• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1233-1241
• /
• 2022

Tumors of the brain are the deadliest, with a life expectancy of only a few years for those with the most advanced forms. Diagnosing a brain tumor is critical to developing a treatment plan to help patients with the disease live longer. A misdiagnosis of brain tumors will lead to incorrect medical treatment, decreasing a patient's chance of survival. Radiologists classify brain tumors via biopsy, which takes a long time. As a result, the doctor will need an automatic classification system to identify brain tumors. Image classification is one application of the deep learning method in computer vision. One of the deep learning's most powerful algorithms is the convolutional neural network (CNN). This paper will introduce a novel deep learning structure and image gradient to classify brain tumors. Meningioma, glioma, and pituitary tumors are the three most popular forms of brain cancer represented in the Figshare dataset, which contains 3,064 T1-weighted brain images from 233 patients. According to the numerical results, our method is more accurate than other approaches.

• Journal of Veterinary Clinics
• /
• v.9 no.2
• /
• pp.457-466
• /
• 1992

An 11 years old Irish Setter bitch was euthanlzed and necropsied because of clinical findings such as severe purulent nasal discharge and formation of large tumor mass, 8 ${\times}$8cm in size, in the abdominal cavity. A complete unilateral mastectomy had been carried out twice 14 and 22 months before necropsy. The surgically removed masess of the mammary glands had been diagnosed as malignant mixed tumor in each time. Grossly, tumor masses were observed in nasal cavity, infralumbar lymph node, lung, abdominal cavityn and brain. Microscopic findings of the surgically removed masses consisted of tumor epithelial cells, tumor hyaline cartilage-like structures and abundant connective tissues. The mass of the lymph node had similar microscopic features to those of the original malignant mixed tumor of the mammary glands. The tumor osseous tissue and osteoid were observed in the abdominal cavity, lung, and brain. Myoepithelial cells were frequently found on association with the metastatic tumors. From the results, it was concluded that malignant mixed tumor of the mammary glands metastasized to the infralunbar lymph node, abdominal cavity, lung and brain. In addition, the observation in this study supported two theories at the same time that the bone in malignant mixed tumor arises by endochondral ossification of the cartilage formed by the myoepithelial cells and arises by intramembranous ossification of stromal connective tissue or transformed myeopithelial cells. Solid carcinoma of the nasal epielia and granulosa cell tumor were also diagnosed in a mass of the nasal cavity and of the ovaries respectively.

• THE JOURNAL OF KOREAN ORIENTAL ONCOLOGY
• /
• v.5 no.1
• /
• pp.151-158
• /
• 1999

We have experienced a case of metastatic brain tumor originated from lung cancer treated by oriental medicine (Herbal medication, Acupuncture therapy, Moxa therapy) and We have a good result from that case to report it. According to the therapentic effects, it could be suggeted that Younggyaechulgamtanggagambang extracts and oriental medical symptomatic treatment were significant in improvement of the patient.

• Journal of Korean Neurosurgical Society
• /
• v.39 no.2
• /
• pp.136-140
• /
• 2006

The authors report three microcystic meningiomas with its characteristic immunohistochemical findings and chromosomal pattern. Three patients with surgically treated microcystic meningioma were studied for its radiological, histopathological findings, and chromosomal analysis was done in the one patient. Tumors were convexity meningioma in the frontal area. The tumors were enhanced homogenously in the two, and enhanced in homogenously with multiple small cysts in the other one on preoperative magenetic resonance image. Pathological examination showed marked nuclear pleomorphism, many small cysts, hyaline thickening in blood vessel wall, and mucinous background, compatable to microcystic type. EMA and vimentin were positive on the immunohistochemical stain. Chromosomal analysis showed tetrasomies of chromosome 5, 13, 17, and 20, and trisomies of chromosome 6, 7, 9, 11, 12, 16, 19, and 21, which are quite different from those of benign meningioma.

• Journal of Korean Neurosurgical Society
• /
• v.39 no.4
• /
• pp.306-309
• /
• 2006

Ectopic pituitary adenoma, occurring outside the sella turcica without any continuity with intrasellar pituitary gland is very rare. So far, less than 90 such cases have been reported in the literature. Regarding to ectopic locations, suprasellar region, sphenoid sinus and clivus have been reported in decending order of frequency. To our best knowledge, growth hormone-secreting ectopic pituitary adenoma in the clivus has never been reported. With the pertinent literature review, we present our unique case with its characteristic magnetic resonance imaging and immunohistochemical features.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2788-2808
• /
• 2023

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.

