Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 43,121 to 43,130 of 223,853 articles

A multimodal retinal image dataset for diabetic retinopathy detection using foundation models.

Scientific data
Diabetic Retinopathy (DR), a leading cause of preventable blindness worldwide, underscores the urgent need for robust AI-driven diagnostic tools. Although various deep learning models for retinal imaging have emerged, their evaluation remains constra... read more 

A meta learning and task adaptive approach for drug target affinity prediction.

Nature communications
Accurate and robust prediction of drug-target affinity (DTA) plays a critical role in drug discovery. While deep learning has advanced DTA prediction, existing methods struggle with limited training data and poor generalization. In this study, we pro... read more 

Synthetic data-driven deep learning for label-free autonomous atomic force microscopy.

Nature communications
Atomic force microscopy (AFM) is a widely used tool for nanoscale characterization across materials science, energy research, and biology. However, its adoption in high-throughput materials discovery and statistically driven studies remains limited b... read more 

Behavioral screening defines the molecular Parkinsonism-related subgroups in Drosophila.

Nature communications
Parkinson's disease (PD) and related familial Parkinsonism are defined by motor dysfunction, but the specific upstream molecular causes of these clinical symptoms can vary widely. We hypothesize that these causes converge onto a limited number of cor... read more 

Integrative spatial profiling pipeline for determining TME architectures in archival clinical specimens using CmTSA superplex technology.

Cell discovery
The tumor microenvironment (TME) comprises diverse cellular components that spatially interact to form distinct functional niches (FNs). Profiling these TME spatial features has proven to be a critical approach for correlating tumor progression and t... read more 

Label-Free Raman Spectral Identification of NK and NKT Cells in Immune Heterogeneous Cell Populations.

Analytical chemistry
NK and NKT cells act as major effector subsets across multiple immune heterogeneous cell populations (HCPs), and their precise identification is essential for assessing product quality and predicting clinical efficacy. Here, we present a label-free i... read more 

Toward a cure for multiple myeloma within a decade.

Blood cancer journal
Multiple myeloma (MM), long viewed as incurable, is entering a transformative era marked by deeper remissions, prolonged survival, and the realistic prospect of cure. The greatest opportunity lies at diagnosis, before genomic heterogeneity and immune... read more 

Research on electromagnetic compatibility analysis of automation equipment based on generative adversarial networks and pulse sparse convolution.

PloS one
Electromagnetic interference (EMI) analysis in high-speed industrial systems is increasingly challenged by multi-gigahertz sampling rates, complex transient behaviors, and stringent real-time constraints. To address these challenges, this paper propo... read more 

Pressure sensing technology for remote control: Can we motivate users to stay on the learning curve?

PloS one
Learning to use a novel human-in-the-loop control system is often a slow and frustrating process due to the need to understand new interaction paradigms. Unsurprisingly, research has commonly focused on identifying methods to accelerate such learning... read more 

A synergy-based lower limb exoskeleton that embodies natural human motor intelligence.

Bioinspiration & biomimetics
A key issue in wearable robotics is the design of an exoskeleton robot with human-like motor capabilities to match the wearer's natural locomotion in daily life. It poses a challenge for an exoskeleton to replicate the sophisticated motor intelligenc... read more