{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:00:24Z","timestamp":1766127624214,"version":"3.48.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key Project of Natural Science Basic Research Program of Shaanxi","award":["2025JC-QYXQ-041"],"award-info":[{"award-number":["2025JC-QYXQ-041"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00530-025-02013-y","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T08:12:53Z","timestamp":1760083973000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tool-YOLO: a target detection network based on feature extraction and feature fusion"],"prefix":"10.1007","volume":"31","author":[{"given":"Guanqun","family":"Guo","sequence":"first","affiliation":[]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Boqiang","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Jiayu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Wenjie","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"2013_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103945","volume":"149","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Sun, Q., Liu, Z., Gu, L.: Visual detection and tracking algorithms for minimally invasive surgical instruments: a comprehensive review of the state-of-the-art. Robot. Auton. Syst. 149, 103945 (2022)","journal-title":"Robot. Auton. Syst."},{"key":"2013_CR2","doi-asserted-by":"publisher","unstructured":"Agustinos, A., Wolf, R., Long, J. A., Cinquin, P., Voros, S.: Visual servoing of a robotic endoscope holder based on surgical instrument tracking. In: Proceedings of the 5th IEEE RAS\/EMBS International Conference on Biomedical Robotics and Biomechatronics, pp. 13-18, (2014). https:\/\/doi.org\/10.1109\/BIOROB.2014.6913744.","DOI":"10.1109\/BIOROB.2014.6913744."},{"issue":"3","key":"2013_CR3","doi-asserted-by":"publisher","DOI":"10.1002\/rcs.70083","volume":"21","author":"L Zhang","year":"2025","unstructured":"Zhang, L., Guo, G., Wang, W.: Uk-yolov10: deep learning-based detection of surgical instruments. Int. J. Med. Robot. 21(3), e70083 (2025). https:\/\/doi.org\/10.1002\/rcs.70083","journal-title":"Int. J. Med. Robot."},{"issue":"2","key":"2013_CR4","first-page":"23","volume":"14","author":"J Sherman","year":"2010","unstructured":"Sherman, J., Cadeddu, J.A., Boguslavsky, S., Fernandez, R.: Surgical instrumentation in laparoscopic surgery: maintenance and inspection guidelines. J. Minim. Invasive Surg. 14(2), 23\u201329 (2010)","journal-title":"J. Minim. Invasive Surg."},{"issue":"4","key":"2013_CR5","first-page":"649","volume":"98","author":"PP Shadduck","year":"2018","unstructured":"Shadduck, P.P., Braxton, S.W., Hong, J.: Advances in laparoscopic instruments: current trends and future innovations. Surg. Clin. N. Am. 98(4), 649\u2013666 (2018)","journal-title":"Surg. Clin. N. Am."},{"issue":"6","key":"2013_CR6","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1016\/j.jmig.2015.05.004","volume":"22","author":"F Fanfani","year":"2015","unstructured":"Fanfani, F., Restaino, S., Alletti, S.G., et al.: Telelap alf-x robotic-assisted laparoscopic hysterectomy: feasibility and perioperative outcomes. J. Minim. Invasive Gynecol. 22(6), 1011\u20131017 (2015)","journal-title":"J. Minim. Invasive Gynecol."},{"issue":"4","key":"2013_CR7","doi-asserted-by":"publisher","first-page":"6473","DOI":"10.1109\/LRA.2021.3094644","volume":"6","author":"J Sandoval","year":"2021","unstructured":"Sandoval, J., Laribi, M.A., Faure, J.P., et al.: Towards an autonomous robot-assistant for laparoscopy using exteroceptive sensors: feasibility study and implementation. IEEE Robot. Autom. Lett. 6(4), 6473\u20136480 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2013_CR8","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s11548-022-02777-y","volume":"18","author":"Q Zheng","year":"2023","unstructured":"Zheng, Q., Yang, R., Ni, X., et al.: Development and validation of a deep learning-based laparoscopic system for improving video quality. Int. J. Comput. Assist. Radiol. Surg. 18, 257\u2013268 (2023). https:\/\/doi.org\/10.1007\/s11548-022-02777-y","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"2013_CR9","doi-asserted-by":"publisher","unstructured":"Kletz, S., Schoeffmann, K., Benois-Pineau, J., Husslein, H.: Identifying surgical instruments in laparoscopy using deep learning instance segmentation. In: Proceedings of the International Conference on Content-Based Multimedia Indexing (CBMI), pp. 1-6 (2019). https:\/\/doi.org\/10.1109\/CBMI.2019.8877379.","DOI":"10.1109\/CBMI.2019.8877379."},{"key":"2013_CR10","doi-asserted-by":"publisher","unstructured":"Fox, M., Taschwer, M., Schoeffmann, K.: Pixel-based tool segmentation in cataract surgery videos with mask R-CNN. In: Proceedings of the IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), pp. 565-568 (2020). https:\/\/doi.org\/10.1109\/CBMS49503.2020.00112.","DOI":"10.1109\/CBMS49503.2020.00112."},{"key":"2013_CR11","doi-asserted-by":"publisher","unstructured":"Ciaparrone, G., Bardozzo, F., Priscoli, M. D., Kallewaard, J. L., Zuluaga, M. R., Tagliaferri, R.: A comparative analysis of multi-backbone mask R-CNN for surgical tools detection. