Duke Kunshan University

Limited-angle cone-beam CT (CBCT) reconstruction suffers from missing projection data, leading to severe streak artifacts, structural distortions, and degraded image quality. This study proposes a conditional diffusion-based projection extrapolation framework...

MD values quantify visual loss. Through OCT images, physicians can obtain MD values to assess patients' visual status. This task is crucial for early patient screening. However, current AI-based MD prediction methods lack interpretability—a common limitation...

To develop a pixel-level uncertainty-aware consistency (UA-Cons) learning framework to optimize the feature compensation behavior of deep neural networks in scenarios where multi-parametric MRI modalities are incomplete.

Breast cancer screening reduces breast cancer mortality through early detection, with mammography as the most widely used imaging modality. However, radiologist interpretation is time-consuming, and existing AI tools still suffer from missed subtle lesions an...

To propose a federated learning (FL) framework incorporating a novel deep ensemble strategy for multi-institutional brain metastasis (BM) segmentation, improving performance in limited local datasets while preserving privacy by avoiding large-scale data trans...

Monte Carlo (MC) particle transport methods which with high computational cost of MC simulations severely limits their efficiency of BNCT dose calculations. We developed a physics-informed neural network (PINN) framework for efficient and physically consisten...

To explore a comprehensive pre-therapeutic dose prediction workflow for Lu‑177‑PSMA radiopharmaceutical therapy by combining a physiologically based pharmacokinetic (PBPK) model with Monte Carlo simulation.

Convolutional neural networks (CNNs) are effective in modeling local textures and fine-grained spatial structures, while Coordinate Attention captures long-range spatial dependencies, enhancing global contextual awareness and preserving positional information...

Conventional filtered backprojection with a fixed Ram-Lak filter in cone-beam CT (CBCT) reconstruction method often amplifies noise and streak artifacts under sparse-view acquisition, limiting image quality for image-guided radiotherapy. This study investigat...

To evaluate the impact of respiratory motion on dose distribution and spatial modulation in VMAT-based Lattice Spatially Fractionated Radiotherapy(Lattice-SFRT), and to evaluate the stability of peak–valley dose characteristics using four-dimensional(4D) dose...

Preoperative phenotyping of vessels that encapsulate tumor clusters (VETC) and microvascular invasion (MVI) is clinically important in hepatocellular carcinoma (HCC) diagnosis and treatment. While most studies rely on MRI, CT-based prediction remains limited...

To develop and evaluate a voxel-based straight-line trajectory planning framework for CT-guided lung biopsy that enables safe and efficient pre-procedural identification of needle paths while minimizing risk to organs at risk (OARs).

To develop and evaluate a federated learning (FL) framework for brain metastasis (BM) segmentation that integrates an uncertainty score into a novel FL objective, improving segmentation robustness and potentially performance when training on limited-size data...

To evaluate whether a federated learning (FL) scheme that leverages adult glioma patient data improves multi-parametric MRI (mp-MRI) based pediatric glioma segmentation.

To develop a deep learning framework that simultaneously synthesizes lung perfusion and ventilation images from three-dimensional (3D) CT and to evaluate its potential clinical utility.

Automated segmentation of lung nodules in chest CT is critical for early cancer screening but remains challenging due to the small size and variable morphology of nodules, which often resemble vessels or pleura. This study proposes a novel framework integrati...

Our previous work proposed a Neural ODE–based U-Net (NODE-UNet) that generates continuous trajectories to visualize the evolution of feature representations from the initial input to the terminal state. We hypothesize that modeling contextual consistency alon...

Low-field MRI suffers from intrinsically low SNR, which limits image quality and slows wide clinical adoption. Deep learning–based denoising shows strong promise, yet supervised training requires paired high-quality references that are rarely available for lo...

Photodynamic therapy and photothermal therapy commonly rely on tetrapyrrole based photosensitizers, whose therapeutic efficacy is governed by their electronic absorption property in the visible and near infrared regions. Accurate prediction of absorption spec...

To enhance breast malignancy prediction, this study develops a multimodal framework that integrates automated, Vision-Language Model (VLM)-derived BI-RADS lexicons with quantitative radiomic features.

Ultrahigh dose-rate (FLASH) radiotherapy delivers radiation within millisecond timescales, yet direct measurement of radiolytic oxidative processes during beam delivery remains technically challenging. This study aimed to develop and apply a real-time optical...