Bone shadow segmentation from ultrasound data for orthopedic surgery using GAN

• Published in: International journal for computer assisted radiology and surgery Vol. 15; no. 9; pp. 1477 - 1485
• Main Authors: Alsinan, Ahmed Z., Patel, Vishal M., Hacihaliloglu, Ilker
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.09.2020; Springer Nature B.V
• Subjects: Acoustic noise; Acoustics; Algorithms; Annotations; Artifact identification; Artificial neural networks; Bone and Bones - diagnostic imaging; Bone Diseases - diagnostic imaging; Bone surgery; Computer Imaging; Computer Science; Computer Simulation; Data collection; Diagnosis, Computer-Assisted - methods; Diagnostic systems; Field of view; Fluoroscopy; Generative adversarial networks; Health Informatics; Humans; Image Processing, Computer-Assisted; Image segmentation; Imaging; Imaging, Three-Dimensional - methods; In vivo methods and tests; Medicine; Medicine & Public Health; Methods; Neural Networks, Computer; Original Article; Orthopedic Procedures; Orthopedics; Pattern Recognition and Graphics; Radiology; Real time; Registration; Reproducibility of Results; Shadows; Signal to noise ratio; Surgery; Ultrasonic imaging; Ultrasonography; Ultrasound; Vision; Deep learning; Orthopedic surgery; Bone; Segmentation; Ultrasound; Generative adversarial network

Purpose Real-time, two (2D) and three-dimensional (3D) ultrasound (US) has been investigated as a potential alternative to fluoroscopy imaging in various surgical and non-surgical orthopedic procedures. However, low signal to noise ratio, imaging artifacts and bone surfaces appearing several millime...