{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T06:43:50Z","timestamp":1775803430128,"version":"3.50.1"},"reference-count":31,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Xinjiang Urumqi Hongshan Science and Technology Innovation Young Talents Program","award":["B241013006"],"award-info":[{"award-number":["B241013006"]}]},{"name":"Xinjiang Urumqi Hongshan Science and Technology Innovation Young Talents Program","award":["F2024203049"],"award-info":[{"award-number":["F2024203049"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Non-invasive ultrasound diagnosis, combined with deep learning, is frequently used for detecting thyroid diseases. However, real-time detection on portable devices faces limitations due to constrained computational resources, and existing models often lack sufficient capability for small object detection of thyroid nodules. To address this, this paper proposes an improved lightweight small object detection network framework called LISA-YOLO, which enhances the lightweight multi-scale collaborative fusion algorithm. The proposed framework exploits the inherent symmetrical characteristics of ultrasound images and the symmetrical architecture of the detection network to better capture and represent features of thyroid nodules. Specifically, an improved depthwise separable convolution algorithm replaces traditional convolution to construct a lightweight network (DG-FNet). Through symmetrical cross-scale fusion operations via FPN, detection accuracy is maintained while reducing computational overhead. Additionally, an improved bidirectional feature network (IMS F-NET) fully integrates the semantic and detailed information of high- and low-level features symmetrically, enhancing the representation capability for multi-scale features and improving the accuracy of small object detection. Finally, a collaborative attention mechanism (SAF-NET) uses a dual-channel and spatial attention mechanism to adaptively calibrate channel and spatial weights in a symmetric manner, effectively suppressing background noise and enabling the model to focus on small target areas in thyroid ultrasound images. Extensive experiments on two image datasets demonstrate that the proposed method achieves improvements of 2.3% in F1 score, 4.5% in mAP, and 9.0% in FPS, while maintaining only 2.6 M parameters and reducing GFLOPs from 6.1 to 5.8. The proposed framework provides significant advancements in lightweight real-time detection and demonstrates the important role of symmetry in enhancing the performance of ultrasound-based thyroid diagnosis.<\/jats:p>","DOI":"10.3390\/sym17081249","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T07:45:11Z","timestamp":1754466311000},"page":"1249","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LISA-YOLO: A Symmetry-Guided Lightweight Small Object Detection Framework for Thyroid Ultrasound Images"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8656-900X","authenticated-orcid":false,"given":"Guoqing","family":"Fu","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China"},{"name":"School of Information Engineering, Xinjiang Institute of Engineering, Urumqi 830023, China"}]},{"given":"Guanghua","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China"}]},{"given":"Wen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electromechanical Engineering, Xinjiang Institute of Engineering, Urumqi 830023, China"}]},{"given":"Hao","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"ref_1","first-page":"209","article-title":"Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"103039","DOI":"10.1016\/j.media.2023.103039","article-title":"A knowledge-interpretable multi-task learning framework for automated thyroid nodule diagnosis in ultrasound videos","volume":"91","author":"Wu","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1016\/j.bbe.2021.02.008","article-title":"Deep learning on ultrasound images of thyroid nodules","volume":"41","author":"Sharifi","year":"2021","journal-title":"Biocybern. Biomed. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"22662","DOI":"10.1109\/ACCESS.2024.3359367","article-title":"Automatic thyroid nodule detection in ultrasound imaging with improved yolov5 neural network","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Vahdati, S., Khosravi, B., Robinson, K.A., Rouzrokh, P., Moassefi, M., Akkus, Z., and Erickson, B.J. (2024). A multi-view deep learning model for thyroid nodules detection and characterization in ultrasound imaging. Bioengineering, 11.","DOI":"10.3390\/bioengineering11070648"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ajilisa, O.A., Jagathy Raj, V.P., and Sabu, M.K. (2023). A deep learning framework for the characterization of thyroid nodules from ultrasound images using improved inception network and multi-level transfer learning. Diagnostics, 13.","DOI":"10.3390\/diagnostics13142463"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhao, Z.-A., Chen, Y., Mao, Y.-J., and Cheung, J.C. (2025). Enhancing thyroid nodule detection in ultrasound images: A novel yolov8 architecture with a c2fa module and optimized loss functions. Echnologies, 13.","DOI":"10.3390\/technologies13010028"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yang, X., Geng, H., Wang, X., Li, L., An, X., and Cong, Z. (2024). Identification of lesion location and discrimination between benign and malignant findings in thyroid ultrasound imaging. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-83888-1"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ekong, F., Yu, Y., Patamia, R.A., Feng, X., Tang, Q., Mazumder, P., and Cai, J. (2022). Bayesian depth-wise convolutional neural network design for brain tumor mri classification. Diagnostics, 12.","DOI":"10.3390\/diagnostics12071657"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"325","DOI":"10.7326\/0003-4819-159-5-201309030-00006","article-title":"A prospective assessment defining the limitations of thyroid nodule pathologic evaluation","volume":"159","author":"Cibas","year":"2013","journal-title":"Ann. Intern. Med."