Detection of Virus and Small Cell Patches in Foci Images Using Switchable Convolution and Feature Pyramid Networks
For biomedical researchers needing accurate detection of variable-sized targets in microscopy images, this work offers an incremental improvement over standard YOLOv2.
The authors enhanced YOLOv2 with Feature Pyramid Network and switchable atrous convolution to detect virus and small cell patches in foci images, achieving 40.5% mAP (25% IoU) for small cells and 68% mAP for virus patches.
Accurate detection and counting of virus patches in focus-forming unit (FFU) images, also known as foci images, are important for quantifying viral infection and analyzing cellular structures. This task is challenging because biomedical targets often vary substantially in size, density, contrast, and shape. In this paper, we propose an enhanced YOLOv2-based detector that integrates a Feature Pyramid Network (FPN) to improve multi-scale feature representation. We also incorporate a switchable atrous convolution mechanism to adapt the receptive field for fine-grained targets in dense microscopy images. The proposed method is evaluated on biomedical foci image datasets for virus patch and small cell patch detection. For small cell patch detection, the model achieves a mean average precision (mAP) of 40.5% at a 25% Intersection over Union (IoU) threshold. For FFU virus patch detection, the model achieves an mAP of 68%. These results indicate that combining FPN-based feature fusion with switchable convolution improves the suitability of YOLOv2 for specialized biomedical object detection tasks