AI detects toxicity in preclinical histopathology using novel anomaly detection

Researchers have developed an AI framework to detect toxicity in preclinical histopathology using whole-slide images. This system can identify healthy tissue, known pathologies, and flag samples with novel anomalies. By fine-tuning a Vision Transformer with Low-Rank Adaptation and employing Mahalanobis distance for anomaly detection, the method aims to improve the efficiency and scale of toxicity assessment in drug development. AI

IMPACT Could accelerate preclinical drug development by automating toxicity assessment in histopathology.

RANK_REASON Research paper detailing a novel AI method for toxicity assessment in histopathology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Class-Aware Mahalanobis Distance
• DINOv2
• Histopathology
• Lora
• Low Rank Adaptation
• Mahalanobis distance
• Olga Grafová
• rodent liver
• vision transformer

• paper
• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →