Review of Semantic Segmentation of Medical Images Using Modified Architectures of UNET

• Published in: Diagnostics (Basel) Vol. 12; no. 12; p. 3064
• Main Authors: Krithika Alias AnbuDevi, M, Suganthi, K
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01-12-2022; MDPI
• Subjects: Brain research; CNN; CT imaging; Deep learning; Diagnostic imaging; dice similarity coefficient; Image segmentation; Medical imaging equipment; MRI; Neural networks; Review; semantic segmentation; Semantics; Technology application; UNET; India; dice similarity coefficient; CNN; semantic segmentation; MRI; UNET
• ISSN: 2075-4418; 2075-4418
• DOI: 10.3390/diagnostics12123064

In biomedical image analysis, information about the location and appearance of tumors and lesions is indispensable to aid doctors in treating and identifying the severity of diseases. Therefore, it is essential to segment the tumors and lesions. MRI, CT, PET, ultrasound, and X-ray are the different imaging systems to obtain this information. The well-known semantic segmentation technique is used in medical image analysis to identify and label regions of images. The semantic segmentation aims to divide the images into regions with comparable characteristics, including intensity, homogeneity, and texture. UNET is the deep learning network that segments the critical features. However, UNETs basic architecture cannot accurately segment complex MRI images. This review introduces the modified and improved models of UNET suitable for increasing segmentation accuracy.