62 papers
Radiology and imaging serve as the eyes of modern medicine, allowing doctors to peer inside the human body without making a single incision. This rapidly evolving field uses technologies like X-rays, MRI scans, and ultrasound to detect diseases, guide treatments, and monitor patient recovery. As new research emerges, these visual tools become increasingly sophisticated, offering deeper insights into conditions ranging from broken bones to complex neurological disorders.
At Gist.Science, we bridge the gap between raw scientific data and public understanding by processing every new preprint in this category from medRxiv. Our team translates these complex studies into both plain-language overviews and detailed technical summaries, ensuring that breakthroughs in medical imaging are accessible to everyone, from students to specialists. Below are the latest papers in radiology and imaging, ready for you to explore.
This paper presents a dual-filament, voxel-level 3D printing method that fabricates patient-specific CT phantoms with embedded metallic implants and tunable artifact intensity, enabling objective benchmarking of metal artifact reduction algorithms and spectral CT performance.
FreqFuseNet addresses a critical 863-fold activation-scale mismatch in dual-frequency feature fusion by normalizing the FcaNet branch to the FFT scale, thereby enabling a stable 5% residual injection that significantly improves the segmentation accuracy of thin-wall head-and-neck organs-at-risk while maintaining a lightweight architecture.
This paper presents an automated end-to-end workflow for generating patient-specific, 4D-printed, multi-material phantoms that replicate realistic anatomy, physiological motion, and multimodal imaging properties to enable independent quality assurance of adaptive radiotherapy on 1.5T MR-Linac systems.
Using high-resolution 7T whole-brain MRSI, this study reveals that amyotrophic lateral sclerosis is characterized by a metabolic dissociation between motor-selective neuronal loss and somatotopically patterned glutamatergic dysregulation, identifying Glx/tNAA as a sensitive, design-ready biomarker for clinical trials.
This study demonstrates that a Bottleneck Transformer U-Net (BTU-Net) model achieves human-level accuracy in automatically segmenting vascular perfusion defects on planar V/Q scintigraphy, offering a robust solution to standardize pulmonary embolism diagnosis and reduce interobserver variability.
This study demonstrates that ultrasound time-harmonic elastography can simultaneously quantify and distinguish the independent and superimposed effects of voluntary muscle contraction and blood flow restriction on the elastic and viscous properties of skeletal muscle in vivo.
This paper introduces an open, reproducible gamma-variate pipeline for CT-perfusion analysis that ensures cross-site comparability through standardized ASIST-Japan visualization and validates its accuracy and bit-stable reproducibility using synthetic benchmarks with known ground truth.
This study utilized the UK7T travelling head dataset to demonstrate that 7T MRI measurements of hippocampal subfield susceptibility and volume exhibit high reproducibility across repeated acquisitions, with intra-subject variability significantly lower than inter-subject differences and intraclass correlation coefficients exceeding 0.82 for all subfields.
This paper presents a fine-tuned SAM2 model for coronary artery segmentation in X-ray fluoroscopy that significantly outperforms zero-shot baselines (achieving a Dice score of 0.767 on the ARCADE dataset) and demonstrates robust vessel tracking in video studies by effectively distinguishing arteries from confounding structures like ribs and stents.
This study demonstrates that a deep learning model can accurately quantify breast arterial calcification from screening mammograms to identify women at elevated cardiovascular risk, although adding this AI-derived biomarker to existing risk scores like PREVENT offers minimal improvement in overall predictive discrimination.