Automated detection of pinworm parasite eggs using YOLO convolutional block attention module for enhanced microscopic image analysis

Abstract

Experimental evaluation of the YCBAM model demonstrated a precision of 0.9971, a recall of 0.9934, and a training box loss of 1.1410, indicating efficient learning and convergence. The model achieved a mean Average Precision (mAP) of 0.9950 at an IoU threshold of 0.50 and a mAP50-95 score of 0.6531 across varying IoU thresholds, confirming its superior detection performance. The integration of YOLO with self-attention and CBAM significantly improves the automated detection of pinworm eggs, offering a highly accurate and reliable diagnostic tool for medical parasitology. This framework has the potential to reduce diagnostic errors, save time, and support healthcare professionals in making informed decisions.