HFS-YOLO11 Based Target Detection Algorithm for Thyroid Nodules
DOI:
https://doi.org/10.53469/wjimt.2025.08(05).18Keywords:
Target detection, Thyroid nodules, HFS-YOLO11Abstract
Aiming to address the accuracy bottleneck of the YOLO11 algorithm in thyroid nodule detection, this paper proposes an efficient and accurate haar field spatial-you only look once 11 (HFS-YOLO11) network. The network innovatively incorporates a multi-scale spatial pyramid attention (MSPA) module to enhance feature expression and establish long-range dependencies; introduces a haar wavelet-based downsampling (HWD) module to minimize the information loss during the sampling process; and replaces C3K2 with the receptive field attention convolutional (RFAConv) module at the neck layer to optimize spatial feature extraction and enhance the processing capability for large convolutional kernels. The experimental results show that HFS-YOLO11 significantly improves thyroid nodule detection, with a 3.9% improvement in mAP50, a 1.8% improvement in mAP50-95, a 3.2% improvement in recall, and a 3.6% improvement in precision.
References
Yang J, Shi X, Wang B, et al. Ultrasound image classification of thyroid nodules based on deep learning[J]. Frontiers in Oncology, 2022, 12: 905955.
Haugen B R, Alexander E K, Bible K C, et al. 2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the American Thyroid Association guidelines task force on thyroid nodules and differentiated thyroid cancer[J]. Thyroid, 2016, 26(1): 1-133.
Kitahara C M, Sosa J A. Understanding the ever-changing incidence of thyroid cancer[J]. Nature Reviews Endocrinology, 2020, 16(11): 617-618.
Li H, Weng J, Shi Y, et al. An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images[J]. Scientific reports, 2018, 8(1): 6600.
Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28.
Song W, Li S, Liu J, et al. Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition[J]. IEEE journal of biomedical and health informatics, 2018, 23(3): 1215-1224.
Wang L, Yang S, Yang S, et al. Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network[J]. World journal of surgical oncology, 2019, 17: 1-9.
Zhang L, Zhuang Y, Hua Z, et al. Automated location of thyroid nodules in ultrasound images with improved YOLOV3 network[J]. Journal of X-ray Science and Technology, 2021, 29(1): 75-90.
Guo R, Xu L, Guo J, et al. Automatic detection and classification algorithm of thyroid nodules in CT images based on YOLOv5s[C]//2023 9th International Conference on Computer and Communications (ICCC). IEEE, 2023: 1701-1706.
Li X, Yin P, Qu Y, et al. Research on Multi-Object Tracking Algorithm for Thyroid Nodules Based on ByteTrack[C]//2024 IEEE 3rd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA). IEEE, 2024: 1589-1592.
Yang D, Xia J, Li R, et al. Automatic thyroid nodule detection in ultrasound imaging with improved yolov5 neural network[J]. IEEE Access, 2024, 12: 22662-22670.
Russell B C, Torralba A, Murphy K P, et al. LabelMe: a database and web-based tool for image annotation[J]. International journal of computer vision, 2008, 77: 157-173.
Khanam R, Hussain M. Yolov11: An overview of the key architectural enhancements[J]. arXiv preprint arXiv:2410.17725, 2024.
Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.
Yu Y, Zhang Y, Cheng Z, et al. Multi-scale spatial pyramid attention mechanism for image recognition: An effective approach[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108261.
G. Xu, W. Liao, X. Zhang, C. Li, X. He, and X. Wu, “Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentation,” Pattern Recogn., vol. 143, Jul. 2023, Art. no. 109819.
Zhang X, Liu C, Yang D, et al. RFAConv: Innovating spatial attention and standard convolutional operation[J]. arXiv preprint arXiv:2304.03198, 2023.
Loshchilov I, Hutter F. Sgdr: Stochastic gradient descent with warm restarts[J]. arXiv preprint arXiv:1608.03983, 2016.
Lim K J, Choi C S, Yoon D Y, et al. Computer-aided diagnosis for the differentiation of malignant from benign thyroid nodules on ultrasonography[J]. Academic radiology, 2008, 15(7): 853-858.