• Title/Summary/Keyword: 신경교종

Search Result 58, Processing Time 0.029 seconds

Multimodal MRI analysis model based on deep neural network for glioma grading classification (신경교종 등급 분류를 위한 심층신경망 기반 멀티모달 MRI 영상 분석 모델)

  • Kim, Jonghun;Park, Hyunjin
    • 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.

  • PDF

Postoperative Radiotherapy for Low Grade Glioma of the Brain (뇌 신경교종의 수술 후 방사선치료)

  • Chun, Ha-Chung;Lee, Myung-Za
    • Radiation Oncology Journal
    • /
    • v.18 no.2
    • /
    • pp.79-84
    • /
    • 2000
  • Purpose : To evaluate the effectiveness and tolerance of postoperative e지ernai beam radiotherapy for patients with low grade glioma of the brain and define the optimal radiotherapeutic regimen. Materials and Methods : Between June, 1985 and May, 1998, 72 patients with low grade gliomas were treated with postoperative radiotherapy immediately following surgery. Median age was 37 years with range of 11 to 76 years. Forty one patients were male and 31 patients were female with male to female ratio of 1.3:1. Of those patients, 15 underwent biopsy alone and remaining 57 did subtotal resection. The distribution of the patients according to histologic type was as follows: astrocytomas-42 patients (58$\%$), mixed oligodendrogliomas-19 patients (27$\%$), oiigodendrogliomas-11 patients (15$\%$). Two patients were treated with whole brain irradiation followed by cone down boost and remaining 70 patients were treated with localized field with appropriate margin. Ail of the patients were treated with conventional once a day fractionation. Most of patients received total tumor dose of 5000 $\~$ 5500 cGy. Results : The overall 5 and 7 year survival rates for entire group of 72 patients were 61$\~$ and 50$\~$. Corresponding disease free survival rates for entire patients were 53$\~$ and 45$\~$, respectively. The 5 and 7 year overall survival rates for astrocytomas, mixed oligodendrogiiomas, and oligodendrogiiorras were 48$\%$ and 45$\%$, 76$\%$ and 56$\%$, and 80$\%$ and 52$\%$, respectively. Patients who underwent subtotal resection showed better survival rates than those who did biopsy alone. The overall 5 year survival rates for sub total resection patients and biopsy alone patients were 57$\%$ and 43$\%$, respectively. Forty six patients who were 40 years or younger survived batter than 26 patients who were 41 years or older (overall survival rate at 5 years, 69$\%$ vs 45$\%$). Although one patient was not able to complete the treatment because of neurological deterioration, there was no significant treatment related acute toxicities. Conclusion : Postoperative radiotherapy was safe and effective treatment for patients with low grade gliomas. However, we probably need prospective randomized trial to define optimal treatment timing and schedule for low grade gliomas and select patient group for different treatment philosophies.

  • PDF

Correlation Between the Expression of Epidermal Growth Factor Receptor and MR Features in Glioma (신경교종에서 표피성장인자수용체의 발현도와 자기공명영상 소견의 상관관계)

  • 김범수;신경섭
    • Investigative Magnetic Resonance Imaging
    • /
    • v.1 no.1
    • /
    • pp.125-129
    • /
    • 1997
  • Purpose: The aim of this study was to find correlation between the expression of epidermal growth factor receptor (EGFR) and MR findings in the brain glioma. Materials and Methods: MR features including edema, margin, necrosis, heterogeneity, hemorrhage and contrast enhancement were retrospectively analyzed with preoperative MR images in 41 patients with proven brain gliomas (8 low grade astrocytomas, 12 anaplastic astrocytomas, 21 glioblastoma multiformes). Immunohistochemical study of EGFR was done and their expressions were graded by both stained distribution and intensity. Correlation analysis between the MR features and EGFR expressions was done. Results: Peritumoral edema was correlated with both distribution (r=0.71, p=0.00) and stain intensity (r=0.69, p=0.00) of EGFR expression. Other MR features showed no statistical correlation with EGFR expression. Conclusion: MRI is useful in evaluation of brain glioma, and peritumoral edema is useful finding that suggests EGFR expression as well as malignant histopathologic grade of the tumor.

  • PDF

Nucleolar Organizer Regions in Glioma (신경교종에서 핵소체 조성부의 의의)

  • Nam, Hae-Joo;Kim, Dong-Suk;Choi, Won-Hee;Lee, Tae-Sook
    • 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.

  • PDF

Prediction of overall survival for patients with malignant glioma using convolutional neural network (합성곱 신경망 모델을 이용한 악성 뇌교종 환자 예후 예측)

  • Kwon, Junmo;Park, Hyunjin
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.10a
    • /
    • pp.297-299
    • /
    • 2022
  • Malignant glioma has a poor prognosis with the reported median survival of between 6 months to 14 months. Thus, it is crucial to predict the accurate survival of patients with malignant glioma. In this paper, we propose a convolutional neural network to predict the overall survival and age of the patients. A total of four MRI modalities, T1, T1-contrast enhanced, T2, and fluid-attenuated inversion recovery, which effectively capture spatial characteristics of malignant glioma, were used as input images. Age is an important factor impacting the overall survival, thus incorporating it into the model will thereby improve the performance of the proposed model. Our model successfully predicted overall survival and age of the patients with pearson correlation coefficients of 0.1748 and 0.3056, respectively.

