Research Articles
Automated Phenotypic Screening for Novel Anthelmintics: High-Throughput Assays and AI-Driven Discovery
The escalating threat of anthelmintic resistance in human and veterinary parasitic nematodes necessitates the accelerated discovery of new therapeutic compounds.
Ensuring Diagnostic Accuracy: A Comprehensive Guide to Inter-Rater Reliability in Parasite Morphology Identification
Accurate parasite identification is foundational to effective disease diagnosis, treatment, and research.
Sensitivity and Specificity in Parasite Diagnostics: From Foundational Concepts to AI and Molecular Innovations
This article provides a comprehensive analysis of sensitivity and specificity across the evolving landscape of parasitic disease diagnostics.
Cross-Dataset Validation of Malaria Parasite Classification Models: Challenges, Strategies, and Clinical Translation
This article provides a comprehensive analysis of cross-dataset validation for deep learning models in malaria parasite classification, a critical step for ensuring real-world clinical applicability.
Beyond Accuracy: A Framework for Validating Deep Learning Models Against Human Expert Diagnosis
The integration of deep learning into clinical diagnostics promises enhanced accuracy and efficiency, yet its successful adoption hinges on rigorous and meaningful validation against human expert benchmarks.
McMaster vs. Mini-FLOTAC: A Comprehensive Comparison of Diagnostic Performance for Gastrointestinal Parasites
This article provides a systematic comparison of the McMaster and Mini-FLOTAC diagnostic techniques for detecting gastrointestinal parasites.
Beyond Accuracy: Advanced Strategies for Handling Class Imbalance in Parasite Image Classification
Class imbalance is a pervasive challenge that significantly hinders the development of robust deep-learning models for parasite image classification, often leading to biased predictions and poor generalization on rare species...
Navigating Morphological Variations in Parasite Egg Identification: From Traditional Microscopy to AI-Driven Solutions
Accurate identification of parasitic helminth eggs is fundamental for diagnosis, surveillance, and drug development, yet it is persistently challenged by significant morphological variations.
Advancing Quality Control in Protozoan Microscopy: From Foundational Methods to AI-Powered Solutions
This article provides a comprehensive overview of quality control in the microscopic identification of protozoan parasites, a critical process for research and drug development.
Self-Supervised Learning and AI Strategies to Reduce Manual Labeling in Parasite Image Analysis
Manual labeling of parasite microscopy images is a major bottleneck in developing AI-based diagnostic tools, consuming significant time and expert resources.