• 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%.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.12
• /
• pp.5303-5307
• /
• 2016

Objective: Brain tumors cause great mortality and morbidity worldwide, and success rates with surgical treatment remain very low. Several recent studies have focused on introduction of novel effective medical therapeutic approaches. Genistein is a member of the isoflavonoid family which has proved to exert anticancer effects. Here we assessed the effects of genistein on the expression of MMP-2 and VEGF in low and high grade gliomas in vitro. Materials and Methods: High and low grade glioma tumor tissue samples were obtained from a total of 16 patients, washed with PBS, cut into small pieces, digested with collagenase type I and cultured in DMEM containing 10% FBS. When cells reached passage 3, they were exposed to genistein and MMP-2 and VEGF gene transcripts were determined by quantitative real time PCR (qRT-PCR). Results: Expression of MMP-2 demonstrated 580-fold reduction in expression in low grade glioma cells post treatment with genistein compared to untreated cells (P value= 0.05). In cells derived from high grade lesions, expression of MMP-2 was 2-fold lower than in controls (P value> 0.05). Genistein caused a 4.7-fold reduction in VEGF transcript in high grade glioma cells (P value> 0.05) but no effects were evident in low grade glioma cells. Conclusion. Based on the data of the present study, low grade glioma cells appear much more sensitive to genistein and this isoflavone might offer an appropriate therapeutic intervention in these patients. Further investigation of this possibility is clearly warranted.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.11
• /
• pp.5725-5728
• /
• 2012

Growing evidence shows that deregulation of the circadian clock plays an important role in the development of malignant tumors, including gliomas. However, the molecular mechanisms of gene chnages controlling circadian rhythm in glioma cells have not been explored. Using real time polymerase chain reaction and immunohistochemistry techniques, we examined the expression of two important clock genes, cry1 and cry2, in 69 gliomas. In this study, out of 69 gliomas, 38 were cry1-positive, and 51 were cry2-positive. The expression levels of cry1 and cry2 in glioma cells were significantly different from the surrounding non-glioma cells (P<0.01). The difference in the expression rate of cry1 and cry 2 in high-grade (grade III and IV) and low-grade (grade 1 and II) gliomas was non-significant (P>0.05) but there was a difference in the intensity of immunoactivity for cry 2 between high-grade gliomas and low-grade gliomas (r=-0.384, P=0.021). In this study, we found that the expression of cry1 and cry2 in glioma cells was much lower than in the surrounding non-glioma cells. Therefore, we suggest that disturbances in cry1 and cry2 expression may result in the disruption of the control of normal circadian rhythm, thus benefiting the survival of glioma cells. Differential expression of circadian clock genes in glioma and non-glioma cells may provide a molecular basis for the chemotherapy of gliomas.

• 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.

• Journal of Korean Neurosurgical Society
• /
• v.57 no.6
• /
• pp.469-472
• /
• 2015

Undifferentiated sarcomas are rarely identified in the intracranial region. A 23-year-old man was admitted with a chief complaint of headache. Initial magnetic resonance images showed signs of low-grade glioma in the frontal lobe. Stereotactic biopsy was performed, and a diagnosis of diffuse astrocytoma was confirmed. Three months later, the patient presented with a high-grade tumor as seen on imaging studies. He underwent total resection of the tumor and histopathological tests identified an undifferentiated sarcoma. The patient died eight months later due to massive tumor bleeding. To the best of our knowledge, this is the first report of undifferentiated sarcoma arising from low-grade glioma without any chemotherapy or radiotherapy.