  • PDF

Cyanate Induces Apoptosis of Rat Glioma Cell Line (시안산에 의한 신경아교종세포의 자멸사)

  • Choi, Hye-Jung;Lee, Sang-Hee
    • Journal of Life Science
    • /
    • v.27 no.3
    • /
    • pp.267-274
    • /
    • 2017
  • The patient with end-stage renal disease show several nervous complications. The factors contributing to the nervous complications are still incompletely characterized. Cyanate, known as one of the uremic toxins, is derived spontaneously from urea. To investigate the mechanism of cyanate-induced effect on C6 glioma cells, the glioma cells were treated with 0, 1, 5, 10, 20 and 40 mM cyanate. There was a dose-dependent decrease in cell viability and the decreased number of cell was observed in glioma cells by treatment with cyanate. Western blot showed the down- regulation of procaspase-3, which means up-regulation of caspase-3, and the up-regulation of caspase-8, but the down-regulation by cyanate. In addition, cDNA microarray showed 934 down-regulated genes and 165 up-regulated genes on 1,099 genes in cyanate treated group. Treatment with cyanate led to 16 down-regulated genes and 6 up-regulated genes on apoptosis category, and especially heat shock 70 kD protein 1A gene on the category of apoptosis was significantly up-regulated. These results suggest that cyanate can induce apoptosis through caspase-8 and caspase-3 in glioma cells and decrease of gene expression including apoptosis category in glioma cells. These effects of cyanate may play a role in the nervous complications of patient with end-stage renal disease.

A BRW Stereotaxic Biopsy of Brain Stem Glioma (BRW Stereotaxic System을 이용한 뇌간신경교종의 정위수술적 생검술)

  • Baek, Seoung-Chan;Choi, Byung-Yearn;Moon, Choong-Bae;Chi, Young-Chul;Cho, Soo-Ho
    • Journal of Yeungnam Medical Science
    • /
    • v.3 no.1
    • /
    • pp.343-349
    • /
    • 1986
  • Histopathological diagnosis of brain stem glioma should be performed for the purpose of the determination of its management and clinical course, but its surgical biopsy has been followed by high mortality and morbidity. We performed the tissue sampling for histological examination with BRW stereotaxic system under local anesthesia successfully.

  • PDF

Deep Multimodal MRI Fusion Model for Brain Tumor Grading (뇌 종양 등급 분류를 위한 심층 멀티모달 MRI 통합 모델)

  • Na, In-ye;Park, Hyunjin
    • 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.

  • PDF

In Vivo H-1 MR Spectroscopy of Intracranial solid Tumors (두개강내 고형성 종양의 H-1 자기공명분광법)

  • 성수옥;장기현;한문희;연경모;한만청
    • Investigative Magnetic Resonance Imaging
    • /
    • v.1 no.1
    • /
    • pp.86-93
    • /
    • 1997
  • Purpose: To assess the ability of in vivo H-1 MRS to determine the degree of malignancy and to characterize the histopathologic type of intracranial solid tumors. Materials and Methods: In vivo H-1 MR spectra of the pathologically-proven 81 intracranial soild tumors (low-grade glioma 17 cases, high-grade glioma 31 cases, lymphoma 9 cases, meningioma 8 cases, central neurocytoma 4 cases, medulloblastoma 3 cases, PNET 3 cases, metastasis 2 cases, others 4 cases) were analyzed. H-1 MR spectroscopy was performed on a 1.5T MR unit using PRESS sequence with a TR of 2000ms, a TE of 270 or 135ms and a voxel size of $2{\times}2{\times}2cm^3$ for all spectra. N-acetyl aspartate (NAA)/Creatine complex(Cr), Choline complex (Cho)/Cr, and lactate (Lac)/Cr ratios were measured on the peak heights of each resonance and compared among the different tumors. Results: All intracranial solid tumors demonstrated decreased NAA, elevated Cho and lactate, and variable Cr levels. All tumors showed increased Cho/Cr and Lac/Cr, whereas NAA/Cr level was decreased. Mean Cho/Cr and Lac/Cr ratios were significantly higher in high-grade gliomas than in low-grade gliomas. However, NAA/Cr ratio showed no significant difference between low-grade and high-grade gliomas. Very high Cho peaks were seen in lymphomas, meningiomas, medulloblastomas, and neurocytomas in addition to high-grade gliomas. Conclusion: H-1 MRS may be useful in differentiating between low-grade and high-grade gliomas, however cannot characterize the histologic types or subtypes of tumors.

  • PDF