Paper Title
A DEEP LEARNING MODEL FOR MEDICAL IMAGE SEGMENTATION USING U-NET

Abstract
Recent advancements in deep learning have revolutionized medical image segmentation. Notably, the U-Net architecture, introduced in 2015, has demonstrated exceptional capabilities in accurately segmenting even small structures, while its design allows for easy adaptation to various tasks. Medical image segmentation is an essential tool in healthcare, aiding in clinical decision-making, treatment planning, and accurate diagnoses. This review delves into the various techniques used for medical image segmentation, exploring their methodologies, limitations, and recent advancements. We will examine different medical imaging modalities like MRI, CT, and ultrasound, while summarizing the current state-of-the-art segmentation methods, encompassing both traditional approaches and cutting-edge deep learning techniques. Finally, we will discuss the challenges inherent to medical image segmentation and explore potential areas for future research and development in this critical field. Keywords – Deep Learning, U-Net, Medical Image Segmentation, CNN, FCN, Neural Network