, non-invasive preoperative diagnosis in neurooncology is appreclated. One of the perspective areas is artificial intelligence applied for neuroimaging to identify significant patterns associated with histological and molecular profiles of tumors and not obvlous for a specialist. OBJECTIVE: To evaluate diagnostic accuracy of deep learning methods for glioma typing according to the 2007 WHO classification based on preoperative magnetic resonance imaging (MRI) data. MATERIAL AND METHODS: The study included MR scans of patients with glial tumors undergoing neurosurgical treatment at the Burdenko National Medical Research Center for Neurosurgery. All patients underwent preoperative contrast-enhanced MRI. 2D and 3D MR scans were used for learning of artificial neural networks with two architectures (Resnest200e and DenseNet, respectively) in classifying tumors into 4 categories (WHO grades I-IV). Learning was provided on 80% of random examinations. Classification quality metrics were evaluated in other 20% of examinations (validation and test samples). RESULTS: Analysis included 707 contrast-enhanced T1 welghted images. 3D classification based on DenseNet model showed the best result in predicting WHO tumor grade (accuracy 83%, AUC 0.95). Other authors reported similar results for other methods. CONCLUSION: The first results of our study confirmed the fundamental possibility of grading axial contrast-enhanced T1 images according to the 2007 WHO classes using deep learning models.

Prediction of Postoperative Speech Dysfunctions in Neurosurgery Based on Cortico-Cortical Evoked Potentials and Machine Learning Technology.

Intraoperative recording of cortico-cortical evoked potentials (CCEPs) enables studying effective connections between various functional areas of the cerebral cortex. The fundamental possibility of postoperative speech dysfunction prediction in neurosurgery based on CCEP signal variations could serve as a basis to develop the criteria for the physiological permissibility of intracerebral tumors removal for maximum preservation of the patients' quality of life. The aim of the study was to test the possibility of predicting postoperative speech disorders in patients with glial brain tumors by using the CCEP data recorded intraoperatively before the stage of tumor resection. Materials and Methods: CCEP data were reported for 26 patients. To predict the deterioration of speech functions in the postoperative period, we used four options for presenting CCEP data and several machine learning models: a random forest of decision trees, logistic regression, and support vector machine method with different types of kernels: linear, radial, and polynomial. Twenty variants of models were trained: each in 300 experiments with resampling. A total of 6000 tests were performed in the study. Results: The prediction quality metrics for each model trained in 300 tests with resampling were averaged to eliminate the influence of "successful" and "unsuccessful" data grouping. The best result with F1-score = 0.638 was obtained by the support vector machine with a polynomial kernel. In most tests, a high sensitivity score was observed, and in the best model, it reached a value of 0.993; the specificity of the best model was 0.370. Conclusion: This pilot study demonstrated the possibility of predicting speech dysfunctions based on CCEP data taken before the main stage of glial tumors resection; the data were processed using traditional machine learning methods. The best model with high sensitivity turned out to be insufficiently specific. Further studies will be aimed at assessing the changes in CCEP during the operation and their relationship with the development of postoperative speech deficit.

[Dynamic11C-methionine PET/CT in differential diagnosis of brain gliomas]. / Dinamicheskaya PET/KT s 11S-metioninom v differentsial'noi diagnostike glial'nykh opukholei golovnogo mozga.

