#image reconstruction
10 resultsSPULTRA: Low-Dose CT Image Reconstruction with Joint Statistical and Learned Image Models
Siqi Ye, Saiprasad Ravishankar, Yong Long +1
The paper proposes SPULTRA, a low-dose CT reconstruction method that uses a shifted-Poisson likelihood with raw measurements and a data-driven regularizer based on a union of learn…
MC-ISTA-Net: Adaptive Measurement and Initialization and Channel Attention Optimization inspired Neural Network for Compressive Sensing
Nanyu Li, Cuiyin Liu
The paper proposes MC-ISTA-Net, a neural network for compressive sensing image reconstruction that learns adaptive measurement matrices, improves input initialization, and incorpor…
Optoacoustic Model-Based Inversion Using Anisotropic Adaptive Total-Variation Regularization
Shai Biton, Nadav Arbel, Gilad Drozdov +2
The paper proposes an adaptive anisotropic total‑variation regularization method for optoacoustic tomography that better preserves complex boundaries and improves image contrast co…
Review of Algorithms for Compressive Sensing of Images
Yoni Sher
The paper reviews classical compressive sensing algorithms for images, emphasizing total variation methods and evaluating their performance under realistic LiDAR noise to help begi…
Y-Net: A Hybrid Deep Learning Reconstruction Framework for Photoacoustic Imaging in vivo
Hengrong Lan, Daohuai Jiang, Changchun Yang +1
The paper introduces Y-Net, a hybrid convolutional neural network that jointly processes raw photoacoustic data and beamformed images to improve non‑iterative image reconstruction…
Learned backprojection for sparse and limited view photoacoustic tomography
Johannes Schwab, Stephan Antholzer, Markus Haltmeier
The paper introduces a machine‑learning approach that learns weight factors for filtered backprojection to improve photoacoustic image reconstruction when data are sparse or limite…
DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution
Shanshan Wang, Huitao Cheng, Leslie Ying +5
The paper introduces DeepcomplexMRI, a deep residual complex‑valued convolutional network that learns from multi‑channel MRI data to accelerate parallel MR image reconstruction whi…
Learning to Synthesize: Robust Phase Retrieval at Low Photon counts
Mo Deng, Shuai Li, Alexandre Goy +2
The paper introduces a "learning to synthesize" deep‑learning framework that separately processes low‑ and high‑frequency components and then combines them to achieve high‑resoluti…
DiamondGAN: Unified Multi-Modal Generative Adversarial Networks for MRI Sequences Synthesis
Hongwei Li, Johannes C. Paetzold, Anjany Sekuboyina +5
The paper presents DiamondGAN, a scalable multi‑modal generative adversarial network that can synthesize missing MRI sequences from arbitrary subsets of non‑aligned input modalitie…
Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks
Dong Liang, Jing Cheng, Ziwen Ke +1
The paper reviews deep learning approaches for reconstructing MRI images from undersampled k-space data, focusing on data‑driven, model‑driven, and integrated methods that combine…