Multi-parameter ultrasound imaging for musculoskeletal tissues based on a physics informed generative adversarial network

Abstract Full waveform inversion (FWI) has showed great potential in the detection of musculoskeletal disease. However, FWI is an ill-posed inverse problem and has a high requirement on the initial model during the imaging process. An inaccurate initial model may lead to local minima in the inversion and unexpected imaging results caused by cycle-skipping phenomenon. Deep learning methods have been applied in musculoskeletal imaging, but need a large amount of data for training. Inspired by work related to generative adversarial networks with physical informed constrain, we proposed a method named as bone ultrasound imaging with physics informed generative adversarial network (BUIPIGAN) to achieve unsupervised multi-parameter imaging for musculoskeletal tissues, focusing on speed of sound (SOS) and density. In the in-silico experiments using a ring array transducer, conventional FWI methods and BUIPIGAN were employed for multi-parameter imaging of two musculoskeletal tissue models. The results were evaluated based on visual appearance, structural similarity index measure (SSIM), signal-to-noise ratio (SNR), and relative error (RE). For SOS imaging of the tibia–fibula model, the proposed BUIPIGAN achieved accurate SOS imaging with best performance. The specific quantitative metrics for SOS imaging were SSIM 0.9573, SNR 28.70 dB, and RE 5.78%. For the multi-parameter imaging of the tibia–fibula and human forearm, the BUIPIGAN successfully reconstructed SOS and density distributions with SSIM above 94%, SNR above 21 dB, and RE below 10%. The BUIPIGAN also showed robustness across various noise levels (i.e., 30 dB, 10 dB). The results demonstrated that the proposed BUIPIGAN can achieve high-accuracy SOS and density imaging, proving its potential for applications in musculoskeletal ultrasound imaging.