• Harshavardhan Bammidi
• Rahul Gottimukkula
• Posanapally Venkat
• Dr. Pinamala Sruthi

Understanding the course of a disease is greatly aided by the automated segmentation of brain tumors from multimodal MR images, especially given the complexity of gliomas. Precise segmentation methods are crucial to address this problem by classifying tumors into intratumoral classes. When compared to conventional computer vision techniques, deep learning algorithms—most notably Convolutional Neural Networks (CNNs)—have proven superior in semantic segmentation tasks. In our research, we propose employing the U-Net architecture for brain tumor segmentation, a widely acknowledged and effective approach in biomedical image analysis. To evaluate the model's effectiveness, we assessed its performance across several key metrics, including accuracy, dice score, sensitivity, specificity, Intersection over Union (IoU), among others. These metrics provide a comprehensive understanding of the model's segmentation accuracy and robustness, enabling us to gauge its capability in accurately delineating tumor sub-regions and overall performance. By leveraging the U-Net architecture, our aim is to generate precise segmentation maps that capture the spatial distribution and characteristics of brain tumors across different modalities. Our study underscores the significance of harnessing advanced deep learning techniques to improve the accuracy and reliability of brain tumor segmentation, thereby facilitating enhanced clinical decision-making and patient care.

CNN, UNET, MRI, TUMOR

"Deep Learning for Precise Brain Tumor Segmentation from MRI Scans", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.d396-d401, April-2024, Available :http://www.jetir.org/papers/JETIR2404354.pdf

"Deep Learning for Precise Brain Tumor Segmentation from MRI Scans", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppd396-d401, April-2024, Available at : http://www.jetir.org/papers/JETIR2404354.pdf