Xiong Mengying, Wu Aiping, Yang Yue, Fu Qingqing
School of Electronic Information and Electrical Engineering, Yangtze University, Jingzhou 434023, China.
School of Computing Science and Artificial Intelligence, Suzhou City University, Suzhou 215104, China.
Sensors (Basel). 2025 Jun 11;25(12):3645. doi: 10.3390/s25123645.
Aiming at the problems of inaccurate segmentation and low detection efficiency caused by irregular tumor shape and large size differences in brain MRI images, this study proposes a brain tumor segmentation algorithm, YOLO-BT, based on YOLOv11. YOLO-BT uses UNetV2 as the backbone network to enhance the feature extraction ability of key regions through the attention mechanism. The BiFPN structure is introduced into the neck network to replace the traditional feature splicing method, realize the two-way fusion of cross-scale features, improve detection accuracy, and reduce the amount of calculations required. The D-LKA mechanism is introduced into the C3k2 structure, and the large convolution kernel is used to process complex image information to enhance the model's ability to characterize different scales and irregular tumors. In this study, multiple sets of experiments were performed on the Figshare Brain Tumor dataset to test the performance of YOLO-BT. The data results show that YOLO-BT improves Precision by 2.7%, Recall, mAP50 by 0.9%, and mAP50-95 by 0.3% in the candidate box-based evaluation compared to YOLOv11. In mask-based evaluations, Precision improved by 2.5%, Recall by 2.8%, mAP50 by 1.1%, and mAP50-95 by 0.5%. At the same time, the mIOU increased by 6.1%, and the Dice coefficient increased by 3.6%. It can be seen that the YOLO-BT algorithm is suitable for brain tumor detection and segmentation.
针对脑磁共振成像（MRI）图像中肿瘤形状不规则、大小差异大导致分割不准确和检测效率低的问题，本研究提出了一种基于YOLOv11的脑肿瘤分割算法YOLO - BT。YOLO - BT使用UNetV2作为主干网络，通过注意力机制增强关键区域的特征提取能力。将BiFPN结构引入颈部网络以取代传统的特征拼接方法，实现跨尺度特征的双向融合，提高检测精度并减少所需的计算量。将D - LKA机制引入C3k2结构，使用大卷积核处理复杂图像信息，以增强模型表征不同尺度和不规则肿瘤的能力。在本研究中，对Figshare脑肿瘤数据集进行了多组实验，以测试YOLO - BT的性能。数据结果表明，与YOLOv11相比，在基于候选框的评估中，YOLO - BT的精确率提高了2.7%，召回率、mAP50提高了0.9%，mAP50 - 95提高了0.3%。在基于掩码的评估中，精确率提高了2.5%，召回率提高了2.8%，mAP50提高了1.1%，mAP50 - 95提高了0.5%。同时，交并比（mIOU）提高了6.1%，骰子系数提高了3.6%。可见，YOLO - BT算法适用于脑肿瘤检测与分割。
