CheXTemporal supplies paired chest X-rays with explicit temporal progression taxonomy and spatial grounding to benchmark and improve models on longitudinal reasoning tasks.
2018.2837502
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Introduces soft Tuy-completeness with greedy (1-1/e approx) and MILP solvers for projection selection in cone-beam CT, reports 0.998 median greedy-to-MILP ratio on benchmarks, and defines ESR as a trajectory diagnostic for feature size.
EchoXFlow is a new dataset of 37,125 beamspace echocardiography recordings with separable modalities, Doppler data, ECG, and clinical annotations that enables acquisition-aware learning not possible with standard scan-converted videos.
ML-SPnP accelerates stochastic PnP for SVCT by using MRA approximation spaces where prior-coherence corrections vanish in expectation, yielding comparable quality at reduced runtime.
EnTrust decomposes multimodal features into consensus, specific, and conflict signals, conditions a diffusion segmentation model on disagreements, and maps hypothesis divergence to calibrated pixel-wise uncertainty, reporting SOTA accuracy and 40% lower calibration error than baselines.
MoE-dqINR factorizes INR-based MRI reconstruction into shared spatial experts plus state-conditioned routing to unify dynamic and quantitative reconstruction at roughly 30 seconds per scan.
ForcingDAS is a diffusion-based data assimilation framework that learns joint-trajectory priors to unify filtering and smoothing while reducing error accumulation on non-Markovian observations.
A multiscale retinal hemodynamics model with an analytic solution for the capillary-tissue system that enables faster computation and parameter exploration.
MedCAGD introduces a context-aware gated decoder with channel recalibration, gated skip fusion, and global context aggregation that outperforms baselines on 11 medical segmentation benchmarks while remaining computationally practical.
A semi-supervised VAE combined with static and residual motion LDMs generates anatomically consistent 4D cardiac MRI, achieving Pearson r > 0.8 controllability and 1.4% Dice improvement in downstream segmentation when used for data augmentation.
End-to-end pipeline uses ResViT-2.5D to synthesize post-resection MRI from ioUS then anchors deformable registration, yielding 5.86 mm TRE on 14 ReMIND subjects while producing an integrated whole-brain volume reflecting intraoperative state.
A 3D gamma-index provides an acceptance criterion for forecasts by checking agreement within explicit spatial, temporal, and intensity tolerances instead of exact matches.
A public GPU workflow for non-Fourier SENSE MRI reconstruction with sensitivity and off-resonance mapping enables fast, accurate imaging from challenging spiral trajectories.
Systematic tests of 27 ultrasound tasks show that unified training is more consistent than clinically-grouped training, with performance hinging on data availability and task characteristics.
MeCSAFNet reports mIoU gains of 4.8-19.6% over U-Net and SegFormer baselines on FBP and Potsdam datasets by processing spectral channels separately and fusing features with CBAM attention.
citing papers explorer
-
CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography
CheXTemporal supplies paired chest X-rays with explicit temporal progression taxonomy and spatial grounding to benchmark and improve models on longitudinal reasoning tasks.
-
Soft Tuy-Completeness for Robust Projection Selection in Cone-Beam CT
Introduces soft Tuy-completeness with greedy (1-1/e approx) and MILP solvers for projection selection in cone-beam CT, reports 0.998 median greedy-to-MILP ratio on benchmarks, and defines ESR as a trajectory diagnostic for feature size.
-
EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function
EchoXFlow is a new dataset of 37,125 beamspace echocardiography recordings with separable modalities, Doppler data, ECG, and clinical annotations that enables acquisition-aware learning not possible with standard scan-converted videos.
-
Multilevel Stochastic Plug-and-Play for Sparse-View CT Reconstruction
ML-SPnP accelerates stochastic PnP for SVCT by using MRA approximation spaces where prior-coherence corrections vanish in expectation, yielding comparable quality at reduced runtime.
-
EnTrust: Modeling Inter-Modal Conflict for Trustworthy Multimodal Medical Image Analysis
EnTrust decomposes multimodal features into consensus, specific, and conflict signals, conditions a diffusion segmentation model on disagreements, and maps hypothesis divergence to calibrated pixel-wise uncertainty, reporting SOTA accuracy and 40% lower calibration error than baselines.
-
MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstruction
MoE-dqINR factorizes INR-based MRI reconstruction into shared spatial experts plus state-conditioned routing to unify dynamic and quantitative reconstruction at roughly 30 seconds per scan.
-
ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
ForcingDAS is a diffusion-based data assimilation framework that learns joint-trajectory priors to unify filtering and smoothing while reducing error accumulation on non-Markovian observations.
-
A novel multiscale modelling for the hemodynamics in retinal microcirculation with an analytic solution for the capillary-tissue coupled system
A multiscale retinal hemodynamics model with an analytic solution for the capillary-tissue system that enables faster computation and parameter exploration.
-
MedCAGD: Context-Aware Gated Decoder for Efficient Medical Image Segmentation
MedCAGD introduces a context-aware gated decoder with channel recalibration, gated skip fusion, and global context aggregation that outperforms baselines on 11 medical segmentation benchmarks while remaining computationally practical.
-
Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis
A semi-supervised VAE combined with static and residual motion LDMs generates anatomically consistent 4D cardiac MRI, achieving Pearson r > 0.8 controllability and 1.4% Dice improvement in downstream segmentation when used for data augmentation.
-
What neurosurgeons need to see: synthetic intra-operative MRI from ultrasound for brain-shift compensation in brain tumour surgery
End-to-end pipeline uses ResViT-2.5D to synthesize post-resection MRI from ioUS then anchors deformable registration, yielding 5.86 mm TRE on 14 ReMIND subjects while producing an integrated whole-brain volume reflecting intraoperative state.
-
A Tolerance-Based Framework for Spatio-Temporal Forecast Validation Using the gamma-Index
A 3D gamma-index provides an acceptance criterion for forecasts by checking agreement within explicit spatial, temporal, and intensity tolerances instead of exact matches.
-
A GPU-enhanced workflow for non-Fourier SENSE reconstruction
A public GPU workflow for non-Fourier SENSE MRI reconstruction with sensitivity and off-resonance mapping enables fast, accurate imaging from challenging spiral trajectories.
-
Understanding Task Aggregation for Generalizable Ultrasound Foundation Models
Systematic tests of 27 ultrasound tasks show that unified training is more consistent than clinically-grouped training, with performance hinging on data availability and task characteristics.
-
Multi-encoder ConvNeXt Network with Smooth Attentional Feature Fusion for Multispectral Semantic Segmentation
MeCSAFNet reports mIoU gains of 4.8-19.6% over U-Net and SegFormer baselines on FBP and Potsdam datasets by processing spectral channels separately and fusing features with CBAM attention.