Automated detection of fetal vascular malperfusion via data augmentation and algorithm improvement

Fetal vascular malperfusion (FVM) is an important pathological factor leading to adverse pregnancy outcomes, but current manual diagnosis faces challenges such as high subjectivity and low efficiency. To address these problems, this paper proposes a joint analysis strategy based on data augmentation and deep learning model improvement. Using MONAI-based data augmentation it increases the number of FVM histopathology images while embedding a LocalWindow attention mechanism to enhance the YOLOv11 model. The experimental results show that this synergistic strategy of data augmentation and model improvement yields optimal recognition performance, with the F1 score, mAP50, and mAP50-95 increased by 7.84%, 6.53%, and 6.63%, respectively, compared with the YOLOv11 baseline model. This study indicates that a strategy combining data augmentation with model structural improvement can effectively enhance detection performance for FVM and provides a useful reference for the development of intelligent diagnostic tools for FVM in clinical practice.