9 papers
Virtual Biopsy for Intracranial Tumors Diagnosis on MRI
Xinzhe Luo, Shuai Shao, Yan Wang +3
Deep intracranial tumors situated in eloquent brain regions controlling vital functions present critical diagnostic challenges. Clinical practice has shifted toward stereotactic bi…
ReBA-Pred-Net: Weakly-Supervised Regional Brain Age Prediction on MRI
Shuai Shao, Yan Wang, Shu Jiang +6
Brain age has become a prominent biomarker of brain health. Yet most prior work targets whole brain age (WBA), a coarse paradigm that struggles to support tasks such as disease cha…
Adaptive Conditional Contrast-Agnostic Deformable Image Registration with Uncertainty Estimation
Yinsong Wang, Xinzhe Luo, Siyi Du +1
Deformable multi-contrast image registration is a challenging yet crucial task due to the complex, non-linear intensity relationships across different imaging contrasts. Convention…
Self-Supervised Slice-to-Volume Reconstruction with Gaussian Representations for Fetal MRI
Yinsong Wang, Thomas Fletcher, Xinzhe Luo +3
Reconstructing 3D fetal MR volumes from motion-corrupted stacks of 2D slices is a crucial and challenging task. Conventional slice-to-volume reconstruction (SVR) methods are time-c…
Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification
Siyi Du, Xinzhe Luo, Declan P. O'Regan +1
Multimodal deep learning (MDL) has achieved remarkable success across various domains, yet its practical deployment is often hindered by incomplete multimodal data. Existing incomp…
UPMRI: Unsupervised Parallel MRI Reconstruction via Projected Conditional Flow Matching
Xinzhe Luo, Yingzhen Li, Chen Qin
Reconstructing high-quality images from substantially undersampled k-space data for accelerated MRI presents a challenging ill-posed inverse problem. While supervised deep learning…
STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification
Siyi Du, Xinzhe Luo, Declan P. O'Regan +1
Multimodal image-tabular learning is gaining attention, yet it faces challenges due to limited labeled data. While earlier work has applied self-supervised learning (SSL) to unlabe…
Unsupervised Accelerated MRI Reconstruction via Ground-Truth-Free Flow Matching
Xinzhe Luo, Yingzhen Li, Chen Qin
Accelerated magnetic resonance imaging involves reconstructing fully sampled images from undersampled k-space measurements. Current state-of-the-art approaches have mainly focused…
CAR: Contrast-Agnostic Deformable Medical Image Registration with Contrast-Invariant Latent Regularization
Yinsong Wang, Siyi Du, Shaoming Zheng +2
Multi-contrast image registration is a challenging task due to the complex intensity relationships between different imaging contrasts. Conventional image registration methods are…