An Automatic Detection Method for Hematoma Features in Placental Abruption Ultrasound Images Based on Few-Shot Learning
This addresses the need for consistent, objective diagnosis of placental abruption in clinical settings, though it appears incremental as it builds on existing YOLO architectures.
The paper tackles the problem of automating hematoma detection in placental abruption ultrasound images, which traditionally relies on subjective physician assessment, by proposing an improved few-shot learning model called EH-YOLOv11n that achieves 78% detection accuracy, a 2.5% improvement over YOLOv11n and 13.7% over YOLOv8.
Placental abruption is a severe complication during pregnancy, and its early accurate diagnosis is crucial for ensuring maternal and fetal safety. Traditional ultrasound diagnostic methods heavily rely on physician experience, leading to issues such as subjective bias and diagnostic inconsistencies. This paper proposes an improved model, EH-YOLOv11n (Enhanced Hemorrhage-YOLOv11n), based on small-sample learning, aiming to achieve automatic detection of hematoma features in placental ultrasound images. The model enhances performance through multidimensional optimization: it integrates wavelet convolution and coordinate convolution to strengthen frequency and spatial feature extraction; incorporates a cascaded group attention mechanism to suppress ultrasound artifacts and occlusion interference, thereby improving bounding box localization accuracy. Experimental results demonstrate a detection accuracy of 78%, representing a 2.5% improvement over YOLOv11n and a 13.7% increase over YOLOv8. The model exhibits significant superiority in precision-recall curves, confidence scores, and occlusion scenarios. Combining high accuracy with real-time processing, this model provides a reliable solution for computer-aided diagnosis of placental abruption, holding significant clinical application value.