FPDANet: A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasound

TL;DR

This paper introduces FPDANet, a novel multi-section classification model that enhances fetal ultrasound image analysis by integrating bilateral multi-scale information fusion and a positional attention mechanism, improving accuracy and robustness.

Contribution

The paper presents FPDANet, a new multi-scale, attention-based network specifically designed for fetal ultrasound classification, addressing limitations of traditional ResNet models.

Findings

Achieved 91.05% Top-1 accuracy

Achieved 100% Top-5 accuracy

Proved effectiveness and robustness of FPDANet

Abstract

ResNet has been widely used in image classification tasks due to its ability to model the residual dependence of constant mappings for linear computation. However, the ResNet method adopts a unidirectional transfer of features and lacks an effective method to correlate contextual information, which is not effective in classifying fetal ultrasound images in the classification task, and fetal ultrasound images have problems such as low contrast, high similarity, and high noise. Therefore, we propose a bilateral multi-scale information fusion network-based FPDANet to address the above challenges. Specifically, we design the positional attention mechanism (DAN) module, which utilizes the similarity of features to establish the dependency of different spatial positional features and enhance the feature representation. In addition, we design a bilateral multi-scale (FPAN) information fusion module to capture contextual and global feature dependencies at different feature scales, thereby further improving the model representation. FPDANet classification results obtained 91.05\% and 100\% in Top-1 and Top-5 metrics, respectively, and the experimental results proved the effectiveness and robustness of FPDANet.