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 1-8 (2020). https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9206854.","DOI":"10.1109\/IJCNN48605.2020.9206854."},{"key":"2013_CR12","doi-asserted-by":"publisher","unstructured":"Sanchez-Matilla, R., Robu, M., Luengo, I., Stoyanov, D.: Scalable joint detection and segmentation of surgical instruments with weak supervision. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Cham, Switzerland: Springer, pp. 501-511 (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_47","DOI":"10.1007\/978-3-030-87196-3_47"},{"issue":"4","key":"2013_CR13","doi-asserted-by":"publisher","first-page":"1068","DOI":"10.1109\/TMRB.2022.3214377","volume":"4","author":"K Lam","year":"2022","unstructured":"Lam, K., Lo, F.P.-W., An, Y., Darzi, A., Kinross, J.M., Purkayastha, S., Lo, B.: Deep learning for instrument detection and assessment of operative skill in surgical videos. IEEE Trans. Med. Robot. Bionics 4(4), 1068\u20131071 (2022). https:\/\/doi.org\/10.1109\/TMRB.2022.3214377","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"2013_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Y., He, G., Ahmed, M. F.: A real-time laparoscopic surgical instrument detection system based on YOLOv5. In: Proceedings of the 16th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1-6 (2023)","DOI":"10.1109\/CISP-BMEI60920.2023.10373249"},{"key":"2013_CR15","doi-asserted-by":"crossref","unstructured":"Choi, B., Jo, K., Choi, S. et al., Surgical-tools detection based on convolutional neural network in laparoscopic robot-assisted surgery. In: Proceedings of the 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, pp. 1756-1759 (2017)","DOI":"10.1109\/EMBC.2017.8037183"},{"key":"2013_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Q., Sun, G., et al.: Object detection of surgical instrument based on YOLOv4. In: Proceedings of the 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM), IEEE, pp. 578-581 (2021)","DOI":"10.1109\/ICARM52023.2021.9536075"},{"issue":"4","key":"2013_CR17","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/TMRB.2023.3310031","volume":"5","author":"W Wang","year":"2023","unstructured":"Wang, W., Luo, Y., Wang, J., Wang, X., Song, H.: ToolNet-X: surgical instrument detection combined with high-order spatial interaction. IEEE Trans. Med. Robot. Bionics 5(4), 857\u2013866 (2023)","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"2013_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107548","volume":"105","author":"Z Xu","year":"2025","unstructured":"Xu, Z., Luo, F., Chen, F., Wu, H., Yu, M.: Surgical tool detection in open surgery based on improved-yolov8. Biomed. Signal Process. Control 105, 107548 (2025). https:\/\/doi.org\/10.1016\/j.bspc.2025.107548","journal-title":"Biomed. Signal Process. Control"},{"key":"2013_CR19","unstructured":"Wang, A., Chen, H., Liu, L., et al., YOLOv10: real-time end-to-end object detection, arXiv preprint arXiv:2405.14458, (2024)"},{"key":"2013_CR20","doi-asserted-by":"crossref","unstructured":"Jin, A., Yeung, S., Jopling, J., Krause, J., Azagury, D., Milstein, A., Fei-Fei, L.: Tool detection and operative skill assessment in surgical videos using region-based convolutional neural networks. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 691-699 (2018)","DOI":"10.1109\/WACV.2018.00081"},{"key":"2013_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3333034","author":"A Murali","year":"2023","unstructured":"Murali, A., Alapatt, D., Mascagni, P., Vardazaryan, A., Garcia, A., Okamoto, N., Mutter, D., Padoy, N.: Latent graph representations for critical view of safety assessment. IEEE Trans. Med. Imag. (2023). https:\/\/doi.org\/10.1109\/TMI.2023.3333034","journal-title":"IEEE Trans. Med. Imag."},{"issue":"9","key":"2013_CR22","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2013_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"2013_CR24","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s41095-021-0227-8","volume":"7","author":"A Hamdi","year":"2021","unstructured":"Hamdi, A., Li, Z., Li, T., Yang, J.: Attention mechanisms in computer vision: a survey. Comput. Vis. Media 7(4), 385\u2013409 (2021). https:\/\/doi.org\/10.1007\/s41095-021-0227-8","journal-title":"Comput. Vis. Media"},{"key":"2013_CR25","doi-asserted-by":"crossref","unstructured":"Yun, S., Ro, Y.: Shvit: single-head vision transformer with memory efficient macro design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5756-5767 (2024)","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"2013_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need, in advances in neural information processing systems (NeurIPS), (2017)"},{"key":"2013_CR27","doi-asserted-by":"crossref","unstructured":"Shi, D.: TransNeXt: robust foveal visual perception for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17773-17783 (2024)","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"2013_CR28","doi-asserted-by":"publisher","first-page":"90847","DOI":"10.1109\/ACCESS.2020.2994222","volume":"8","author":"M Hasnain","year":"2020","unstructured":"Hasnain, M., et al.: Evaluating trust prediction and confusion matrix measures for web services ranking. IEEE Access 8, 90847\u201390861 (2020)","journal-title":"IEEE Access"},{"key":"2013_CR29","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et al.