Deep learning has been extensively applied to segmentation in medical imaging. U-Net proposed in 2015 shows the advantages of accurate segmentation of small targets and its scalable network architecture. With the increasing requirements for the performance of segmentation in medical imaging in recent years, U-Net has been cited academically more than 2500 times. Many scholars have been constantly developing the U-Net architecture. This paper summarizes the medical image segmentation technologies based on the U-Net structure variants concerning their structure, innovation, efficiency, etc.; reviews and categorizes the related methodology; and introduces the loss functions, evaluation parameters, and modules commonly applied to segmentation in medical imaging, which will provide a good reference for the future research.
6 January 2022 in Artificial Intelligence in Medicine
Terahertz (THz)-band (0.1~10 THz) communications are celebrated to be a crucial enabling technology for sixth generation (6G) wireless systems that fulfil the stringent requirements of future healthcare scenarios. Broadband THz sources have drawn the attention of researchers by virtue of their prominent detectability and their noninvasive and non-ionization properties. More importantly, the most advanced wideband THz sources enable THz communication in vivo with many appealing properties, including potential link capacities (terabit-per-second), miniature transceivers, and high energy efficiency. Compared to conventional devices, nano-scale devices will be potentially pivotal in subsequent medical diagnostics and treatment technologies, by virtue of the non-ionizing property of THz light and its high sensitivity in conveniently reaching delicate body sites. Thereby, real-time, label-free detection methods are expected to perform a crucial effect in clinical practice; however, difficulties such as unknown biological safety still need to be overcome. With channel modeling progress of the THz frequencies, we have considered both the radiation of the medium and the molecular absorption from the transmitted signal, and envisoned the possibility to solve the challenges such as the spectrum scarcity and capacity limitation.