{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:43:37Z","timestamp":1772793817767,"version":"3.50.1"},"reference-count":57,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100015548","name":"Vietnam National University, Hanoi","doi-asserted-by":"crossref","award":["QG.24.63"],"award-info":[{"award-number":["QG.24.63"]}],"id":[{"id":"10.13039\/100015548","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Accurate and real-time surgical tool detection is essential in minimally invasive surgery (MIS) to ensure safe and effective computer-assisted interventions (CAI) and robot-assisted surgery (RAS). However, achieving high accuracy under the strict computational constraints of embedded surgical platforms remains a significant challenge. This article introduces a set of enhanced lightweight You Only Look Once (YOLO)v8 variants specifically tailored for real-time surgical tool localization. The proposed architectures integrate several key innovations: Ghost Convolution for efficient feature extraction, a C2f-Ghost module for compact representation, and the SC3T module, which synergizes Transformer blocks with Spatial Pyramid Pooling. Additionally, attention mechanisms\u2014including the Context Augmentation Module (CAM) and Convolutional Block Attention Module (CBAM)\u2014are incorporated to refine feature discriminability. Furthermore, the Scylla-Intersection over Union (SIoU) loss is employed to optimize bounding box regression for elongated instruments. Evaluations on the public m2cai16-tool-locations dataset demonstrate that the best variant achieves 95.7% mAP@0.5 while reducing parameters and Giga FLOating-point Operation(s) Per Seconds (GFLOPs) by up to 3\u00d7 and 1.8\u00d7, respectively, compared to the YOLOv8 baseline. These results indicate that our design offers a competitive accuracy-efficiency trade-off, facilitating practical deployment in resource-constrained, real-time surgical systems.<\/jats:p>","DOI":"10.7717\/peerj-cs.3622","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T08:30:21Z","timestamp":1772785821000},"page":"e3622","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight YOLOv8 variants for enhanced real-time surgical tool detection"],"prefix":"10.7717","volume":"12","author":[{"given":"Tuan Manh","family":"Do","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thai Dinh","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai Xuan","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"10.7717\/peerj-cs.3622\/ref-1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934","article-title":"YOLOv4: optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"issue":"2","key":"10.7717\/peerj-cs.3622\/ref-2","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1016\/j.media.2016.09.003","article-title":"Vision-based and marker-less surgical tool detection and tracking: a review of the literature","volume":"35","author":"Bouget","year":"2017","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.3622\/ref-3","first-page":"6154","article-title":"Cascade R-CNN: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.7717\/peerj-cs.3622\/ref-4","first-page":"1756","article-title":"Surgical-tools detection based on convolutional neural network in laparoscopic robot-assisted surgery","author":"Choi","year":"2017"},{"key":"10.7717\/peerj-cs.3622\/ref-5","first-page":"576","article-title":"Human detection based yolo backbones-transformer in UAVs","author":"Do","year":"2023"},{"key":"10.7717\/peerj-cs.3622\/ref-6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"5","key":"10.7717\/peerj-cs.3622\/ref-7","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/tmi.2017.2787672","article-title":"Articulated multi-instrument 2-D pose estimation using fully convolutional networks","volume":"37","author":"Du","year":"2018","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3622\/ref-8","first-page":"84","article-title":"Real-time segmentation of non-rigid surgical tools based on deep learning and tracking","author":"Garc\u00eda-Peraza-Herrera","year":"2016"},{"key":"10.7717\/peerj-cs.3622\/ref-9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.12740","article-title":"SIOU loss: more powerful learning for bounding box regression","author":"Gevorgyan","year":"2022"},{"issue":"3","key":"10.7717\/peerj-cs.3622\/ref-10","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: a survey","volume":"8","author":"Guo","year":"2022","journal-title":"Computational Visual Media"},{"key":"10.7717\/peerj-cs.3622\/ref-11","first-page":"1580","article-title":"GhostNet: more features from cheap operations","author":"Han","year":"2020"},{"issue":"9","key":"10.7717\/peerj-cs.3622\/ref-12","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/tpami.