Embedding learnable Lorentzian basis functions into the spectral encoding layer of an implicit neural representation enables high-fidelity CEST Z-spectrum reconstruction from as few as 21 frequency offsets.
Title resolution pending
11 Pith papers cite this work, alongside 88 external citations. Polarity classification is still indexing.
11
Pith papers citing it
88
external citations · external index
representative citing papers
ECUAS_n is a parameterized family of proper scoring rules for jointly assessing prediction accuracy and uncertainty quality in automated decision systems.
LiFT factorizes 3D medical volume synthesis into per-slice 2D generation and inter-slice trajectory learning, using a tri-planar drifting loss for unconditional coherence and a z-context mixer for paired translation tasks.
A Jacobian sensitivity curve computed at initialization identifies the narrowest U-Net configuration that avoids performance collapse, matching nnU-Net accuracy with 400-1600x fewer parameters on six medical datasets.
SAMRI fine-tunes only the mask decoder of SAM on 1.1 million MRI slices from 30 datasets to reach mean DSC 0.87 on 47 targets and strong zero-shot performance.
In a private dataset of 353 patients, medical records and cardiac biomarkers outperform vascular biomarkers and GNNs on vascular graphs for PE risk stratification, suggesting vascular graphs hold no discriminative information.
2D diffusion-generated synthetic X-rays enable training of anatomical landmark detectors that generalize to real images with performance rivaling real-data training.
CDPM-Align applies multi-scale guidance-aligned conditional diffusion pretraining on three small heterogeneous datasets to improve accuracy and uncertainty in few-shot (10-25 image) anatomical landmark detection.
BiasCareVL is a bias-aware vision-language framework trained on 3.44 million medical samples that outperforms prior methods on clinical tasks like diagnosis and segmentation while aiming for equitable performance under data imbalances.
Introduces CFR module for point-by-point feature alignment across curved vessel modalities and CR Loss for risk-weighted multi-level stenosis grading, reporting outperformance on an in-house dataset.
Profiling of Med-DDPM shows cuDNN kernels dominate training; TF32 Tensor Core activation and 3D channels-last layout reduce SM cycles up to 100x and raise Tensor Core utilization on A100 without quality loss.
citing papers explorer
-
Self-Supervised Implicit CEST Reconstruction via Physics-Informed Lorentz Encoding
Embedding learnable Lorentzian basis functions into the spectral encoding layer of an implicit neural representation enables high-fidelity CEST Z-spectrum reconstruction from as few as 21 frequency offsets.
-
ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems
ECUAS_n is a parameterized family of proper scoring rules for jointly assessing prediction accuracy and uncertainty quality in automated decision systems.
-
LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
LiFT factorizes 3D medical volume synthesis into per-slice 2D generation and inter-slice trajectory learning, using a tri-planar drifting loss for unconditional coherence and a z-context mixer for paired translation tasks.
-
XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity
A Jacobian sensitivity curve computed at initialization identifies the narrowest U-Net configuration that avoids performance collapse, matching nnU-Net accuracy with 400-1600x fewer parameters on six medical datasets.
-
SAMRI: Segment Any MRI
SAMRI fine-tunes only the mask decoder of SAM on 1.1 million MRI slices from 30 datasets to reach mean DSC 0.87 on 47 targets and strong zero-shot performance.
-
Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Need
In a private dataset of 353 patients, medical records and cardiac biomarkers outperform vascular biomarkers and GNNs on vascular graphs for PE risk stratification, suggesting vascular graphs hold no discriminative information.
-
2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models
2D diffusion-generated synthetic X-rays enable training of anatomical landmark detectors that generalize to real images with performance rivaling real-data training.
-
CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection
CDPM-Align applies multi-scale guidance-aligned conditional diffusion pretraining on three small heterogeneous datasets to improve accuracy and uncertainty in few-shot (10-25 image) anatomical landmark detection.
-
Bias-constrained multimodal intelligence for equitable and reliable clinical AI
BiasCareVL is a bias-aware vision-language framework trained on 3.44 million medical samples that outperforms prior methods on clinical tasks like diagnosis and segmentation while aiming for equitable performance under data imbalances.
-
Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction
Introduces CFR module for point-by-point feature alignment across curved vessel modalities and CR Loss for risk-weighted multi-level stenosis grading, reporting outperformance on an in-house dataset.
-
Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
Profiling of Med-DDPM shows cuDNN kernels dominate training; TF32 Tensor Core activation and 3D channels-last layout reduce SM cycles up to 100x and raise Tensor Core utilization on A100 without quality loss.