• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.425-427
• /
• 2022

The grade of glioma is important information related to survival and thus is important to classify the grade of glioma before treatment to evaluate tumor progression and treatment planning. Glioma grading is mostly divided into high-grade glioma (HGG) and low-grade glioma (LGG). In this study, image preprocessing techniques are applied to analyze magnetic resonance imaging (MRI) using the deep neural network model. Classification performance of the deep neural network model is evaluated. The highest-performance EfficientNet-B6 model shows results of accuracy 0.9046, sensitivity 0.9570, specificity 0.7976, AUC 0.8702, and F1-Score 0.8152 in 5-fold cross-validation.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.198-204
• /
• 2021

Glioma is one of the common types of brain tumors starting in the brain's glial cell. These tumors are classified into low-grade or high-grade tumors. Physicians analyze the stages of brain tumors and suggest treatment to the patient. The status of the tumor has an importance in the treatment. Nowadays, computerized systems are used to analyze and classify brain tumors. The accurate grading of the tumor makes sense in the treatment of brain tumors. This paper aims to develop a classification of low-grade glioma and high-grade glioma using a deep learning algorithm. This system utilizes four transfer learning algorithms, i.e., AlexNet, GoogLeNet, ResNet18, and ResNet50, for classification purposes. Among these algorithms, ResNet18 shows the highest classification accuracy of 97.19%.

• Investigative Magnetic Resonance Imaging
• /
• v.26 no.2
• /
• pp.104-116
• /
• 2022

The purpose of this study is to systematically determine an optimal percentile cut-off in histogram analysis for calculating the mean parameters obtained from a non-Gaussian continuous-time random-walk (CTRW) diffusion model for differentiating individual glioma grades. This retrospective study included 90 patients with histopathologically proven gliomas (42 grade II, 19 grade III, and 29 grade IV). We performed diffusion-weighted imaging using 17 b-values (0-4000 s/mm²) at 3T, and analyzed the images with the CTRW model to produce an anomalous diffusion coefficient (D_m) along with temporal (𝛼) and spatial (𝛽) diffusion heterogeneity parameters. Given the tumor ROIs, we created a histogram of each parameter; computed the P-values (using a Student's t-test) for the statistical differences in the mean D_m, 𝛼, or 𝛽 for differentiating grade II vs. grade III gliomas and grade III vs. grade IV gliomas at different percentiles (1% to 100%); and selected the highest percentile with P < 0.05 as the optimal percentile. We used the mean parameter values calculated from the optimal percentile cut-offs to do a receiver operating characteristic (ROC) analysis based on individual parameters or their combinations. We compared the results with those obtained by averaging data over the entire region of interest (i.e., 100th percentile). We found the optimal percentiles for D_m, 𝛼, and 𝛽 to be 68%, 75%, and 100% for differentiating grade II vs. III and 58%, 19%, and 100% for differentiating grade III vs. IV gliomas, respectively. The optimal percentile cut-offs outperformed the entire-ROI-based analysis in sensitivity (0.761 vs. 0.690), specificity (0.578 vs. 0.526), accuracy (0.704 vs. 0.639), and AUC (0.671 vs. 0.599) for grade II vs. III differentiations and in sensitivity (0.789 vs. 0.578) and AUC (0.637 vs. 0.620) for grade III vs. IV differentiations, respectively. Percentile-based histogram analysis, coupled with the multi-parametric approach enabled by the CTRW diffusion model using high b-values, can improve glioma grading.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.416-418
• /
• 2022

Glioma is a type of brain tumor that occurs in glial cells and is classified into two types: high hrade hlioma with a poor prognosis and low grade glioma. Magnetic resonance imaging (MRI) as a non-invasive method is widely used in glioma diagnosis research. Studies to obtain complementary information by combining multiple modalities to overcome the incomplete information limitation of single modality are being conducted. In this study, we developed a 3D CNN-based model that applied input-level fusion to MRI of four modalities (T1, T1Gd, T2, T2-FLAIR). The trained model showed classification performance of 0.8926 accuracy, 0.9688 sensitivity, 0.6400 specificity, and 0.9467 AUC on the validation data. Through this, it was confirmed that the grade of glioma was effectively classified by learning the internal relationship between various modalities.

• 대한핵의학회:학술대회논문집
• /
• 1995.05a
• /
• pp.189-189
• /
• 1995

• Journal of Korean Neurosurgical Society
• /
• v.39 no.3
• /
• pp.176-182
• /
• 2006

Objective : This study concernes the usefulness of $^{11}C-methyl-L-and$ D-methionine[Met]-positron emission tomography[PET] for glioma grading and detection of recurrence in gliomas, compared with fluorine-18, 2-fluoro-deoxyglucose[FDG]-PET. Methods : Eighty patients underwent Met-PET study for evaluation of glioma : 37 astrocytomas [WHO grade II, 3; III, 8; IV, 26]. 27 oligodendrogliomas [WHO grade II, 16; III, 11]. and 12 suspicious recurrent gliomas. All images were taken within 2 weeks before operation. For suspicious recurrent cases on magnetic resonance images, both FDG-PET and Met-PET were performed. Results : In astrocytoma, Mean maximum standard uptake value[SUV] of region of interest[ROI] was not different between WHO grades [p=0.108]. but ROI/normal contralateral tissue SUV [T/N] ratio was statistically different between WHO grades [p=0.002]. T/N ratio was more closely related to visual scale than maximum SUV of ROI [p<0.001 and p=0.107 respectively]. In oligodendroglioma, there was no statistical difference between WHO grades in view of maximum SUV and T/N ratio. For recurrent gliomas, sensitivity of FDG-PET and Met-PET was 25% and 100%, while specificity of FDG-PET and Met-PET were 100% and 80%, respectively. Conclusion : Met-PET might be an appropriate tool for tumor grading in astrocytoma and be more sensitive for detection of recurrence in gliomas than FDG-PET.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.4
• /
• pp.465-475
• /
• 2023