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3622\/ref-13","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.7717\/peerj-cs.3622\/ref-14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.04861","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"10.7717\/peerj-cs.3622\/ref-15","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"issue":"7","key":"10.7717\/peerj-cs.3622\/ref-16","doi-asserted-by":"publisher","first-page":"677","DOI":"10.3390\/machines11070677","article-title":"YOLO-v1 to YOLO-v8, the rise of yolo and its complementary nature toward digital manufacturing and industrial defect detection","volume":"11","author":"Hussain","year":"2023","journal-title":"Machines"},{"key":"10.7717\/peerj-cs.3622\/ref-17","first-page":"691","article-title":"Tool detection and operative skill assessment in surgical videos using region-based convolutional neural networks","author":"Jin","year":"2018"},{"key":"10.7717\/peerj-cs.3622\/ref-18","article-title":"Ultralytics YOLOv5","author":"Jocher","year":"2020"},{"key":"10.7717\/peerj-cs.3622\/ref-19","article-title":"Ultralytics YOLOv8 (Version 8.0.0) Computer software","author":"Jocher","year":"2023"},{"issue":"2","key":"10.7717\/peerj-cs.3622\/ref-20","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/s40846-019-00503-9","article-title":"Designing a new endoscope for panoramic-view with focus-area 3D-vision in minimally invasive surgery","volume":"40","author":"Kim","year":"2020","journal-title":"Journal of Medical and Biological Engineering"},{"key":"10.7717\/peerj-cs.3622\/ref-21","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI52829.2022.9761454","article-title":"A novel deep learning architecture by integrating visual simultaneous localization and mapping (VSLAM) into CNN for real-time surgical video analysis","author":"Lan","year":"2022"},{"key":"10.7717\/peerj-cs.3622\/ref-22","first-page":"537","article-title":"Robust surgical tool detection in laparoscopic surgery using YOLOv8\u00a0model","author":"Le","year":"2023"},{"key":"10.7717\/peerj-cs.3622\/ref-23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976","article-title":"YOLOv6: a single-stage object detection framework for industrial applications","author":"Li","year":"2022"},{"key":"10.7717\/peerj-cs.3622\/ref-24","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.7717\/peerj-cs.3622\/ref-25","first-page":"21","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.7717\/peerj-cs.3622\/ref-26","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"issue":"7","key":"10.7717\/peerj-cs.3622\/ref-27","doi-asserted-by":"publisher","first-page":"105670","DOI":"10.1016\/j.bspc.2023.105670","article-title":"SINet: a hybrid deep CNN model for real-time detection and segmentation of surgical instruments","volume":"88","author":"Liu","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"issue":"9","key":"10.7717\/peerj-cs.3622\/ref-28","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1038\/s41551-017-0132-7","article-title":"Surgical data science for next-generation interventions","volume":"1","author":"Maier-Hein","year":"2017","journal-title":"Nature Biomedical Engineering"},{"issue":"11","key":"10.7717\/peerj-cs.3622\/ref-29","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1007\/s11548-024-03115-0","article-title":"DBH-YOLO: a surgical instrument detection method based on feature separation in laparoscopic surgery","volume":"19","author":"Pan","year":"2024","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"10.7717\/peerj-cs.3622\/ref-30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2022.3162596","article-title":"Autonomous recognition of multiple surgical instruments tips based on arrow OBB-YOLO network","volume":"71","author":"Peng","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.7717\/peerj-cs.3622\/ref-31","doi-asserted-by":"crossref","DOI":"10.1109\/ISSC61953.2024.10603096","article-title":"Cholecystectomy surgical instrument detection using variants of YOLOv8","author":"Raja","year":"2024"},{"key":"10.7717\/peerj-cs.3622\/ref-32","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.7717\/peerj-cs.3622\/ref-33","first-page":"7263","article-title":"YOLO9000: better, faster, stronger","author":"Redmon","year":"2017"},{"key":"10.7717\/peerj-cs.3622\/ref-34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767","article-title":"YOLOv3: an incremental improvement","author":"Redmon","year":"2018"},{"issue":"6","key":"10.7717\/peerj-cs.3622\/ref-35","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/tpami.