8 papers
Enabling self-supervised learned primal dual with Noise2Inverse
Antti Sällinen, Siiri Rautio, Santeri Kaupinmäki +1
X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are noisy and incomplete. While lear…
QVaR: a Quantum Variational Regularization method for Linear Inverse Problems
Siiri Rautio, Hjørdis Schlüter, Andreas Hauptmann +1
We present a tailored framework for solving regularized linear inverse problems using quantum optimization methods. By discretizing the solution space and encoding data fidelity an…
Complex Wavelet-Based Sinogram Segmentation for Metal Artifact Reduction in Cone-Beam CT
Siiri Rautio, Alexander Meaney, Salla-Maaria Latva-Äijö +4
Metal objects pose a significant challenge in cone-beam computed tomography, as their strong and energy-dependent X-ray attenuation leads to inconsistent projections and severe str…
Learned enclosure method for experimental EIT data
Sara Sippola, Siiri Rautio, Andreas Hauptmann +2
Electrical impedance tomography (EIT) is a non-invasive imaging method with diverse applications, including medical imaging and non-destructive testing. The inverse problem of reco…
Stroke classification using Virtual Hybrid Edge Detection from in silico electrical impedance tomography data
Juan Pablo Agnelli, Fernando S. Moura, Siiri Rautio +4
Electrical impedance tomography (EIT) is a non-invasive imaging method for recovering the internal conductivity of a physical body from electric boundary measurements. EIT combined…
CT scans without X-rays: parallel-beam imaging from nonlinear current flows
Melody Alsaker, Siiri Rautio, Fernando Moura +5
Parallel-beam X-ray computed tomography (CT) and electrical impedance tomography (EIT) are two imaging modalities which stem from completely different underlying physics, and for d…
Bilevel learning of regularization models and their discretization for image deblurring and super-resolution
Tatiana A. Bubba, Luca Calatroni, Ambra Catozzi +6
Bilevel learning is a powerful optimization technique that has extensively been employed in recent years to bridge the world of model-driven variational approaches with data-driven…
Learning a microlocal prior for limited-angle tomography
Siiri Rautio, Rashmi Murthy, Tatiana A. Bubba +2
Limited-angle tomography is a highly ill-posed linear inverse problem. It arises in many applications, such as digital breast tomosynthesis. Reconstructions from limited-angle data…