OBJECTIVE: To evaluate the possibilities of dynamic preoperative 11C-methionine (MET) PET/CT in differential diagnosis of various types of brain gliomas in adults. MATERIAL AND METHODS: The study included 74 patients aged 48±14 years with supratentorial gliomas: Grade IV - glioblastoma (GB, n=33), Grade III - anaplastic oligodendroglioma (AOD, n=10) and anaplastic astrocytoma (AA, n=12), Grade II - diffuse astrocytoma (DA, n=13) and oligodendroglioma (OD, n=6). All patients underwent standard MRI and dynamic MET PET/CT within 20 minutes after intravenous injection of radiopharmaceutical. Then, we compared MRI and PET/CT data and comprehensively analyzed the early stages of time-activity curve using 2 parameters: the first pass peak (FPP) and the first peak of maximum uptake (Pmax). RESULTS: We have significantly distinguished high-grade tumors (GB and AA+AOD) and certain benign gliomas (DA and OD) (p<0.05). AUC was over 0.7 and 0.8 for FPP and Pmax in differential diagnosis of various gliomas, respectively. We found that difficulties in differential diagnosis of gliomas arise mainly if oligodendrogliomas are included in the control group. CONCLUSION: Dynamic PET/CT with analysis of FPP and Pmax increases specificity of differential diagnosis of various gliomas compared to standard static imaging. These data are valuable for choice of optimal treatment strategy, as well as fundamental research of metabolic processes and vascularization of various tumors.

[Phosphorus MR spectroscopy and 18F-FDG PET/CT in the study of energy metabolism of glial tumors]. / Fosfornaya MR-spektroskopiya i PET/KT s 18F-FDG v izuchenii energeticheskogo metabolizma glial'nykh opukholei.

OBJECTIVE: To study energy metabolism in glial tumors using dynamic MR spectroscopy and 18F-FDG PET/CT. MATERIAL AND METHODS: The study included 19 patients (9 women and 10 men) with newly diagnosed supratentorial glial tumors WHO Grade I-IV (diffuse astrocytoma - 4 cases, oligodendroglioma - 4 cases, anaplastic astrocytoma - 5 cases, glioblastoma - 6 cases). All patients underwent examination and surgical treatment at the Burdenko Neurosurgery Center. Dynamic MR spectroscopy and 18F-FDG PET/CT were applied in each patient. RESULTS: We found multiple correlations between the ratio of bioorganic phosphate peaks and parameters of glucose uptake by tumor tissue. These relationships were more significant in patients with high-grade tumors: positive significant correlation between SUVtumor and PME/PCr ratio (RS=0.75, p=0.01), T/Nmix and ßATP/Pi ratio (Rs=0.76, p=0.02), SUVpeaktumor and aATP/Pi ratio (RS=0.77, p=0.008). Moreover, there were negative correlations between SUVtumor and PCr/bATP ratio (RS= -0.66, p=0.05), T/Nmix and PDE/bATP ratio (RS= -0.83, p=0.006), SUVpeaktumor and PDE/aATP ratio (RS= -0.76, p=0.009). CONCLUSION: High-grade gliomas were characterized by higher glucose consumption, ATP release (intensification of energy metabolism) and faster cell membrane synthesis. These processes indicate enhanced proliferation of tumor cells (intensification of plastic metabolism).

Feasibility of generalised diffusion kurtosis imaging approach for brain glioma grading.

PURPOSE: An accurate differentiation of brain glioma grade constitutes an important clinical issue. Powerful non-invasive approach based on diffusion MRI has already demonstrated its feasibility in glioma grade stratification. However, the conventional diffusion tensor (DTI) and kurtosis imaging (DKI) demonstrated moderate sensitivity and performance in glioma grading. In the present work, we apply generalised DKI (gDKI) approach in order to assess its diagnostic accuracy and potential application in glioma grading. METHODS: Diffusion scalar metrics were obtained from 50 patients with different glioma grades confirmed by histological tests following biopsy or surgery. All patients were divided into two groups with low- and high-grade gliomas as grade II versus grades III and IV, respectively. For a comparison, trained radiologists segmented the brain tissue into three regions with solid tumour, oedema, and normal appearing white matter. For each region, we estimated the conventional and gDKI metrics including DTI maps. RESULTS: We found high correlations between DKI and gDKI metrics in high-grade glioma. Further, gDKI metrics enabled introduction of a complementary measure for glioma differentiation based on correlations between the conventional and generalised approaches. Both conventional and generalised DKI metrics showed quantitative maps of tumour heterogeneity and oedema behaviour. gDKI approach demonstrated largely similar sensitivity and specificity in low-high glioma differentiation as in the case of conventional DKI method. CONCLUSION: The generalised diffusion kurtosis imaging enables differentiation of low- and high-grade gliomas at the same level as the conventional DKI. Additionally, gDKI exhibited higher sensitivity to tumour heterogeneity and tissue contrast between tumour and healthy tissue and, thus, may contribute as a complementary source of information on tumour differentiation.

