pCoRev: Physics-Informed Contrastive Learning for Unsupervised Reverberation Artifact Suppression in Ultrafast Plane-Wave Imaging

Abstract

Reverberation artifact suppression in ultrafast plane-wave (PW) imaging remains challenging because artifact-free reference data are generally unavailable and multipath echoes often resemble tissue signals. Coherent plane-wave compounding (CPWC) attenuates reverberation only partially and sacrifices the frame rate that motivates PW imaging. We propose pCoRev, an unsupervised physics-informed contrastive learning framework that leverages the distinct angular coherence characteristics of tissue echoes and reverberation artifacts. A single-angle I/Q frame is the network input, and the remaining angles of the same CPWC acquisition provide angle-consistent positive pairs, residual-derived negative pairs, and coherence-guided self-supervision, so no paired artifact-free data are required. On a fabricated reverberation phantom with 31 validation acquisitions, pCoRev achieved the best contrast ratio (CR), contrast-to-noise ratio (CNR), and generalized CNR (gCNR) of 38.76 +/- 5.40 dB, 11.75 +/- 1.81 dB, and 0.932 +/- 0.051 against delay-and-sum (DAS), delay-multiply-and-sum, a supervised 3D convolutional neural network, and unsupervised deep coherence learning. Because the network is trained on single-angle inputs, it also operates on a single PW transmission: with one angle, pCoRev reached a CR of 32.10 +/- 7.79 dB and a CNR of 10.39 +/- 3.02 dB, exceeding 75-angle compounded DAS (20.45 +/- 3.84 dB and 8.38 +/- 2.00 dB) with 75-fold fewer transmissions. On four clinical acquisitions from other scanners, pCoRev improved CR over DAS by 9 to 21 dB without fine-tuning. These results indicate that physics-informed unsupervised contrastive learning suppresses reverberation effectively while preserving the frame-rate advantage of ultrafast PW imaging.