Search Results for author:
Found 37 papers, 13 papers with code
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning
Thanks to our variable discretization, the embedding features optimized by IMSVD offer unique explainability at the variable level.
Development and Validation of a Dynamic-Template-Constrained Large Language Model for Generating Fully-Structured Radiology Reports
Current LLMs for creating fully-structured reports face the challenges of formatting errors, content hallucinations, and privacy leakage issues when uploading data to external servers. We aim to develop an open-source, accurate LLM for creating fully-structured and standardized LCS reports from varying free-text reports across institutions and demonstrate its utility in automatic statistical analysis and individual lung nodule retrieval.
3D Photon Counting CT Image Super-Resolution Using Conditional Diffusion Model
This study aims to improve photon counting CT (PCCT) image resolution using denoising diffusion probabilistic models (DDPM).
Deep Few-view High-resolution Photon-counting Extremity CT at Halved Dose for a Clinical Trial
Despite the success of deep learning methods for 2D few-view reconstruction, applying them to HR volumetric reconstruction of extremity scans for clinical diagnosis has been limited due to GPU memory constraints, training data scarcity, and domain gap issues.
Low-dose CT Denoising with Language-engaged Dual-space Alignment
While various deep learning methods were proposed for low-dose computed tomography (CT) denoising, they often suffer from over-smoothing, blurring, and lack of explainability.
Photon-counting CT using a Conditional Diffusion Model for Super-resolution and Texture-preservation
Ultra-high resolution images are desirable in photon counting CT (PCCT), but resolution is physically limited by interactions such as charge sharing.
IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models
Second, we fine-tune the image quality captioning VLM on the CT-IQA dataset to generate quality descriptions.
Diffusion Prior Regularized Iterative Reconstruction for Low-dose CT
Computed tomography (CT) involves a patient's exposure to ionizing radiation.
Head-Neck Dual-energy CT Contrast Media Reduction Using Diffusion Models
Iodinated contrast media is essential for dual-energy computed tomography (DECT) angiography.
Specialty-Oriented Generalist Medical AI for Chest CT Screening
Modern medical records include a vast amount of multimodal free text clinical data and imaging data from radiology, cardiology, and digital pathology.
Parallel Diffusion Model-based Sparse-view Cone-beam Breast CT
Specifically, in this study we transform the cutting-edge Denoising Diffusion Probabilistic Model (DDPM) into a parallel framework for sub-volume-based sparse-view breast CT image reconstruction in projection and image domains.
Translating Radiology Reports into Plain Language using ChatGPT and GPT-4 with Prompt Learning: Promising Results, Limitations, and Potential
The large language model called ChatGPT has drawn extensively attention because of its human-like expression and reasoning abilities.
LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and Deblurring
Here, we propose to link in-plane and through-plane transformers for simultaneous in-plane denoising and through-plane deblurring, termed as LIT-Former, which can efficiently synergize in-plane and through-plane sub-tasks for 3D CT imaging and enjoy the advantages of both convolution and transformer networks.
QS-ADN: Quasi-Supervised Artifact Disentanglement Network for Low-Dose CT Image Denoising by Local Similarity Among Unpaired Data
Deep learning has been successfully applied to low-dose CT (LDCT) image denoising for reducing potential radiation risk.
Quad-Net: Quad-domain Network for CT Metal Artifact Reduction
Here we extend the state-of-the-art dual-domain deep network approach into a quad-domain counterpart so that all the features in the sinogram, image, and their corresponding Fourier domains are synergized to eliminate metal artifacts optimally without compromising structural subtleties.
HOME: High-Order Mixed-Moment-based Embedding for Representation Learning
Minimum redundancy among different elements of an embedding in a latent space is a fundamental requirement or major preference in representation learning to capture intrinsic informational structures.
Self-Supervised Representation Learning With MUlti-Segmental Informational Coding (MUSIC)
Self-supervised representation learning maps high-dimensional data into a meaningful embedding space, where samples of similar semantic contents are close to each other.