[Broca's area intraoperative mapping with cortico-cortical evoked potentials]. / Intraoperatsionnoe kartirovanie rechevoi zony Broka metodom registratsii kortiko-kortikal'nykh vyzvannykh potentsialov.

OBJECTIVE: Mapping of effective speech connections between the frontal and temporal lobes with cortico-cortical evoked potentials. MATERIAL AND METHODS: There were 3 patients with brain tumors in the left frontoparietal region. The neoplasms were localized in the dominant hemisphere near cortical speech centers and pathways. Cortico-cortical evoked potentials were intraoperatively recorded in response to bipolar stimulation with a direct current delivered through the subdural electrodes (single rectangular biphasic impulses with duration of 300 µs and frequency of 1 Hz). Stimulation intensity was gradually increased from 2 mA within 3-4 mA. Registration was carried out by averaging ECoG (30-50 stimuli in each session) in the 300-ms epoch after stimulus. Direct cortical stimulation was used to validate the results of cortico-cortical speech mapping with cortico-cortical evoked potentials. RESULTS: In our cases, we obtained cortico-cortical evoked potentials from inferior frontal gyrus after stimulation of superior temporal gyrus. In one case, this effective relationship was unidirectional, in the other two patients reciprocal. Mean latency of N1 peak was 65 ms (range 49.6-90 ms), mean amplitude 71 µV (range 50-100 µV). Cortico-cortical mapping data were confirmed by detection of Broca's area in 2 out of 3 cases out during direct cortical stimulation with maximum amplitude of N1 wave. «Awake craniotomy¼ protocol was applied. In one case, Broca's area was not detected during direct stimulation. No postoperative speech impairment was noted. CONCLUSION: Initial results of cortical mapping with cortico-cortical evoked potentials in a small sample confirmed its practical significance for analysis of cortical projections of effective speech communications between the frontal and temporal lobes. Further study of this method in large samples is required.

[Positron emission tomography with 11C-methionine in primary brain tumor diagnosis]. / Primenenie PET-KT s 11C-metioninom v pervichnoi diagnostike gliom.

OBJECTIVE: To investigate the variations in 11C-methionine uptake in the intact brain tissue and in glial brain tumors of different types. MATERIAL AND METHODS: Forty patients (21 men, 19 women) with gliomas, Grade I-IV, underwent 11C-methionine PET-CT and contrast-enhanced MRI. Standardized uptake value (SUV), tumor-to-normal (T/N) ratios and tumor volume were analyzed. RESULTS: The high inter-subject variability was detected in the intact brain tissue (SUV in the frontal lobe (FL) varies from 0.47 to 1.73). Amino acid metabolism was more active in women than in men (FL SUV 1.32±0.22 and 1.05±0.24, respectively). T/N ratio better differentiates gliomas by the degree of anaplasia compared to SUV. Gliomas of Grade III (T/N=2.64±0.98) were significantly different (p<0.05) from those of Grade IV (T/N=3.83±0.75). The lowest level of methionine uptake was detected in diffuse astrocytomas (T/N=1.52±0.57), which was lower than with anaplastic astrocytomas (T/N=2.34±0.77, p<0.05). CONCLUSIONS: 11C-methionine PET-CT was informative in the high/low degree of malignancy differentiation (T/N 1.66±0.71 for Grade I-II and 3.18±1.06 for Grade III-IV, p<0.05). The method was also useful in separating astrocytomas of Grade II and III. The considerable variation of SUV in the intact brain tissue as well as the difference in uptake between selected areas of the brain were revealed.