Stay Ahead of the Curve in Radiology AI.
RadAI Slice is your weekly intelligence briefing on the most critical developments at the intersection of radiology and artificial intelligence. Stop searching. Start leading.Subscribe to join 8,400+ radiology professionals tracking the future of imaging AI.
Lastest Issues
The latest developments in Radiology & AI.
AI MRI model boosts early liver cancer detection to 87.9% sensitivity
AI-enhanced CT reshapes head and neck cancer risk stratification
MRI AI predicts outcomes in non-ischemic cardiomyopathy (ECV HR 3.09)
AI model improves early detection of Alzheimer's in diverse groups
Your Weekly Slice of Innovation
Each issue is precisely structured to give you exactly what you need. No fluff, just facts and forward-looking insights.
Recent Industry News
The Latest Research
FDA Approvals Database
Latest News & Trends
Physical Activity Linked to Breast Tissue Biomarkers in Teens
A study links adolescent recreational physical activity to changes in breast tissue composition and stress biomarkers, potentially impacting future breast cancer risk.
FDA Clears AI Platform for Comprehensive Cardiac Risk Assessment on CT
HeartLung Corporation's AI-CVD receives FDA clearance for opportunistic multi-condition screening on routine chest CT scans.
LLM Boosts Terminology Expansion in Radiology Reports Over RadLex
A large language model (LLM) significantly outperforms RadLex in expanding terms for radiology report language standardization.
From the Research Hub
Fully automated Res3DNet model to predict IDH mutation of gliomas from whole-brain MRI free of tumor segmentation.
Accurate prediction of IDH mutation status in gliomas is critical for guiding diagnosis, prognosis, and treatment planning. We enrolled 2,537 preoperative MRI of glioma patients (mean age 55.91 ± 14.79, 1,063 females) from 11 different datasets, consisting of 1,382 patients (mean age 58.26 ± 14.38, 548 females) in training set, 346 patients (mean age 57.43 ± 14.04, 141 females) in internal validation set, and 809 patients (mean age 53.92 ± 14.04, 374 females) in external test set, including 242 patients from The Cancer Genome Archive (TCGA) dataset. A fully automated Res3DNet model was established for isocitrate dehydrogenase (IDH) gene prediction. Four radiologists also read images from TCGA test dataset as a comparison with the deep learning model. Our Res3DNet model achieved AUCs of 0.946 (internal validation), 0.872 (external test), and 0.912 (TCGA test), with corresponding accuracies of 0.925, 0.806, and 0.840, respectively, outperforming ResNet model, I3D model, transformer model, and four radiologists.
Medical Microwave Imaging Using Physics-Guided Deep Learning Part 2: The Inverse Solver.
Deep learning has the potential to address the bottleneck of conventional medical microwave tomography, which is ill-posed and has a high computation cost. However, current physics-guided deep learning methods may fail to capture the imaged object's salient regions, resulting in misdiagnosis. A deep neural network inspired by the distorted Born iterative method (DBIM) is proposed to address this challenge. This method, which avoids using Green's function, provides a theoretical explanation of why current deep learning methods guided by iterative physics algorithms fail in detecting abnormal tissues, making them unsuitable for real-life clinical applications. The proposed method consists of two main components: a set of forward neural network solvers and a series of inverse neural network blocks for updating the dielectric contrast of the imaging domain. The training of the network, designed to emulate the DBIM framework, is regularized by a hybrid loss function composed of two supervised and one self-supervised function. Each iteration in DBIM is performed using a neural network block with parameters different from those of other blocks, forming a sequential iterative approach. By calculating the perturbations in the electrical properties' profiles at each iteration, the proposed network can accurately reconstruct abnormal tissues associated with signals masked by those from healthy tissues. Assessments of the proposed method using the relative error, structure similarity index measure, Dice similarity coefficient, and Hausdorff distance show significant enhancements (19%, 18%, 40%, and 72%, respectively) compared to two recent deep learning-based microwave medical imaging algorithms.
Who Falls After Stroke? Evidence From a Prospective Stroke Cohort
BackgroundFalls are a frequent and serious complication after stroke, affecting more than 30% of survivors within the first year. While age and comorbidities are established risk factors for falls, stroke-specific contributors--particularly lesion-related impairments in mobility and gait--are less well understood and may inform targeted secondary prevention. MethodsWe analyzed data from 94 patients with disabling subacute ischemic stroke enrolled in the prospective BAPTISe cohort, a predefined imaging and biomarker sub-cohort of the multicenter PHYS-STROKE trial. Detailed gait and mobility assessments were performed at baseline. Principal component (PC) analysis reduced seven mobility-related and four gait-related variables into two composite scores: PC1-Mobility and PC1-Gait, explaining 56% and 82% of variance, respectively. PC1-Mobility reflected global disability and functional mobility in daily life, whereas PC1-Gait captured spatiotemporal walking capacity and efficiency. Lesion network mapping (LNM) using a normative connectome identified functional networks associated with each domain. Patient-reported falls up to six months post-enrollment were the primary endpoint. ResultsLNM of PC1-Mobility revealed a predominantly cortical network involving pre- and postcentral gyri, superior and middle frontal gyri, and sensorimotor integration areas. In contrast, PC1-Gait was associated with subcortical and infratentorial connectivity, including bilateral thalamus, brainstem, and cerebellum. In multivariable regression, network similarity scores were not independently associated with falls; only older age was significant (adjusted OR1.08, 95%CI1.02-1.15,p=0.013). LNM of fall occurrence showed a cortical network with significant spatial overlap with the PC1-Mobility network(p<0.001). ConclusionThis exploratory, hypothesis-generating study identified distinct lesion-derived functional networks associated with post-stroke mobility and gait impairment. Our findings suggest that falls may be more closely linked to disruptions in cortical networks involved in voluntary motor control and whole-body coordination, rather than subcortical structures primarily modulating gait. These results provide a foundation for future research aimed at improving fall risk stratification and targeted prevention strategies in stroke survivors.
From the RadAI FDA Approvals Database
Sim&Cure
Sim&Size
Sim&Size is a software tool that helps clinicians visualize blood vessels and devices inside them, aiding in planning and treatment of neurovascular conditions. It supports doctors by providing clear images of vascular anatomy to improve patient care.
Ge Medical Systems, LLC
AIR Recon DL
AIR Recon DL is an MRI system designed to capture detailed images of the body using nuclear magnetic resonance technology. It helps clinicians by providing high-quality images that support diagnosis and treatment planning in radiology.
Edan Instruments, Inc.
Diagnostic Ultrasound System (Nano C5, Nano C5 EXP, Nano L12, and Nano L12 EXP)
The Diagnostic Ultrasound System by Edan Instruments, Inc. is a device that produces medical ultrasound images to help clinicians visualize internal body structures and support diagnostic decisions. It assists healthcare providers by providing clear ultrasound images that improve patient assessment and care.
The Sharpest Insights, Effortlessly
Save Time
We scour dozens of sources so you don't have to. Get all the essential information in a 5-minute read.
Stay Informed
Never miss a critical update. Understand the trends shaping the future of your practice and research.
Gain an Edge
Be the first to know about the tools and technologies that matter, from clinical practice to academic research.
Ready to Sharpen Your Edge?
Subscribe to join 8,400+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.