Safer Surgeries Using AI: Enhancing Surgical Accuracy with Machine Learning Algorithms for Instrument Counting
DOI:
https://doi.org/10.47611/jsrhs.v13i3.7405Keywords:
convolutional neural networks, CNN, surgical tool recognition, retained surgical instruments, RSIs, patient safety, machine learning, ML, data augmentation, dropout, dropout regularization, ethical concerns, computer-aided surgeryAbstract
This study explores the integration of Convolutional Neural Networks (CNNs) into surgical procedures to address the critical issue of retained surgical instruments (RSIs), enhancing patient safety. RSIs are when a foreign object is unintentionally left within a patient after surgery or other invasive procedures. This paper discusses challenges associated with manual counting methods and the potential of CNNs in automating surgical tool recognition. It employs an experimental design to investigate the impact of model hyperparameters on machine learning performance, utilizing the "Labeled Surgical Tools and Images" dataset for training. Preprocessing techniques, data augmentation, and Dropout regularization enhanced model robustness. Results from multiple training trials demonstrate the efficacy of the CNN-based model in accurately identifying and classifying surgical instruments, even in limited data scenarios. This research identifies overfitting as a challenge and addresses it through model adjustments and regularization techniques; it also highlights the findings’ implications for improving surgical instrument count accuracy and enhancing patient safety. This study concludes by emphasizing the transformative potential of CNNs in surgical practice and the importance of ongoing research further to advance machine learning technologies in real-world surgical settings.
Downloads
References or Bibliography
Bamba, Y., Ogawa, S., Michio Itabashi, Shingo Kameoka, Okamoto, T., & Yamamoto, M. (2021). Automated recognition of objects and types of forceps in surgical images using deep learning. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-01911-1
Bamba, Y., Ogawa, S., Michio Itabashi, Shindo, H., Shingo Kameoka, Okamoto, T., & Yamamoto, M. (2021). Object and anatomical feature recognition in surgical video images based on a convolutional neural network. International Journal of Computer Assisted Radiology and Surgery, 16(11), 2045–2054. https://doi.org/10.1007/s11548-021-02434-w
Chiew, C. J., Liu, N., Ting Hway Wong, Yilin Eileen Sim, & Hairil Rizal Abdullah. (2019). Utilizing Machine Learning Methods for Preoperative Prediction of Postsurgical Mortality and Intensive Care Unit Admission. Annals of Surgery, 272(6), 1133–1139. https://doi.org/10.1097/sla.0000000000003297
Chinedu Innocent Nwoye, Yu, T., Cristians González, Seeliger, B., Pietro Mascagni, Mutter, D.,
Marescaux, J., & Padoy, N. (2022). Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Medical Image Analysis, 78, 102433–102433. https://doi.org/10.1016/j.media.2022.102433
García-Peraza-Herrera, L. C., Fidon, L., D’Ettorre, C., Stoyanov, D., Vercauteren, T., & Sébastien Ourselin. (2021). Image Compositing for Segmentation of Surgical Tools Without Manual Annotations. IEEE Transactions on Medical Imaging, 40(5), 1450–1460. https://doi.org/10.1109/tmi.2021.3057884
Gawande, A. A., Studdert, D. M., E. John Orav, Brennan, T. A., & Zinner, M. J. (2003). Risk Factors for Retained Instruments and Sponges after Surgery. The New England Journal of Medicine, 348(3), 229–235. https://doi.org/10.1056/nejmsa021721
Jaafar Jaafari, Douzi, S., Khadija Douzi, & Badr Hssina. (2021). Towards more efficient CNN-based surgical tools classification using transfer learning. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00509-8
Lam, K., Chen, J., Wang, Z., Iqbal, F., Darzi, A., Lo, B., Sanjay Purkayastha, & Kinross, J. (2022). Machine learning for technical skill assessment in surgery: a systematic review. Npj Digital Medicine, 5(1). https://doi.org/10.1038/s41746-022-00566-0
Lehr, J., Kelterborn, K., Briese, C., Schlueter, M. A., Kroeger, O., & Krueger, J. (2023). Image-based recognition of surgical instruments by means of convolutional neural networks. International Journal of Computer Assisted Radiology and Surgery, 18(11), 2043–2049. https://doi.org/10.1007/s11548-023-02885-3
Lee, J.-D., Chien, J.-C., Hsu, Y.-T., & Wu, C. (2021). Automatic Surgical Instrument Recognition—A Case of Comparison Study between the Faster R-CNN, Mask R-CNN, and Single-Shot Multi-Box Detectors. Applied Sciences, 11(17), 8097–8097. https://doi.org/10.3390/app11178097
Liu, K., Zhao, Z., Shi, P., Li, F., & He, S. (2022). Real-time surgical tool detection in computer-aided surgery based on enhanced feature-fusion convolutional neural network. Journal of Computational Design and Engineering, 9(3), 1123–1134. https://doi.org/10.1093/jcde/qwac049
Marzullo, A., Moccia, S., Catellani, M., Calimeri, F., & Elena De Momi. (2021). Towards realistic laparoscopic image generation using image-domain translation. Computer Methods and Programs in Biomedicine, 200, 105834–105834. https://doi.org/10.1016/j.cmpb.2020.105834
Praveen SR Konduri, & Siva, G. (2024). Full resolution convolutional neural network based organ and surgical instrument classification on laparoscopic image data. Biomedical Signal Processing and Control, 87, 105533–105533. https://doi.org/10.1016/j.bspc.2023.105533
Prellberg, J., & Kramer, O. (n.d.). Multi-label Classification of Surgical Tools with Convolutional Neural Networks. Retrieved December 11, 2023, from https://arxiv.org/pdf/1805.05760.pdf
Recommended Standard of Practice for Counts. (n.d.). https://www.ast.org/uploadedFiles/Main_Site/Content/About_Us/Standard%20Counts.pdf
Tracking surgical instruments with AI: A new approach to patient safety. (2023, October 25). Healthcare IT News. https://www.healthcareitnews.com/news/tracking-surgical-instruments-ai-new-approach-patient-safety
Weprin, S., Fabio Crocerossa, Meyer, D., Maddra, K., Valancy, D., Osardu, R., Hae Sung Kang, Moore, R. H., Carbonara, U., Kim, F. J., & Autorino, R. (2021). Risk factors and preventive strategies for unintentionally retained surgical sharps: a systematic review. Patient Safety in Surgery, 15(1). https://doi.org/10.1186/s13037-021-00297-3
Zejnullahu, V. A., Bicaj, B. X., Zejnullahu, V. A., & Hamza, A. R. (2017). Retained Surgical Foreign Bodies after Surgery. Open Access Macedonian Journal of Medical Sciences, 5(1), 97–100. https://doi.org/10.3889/oamjms.2017.005
Published
How to Cite
Issue
Section
Copyright (c) 2024 Zenia Haroon
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
