An emerging technology may help improve efficiency and outcomes of laparoscopic and robotic-assisted surgeries.
The accuracy of intraoperative anatomical measurements can be a key factor in reducing the risk of postoperative complications and facilitating optimal outcomes. Now a new technology reportedly offers real-time digital measurements that can be incorporated into intraoperative videos.
Instead of eyeballing an approximate measurement or attempting to utilize an intraoperative ruler, surgeons may use the technology to make more precise tissue measurements by indicating points on the tissue with surgical tools, according to RSIP Vision, the manufacturer of the technology. The company noted the deep learning-based technology can provide an effective intraoperative complement to the use of third-party endoscopic imaging systems and medical robot manufacturers.
“Aside from simply viewing the image, our technology can use the surgical tools in the image as a virtual measurement device,” explained Ron Soferman, the chief executive officer of RSIP Vision. “Calibration is performed using a dedicated algorithm which extrapolates the camera parameters. Once the image is calibrated, we can perform accurate measurements within the field of view, even in 3D.”
The company cited sleeve gastrectomy as one example of a procedure in which this technology can be beneficial. Noting the importance of avoiding damage to the pylorus in this procedure, RSIP Vision says accurate digital measurement of the resection distance simplifies the surgery and lowers the risk of complications. Similarly, David Hochstein, M.D., who is affiliated with the Rambam Hospital in Haifa, Israel, said the technology may have an impact in trauma and acute care surgery cases that often require bowel resection.
“We must consider the balance between removing enough of the ischemic or severely inflamed intestine without risking short-bowel syndrome,” noted Dr. Hochstein. “Having an accurate and easy way to perform measurements within the image during the procedure will significantly increase our confidence and speed up the surgery.”
New Study Examines Short-Term Consistency of Large Language Models in Radiology
November 22nd 2024While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.