Dual-Domain Self-Supervised Artifact Removal Framework for Photoacoustic Computed Tomography
For PACT imaging, this work provides an artifact removal method that is self-supervised and computationally efficient, but it is an incremental improvement over existing artifact reduction techniques.
This paper addresses reconstruction artifacts in photoacoustic computed tomography (PACT) caused by sparse detection. The proposed self-supervised framework, using a Siamese network and composite loss, significantly suppresses artifacts across simulations, phantoms, and in vivo data, while achieving high computational efficiency.
Photoacoustic Computed Tomography (PACT) often faces severe challenges from reconstruction artifacts due to sparse detection conditions. In this work, based on the distinct differences in artifact patterns between back-projection-based and Fourier-based reconstruction algorithms, we propose a self-supervised artifact removal framework that employs a lightweight Siamese Neural Network and a composite loss function integrating cross-domain fidelity and uncertainty-weighted consistency, effectively decoupling dual-domain features and filtering artifacts. Comprehensive validations using simulations, phantoms, in vivo rat and human experimental data demonstrate that the proposed method can significantly suppress image artifacts. Furthermore, enabled by the acceleration of the spatial-domain and frequency-domain inverse operator, this end-to-end approach also achieves exceptional computational efficiency.