Unsupervised Contrastive Learning based Transformer for Lung Nodule Detection
To effectively train the transformer model on a relatively small dataset, the region-based contrastive learning method is used to boost the performance by pre-training the 3D transformer with public CT images.
X-ray Dissectography Improves Lung Nodule Detection
Although radiographs are the most frequently used worldwide due to their cost-effectiveness and widespread accessibility, the structural superposition along the x-ray paths often renders suspicious or concerning lung nodules difficult to detect.
Convolutional Neural Network to Restore Low-Dose Digital Breast Tomosynthesis Projections in a Variance Stabilization Domain
To accurately control the network operation point, in terms of noise and blur of the restored image, we propose a loss function that minimizes the bias and matches residual noise between the input and the output.
X-ray Dissectography Enables Stereotography to Improve Diagnostic Performance
X-ray imaging is the most popular medical imaging technology.
Phase function estimation from a diffuse optical image via deep learning
The phase function is a key element of a light propagation model for Monte Carlo (MC) simulation, which is usually fitted with an analytic function with associated parameters.
Stationary Multi-source AI-powered Real-time Tomography (SMART)
The reconstructed volumetric images convincingly demonstrate the merits of the SMART system using the AI-empowered interior tomography approach, enabling cardiac micro-CT with the unprecedented temporal resolution of 30ms, which is an order of magnitude higher than the state of the art.
AI-Enabled Ultra-Low-Dose CT Reconstruction
By the ALARA (As Low As Reasonably Achievable) principle, ultra-low-dose CT reconstruction is a holy grail to minimize cancer risks and genetic damages, especially for children.
Task-Oriented Low-Dose CT Image Denoising
The extensive use of medical CT has raised a public concern over the radiation dose to the patient.
Image Synthesis for Data Augmentation in Medical CT using Deep Reinforcement Learning
Deep learning has shown great promise for CT image reconstruction, in particular to enable low dose imaging and integrated diagnostics.
SPICE: Semantic Pseudo-labeling for Image Clustering
In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy.
Ranked #2 on
Image Clustering
on ImageNet-10
Noise Entangled GAN For Low-Dose CT Simulation
We propose a Noise Entangled GAN (NE-GAN) for simulating low-dose computed tomography (CT) images from a higher dose CT image.
Suppression of Correlated Noise with Similarity-based Unsupervised Deep Learning
Limited by the independent noise assumption, current unsupervised denoising methods cannot process correlated noises as in CT images.
Self-supervised Representation Learning for Evolutionary Neural Architecture Search
To enhance the predictive performance of neural predictors, we devise two self-supervised learning methods from different perspectives to pre-train the architecture embedding part of neural predictors to generate a meaningful representation of neural architectures.
Deep Learning based Spectral CT Imaging
To address the image deblurring problem associated with the $L_2^2$-loss, we propose a general $L_p^p$-loss, $p>0$ Furthermore, the images from different energy bins share similar structures of the same object, the regularization characterizing correlations of different energy bins is incorporated into the $L_p^p$-loss function, which helps unify the deep learning based methods with traditional compressed sensing based methods.
Stabilizing Deep Tomographic Reconstruction
ACID synergizes a deep reconstruction network trained on big data, kernel awareness from CS-inspired processing, and iterative refinement to minimize the data residual relative to real measurement.
Low-dimensional Manifold Constrained Disentanglement Network for Metal Artifact Reduction
Deep neural network based methods have achieved promising results for CT metal artifact reduction (MAR), most of which use many synthesized paired images for training.
NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search
In this paper, we propose a neural predictor guided evolutionary algorithm to enhance the exploration ability of EA for NAS (NPENAS) and design two kinds of neural predictors.
GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering
To train the GATCluster in a completely unsupervised manner, we design four self-learning tasks with the constraints of transformation invariance, separability maximization, entropy analysis, and attention mapping.
AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection
Many of the state-of-the-art methods predict the boundaries of action instances based on predetermined anchors akin to the two-dimensional object detection detectors.
DASNet: Reducing Pixel-level Annotations for Instance and Semantic Segmentation
Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data.
