Learned Regularization for Sparse-View CT: Accuracy, Lesion Detectability and Distribution Shift of a Plug-and-Play Prior against Tuned Total Variation
Mohammed Abo Oraig
Abstract
Learned image priors are often proposed to replace hand-crafted regularizers in sparse-view computed tomography (CT), yet they are usually judged by PSNR on data resembling their training set. We evaluate one noise-conditioned DnCNN denoiser used as a Plug-and-Play prior against filtered back-projection (FBP), Tikhonov and total-variation (TV) regularization, with every method tuned on validation data and all differences paired. On synthetic 28x28 digit images, the prior beats box-constrained TV by about 3.4 dB at moderate noise (sigma = 0.05, 20 angles), but the advantage shrinks at low noise and reverses under distribution shift: an MNIST-trained prior is 3.1 dB (Fashion-MNIST) and 4.3-4.6 dB (Shepp-Logan phantom) below TV, whereas a Fashion-MNIST-trained prior beats TV by 2.2 dB on Fashion-MNIST, consistent with prior mismatch rather than a failure of PnP itself. In a lesion-insertion test the prior detects lesions worse than TV in distribution despite its higher PSNR, and under mismatch it produces more lesion-like false blobs than box-constrained TV for seven of eight lesion types. On real LoDoPaB-CT slices (patient-disjoint split; 30, 60 and 120 angles; three dose levels; 40 test patients), the prior does not consistently outperform a well-tuned TV in PSNR (-0.93 to +0.33 dB) and has lower SSIM in eight of nine conditions. Its lesion-detection AUC is higher than this TV's in all nine conditions (significant in six) but never significantly higher than that of Hann-filtered FBP, which the PSNR-tuned TV falls below in detection in all nine conditions (seven significant). On non-anatomical phantoms its PSNR falls below TV in all six conditions. PSNR and lesion detectability thus rank the methods differently. Our conclusions concern one small denoiser, and the CT analysis was developed after seeing results, without pre-specified primary comparisons.
Create a lesson
Related papers
AnyVIO: Feed-Forward Streaming Visual-Inertial Odometry Across Platforms
Omoruyi Atekha, Marcus Greiff, Ray Zhang et al.
Susceptibility source separation via Closed-form Alternating Newton-type Optimization
Ignacio Contreras-Zúñiga, Cristian Tejos, Carlos Milovic
Physics-Informed Deep Learning for Shear Wave Speed Estimation in MR Elastography
Stefan Martin, Jakob Schattenfroh, Patrick Schuenke et al.
LBW-NPS: A Local Band-Weighted Noise Power Spectrum Loss for Texture-Preserving Low-Dose CT Denoising
Fatma Elif Yalçındağ, Mehmet Ozan Ünal, Metin Ertaş et al.
Life-IQA+: Boosting Blind Image Quality Assessment via GCN-enhanced Layer Interaction and Flexible Hierarchical Expert Specialization
Long Tang, Guoquan Zheng, Huiyu Duan et al.
Uncertainty-Aware Multimodal Deep Learning for Prediction of Radiation-Induced Xerostomia in Head and Neck Cancer
Jin Yang, Tian Liu, Jose Penagaricano et al.