Artificial Intelligence Medical Compendium

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

Showing 57,771 to 57,780 of 227,388 articles

Seeing structure, sensing softening: Decoding the microstructural mediation between optical properties and peach firmness using spatial frequency domain imaging.

Food research international (Ottawa, Ont.)
Elucidating the relationship between fruit optical properties and quality attributes is fundamental to nondestructive assessment. However, most existing studies rely on 'black box' chemometric models that correlate spectral signals with quality indic... read more 

Ethics in the World of Artificial Intelligence.

Dental clinics of North America
Across health care, traditional principles of biomedical ethics (autonomy, beneficence, nonmaleficence, and justice) form a base expectation for the use of new technology that applies equally to the spread of artificial intelligence (AI). These vague... read more 

Predicting and interpreting protein and phosphoprotein abundance from pan-cancer and single-cell transcriptomes.

iScience
Proteins that impact phenotype and disease are often approximated by RNA expression, which poorly infers protein abundance. We developed DeepGxP, a deep-learning model trained on The Cancer Genome Atlas pan-cancer data, to predict protein abundance f... read more 

A case-based complexity approach to health inequality: Understanding and tracing place-based differences to enhance policy calibration.

SSM - population health
Health inequalities are not static gradients of deprivation but emergent properties of complex, place-based social systems. This study applied a case-based complexity (CBC) approach, via the COMPLEX-IT platform, to analyse healthy life expectancy (HL... read more 

Anonymous transactional dataset in a local food and beverages (F&B) micro-small-medium enterprise (MSME) for recommender systems.

Data in brief
The dataset presented in this article comprises anonymous transactional records and associated product metadata collected from a local Food and Beverages (F&B) Micro-Small-Medium Enterprise (MSME) operating in a local city in Indonesia. This data can... read more 

OpenStreetMap-derived multimodal dataset across 23 cities: Paired urban morphology tiles with bioclimatic variables.

Data in brief
We present an OpenStreetMap-derived multimodal dataset spanning 23 cities and 11,711 tile-level samples. For each 768 × 768 m tile, we provide an aligned image pair: (i) a stylized ecological baseline that generalizes green and water features togethe... read more 

NuiWorld: Exploring a Scalable Framework for End-to-End Controllable World Generation

arXiv
World generation is a fundamental capability for applications like video games, simulation, and robotics. However, existing approaches face three main obstacles: controllability, scalability, and efficiency. End-to-end scene generation models have be... read more 

Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models

arXiv
Visual Question Answering (VQA) often requires coupling fine-grained perception with factual knowledge beyond the input image. Prior multimodal Retrieval-Augmented Generation (MM-RAG) systems improve factual grounding but lack an internal policy for ... read more 

Critical Organization of Deep Neural Networks, and p-Adic Statistical Field Theories

arXiv
We rigorously study the thermodynamic limit of deep neural networks (DNNS) and recurrent neural networks (RNNs), assuming that the activation functions are sigmoids. A thermodynamic limit is a continuous neural network, where the neurons form a conti... read more 

m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning

arXiv
Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead representations with egocentric views. We introduce m2sv, a scalable benchma... read more