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
• ISSN: 1861-6410; 1861-6429; 1861-6429
• DOI: 10.1007/s11548-020-02221-z

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 millimeters (mm) in thickness have hindered the wide spread adaptation of this safe imaging modality. Limited field of view and manual data collection cause additional problems during US-based orthopedic procedures. In order to overcome these limitations various bone segmentation and registration methods have been developed. Acoustic bone shadow is an important image artifact used to identify the presence of bone boundaries in the collected US data. Information about bone shadow region can be used (1) to guide the orthopedic surgeon or clinician to a standardized diagnostic viewing plane with minimal artifacts, (2) as a prior feature to improve bone segmentation and registration. Method In this work, we propose a computational method, based on a novel generative adversarial network (GAN) architecture, to segment bone shadow images from in vivo US scans in real-time. We also show how these segmented shadow images can be incorporated, as a proxy, to a multi-feature guided convolutional neural network (CNN) architecture for real-time and accurate bone surface segmentation. Quantitative and qualitative evaluation studies are performed on 1235 scans collected from 27 subjects using two different US machines. Finally, we provide qualitative and quantitative comparison results against state-of-the-art GANs. Results We have obtained mean dice coefficient (± standard deviation) of 93 % ( ± 0.02 ) for bone shadow segmentation, showing that the method is in close range with manual expert annotation. Statistical significant improvements against state-of-the-art GAN methods (paired t -test p < 0.05 ) is also obtained. Using the segmented bone shadow features average bone localization accuracy of 0.11 mm ( ± 0.16 ) was achieved. Conclusions Reported accurate and robust results make the proposed method promising for various orthopedic procedures. Although we did not investigate in this work, the segmented bone shadow images could also be used as an additional feature to improve accuracy of US-based registration methods. Further extensive validations are required in order to fully understand the clinical utility of the proposed method.