Deep-learning-based instrument detection for intra-operative robotic assistance

Abstract

Purpose: Robotic scrub nurses have the potential to become an attractive solution for the operating room. Surgical instrument detection is a fundamental task for these systems, which is the focus of this work. We address the detection of the complete surgery set for wisdom teeth extraction, and propose a data augmentation technique tailored for this task. Methods: Using a robotic scrub nurse system, we create a dataset of 369 unique multi-instrument images with manual annotations. We then propose the Mask-Based Object Insertion method, capable of automatically generating a large amount of synthetic images. By using both real and artificial data, different Mask R-CNN models are trained and evaluated. Results: Our experiments reveal that models trained on the synthetic data created with our method achieve comparable performance to that of models trained on real images. Moreover, we demonstrate that the combination of real and our artificial data can lead to a superior level of generalization. Conclusion: The proposed data augmentation technique is capable of dramatically reducing the labelling work required for training a deep-learning-based detection algorithm. A dataset for the complete instrument set for wisdom teeth extraction is made available for the scientific community, as well as the raw information required for the generation of the synthetic data (https://github.com/Jorebs/Deep-learning-based-instrument-detection-for-intra operative-robotic-assistance).

Can artificial intelligence and robotic nurses replace operating room nurses? The quasi-experimental research

“…Robotic operating room nurses have the potential to be an attractive solution for the operating room [ 4 ]. This study is the first one conducted both in our country and in other countries in which the participating operating room nurses’ levels of knowledge on the subject were investigated by providing training on artificial intelligence and robotic nurses for them.…”

“…As a result of the research, “The training given to the operating room nurses for artificial intelligence and robot nurses affects reducing the anxiety level of nurses toward artificial intelligence.” It is seen that it does not support the (H2) hypothesis. Badilla-Solórzano et al [ 4 ] conducted a study on robotic operating room nurses based on deep learning for instrument detection under conditions similar to those of an actual operating room. In a similar study, Nakano, and Nagamune [ 20 ] performed a study on a robotic scrub nurse to assist operating room nurses.…”

“…Safety, positive improvements, and reducing the possibility of infection during surgical procedures have come to the forefront, which has made the use of robot-assisted surgery more attractive in hospitals. Robots play a supporting role both in surgical procedures and in the operating room [ 4 ]. Nurses should be knowledgeable about both these technologies and the preparation process well if they are to provide care for the patient in surgeries performed with these technologies.…”

“…The use of robotic surgery have several advantages: ıt makes it possible to reach small incision areas, leads to fewer complications in the postoperative period, allows early mobilization, shortens the length of hospitalization and requires fewer personnel in the surgical team [ 16 ]. Badilla-Solórzano et al [ 4 ] conducted a study on robotic operating room nurses based on deep learning for instrument detection under conditions similar to those of an actual operating room. In their study, they uncovered an example of a scrub nurse responsible for handing in surgical instruments to the physician who performs the surgery and getting them back after use.…”

Medical instrument detection with synthetically generated data

“…Obsie, E. et al 7 use this method, for example, to identify plant diseases more robustly. An application of the first approach in a medical context can be found in the article by Badilla-Solorzano, J. et al 8 . The aim of this work is to recognise surgical instruments on an instrument tray by applying the crop-and-past method to an existing real data set in order to artificially expand it.…”