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cao, Y., Zhong, X., Diao, W., Mu, J., Cheng, Y., and Jia, Z. (2021). Radiomics in differentiated thyroid cancer and nodules: Explorations, application, and limitations. Cancers, 13.","DOI":"10.3390\/cancers13102436"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4490","DOI":"10.1038\/onc.2011.626","article-title":"A general method to derive robust organ-specific gene expression-based differentiation indices: Application to thyroid cancer diagnostic","volume":"31","author":"Tarabichi","year":"2012","journal-title":"Oncogene"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/5052435","article-title":"Review of deep learning approaches for thyroid cancer diagnosis","volume":"2022","author":"Anari","year":"2022","journal-title":"Math. Probl. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/S1470-2045(18)30762-9","article-title":"Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: A retrospective, multicohort, diagnostic study","volume":"20","author":"Li","year":"2019","journal-title":"Lancet. Oncol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7959","DOI":"10.1002\/mp.15319","article-title":"A deep learning-based method for detecting and classifying the ultrasound images of suspicious thyroid nodules","volume":"48","author":"Zhao","year":"2021","journal-title":"Med. Phys."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tao, Y., Yu, Y., Wu, T., Xu, X., Dai, Q., Kong, H., Zhang, L., Yu, W., Leng, X., and Qiu, W. (2022). Deep learning for the diagnosis of suspicious thyroid nodules based on multimodal ultrasound images. Front. Oncol., 12.","DOI":"10.3389\/fonc.2022.1012724"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"101905","DOI":"10.1016\/j.eclinm.2023.101905","article-title":"Ultrasound image-based deep learning to assist in diagnosing gross extrathyroidal extension thyroid cancer: A retrospective multicenter study","volume":"58","author":"Qi","year":"2023","journal-title":"EClinicalMedicine"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6355","DOI":"10.1002\/mp.14543","article-title":"Thyroid nodules risk stratification through deep learning based on ultrasound images","volume":"47","author":"Bai","year":"2020","journal-title":"Med. Phys."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, G., Cao, H., Hu, K., Wang, Q., Deng, Y., Gao, J., and Tang, Y. (2025). Geometry-aware 3d point cloud learning for precise cutting-point detection in unstructured field environments. J. Field Robot.","DOI":"10.1002\/rob.22567"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"244","DOI":"10.36548\/jiip.2024.3.003","article-title":"Enhanced early detection of thyroid abnormalities using a hybrid deep learning model: A sequential cnn and k-means clustering approach","volume":"6","author":"Gummalla","year":"2024","journal-title":"J. Innov. Image Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"6212759","DOI":"10.1155\/2019\/6212759","article-title":"Thyroid diagnosis from spect images using convolutional neural network with optimization","volume":"2019","author":"Ma","year":"2019","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Etehadtavakol, M., Etehadtavakol, M., and Ng, E.Y.K. (2024). Enhanced thyroid nodule segmentation through u-net and vgg16 fusion with feature engineering: A comprehensive study. Comput. Methods Programs Biomed., 251.","DOI":"10.1016\/j.cmpb.2024.108209"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3026","DOI":"10.1109\/ACCESS.2024.3523766","article-title":"Red-net: A neural network for 3d thyroid segmentation in chest ct using residual and dilated convolutions for measuring thyroid volume","volume":"13","author":"Kim","year":"2025","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, W., Lu, W., Li, Y., Chen, F., Jiang, F., Wei, J., Wang, B., and Zhao, W. (2025). Parathyroid gland detection based on multi-scale weighted fusion attention mechanism. Electronics, 14.","DOI":"10.3390\/electronics14061092"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Alhussainan, N.F., Ben Youssef, B., and Ben Ismail, M.M. (2024). A deep learning approach for brain tumor firmness detection based on five different yolo versions: YOLOv3\u2013YOLOv7. Computation, 12.","DOI":"10.3390\/computation12030044"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"16189","DOI":"10.1109\/ACCESS.2024.3359418","article-title":"Automated brain tumor segmentation and classification in mri using yolo-based deep learning","volume":"12","author":"Almufareh","year":"2024","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s12559-023-10189-6","article-title":"A yolo-based model for breast cancer detection in mammograms","volume":"16","author":"Prinzi","year":"2024","journal-title":"Cogn. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhou, Y.-T., Yang, T.-Y., Han, X.-H., and Piao, J.-C. (2024). Thyroid-detr: Thyroid nodule detection model with transformer in ultrasound images. Biomed. Signal Process. Control, 98.","DOI":"10.1016\/j.bspc.2024.106762"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gondi, S., and Nagaral, M.U. (2024, January 20\u201321). YOLOv8 based an automated segmentation and classification of thyroid nodules using usg images. Proceedings of the 2024 International Conference on Innovation and Novelty in Engineering and Technology (INNOVA), Vijayapura, India.","DOI":"10.1109\/INNOVA63080.2024.10847001"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ghabri, H., Fathallah, W., Hamroun, M., Othman, S.B., Bellali, H., Sakli, H., and Abdelkrim, M.N. (2023, January 2\u20135). Ai-enhanced thyroid detection using yolo to empower healthcare professionals. Proceedings of the 2023 IEEE International Workshop on Mechatronic Systems Supervision (IW_MSS), Hammamet, Tunisia.","DOI":"10.1109\/IW_MSS59200.2023.10369271"},{"key":"ref_31","first-page":"967","article-title":"A lightweight network for automatic thyroid nodules location and recognition with high speed and accuracy in ultrasound images","volume":"30","author":"Zhou","year":"2022","journal-title":"J. X-Ray Sci. Technol."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/8\/1249\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:24:06Z","timestamp":1760034246000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/8\/1249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":31,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["sym17081249"],"URL":"https:\/\/doi.org\/10.3390\/sym17081249","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,6]]}}}