Low-dose sparse-view HAADF-STEM-EDX tomography of nanocrystals using unsupervised deep learning

Unsupervised deep learning enables low-dose extreme sparse view HAADF-STEM-EDX tomography reconstruction.

Deep Learning Model for Diagnosing Gastric Mucosal Lesions Using Endoscopic Images: Development, Validation, and Method Comparison

AI model for accurate classification of the mucosal lesion along with depth preidction using a single endoscopic image was proposed. Results show that the developed model is on par with or even exceeds performance of practiced experts.

Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement

Thorough review on unsupervised deep learning methods including self-supervised methods and generative model-based methods for biological image reconstruction and enhancement is provided.

Deep learning STEM-EDX tomography of nanocrystals

Resolution of STEM-EDX tomography is greatly enhanced through unsupervised deep learning. We verified the method by comparing the optical properties.

Unpaired deep learning for accelerated MRI using optimal transport driven cycleGAN

A novel unpaired learning scheme for accelerated MRI, OT-cycleGAN was extensively applied and was found effective for the reconstruction of multi-coil static MRI.

Unpaired training of deep learning tMRA for flexible spatio-temporal resolution

OT-cycleGAN for the reconstruction of time resolved magnetic resonance angiography (MRA) was proposed. The derived method enables flexible control of sptial and temporal resolution.

Feature Disentanglement in generating three-dimensional structure from two-dimensional slice with sliceGAN

SliceGAN, stochastic model to synthesize 3D microstructures from 2D images, is endowed with the ability to disentangle features, and continuously control these features via AdaIN.

Two-Stage Deep Learning for Accelerated 3D Time-of-Flight MRA without Matched Training Data

Two-stage unsupervised reconstruction method for 3D TOF-MRA is developed. A novel projection discriminator in the axial reconstruction step drastically enhances the vessel visiblity.

Deep Learning Fast MRI Using Channel Attention in Magnitude Domain

BarbellNet, which consists of long stack of residual channel attention block(RCAB) was proposed for the reconstruction of fast MRI reconstruction. Reconstruction results through this model was placed 6th in the NeurIPS2020 fastMRI challenge.

Missing Cone Artifacts Removal in ODT using Unsupervised Deep Learning in Projection Domain

Unsupervised missing-cone resolving method is proposed in the context of ODT.