Autonomous Recognition of Multiple Surgical Instruments Tips Based on Arrow OBB-YOLO Network

Peng, Jianqing; Chen, Qihan; Kang, Liang; Jie, Haiqing; Yu, Han

doi:10.1109/tim.2022.3162596

Cited by 20 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YOLOv8-OBB utilizes the corner points (obtained from handling the ground truth information for object detection or directly provided in the dataset) for internal training purposes. 23) The model treats these points as the ground truth representation of the object during loss calculations and network optimization. While the model trains using corner points internally, it leverages the xywhr format for predicted outputs.…”

Section: Methodsmentioning

confidence: 99%

Deep Learning-Based Localization and Orientation Estimation of Pedicle Screws in Spinal Fusion Surgery

Kim,

Koo,

Lee

2024

Korean J Neurotrauma

View full text Add to dashboard Cite

Objective This study investigated the application of a deep learning-based object detection model for accurate localization and orientation estimation of spinal fixation surgical instruments during surgery. Methods We employed the You Only Look Once (YOLO) object detection framework with oriented bounding boxes (OBBs) to address the challenge of non-axis-aligned instruments in surgical scenes. The initial dataset of 100 images was created using brochure and website images from 11 manufacturers of commercially available pedicle screws used in spinal fusion surgeries, and data augmentation was used to expand 300 images. The model was trained, validated, and tested using 70%, 20%, and 10% of the images of lumbar pedicle screws, with the training process running for 100 epochs. Results The model testing results showed that it could detect the locations of the pedicle screws in the surgical scene as well as their direction angles through the OBBs. The F1 score of the model was 0.86 (precision: 1.00, recall: 0.80) at each confidence level and mAP50. The high precision suggests that the model effectively identifies true positive instrument detections, although the recall indicates a slight limitation in capturing all instruments present. This approach offers advantages over traditional object detection in bounding boxes for tasks where object orientation is crucial, and our findings suggest the potential of YOLOv8 OBB models in real-world surgical applications such as instrument tracking and surgical navigation. Conclusion Future work will explore incorporating additional data and the potential of hyperparameter optimization to improve overall model performance.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep Learning-Based Localization and Orientation Estimation of Pedicle Screws in Spinal Fusion Surgery

Kim,

Koo,

Lee

2024

Korean J Neurotrauma

View full text Add to dashboard Cite

show abstract

“…Most traditional methods of instrument detection typically have relied on low-level visual features, such as color and shape, for a simple computer vision task of color segmentation or thresholding [35], [36]. As deep learning approaches using CNNs have been increasing in popularity, many methods are proposed to achieve surgical instrument detection with the extraction of high-level features [7], [19], [20], [37], [38]. Andru et al [7] proposed EndoNet which first adopts CNN trained with labeled surgical images to achieve instrument detection and recognition from the video of endoscopic surgery.…”

Section: A Surgical Instrument Detectionmentioning

confidence: 99%

“…Andru et al [7] proposed EndoNet which first adopts CNN trained with labeled surgical images to achieve instrument detection and recognition from the video of endoscopic surgery. Following this work, more neural network architectures are introduced in instrument detection tasks from surgical scenarios, including an attention-guided CNN for real-time instrument detection in minimally invasive surgery [9], a multi-level feature aggregation network for multi-instrument identification [20], an arrow object bounding box network based on YOLO for identification and localization of instrument tips [38], an anchor-free CNN for instrument detection in robot-assisted surgery [23]. Furthermore, weakly supervised methods for surgical instrument detection are proposed to utilize the images without annotations of bounding boxes, which extends the approach of network training [39].…”

Section: A Surgical Instrument Detectionmentioning

confidence: 99%

Anchor-Free Feature Aggregation Network for Instrument Detection in Endoscopic Surgery

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Object detection is an essential task in computer vision, with numerous applications in various domains, including medical imaging [1], [2], surgical procedures [3], and personal protective equipment detection [4]. It plays a crucial role in medical imaging by enabling the identification and localization of abnormalities or objects of interest within medical images [5], [6].…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023)

Ragab,

Abdulkadir,

Muneer

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Under the grant projects ''015LC0-308 for YUTP-FRG'' and ''015MA0-158 for FRGS'' ABSTRACT YOLO (You Only Look Once) is an extensively utilized object detection algorithm that has found applications in various medical object detection tasks. This has been accompanied by the emergence of numerous novel variants in recent years, such as YOLOv7 and YOLOv8. This study encompasses a systematic exploration of the PubMed database to identify peer-reviewed articles published between 2018 and 2023. The search procedure found 124 relevant studies that employed YOLO for diverse tasks including lesion detection, skin lesion classification, retinal abnormality identification, cardiac abnormality detection, brain tumor segmentation, and personal protective equipment detection. The findings demonstrated the effectiveness of YOLO in outperforming alternative existing methods for these tasks. However, the review also unveiled certain limitations, such as well-balanced and annotated datasets, and the high computational demands. To conclude, the review highlights the identified research gaps and proposes future directions for leveraging the potential of YOLO for medical object detection.

show abstract

Autonomous Recognition of Multiple Surgical Instruments Tips Based on Arrow OBB-YOLO Network

Cited by 20 publications

References 38 publications

Deep Learning-Based Localization and Orientation Estimation of Pedicle Screws in Spinal Fusion Surgery

Deep Learning-Based Localization and Orientation Estimation of Pedicle Screws in Spinal Fusion Surgery

Anchor-Free Feature Aggregation Network for Instrument Detection in Endoscopic Surgery

A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023)

Contact Info

Product

Resources

About