一种用于创面检测的改进Faster R-CNN方法

张斯斯; 史忠祥; 江峰; 丁敏; 刘聪聪; 段飞

doi:10.12182/20260560204

摘要:

目的通过引入注意力增强机制和改进后处理策略，对更快的基于区域的卷积神经网络（faster region-based convolutional neural network, Faster R-CNN）进行改进，即用于创面检测的改进Faster R-CNN方法（wound detection method based on improved faster R-CNN, WD-IFRCNN），以提高创面检测的准确性和稳定性。

方法 ①算法构建：以50层残差网络（50-layer residual network, ResNet-50）为主干网络，在第4残差阶段（convolutional stage 4, Conv4_x）和第5残差阶段（convolutional stage 5, Conv5_x）嵌入模糊注意力引导模块（fuzzy mask attention module, FMAM）协同的卷积块注意力模块（convolutional block attention module, CBAM），以增强模型对创面关键区域及边界模糊区域的特征表达能力；同时采用软非极大值抑制（soft non-maximum suppression, Soft-NMS）替代传统非极大值抑制策略，以减少重叠目标场景中的漏检。②算法验证：实验数据集由开源创面图像和临床采集图像构成，共740张原始图像，经数据增强后扩展至5920张，并采用十折交叉验证进行评估。通过内部验证、外部验证、超参数调优和消融实验，采用精确率、召回率、平均精确率和F1分数等指标对模型性能进行评价。

结果 ①内部验证表明，同时在ResNet-50的Conv4_x和Conv5_x阶段嵌入CBAM时模型性能最佳；采用ResNet-50-CBAM作为主干网络时，模型检测效果优于VGG16和ResNet-50。②外部验证表明，WD-IFRCNN的精确率、召回率、平均精确率和F1分数分别达到92.31%、93.95%、92.33%和0.93，其中平均精确率较SSD、YOLOv4、YOLOv5、YOLOv8、DETR、RT-DETR和FR-CNN-FPN分别提高3.21%、2.30%、1.39%、0.86%、0.82%、0.37%和0.63%。③消融实验表明，CBAM、FMAM和Soft-NMS均对模型性能提升具有积极作用，三者联合时检测效果最佳。

结论 WD-IFRCNN能够有效增强模型对创面关键区域及模糊边界区域的特征表达能力，提高创面检测的准确性和稳定性，对复杂创面场景具有较好的适应性，可为临床创面评估与辅助诊断提供一定的技术支持。

Abstract:

Objective By introducing an attention enhancement mechanism and improving the post-processing strategy, the Faster Region-based Convolutional Neural Network (Faster R-CNN) is enhanced. The resulting improved Faster R-CNN method for wound detection (WD-IFRCNN) increases the accuracy and stability of wound detection.

Methods ① Algorithm construction: The 50-layer residual network (ResNet-50) is used as the backbone. In the fourth residual stage (convolutional stage 4, Conv4_x) and fifth residual stage (convolutional stage 5, Conv5_x), the fuzzy mask attention module (FMAM) and convolutional block attention module (CBAM) are embedded together to enhance the model's ability to represent features in key areas and blurry regions of the wound surface. At the same time, soft non-maximum suppression (Soft-NMS) replaces the traditional non-maximum suppression strategy to reduce missed detections in overlapping target scenarios. ② Algorithm validation: The experimental dataset consists of open-source wound images and clinically collected images, totaling 740 original images. After data augmentation, the dataset expands to 5920 images and is evaluated using ten-fold cross-validation. Model performance is assessed through internal validation, external validation, hyperparameter tuning, and ablation experiments, using metrics such as precision, recall, average precision, and F1 score.

Results ① Internal validation showed that the model performs best when CBAM is embedded in both the Conv4_x and Conv5_x stages of ResNet-50. When ResNet-50-CBAM is used as the backbone, the model's detection performance surpasses that of VGG16 and ResNet-50. ② External validation showed that WD-IFRCNN achieves an precision of 92.31%, recall of 93.95%, average precision of 92.33%, and F1 score of 0.93. The average precision was 3.21%, 2.30%, 1.39%, 0.86%, 0.82%, 0.37%, and 0.63% higher than SSD, YOLOv4, YOLOv5, YOLOv8, DETR, RT-DETR, and FR-CNN-FPN, respectively. ③ Ablation experiments showed that CBAM, FMAM, and Soft-NMS each positively impact model performance, with the best results achieved when all are used together.

Conclusion WD-IFRCNN effectively enhances the model's ability to represent features in key areas and blurry regions of the wound surface, improves the accuracy and stability of wound detection, and demonstrates good adaptability to complex wound scenarios. It can provide technical support for clinical wound assessment and auxiliary diagnosis.

一种用于创面检测的改进Faster R-CNN方法

An Improved Faster R-CNN Method for Wound Detection