AAR-Net:a deep neural network for photoacoustic image reconstruction in heterogeneous acoustic media
Photoacoustic imaging suffers from degraded image quality owing to distorted and attenuated ultrasound waves propagating in an acoustic attenuating medium,phase deviation caused by changes in sound speed,and signal broadening related to acoustic attenuation.To address this issue,a deep learning method is proposed to reconstruct pho-toacoustic images of acoustically heterogeneous medium.A deep neural network is constructed,named acoustic arti-facts removal network(AAR-Net)by combining deep gradient descent(DGD)network with U-Net.The DGD module aims to achieve the conversion from signal domain to image domain,which uses the gradient information to reduce the impact of heterogeneous acoustic properties on reconstructed image quality.U-Net module aims to optimize low-qual-ity images output by the DGD module and realize the image-to-image conversion.The simulation,phantom and in vivo studies show that the proposed method outperforms traditional non-learning methods and the state-of-the-art post-pro-cessing based deep learning method.The image similarity and peak signal-to-noise ratio obtained by this method are im-proved by about 20%and 10%,respectively.AAR-Net enables reconstruction of high-quality images without any prior knowledge of acoustic properties of imaging objects.
国家科技期刊平台
NSTL
万方数据