• 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.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.8
• /
• pp.3355-3360
• /
• 2015

Background: Zinc transporters have been considered as essential regulators in many cancers; however, their mechanisms remain unknown, especially in gliomas. Isocitrate dehydrogenase 1(IDH1) mutation is crucial to glioma. This study aimed to investigate whether zinc transporters are correlated with glioma grade and IDH1 mutation status. Materials and Methods: IDH1 mutation status and mRNA expression of four zinc transporters (ZIP4, ZIP9, ZIP11, and ZnT9) were determined by subjecting a panel of 74 glioma tissue samples to quantitative real-time PCR and pyrosequencing. The correlations between the expression levels of these zinc transporter genes and the grade of glioma, as well as IDH1 mutation status, were investigated. Results: Among the four zinc transporter genes, high ZIP4 expression and low ZIP11 expression were significantly associated with higher grade (grades III and IV) tumors compared with lower grade (grades I and II) counterparts (p<0.0001). However, only ZIP11 exhibited weak correlation with IDH1 mutation status (p=0.045). Samples with mutations in IDH1 displayed higher ZIP11 expression than those without IDH1 mutations. Conclusions: This finding indicated that zinc transporters may interact with IDH1 mutation by direct modulation or action in some shared pathways or genes to promote the development of glioma. Zinc transporters may play an important role in glioma. ZIP4 and ZIP11 are promising molecular diagnostic markers and novel therapeutic targets. Nevertheless, the detailed biological function of zinc transporters and the mechanism of the potential interaction between ZIP11 and IDH1 mutation in gliomagenesis should be further investigated.

• Journal of Korean Neurosurgical Society
• /
• v.60 no.1
• /
• pp.15-20
• /
• 2017

Objective : Diagnosing tumor progression and pseudoprogression remains challenging for many clinicians. Accurate recognition of these findings remains paramount given necessity of prompt treatment. However, no consensus has been reached on the optimal technique to discriminate tumor progression. We sought to investigate the role of magnetic resonance perfusion (MRP) to evaluate tumor progression in glioma patients. Methods : An institutional retrospective review of glioma patients undergoing MRP with concurrent clinical follow up visit was performed. MRP was evaluated in its ability to predict tumor progression, defined clinically or radiographically, at concurrent clinical visit and at follow up visit. The data was then analyzed based on glioma grade and subtype. Resusts : A total of 337 scans and associated clinical visits were reviewed from 64 patients. Sensitivity, specificity, positive and negative predictive value were reported for each tumor subtype and grade. The sensitivity and specificity for high-grade glioma were 60.8% and 87.8% respectively, compared to low-grade glioma which were 85.7% and 89.0% respectively. The value of MRP to assess future tumor progression within 90 days was 46.9% (sensitivity) and 85.0% (specificity). Conclusion : Based on our retrospective review, we concluded that adjunct imaging modalities such as MRP are necessary to help diagnose clinical disease progression. However, there is no clear role for stand-alone surveillance MRP imaging in glioma patients especially to predict future tumor progression. It is best used as an adjunctive measure in patients in whom progression is suspected either clinically or radiographically.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.908-918
• /
• 2020

Objective: To categorize the radiological patterns of recurrence after bevacizumab treatment and to derive the pooled proportions of patients with recurrent malignant glioma showing the different radiological patterns. Materials and Methods: A systematic literature search in the Ovid-MEDLINE and EMBASE databases was performed to identify studies reporting radiological recurrence patterns in patients with recurrent malignant glioma after bevacizumab treatment failure until April 10, 2019. The pooled proportions according to radiological recurrence patterns (geographically local versus non-local recurrence) and predominant tumor portions (enhancing tumor versus non-enhancing tumor) after bevacizumab treatment were calculated. Subgroup and meta-regression analyses were also performed. Results: The systematic review and meta-analysis included 17 articles. The pooled proportions were 38.3% (95% confidence interval [CI], 30.6-46.1%) for a geographical radiologic pattern of non-local recurrence and 34.2% (95% CI, 27.3-41.5%) for a non-enhancing tumor-predominant recurrence pattern. In the subgroup analysis, the pooled proportion of non-local recurrence in the patients treated with bevacizumab only was slightly higher than that in patients treated with the combination with cytotoxic chemotherapy (34.9% [95% CI, 22.8-49.4%] versus 22.5% [95% CI, 9.5-44.6%]). Conclusion: A substantial proportion of high-grade glioma patients show non-local or non-enhancing radiologic patterns of recurrence after bevacizumab treatment, which may provide insight into surrogate endpoints for treatment failure in clinical trials of recurrent high-grade glioma.

• 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.