Accurate segmentation and volume estimation of kidney tumors in computed tomography (CT) images are crucial for effectize diagnosis and treatment planning. This review explores a deep learning-based framework designed specifically for the automated segmentation of kidney tumors and subsequent volume calculation. The proposed model employs convolutional neural network (CNN) architecture with multiple layers optimized for image segmentation tasks. The architecture integrates various preprocessing techniques to enhance image quality, such as noise reduction and normalization, which improve the model’s ability to distinguish tumor boundaries. Following segmentation, the system employs a three-dimensional reconstruction algorithm to calculate the tumor volume, which aids in assessing the tumor’s growth and treatment response. Through comparative analysis with existing segmentation techniques, this paper identifies the advantages of deep learning in achieving higher accuracy and robustness. The findings demonstrate the model’s potential in clinical applications, offering a reliable, automated approach to kidney tumor analysis on CT scans.