Research Article
Performance Assessment of Deep Learning-Models for Kidney Tumor Segmentation using CT Images
@INPROCEEDINGS{10.1007/978-3-031-77075-3_11, author={Prudhvi Raj Budumuru and P. Murugapandiyan and Kalva Sri Rama Krishna}, title={Performance Assessment of Deep Learning-Models for Kidney Tumor Segmentation using CT Images}, proceedings={Cognitive Computing and Cyber Physical Systems. 5th EAI International Conference, IC4S 2024, Bhimavaram, India, April 5--7, 2024, Proceedings, Part-I}, proceedings_a={IC4S}, year={2025}, month={2}, keywords={Clinical diagnosis convolutional neural network (CNN) deep learning dice similarity coefficient (DSC) fully-automated image segmentation kidney tumor medical image semi-automated}, doi={10.1007/978-3-031-77075-3_11} }- Prudhvi Raj Budumuru
P. Murugapandiyan
Kalva Sri Rama Krishna
Year: 2025
Performance Assessment of Deep Learning-Models for Kidney Tumor Segmentation using CT Images
IC4S
Springer
DOI: 10.1007/978-3-031-77075-3_11
Abstract
As of Globocan-2020 statistics, more than 0.4 million new kidney cancer/tumor cases have been listed and 0.2 million deaths were aroused due to it across the world. Hence, Kidney tumor investigation and diagnosis is one of the prime cancer treatment processes in medical field. Manual identification of kidney tumor from clinical scan images such like CT and MRI may lead to affect the diagnosis process accuracy. Therefore, semi-automated and fully-automated methods have been developed tremendously since past decade by using image segmentation approaches, convolutional neural network (CNN) and deep learning models to locate the kidney cancer/tumor from medical images and these approaches helps the experts in clinical diagnosis process. Therefore, here a detailed comparative report in terms of dice similarity index score (DSC) has been presented on deep learning-based kidney cancer/tumor segmentation approaches made by various researchers.
