Artefact-Aware Fungal Detection in Dermatophytosis: A Real-Time Transformer-Based Approach for KOH Microscopy

2026-02-22

AI Summary

This study addresses the diagnostic limitations of potassium hydroxide (KOH) microscopy for fungal hyphae detection, which are often compromised by artifacts, uneven keratin clearance, and inter-observer variability. To overcome these challenges, the authors propose the first application of a query-driven real-time Transformer detection model (RT-DETR) to dermatophyte identification, incorporating multi-class annotations to distinguish true fungal elements from artifacts. A morphology-preserving enhancement strategy is specifically designed to maintain the structural integrity of slender hyphae. Evaluated on high-resolution KOH images, the model achieves 97.37% recall, 80.43% precision, and 93.56% AP@0.50 on an independent test set. At the image level, it demonstrates 100% sensitivity and 98.8% accuracy, ensuring zero missed diagnoses and effectively bridging automated image analysis with clinical decision-making.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Interpretability, Explainability, and Transparency
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Dermatophytosis is commonly assessed using potassium hydroxide (KOH) microscopy, yet accurate recognition of fungal hyphae is hindered by artefacts, heterogeneous keratin clearance, and notable inter-observer variability. This study presents a transformer-based detection framework using the RT-DETR model architecture to achieve precise, query-driven localization of fungal structures in high-resolution KOH images. A dataset of 2,540 routinely acquired microscopy images was manually annotated using a multi-class strategy to explicitly distinguish fungal elements from confounding artefacts. The model was trained with morphology-preserving augmentations to maintain the structural integrity of thin hyphae. Evaluation on an independent test set demonstrated robust object-level performance, with a recall of 0.9737, precision of 0.8043, and an AP@0.50 of 93.56%. When aggregated for image-level diagnosis, the model achieved 100% sensitivity and 98.8% accuracy, correctly identifying all positive cases without missing a single diagnosis. Qualitative outputs confirmed the robust localization of low-contrast hyphae even in artefact-rich fields. These results highlight that an artificial intelligence (AI) system can serve as a highly reliable, automated screening tool, effectively bridging the gap between image-level analysis and clinical decision-making in dermatomycology.

Problem

• dermatophytosis
• KOH microscopy
• artefacts
• fungal detection
• inter-observer variability

Innovation

• RT-DETR
• artifact-aware detection
• KOH microscopy
• fungal hyphae localization
• morphology-preserving augmentation