针对胎儿超声图像低对比度难题，提出双路多尺度融合网络提升分类准确率。
FPDANet: A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasound
- 设计位置注意力模块，增强空间特征依赖关系
- 构建双路多尺度融合结构，捕捉跨尺度上下文信息
- 在胎儿超声数据集上实现91.05%准确率，适合医学影像智能筛查
ResNet因其建模恒定映射的残差依赖能力被广泛应用于图像分类任务。然而，其单向特征传递机制缺乏对上下文信息的有效关联，在胎儿超声图像分类中表现不佳，而这类图像普遍存在对比度低、相似性高、噪声大等问题。为此，本文提出基于双边多尺度信息融合的FPDANet模型以应对上述挑战。具体而言，设计了位置注意力机制（DAN）模块，利用特征相似性建立不同空间位置特征间的依赖关系，增强特征表达能力；同时提出双边多尺度（FPAN）信息融合模块，捕获不同特征尺度下的上下文与全局依赖关系，进一步提升模型表征能力。FPDANet在分类任务中取得Top-1 91.05%和Top-5 100%的性能，实验结果验证了其有效性和鲁棒性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。