80 papers
This study demonstrates that GCPII-targeted PET imaging using FDA-approved agents can noninvasively detect and monitor muscle denervation and reinnervation in peripheral nerve injuries by exploiting the persistent overexpression of GCPII in denervated muscles, offering a promising alternative to invasive electromyography.
This study audits 543 pediatric CT scans at a South African tertiary hospital, finding that radiation doses generally align with international safety standards but are slightly higher during after-hours shifts, highlighting the need for consistent staff training and standardized protocols.
This single-center retrospective study demonstrates that a deep learning model utilizing longitudinal digital breast tomosynthesis (DBT) exams significantly outperforms both single-time-point DBT models and established clinical or FFDM-based risk models in predicting 5-year breast cancer risk, thereby enabling more dynamic and personalized screening strategies.
The SEIOMM-3D-DXA project established age- and sex-specific reference curves for 3D-DXA cortical and trabecular bone parameters using data from 1,366 Spanish adults, demonstrating that compartment-specific analysis can reveal significant bone imbalances missed by traditional areal BMD measurements to improve osteoporosis management.
This paper presents a holistic deep learning pipeline that leverages LLM-driven relabelling of a massive chest X-ray dataset to achieve superior pneumonia detection, localisation, and report generation performance compared to traditional rule-based methods and radiologist benchmarks.
This study demonstrates that left ventricular and left atrial strain measures are composite indicators of cardiac geometry and function, particularly driven by mitral annular plane systolic excursion (MAPSE) and chamber dimensions, which explains their strong prognostic value.
This paper introduces a label-free, information-theoretic framework that optimizes MRE radiomics extraction parameters by maximizing distributional richness, coherence, and stability, demonstrating that neighborhood-based aggregation at a mesoscopic scale (r=4) significantly outperforms traditional heuristic choices across diverse tissues and acquisition protocols.
This study demonstrates that ensemble regression models trained on automated image quality metrics can effectively and transparently predict expert visual ratings for medical image translation, achieving high agreement with human consensus while offering a scalable solution for clinical quality control.
This multi-dataset validation study demonstrates that technical acquisition parameters, specifically radiograph view type, are the primary drivers of performance disparities in chest X-ray AI systems, significantly outweighing the contributions of demographic factors like age and sex, thereby necessitating a shift in regulatory frameworks to prioritize acquisition parameter auditing alongside demographic subgroup analysis.
This study provides multimodal MRI evidence that active second language immersion enhances glymphatic system function—improving brain-CSF coordination and optimizing choroid plexus structure—thereby suggesting a neuroprotective mechanism through improved brain waste clearance.
PANDORA is a data-adaptive platform that resolves the trade-off between computational efficiency and spatial detail in population-scale neuroimaging by compressing over 80,000 UK Biobank MRI scans into a supervoxel representation, enabling rapid, denoised, whole-brain statistical analysis while preserving full-resolution ground truth.
This study presents and validates a ResNet-18-based deep learning model that achieves robust automated detection and risk assessment of vertebral artery calcification on non-contrast head-and-neck CT scans, offering a valuable decision-support tool for early stroke prevention.
This study demonstrates that Standard Model Imaging (SMI) and Diffusion Tensor Imaging (DTI) both effectively characterize microstructural alterations across various white matter tissue classes in multiple sclerosis, with a combined multi-model approach yielding the highest classification performance for distinguishing lesion types and subtle tissue changes.
This study demonstrates that multi-b shell diffusion MRI combined with multiple advanced diffusion models provides superior microstructural characterization and discriminative performance for multiple sclerosis lesions compared to conventional single-shell approaches, despite the continued challenge of distinguishing subtle normal-appearing tissue changes.
This multisite machine learning study demonstrates that models trained on amyloid PET and MRI data can effectively predict future cognitive decline in preclinical Alzheimer's disease with strong generalizability across sites and tracers, thereby enhancing statistical power for clinical trial recruitment and treatment effect detection.
This clinical pilot study demonstrates that incorporating polygenic risk scores into breast cancer screening for women aged 40–49 can effectively stratify risk and personalize screening recommendations without inducing significant anxiety among participants.
This study demonstrates that normative modeling of longitudinal MRI data reveals distinct post-stroke subgroups, showing that active dynamic cortical thickening, rather than static structural reserve, is the critical driver of motor recovery.
This retrospective multi-source clinical validation study demonstrates that the Lenek Intelligent Radiology Assistant (LIRA) is a highly accurate AI-based system for screening and triaging chest radiographs in India, showing strong performance in detecting general abnormalities and tuberculosis to help address radiologist shortages and support disease elimination goals.
This study leverages multi-modal imaging and deep learning on 134,000 UK Biobank participants to establish a high-resolution framework for assessing organ-specific aging, revealing significant heterogeneity, strong links to disease risk, and diverse impacts of lifestyle factors.
The paper proposes TumorCLIP, a lightweight and training-efficient vision-language framework that integrates radiology-informed text prototypes with a stable DenseNet121 visual encoder to achieve high-accuracy, explainable, and robust brain tumor classification from MRI scans while addressing the interpretability and hyperparameter sensitivity limitations of existing deep learning models.