Artificial intelligence assisted operative anatomy recognition in endoscopic pituitary surgery

https://doi.org/10.1001/jamanetworkopen.2019.1095

Surgical assistance
Surgical assistance

abstract

Pituitary tumours are surrounded by critical neurovascular structures and identification of these intra-operatively can be challenging. We have previously developed an AI model capable of sellar anatomy segmentation. This study aims to apply this model, and explore the impact of AI-assistance on clinician anatomy recognition. Participants were tasked with labelling the sella on six images, initially without assistance, then augmented by AI. Mean DICE scores and the proportion of annotations encompassing the centroid of the sella were calculated. Six medical students, six junior trainees, six intermediate trainees and six experts were recruited. There was an overall improvement in sella recognition from a DICE of score 70.7% without AI assistance to 77.5% with AI assistance (+6.7; p < 0.001). Medical students used and benefitted from AI assistance the most, improving from a DICE score of 66.2% to 78.9% (+12.8; p = 0.02). This technology has the potential to augment surgical education and eventually be used as an intra-operative decision support tool.


Corporate Initiatives

Development of micro-surgery support robot

Sony Group Corporation develops microsurgery support robot capable of automatic exchange of surgical instruments and precision operation. Utilizing high-precision operability and AI technology, the robot enables delicate and advanced surgery, such as suturing extremely small blood vessels and nerves, while compensating for the surgeon's hand tremors. This is expected to reduce the burden on the surgeon, while improving the success rate of surgery and easing the burden on the patient. Utilizing cutting-edge robotics technology, we provide innovative solutions that support the future of medical care.


eXeX aims to use AI to improve communication and efficiency during surgery, creating an environment where the entire team can work in harmony. In cooperation with Apple Vision Pro, surgeons can use visual checklists hands-free, and AI responds flexibly to each operating room and surgeon's style. In addition, by combining AI with language models and computer vision, it is possible to grasp the location of tools and give real-time instructions to team members, reducing unnecessary interruptions. Spatial awareness keeps track of the surgeon's line of sight, creating a more intuitive and efficient surgical environment. In this way, eXeX is trying to transform the operating room into a harmonious space like a symphony by using AI.