Deep learning techniques for liver and liver tumor segmentation: A review
View/ Open
Publisher version (Check access options)
Check access options
Date
2022Author
Gul, SidraKhan, Muhammad Salman
Bibi, Asima
Khandakar, Amith
Ayari, Mohamed Arselene
Chowdhury, Muhammad E.H.
...show more authors ...show less authors
Metadata
Show full item recordAbstract
Liver and liver tumor segmentation from 3D volumetric images has been an active research area in the medical image processing domain for the last few decades. The existence of other organs such as the heart, spleen, stomach, and kidneys complicate liver segmentation and tumor identification task since these organs share identical properties in terms of shape, texture, and intensity values. Many automatic and semi-automatic techniques have been presented in recent years, in an attempt to establish a system for the reliable diagnosis and detection of liver illnesses, specifically liver tumors. With the evolution of deep learning techniques and their exceptional performance in the field of medical image processing, medical image segmentation in volumetric images using deep learning techniques has received a great deal of emphasis. The goal of this study is to provide an overview of the available deep learning approaches for segmenting liver and detecting liver tumors, as well as their evaluation metrics including accuracy, volume overlap error, dice coefficient, and mean square distance. This research also includes a detailed overview of the various 3D volumetric imaging architectures, designed specifically for the task of semantic segmentation. The comparison of approaches offered in earlier challenges for liver and tumor segmentation, as well as their dice scores derived from respective site sources, is also provided. 2022 Elsevier Ltd
Collections
- Civil and Environmental Engineering [850 items ]
- Electrical Engineering [2647 items ]
- Technology Innovation and Engineering Education Unit [63 items ]