Vol. 5, Issue 1, Part A (2023)

The segmentation of the liver in medical imaging is a crucial step in diagnosing and treating various hepatic diseases. Traditional manual segmentation is time-consuming and subject to inter-observer variability. This study explores the application of machine learning techniques, particularly convolutional neural networks (CNNs), for automated liver segmentation from computed tomography (CT) and magnetic resonance imaging (MRI) scans. The proposed method is evaluated on a large dataset of liver images, achieving high accuracy and efficiency. We present a detailed comparison of different machine learning models, focusing on their performance in terms of segmentation accuracy, computational time, and robustness.