• Journal of Korean Neurosurgical Society
• /
• v.59 no.2
• /
• pp.106-116
• /
• 2016

Objective : Protein disulfide isomerase (PDI) acts as a chaperone on the cell surface, and it has been reported that PDI is associated with the tumor cell migration and invasion. The aims of this study are to investigate the anti-migration effect of bacitracin, which is an inhibitor of PDI, and the associated factor in this process. Methods : U87-MG glioma cells were treated with bacitracin in 1.25, 2.5, 3.75, and 5.0 mM concentrations. Western blot with caspase-3 was applied to evaluate the cytotoxicity of bacitracin. Adhesion, morphology, migration assays, and organotypic brain-slice culture were performed to evaluate the effect of bacitracin to the tumor cell. Western blot, PCR, and gelatin zymography were performed to investigate the associated factors. Thirty glioma tissues were collected following immunohistochemistry and Western blot. Results : Bacitracin showed a cytotoxicity in 3rd (p<0.05) and 4th (p<0.001) days, in 5.0 Mm concentration. The cell adhesion significantly decreased and the cells became a round shape after treated with bacitracin. The migration ability, the expression of phosphorylated focal adhesion kinase (p-FAK) and matrix metalloproteinase-2 (MMP-2) decreased in a bacitracin dose- and time-dependent manner. The U87-MG cells exhibited low-invasiveness in the 2.5 mM, compared with the untreated in organotypic brain-slice culture. PDI was expressed in the tumor margin, and significantly increased with histological glioma grades (p<0.001). Conclusion : Bacitracin, as a functional inhibitor of PDI, decreased the phosphorylated FAK and the secreted MMP-2, which are the downstream of integrin and play a major role in cell migration and invasion, might become one of the feasible therapeutic strategies for glioblastoma.

• Journal of Korean Neurosurgical Society
• /
• v.48 no.1
• /
• pp.20-30
• /
• 2010

Objective : We determined whether the expression of GRIM-19 is correlated with pathologic types and malignant grades in gliomas, and determined the function of GRIM-19 in human gliomas. Methods : Tumor tissues were isolated and frozen at $-80^{\circ}C$ just after surgery. The tissues consisted of normal brain tissue (4), astrocytomas (2), anaplastic astrocytomas (2), oligodendrogliomas (13), anaplastic oligodendrogliomas (11), and glioblastomas (16). To profile tumor-related genes, we applied RNA differential display using a $Genefishing^{TM}$ DEG kit, and validated the tumor-related genes by reverse transcription polymerase chain reaction (RT-PCR). A human glioblastoma cell line (U343MG-A) was used for the GRIM-19 functional studies. The morphologic and cytoskeletal changes were examined via light and confocal microscopy. The migratory and invasive abilities were investigated by the simple scratch technique and Matrigel assay. The antiproliferative activity was determined by thiazolyl blue Tetrazolium bromide (MTT) assay and FACS analysis. Results : Based on RT-PCR analysis, the expression of GRIM-19 was higher in astrocytic tumors than oligodendroglial tumors. The expression of GRIM-19 was higher in high-grade tumors than low-grade tumors or normal brain tissue; glioblastomas showed the highest expression. After transfection of GRIM-19 into U343MG-A, the morphology of the sense-transfection cells became larger and more spindly. The antisensetransfection cells became smaller and rounder compared with wild type U343MG-A. The MTT assay showed that the sense-transfection cells were more sensitive to the combination of interferon-$\beta$ and retinoic acid than U343MG-A cells or antisense-transfection cells; the antiproliferative activity was related to apoptosis. Conclusion : GRIM-19 may be one of the gene profiles which regulate cell death via apoptosis in human gliomas.

• Investigative Magnetic Resonance Imaging
• /
• v.9 no.1
• /
• pp.2-8
• /
• 2005

Purpose : The purpose of this study was to implement a software to visualize tumor and its surrounding fiber tracts simultaneously using diffusion tensor imaging and examine the feasibility of our software for investigating the influence of tumor on its surrounding fiber connectivity. Material and Methods : MR examination including T1-weigted and diffusion tensor images of a patient with brain tumor was performed on a 3.0 T MRI unit. We used the skull-striped brain and segmented tumor images for volume/surface rendering and anatomical information from contrast-enhanced T1-weighted images. Diffusion tensor images for the white matter fiber-tractography were acquired using a SE-EPI with a diffusion scheme of 25 directions. Fiber-tractography was performed using the streamline and tensorline methods. To correct a spatial mismatch between T1-weighted and diffusion tensor images, they were coregistered using a SPM. Our software was implemented under window-based PC system. Results : We successfully implemented the integrated visualization of the fiber tracts with tube-like surfaces, cortical surface and the tumor with volume/surface renderings in a patient with brain tumor. Conclusion : Our result showed the feasibility of the integrated visualization of brain tumor and its surrounding fiber tracts. In addition, our implementation for integrated visualization can be utilized to navigate the brain for the quantitative analysis of fractional anisotropy to assess changes in the white matter tract integrity of edematic and peri-edematic regions in a number of tumor patients.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.1
• /
• pp.100-106
• /
• 2004

In this paper, we present a novel, rapid approach for the detection of brain tumors and deformity boundaries in medical images using a genetic algorithm with wavelet based preprocessing. The contour detection problem is formulated as an optimization process that seeks the contour of the object in a manner of minimizing an energy function based on an active contour model. The brain tumor segmentation contour, however, cannot be detected in case that a higher gradient intensity exists other than the interested brain tumor and deformities. Our method for discerning brain tumors and deformities from unwanted adjacent tissues is proposed. The proposed method can be used in medical image analysis because the exact contour of the brain tumor and deformities is followed by precise diagnosis of the deformities.