Objective : Our objective is to analyze the occurrence, clinical course and risk factors for glioma patients with leptomeningeal metastasis (LM) according to different metastasis patterns and clinical variables. Methods : We retrospectively reviewed data from 376 World Health Organization (WHO) grade II-IV adult glioma patients who were treated in the National Cancer Center from 2001 to 2020. Patients who underwent surgery at other institutions, those without initial images or those with pathologically unconfirmed cases were excluded. LM was diagnosed based on magnetic resonance imaging (MRI) findings or cerebrospinal fluid (CSF) cytology. The metastasis pattern was categorized as nodular or linear according to the enhancement pattern. Tumor proximity to the CSF space was classified as involved or separated, whereas location of the tumor was dichotomized as midline, for tumors residing in the thalamus, basal ganglia and brainstem, or lateral, for tumors residing in the cerebral and cerebellar hemispheres. Results : A total of 138 patients were enrolled in the study. A total of 44 patients (38%) were diagnosed with LM during a median follow-up of 9 months (range, 0-60). Among the clinical variables, tumor proximity to CSF space, the location of the tumor and the WHO grade were significant factors for LM development in univariate analysis. In multivariate analysis, the midline location of the tumor and WHO grade IV gliomas were the most significant factor for LM development. The hazard ratio was 2.624 for midline located gliomas (95% confidence interval [CI], 1.384-4.974; p=0.003) and 3.008 for WHO grade IV gliomas (95% CI, 1.379-6.561; p=0.006). Conclusion : Midline location and histological grading are an important factor for LM in glioma patients. The proximity to the CSF circulation pathway is also an important factor for WHO grade IV glioma LM. Patients carrying high risks should be followed up more thoroughly.

• Journal of Yeungnam Medical Science
• /
• v.8 no.2
• /
• pp.63-69
• /
• 1991

Nucleolar organizer regions (NOR) are loops of ribosomal DNA(rDNA) which are transcribed by RNA polymerase I. They produce ultimately ribosome and protein. Thus they are believed to reflect nuclear activity. We applied silver colloid staining technique to human glioma to examine relationship between the mean number of Ag-NOR and histopathological grading. The mean number of Ag-NOR(${\pm}$ S.E of the mean)were $1.17{\pm}0.07$ in normal brain, $1.53{\pm}0.25$ in astrocytoma, $2.37{\pm}0.71$ in malignant astrocytoma, and $2.88{\pm}0.41$ in glioblastoma multiforme. And there was a statistically significant difference among these. The results show that Ag-NOR technique is a rather simple and rapid method and will become a helpful tool for estimation of the proliferative potential of glioma.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.9
• /
• pp.4079-4083
• /
• 2014

Background: Previous studies have showed that argonaute 2 is a potential factor related to genesis of several cancers, however, there have been no reports concerning gliomas. Methods: Paraffin specimens of 129 brain glioma cases were collected from a hospital affiliated to Binzhou Medical University from January 2008 to July 2013. We examined both argonaute 2 mRNA and protein expression by real-time quantitative PCR (qRT-PCR), Western blot analysis, and immunohistochemistry (IHC). The survival curves of the patients were determined using the Kaplan-Meier method and Cox regression, and the log-rank test was used for statistical evaluations. Results: Both argonaute 2 mRNA and protein were upregulated in high-grade when compared to low-grade tumor tissues. Multivariate analysis revealed that argonaute 2 protein expression was independently associated with the overall survival (HR=4.587, 95% CI: 3.001-6.993; P=0.002), and that argonaute 2 protein expression and WHO grading were independent prognostic factors for progression-free survival (HR=4.792, 95% CI: 3.993-5.672; P<0.001, and HR=2.109, 95% CI: 1.278-8.229; P=0.039, respectively). Kaplan-Meier analysis with the log-rank test indicated that high argonaute 2 protein expression had a significant impact on overall survival (P=0.0169) and progression-free survival (P=0.0324). Conclusions: The present study showed that argonaute 2 expression is up-regulated in gliomas. Argonaute 2 might also serve as a novel prognostic marker.

• Journal of radiological science and technology
• /
• v.32 no.4
• /
• pp.461-469
• /
• 2009

To predict the tumor grading, various imaging modalities have been applied clinically. This study determines clinical usefulness of perfusion MRI, using relative cerebral blood volume in grading of the gliomas. We did a retrospective review of 17 patients (mean age, 57.5 years; 11 male, 6 female) who underwent perfusion MR and conventional MRI, and then correlated pathologically after operation. Statistical analysis of regional cerebral blood volume and relative cerebral blood volume(rCBV) was performed by using softwares such as PAT by SIEMENS and Xmap ver 2.0 developed by ourselves. Six patients out of 13 were low-grade gliomas while eleven patients were the high-grade gliomas. Mean relative CBV (m_rCBV/white matter) in the low-grade gliomas was 1.62, and mean relative CBV(m_rCBV/cortex) was 0.12. In the high-grade gliomas, mean relative CBV(m_rCBV/white matter) and mean relative CBV(m_rCBV/cortex) were 33.53 and 0.96. Mean relative CBV of gliomas were elevated with a statistical difference(P<.05), compared with contralateral white matter(P=.019) or cortex(P=.025). Furthermore mean relative CBV(m_rCBV/white matter) was much higher than mean relative CBV(m_rCBV/cortex). Perfusion MRI using regional cerebral blood volume and rCBV is very useful imaging modality for grading the glioma.