NeuroVision : Brain Tumor Segmentation and 3D Visualization
Harsh Bharat Patel
, Vrunda Hitesh Patel , Mihir Kiranbhai Parmar , Dr. Jitendra Saturwar
Brain Tumor, UNET, BRATS, MRI, Segmentation, Visualization, Modalities, Dice Score.
Brain tumor segmentation plays a major role in medical image processing. Early diagnosis of brain tumors helps in improving treatment possibilities and increasing the survival rate of the patient. Segmenting brain tumors manually from large volumes of MRI Scans generated in medical routine can be time consuming. This leads to the need for an automatic brain tumor image segmentation system for smooth diagnosis. Brain tumor localization and segmentation from Magnetic Resonance Imaging(MRI) scans are hard and important tasks for several applications in the field of medical analysis. Each brain imaging modality gives unique and key details related to each part of the tumor. Many recent approaches used four modalities namely T1, T1c, T2, and FLAIR. NeuroVision is a flexible and effective Brain Tumor Segmentation and Visualization Web Application. This system uses a CNN-based UNET model for Brain Tumor Segmentation and exhibiting distinct tumor regions. Secondly, Python graphing libraries are used for visualizing different regions of tumors in a 2-D, 3-D, and 360-degree view. A medical report generated includes the tumor’s location inside the brain and percent occupancy of the tumor with respect to the brain. Comprehensive experiments are conducted on the BRATS 2020 dataset and show that the proposed model obtains competitive results. The proposed method achieves a mean whole tumor, enhancing tumor, and tumor core dice scores of 88.3%, 75.3%, and 79.0% respectively.
"NeuroVision : Brain Tumor Segmentation and 3D Visualization", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.7, Issue 4, page no.611-617, April-2022, Available :https://ijnrd.org/papers/IJNRD2204070.pdf
Volume 7
Issue 4,
April-2022
Pages : 611-617
Paper Reg. ID: IJNRD_180932
Published Paper Id: IJNRD2204070
Downloads: 000118868
Research Area: Engineering
Country: -, -, -
ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJNRD (IJ Publication) Janvi Wave
