97 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 study demonstrates that while highly curated, smaller datasets can achieve equivalent 3D segmentation performance to much larger mixed-curation datasets, the latter offers superior generalizability and local improvements, indicating that the optimal balance between data quality and quantity depends on specific training goals.
This systematic review evaluates the current landscape of intraoperative molecular imaging and AI integration in pediatric brain tumor surgery, highlighting the proven efficacy of intraoperative MRI and selective fluorescence guidance while identifying critical gaps in pediatric-specific metabolomic platforms and standardized protocols that must be addressed to optimize oncological and neurodevelopmental outcomes.
This paper introduces Brain-SAM, a specialized model built upon the SAM2 framework that adapts to 3D brain MRI data through a Hiera encoder and UNETR-inspired decoder, achieving superior performance in segmenting various brain lesions compared to state-of-the-art methods like nnU-Net.
This paper presents a calibration framework using axisymmetric projections and sparse sampling to optimize skull attenuation coefficients, thereby improving the accuracy of acoustic simulations and safety assessments for dynamic focused ultrasound neuromodulation through the temporal window across 157 subjects.
This study presents a robust hybrid CNN-Transformer deep learning model that effectively integrates multi-view ultrasound images to achieve superior accuracy in differentiating benign and malignant breast tumors compared to conventional single-image analysis methods.
This study demonstrates that while foundation models for chest X-ray AI show varying degrees of robustness to acquisition parameters like view type, their performance advantages are often dataset-specific and fail to generalize across external validation, revealing that technical biases persist regardless of model architecture or training scale.
This systematic review of 31 studies from 2022 to 2025 demonstrates that deep learning models, particularly advanced U-Net architectures for segmentation and feature-based classifiers for diagnosis, achieve high accuracy in glioma analysis on multiparametric MRI, though the field requires more explainable AI to ensure clinical trust and adoption.