A Jointed Feature Fusion Framework for Photoacoustic Reconstruction
This work provides an incremental improvement in photoacoustic image reconstruction for medical imaging, specifically for scenarios with limited-view data.
This paper addresses the problem of reconstructing photoacoustic images from limited-view data, which typically suffer from artifacts due to ill-posed setups. The proposed JEFF-Net framework, using a quarter of the data (32 channels), successfully reconstructs the full-view image (96 channels) with drastically reduced artifacts, outperforming ground-truth in some quantitative metrics.
Photoacoustic (PA) computed tomography (PACT) reconstructs the initial pressure distribution from raw PA signals. The standard reconstruction of medical image could cause the artifacts due to interferences or ill-posed setup. Recently, deep learning has been used to reconstruct the PA image with ill-posed conditions. Most works remove the artifacts from image domain, and compensate the limited-view from dataset. In this paper, we propose a jointed feature fusion framework (JEFF-Net) based on deep learning to reconstruct the PA image using limited-view data. The cross-domain features from limited-view position-wise data and the reconstructed image are fused by a backtracked supervision. Specifically, our results could generate superior performance, whose artifacts are drastically reduced in the output compared to ground-truth (full-view reconstructed result). In this paper, a quarter position-wise data (32 channels) is fed into model, which outputs another 3-quarters-view data (96 channels). Moreover, two novel losses are designed to restrain the artifacts by sufficiently manipulating superposed data. The numerical and in-vivo results have demonstrated the superior performance of our method to reconstruct the full-view image without artifacts. Finally, quantitative evaluations show that our proposed method outperformed the ground-truth in some metrics.