Segmentation of Liver Tumors in CT Scans Using Active Contour Models and Machine Learning

Liver tumor segmentation in CT scans plays a crucial role in cancer diagnosis and treatment planning. This paper proposes a novel methodology that integrates Active Contour Models (ACMs) with Convolutional Neural Networks (CNNs) for accurate and efficient segmentation of liver tumors. The approach leverages the feature learning capabilities of deep learning and the precise boundary detection of ACMs to achieve state-of-the-art segmentation results. Evaluation on the LiTS dataset demonstrates superior performance in terms of Dice Similarity Coefficient (DSC), Precision, Recall, and computation time. The proposed methodology offers a promising solution for improving clinical decision-making in liver cancer treatment.