An avoiding overlap method between acoustic shadow and organ for automated ultrasound diagnosis and treatment
Momoko MATSUYAMA, Norihiro Koizumi, Yu Nishiyama, Ryosuke Tsumura, Hiroyuki Tsukihara, Kazushi Numata · 2022 IEEE 11th Global Conference on Consumer Electronics (GCCE) · 2022
Ultrasound diagnosis and treatment have attracted attention because they are noninvasive and allow real-time observation of lesions. However, it is difficult to accurately estimate the location of the treatment area because of information loss due to acoustic shadows caused by the reflection of sound waves from hard tissues such as bone. In this study, we propose a probe manipulation method that uses deep learning to avoid overlap between organs and shadows for automated diagnosis.