Artificial Intelligence Medical Compendium

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

Showing 43,821 to 43,830 of 224,055 articles

Perseus: Lineage-Aware Refinement of Kraken2 Taxonomic Classification for Long Read Metagenomes

bioRxiv
Motivation: Long-read metagenomic sequencing improves assembly contiguity and enables genome-resolved analysis of complex microbial communities, but accurate taxonomic classification of long reads and assembled contigs remains challenging. Highly sca... read more 

Photochromic reversion enables long-term tracking of single molecules in living plants.

bioRxiv
Single-molecule imaging enables the observation of individual molecules in living cells (D'Este et al., 2024; Kusumi et al., 2014; Lelek et al., 2021; Nguyen et al., 2023). In plants, however, the tracking of single molecules is typically limited to ... read more 

A population code for semantics in human hippocampus

bioRxiv
As we listen to speech, our brains track the meanings of the words we hear. Recent successes of large language models suggest that distributed population geometry can capture rich semantic relationships between words. Motivated by this idea, we hypot... read more 

From the fly connectome to exact ring attractor dynamics

bioRxiv
A cognitive compass enabling spatial navigation requires the neural representation of head direction (HD), yet the neural circuit architecture enabling this representation remains unclear. While various network models have been proposed to explain HD... read more 

Sleep Disruption Improves Performance in Simple Olfactory and Visual Decision-Making Tasks

bioRxiv
Sleep disruption drastically impacts cognitive functions including decision-making and attention across many different species. In this study, we leveraged the small size and conserved vertebrate brain structure of larval zebrafish to investigate how... read more 

AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions

arXiv
Visual Question Answering (VQA) is a core task for evaluating the capabilities of Vision-Language Models (VLMs). Existing VQA benchmarks primarily feature clear and unambiguous image-question pairs, whereas real-world scenarios often involve varying ... read more 

Interpretable Aneurysm Classification via 3D Concept Bottleneck Models: Integrating Morphological and Hemodynamic Clinical Features

arXiv
We are concerned with the challenge of reliably classifying and assessing intracranial aneurysms using deep learning without compromising clinical transparency. While traditional black-box models achieve high predictive accuracy, their lack of inhere... read more 

VIVECaption: A Split Approach to Caption Quality Improvement

arXiv
Caption quality has emerged as a critical bottleneck in training high-quality text-to-image (T2I) and text-to-video (T2V) generative models. While visual language models (VLMs) are commonly deployed to generate captions from visual data, they suffer ... read more 

Prompt-Based Caption Generation for Single-Tooth Dental Images Using Vision-Language Models

arXiv
Digital dentistry has made significant advances with the advent of deep learning. However, the majority of these deep learning-based dental image analysis models focus on very specific tasks such as tooth segmentation, tooth detection, cavity detecti... read more 

UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration

arXiv
Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one restoration networks do not scale to multiple degradations. As the numbe... read more