Tri-Net v2: Open-source implementation of our Scientific Reports paper on unified skin lesion and symptom-based monkeypox detection [R]
Summary
Tri-Net v2 is an open-source implementation of a Scientific Reports paper for unified skin lesion and symptom-based monkeypox detection.
Similar Articles
BERTopic-Virality Prioritisation: A Scalable Framework for Thematic and Comparative Analysis of COVID-19 and Monkeypox Misinformation on Twitter
BERTopic-VP is a virality-prioritised topic-modelling framework that combines clustering with a misinformation detection module to analyze health misinformation on Twitter, achieving high classification performance for COVID-19 and Monkeypox outbreaks.
Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines
Introduces MMIOC-1M, a large-scale multi-modal benchmark for industrial defect detection, and proposes RTVPNet, a refined text-visual prompt network achieving state-of-the-art performance.
PatTree: a novel approach for automated creation of multimodal, graph-based patient representations for medical classification tasks
This paper introduces PatTree, a graph-based multimodal patient representation that automatically structures heterogeneous clinical data for medical classification tasks. It achieves state-of-the-art performance on the ADNI-1 cohort with 98.5% balanced accuracy for Alzheimer's disease classification.
PathReportEval: A Systematic Benchmark for Pathology Report Generation
This paper introduces PathReportEval, a standardized benchmark and evaluation framework for pathology report generation from whole-slide images, including a new clinically grounded metric called Clinical Report Quality Score (CRQS) that better captures factual correctness than conventional lexical metrics.
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
Pythia is a multi-agent system that autonomously writes and optimizes extraction prompts for clinical concepts without manual prompt engineering or fine-tuning, using a locally hosted open-weights model. It achieves mean sensitivity of 0.76 and specificity of 0.95 on clinical symptom detection, outperforming lexicon-based methods on specificity.