Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper explores the use of Deep Image Prior (DIP) for photoacoustic tomography (PAT) reconstruction, specifically to address artifacts arising from limited-view geometries and noise. They implemented DIP with fast forward/adjoint algorithms for circular geometries, initialized with a fast inverse and TV regularization. Results demonstrate that DIP outperforms classical TV regularization in both simulated and experimental PAT measurements, offering a robust unsupervised reconstruction strategy.
DIP offers a surprisingly effective, unsupervised route to high-quality photoacoustic tomography, even when data is severely limited by noisy, incomplete measurements.
We study the deep image prior (DIP) framework applied to photoacoustic tomography (PAT) as an unsupervised reconstruction approach to mitigate limited-view artifacts and noise commonly encountered in experimental settings. Efficient implementation is achieved by employing recently published fast forward and adjoint algorithms for circular measurement geometries. Initialization via a fast inverse and total variation (TV) regularization are applied to further suppress noise and mitigate overfitting. For comparison, we compute a classical TV reconstruction. Our experiments comprise simulated PAT measurements under limited-view geometries and varying levels of added noise as well as experimental measurements together with using a digital twin for quality assessment. Our findings suggest that DIP framework provides an effective unsupervised strategy for robust PAT reconstruction even in the challenging case of a limited view geometry providing improvement in several quantitative measures over total variation reconstructions.