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9627-9636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2013_CR30","doi-asserted-by":"publisher","first-page":"23748","DOI":"10.1109\/ACCESS.2020.2969885","volume":"8","author":"B Zhang","year":"2020","unstructured":"Zhang, B., Wang, S., Dong, L., et al.: Surgical tools detection based on modulated anchoring network in laparoscopic videos. IEEE Access 8, 23748\u201323758 (2020)","journal-title":"IEEE Access"},{"issue":"1","key":"2013_CR31","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., et al.: Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"2","key":"2013_CR32","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/TCSVT.2020.2986402","volume":"31","author":"S Zhang","year":"2020","unstructured":"Zhang, S., Wen, L., Lei, Z., et al.: Refinedet++: single-shot refinement neural network for object detection. IEEE Trans. Circuits Syst. Video Technol. 31(2), 674\u2013687 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2013_CR33","doi-asserted-by":"crossref","unstructured":"Garcia-Peraza-Herrera, L. C., Li, W., Fidon, L., et al. ToolNet: holistically nested real-time segmentation of robotic surgical tools. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5717-5722 (2017)","DOI":"10.1109\/IROS.2017.8206462"},{"issue":"1","key":"2013_CR34","doi-asserted-by":"publisher","first-page":"132","DOI":"10.3390\/rs10010132","volume":"10","author":"X Yang","year":"2018","unstructured":"Yang, X., Sun, H., Fu, K., Yang, Y., Liang, X., Li, X.: Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sens. 10(1), 132 (2018). https:\/\/doi.org\/10.3390\/rs10010132","journal-title":"Remote Sens."},{"issue":"6","key":"2013_CR35","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2013_CR36","doi-asserted-by":"crossref","unstructured":"Wang, C. Y., Bochkovskiy, A., Liao, H. Y. M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"2013_CR37","first-page":"107984","volume":"37","author":"A Wang","year":"2025","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J.: Yolov10: real-time end-to-end object detection. Adv. Neural. Inf. Process. Syst. 37, 107984\u2013108011 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2013_CR38","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A. C.: SSD: Single shot multibox detector. In: Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, Proceedings, Part I, vol. 14, pp. 21-37. [Online]. (2016). Available: https:\/\/arxiv.org\/abs\/1512.02325","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2013_CR39","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213-229 (2020). [Online]. Available: https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2013_CR40","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1007\/s11548-024-03115-0","volume":"19","author":"X Pan","year":"2024","unstructured":"Pan, X., Bi, M., Wang, H., et al.: DBH-YOLO: a surgical instrument detection method based on feature separation in laparoscopic surgery. Int. J. Comput. Assist. Radiol. Surg. 19, 2215\u20132225 (2024). https:\/\/doi.org\/10.1007\/s11548-024-03115-0","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"2013_CR41","doi-asserted-by":"crossref","unstructured":"Wang, C. Y., Yeh, I. H., Liao, H. Y. M.: YOLOv9: Learning what you want to learn using programmable gradient information. In: European Conference on Computer Vision, pp. 1-21, Springer, Cham, (2025)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"2013_CR42","doi-asserted-by":"crossref","unstructured":"Feng, Y., Huang, J., Du, S., Ying, S., Yong, J. H., Li, Y., et al., Hyper-YOLO: When visual object detection meets hypergraph computation, IEEE Transactions on Pattern Analysis and Machine Intelligence, (2024)","DOI":"10.1109\/TPAMI.2024.3524377"},{"key":"2013_CR43","unstructured":"Yu, Z., Huang, H., Chen, W., Su, Y., Liu, Y., Wang, X.: Yolo-facev2: A scale and occlusion aware face detector, (2022). arXiv preprint arXiv:2208.02019"},{"key":"2013_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L.: Microsoft COCO: Common Objects in Context, in Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, Springer International Publishing, pp. 740\u2013755 (2014). https:\/\/arxiv.org\/abs\/1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02013-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02013-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02013-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:58:12Z","timestamp":1766127492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02013-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":44,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2013"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02013-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"assertion":[{"value":"31 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"424"}}