{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["7(1)"],"submitter":["Protserov S"],"pubmed_abstract":["Deep learning for computer vision can be leveraged for interpreting surgical scenes and providing surgeons with real-time guidance to avoid complications. However, neither generalizability nor scalability of computer-vision-based surgical guidance systems have been demonstrated, especially to geographic locations that lack hardware and infrastructure necessary for real-time inference. We propose a new equipment-agnostic framework for real-time use in operating suites. Using laparoscopic cholecystectomy and semantic segmentation models for predicting safe/dangerous (\"Go\"/\"No-Go\") zones of dissection as an example use case, this study aimed to develop and test the performance of a novel data pipeline linked to a web-platform that enables real-time deployment from any edge device. To test this infrastructure and demonstrate its scalability and generalizability, lightweight U-Net and SegFormer models were trained on annotated frames from a large and diverse multicenter dataset from 136 institutions, and then tested on a separate prospectively collected dataset. A web-platform was created to enable real-time inference on any surgical video stream, and performance was tested on and optimized for a range of network speeds. The U-Net and SegFormer models respectively achieved mean Dice scores of 57% and 60%, precision 45% and 53%, and recall 82% and 75% for predicting the Go zone, and mean Dice scores of 76% and 76%, precision 68% and 68%, and recall 92% and 92% for predicting the No-Go zone. After optimization of the client-server interaction over the network, we deliver a prediction stream of at least 60 fps and with a maximum round-trip delay of 70 ms for speeds above 8 Mbps. Clinical deployment of machine learning models for surgical guidance is feasible and cost-effective using a generalizable, scalable and equipment-agnostic framework that lacks dependency on hardware with high computing performance or ultra-fast internet connection speed."],"journal":["NPJ digital medicine"],"pagination":["231"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11372100"],"repository":["biostudies-literature"],"pubmed_title":["Development, deployment and scaling of operating room-ready artificial intelligence for real-time surgical decision support."],"pmcid":["PMC11372100"],"pubmed_authors":["Masino C","Protserov S","Mashouri P","Brudno M","Zhang H","Madani A","Hunter J"],"additional_accession":[]},"is_claimable":false,"name":"Development, deployment and scaling of operating room-ready artificial intelligence for real-time surgical decision support.","description":"Deep learning for computer vision can be leveraged for interpreting surgical scenes and providing surgeons with real-time guidance to avoid complications. However, neither generalizability nor scalability of computer-vision-based surgical guidance systems have been demonstrated, especially to geographic locations that lack hardware and infrastructure necessary for real-time inference. We propose a new equipment-agnostic framework for real-time use in operating suites. Using laparoscopic cholecystectomy and semantic segmentation models for predicting safe/dangerous (\"Go\"/\"No-Go\") zones of dissection as an example use case, this study aimed to develop and test the performance of a novel data pipeline linked to a web-platform that enables real-time deployment from any edge device. To test this infrastructure and demonstrate its scalability and generalizability, lightweight U-Net and SegFormer models were trained on annotated frames from a large and diverse multicenter dataset from 136 institutions, and then tested on a separate prospectively collected dataset. A web-platform was created to enable real-time inference on any surgical video stream, and performance was tested on and optimized for a range of network speeds. The U-Net and SegFormer models respectively achieved mean Dice scores of 57% and 60%, precision 45% and 53%, and recall 82% and 75% for predicting the Go zone, and mean Dice scores of 76% and 76%, precision 68% and 68%, and recall 92% and 92% for predicting the No-Go zone. After optimization of the client-server interaction over the network, we deliver a prediction stream of at least 60 fps and with a maximum round-trip delay of 70 ms for speeds above 8 Mbps. Clinical deployment of machine learning models for surgical guidance is feasible and cost-effective using a generalizable, scalable and equipment-agnostic framework that lacks dependency on hardware with high computing performance or ultra-fast internet connection speed.","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Sep","modification":"2024-11-15T04:36:30.875Z","creation":"2024-11-15T04:36:30.875Z"},"accession":"S-EPMC11372100","cross_references":{"pubmed":["39227660"],"doi":["10.1038/s41746-024-01225-2"]}}