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3622\/ref-36","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.7717\/peerj-cs.3622\/ref-37","first-page":"2195","article-title":"Endoscopic vision based tracking of multiple surgical instruments in robot-assisted surgery","author":"Ryu","year":"2012"},{"issue":"7","key":"10.7717\/peerj-cs.3622\/ref-38","doi-asserted-by":"publisher","first-page":"1542","DOI":"10.1109\/tmi.2017.2665671","article-title":"Detection and localization of robotic tools in robot-assisted surgery videos using deep neural networks for region proposal and detection","volume":"36","author":"Sarikaya","year":"2017","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3622\/ref-39","doi-asserted-by":"publisher","first-page":"228853\u2013228862","DOI":"10.1109\/access.2020.3046258","article-title":"Real-time surgical tool detection in minimally invasive surgery based on attention-guided convolutional neural network","volume":"8","author":"Shi","year":"2020","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3622\/ref-40","article-title":"What is YOLOv8? A complete guide","author":"Solawetz","year":"2024"},{"key":"10.7717\/peerj-cs.3622\/ref-41","article-title":"Surgical tools dataset. Roboflow Universe, Open Source Dataset","author":"Surgical Tools","year":"2022"},{"key":"10.7717\/peerj-cs.3622\/ref-42","first-page":"10781","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020"},{"issue":"4","key":"10.7717\/peerj-cs.3622\/ref-43","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1080\/21681163.2022.2150688","article-title":"A semi-supervised teacher-student framework for surgical tool detection and localization","volume":"11","author":"Teevno","year":"2023","journal-title":"Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization"},{"key":"10.7717\/peerj-cs.3622\/ref-44","first-page":"9627","article-title":"FCOS: fully convolutional one-stage object detection","author":"Tian","year":"2019"},{"issue":"1","key":"10.7717\/peerj-cs.3622\/ref-45","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/tmi.2016.2593957","article-title":"EndoNet: a deep architecture for recognition tasks on laparoscopic videos","volume":"36","author":"Twinanda","year":"2016","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3622\/ref-46","first-page":"7464","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"issue":"4","key":"10.7717\/peerj-cs.3622\/ref-47","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/tmrb.2023.3310031","article-title":"ToolNet-X: surgical instrument detection combined with high-order spatial interaction","volume":"5","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Medical Robotics and Bionics"},{"key":"10.7717\/peerj-cs.3622\/ref-48","doi-asserted-by":"publisher","first-page":"181723\u2013181732","DOI":"10.1109\/access.2020.3028910","article-title":"Surgical tools detection based on training sample adaptation in laparoscopic videos","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3622\/ref-49","article-title":"YOLOv9: learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"issue":"5","key":"10.7717\/peerj-cs.3622\/ref-50","doi-asserted-by":"publisher","first-page":"2221","DOI":"10.21203\/rs.3.rs-1730847\/v1","article-title":"Research on laparoscopic surgical instrument detection technology based on multi-attention-enhanced feature pyramid network","volume":"17","author":"Wang","year":"2023","journal-title":"Signal, Image and Video Processing"},{"key":"10.7717\/peerj-cs.3622\/ref-51","doi-asserted-by":"crossref","DOI":"10.1109\/ITC-CSCC.2019.8793382","article-title":"An improved YOLOv3-based neural network for de-identification technology","author":"Won","year":"2019"},{"key":"10.7717\/peerj-cs.3622\/ref-52","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.7717\/peerj-cs.3622\/ref-53","article-title":"Context augmentation and feature refinement network for tiny object detection","author":"Xiao","year":"2022"},{"key":"10.7717\/peerj-cs.3622\/ref-54","doi-asserted-by":"publisher","first-page":"23748","DOI":"10.1109\/access.2020.2969885","article-title":"Surgical tools detection based on modulated anchoring network in laparoscopic videos","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3622\/ref-55","first-page":"6848","article-title":"ShuffleNet: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018"},{"issue":"6","key":"10.7717\/peerj-cs.3622\/ref-56","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1049\/htl.2019.0064","article-title":"Real-time surgical instrument detection in robot-assisted surgery using a convolutional neural network cascade","volume":"6","author":"Zhao","year":"2019","journal-title":"Healthcare Technology Letters"},{"key":"10.7717\/peerj-cs.3622\/ref-57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.07850","article-title":"Objects as points","author":"Zhou","year":"2019"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3622.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3622.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3622.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3622.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T08:30:27Z","timestamp":1772785827000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":57,"alternative-id":["10.7717\/peerj-cs.3622"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3622","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"article-number":"e3622"}}