Deng Kaixin, Wen Quan, Yang Fan, Ouyang Hang, Shi Zhuohang, Shuai Shiyu, Wu Zhaowang
College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, China.
PLoS One. 2025 May 13;20(5):e0320757. doi: 10.1371/journal.pone.0320757. eCollection 2025.
OrthoNets use the Gram-Schmidt process to achieve orthogonality among filters but do not impose constraints on the internal orthogonality of individual filters. To reduce the risk of overfitting, especially in scenarios with limited data such as medical image, this study explores an enhanced network that ensures the internal orthogonality within individual filters, named the Orthogonal Channel Shuffle Network ( OSNet). This network is integrated into the Detection Transformer (DETR) framework for brain tumor detection, resulting in the OS-DETR. To further optimize model performance, this study also incorporates deformable attention mechanisms and an Intersection over Union strategy that emphasizes the internal region influence of bounding boxes and the corner distance disparity. Experimental results on the Br35H brain tumor dataset demonstrate the significant advantages of OS-DETR over mainstream object detection frameworks. Specifically, OS-DETR achieves a Precision of 95.0%, Recall of 94.2%, mAP@50 of 95.7%, and mAP@50:95 of 74.2%. The code implementation and experimental results are available at https://github.com/dkx2077/OS-DETR.git.
正交网络（OrthoNets）使用格拉姆-施密特过程来实现滤波器之间的正交性，但不对单个滤波器的内部正交性施加约束。为了降低过拟合风险，尤其是在医学图像等数据有限的场景中，本研究探索了一种增强网络，该网络确保单个滤波器内部的正交性，名为正交通道混洗网络（OSNet）。该网络被集成到用于脑肿瘤检测的检测变压器（DETR）框架中，从而产生了OS-DETR。为了进一步优化模型性能，本研究还纳入了可变形注意力机制和一种交并比策略，该策略强调边界框的内部区域影响和角点距离差异。在Br35H脑肿瘤数据集上的实验结果证明了OS-DETR相对于主流目标检测框架的显著优势。具体而言，OS-DETR的精确率为95.0%，召回率为94.2%，mAP@50为95.7%，mAP@50:95为74.2%。代码实现和实验结果可在https://github.com/dkx2077/OS-DETR.git获取。
