- Title: AI helps train brain surgeons
- Date: 17th October 2023
- Summary: LONDON, ENGLAND, UK (OCTOBER 03, 2023) (Reuters) NEUROSURGEON AND TRAINEE SURGEON USING AN AI ASSISTANT IN A MOCK OPERATING ROOM CONSULTANT NEUROSURGEON HANI MARCUS AND NEUROSURGERY TRAINEE DANYAL KHAN MARCUS TRAINING KHAN TO PERFORM PITUITARY GLAND SURGERY VIDEO FEED OF MOCK OPERATION (SOUNDBITE) (English) HANI MARCUS, CONSULTANT NEUROSURGEON, SAYING: "So, what we're really trying to do is apply AI or artificial intelligence to support surgeons doing brain tumour surgery at the base of the brain. And what this practically entails is us training the AI with hundreds of videos, telling it, if you like, what structures are what, and then at some point over that period, the AI becomes really good itself at recognising things, and able to support other surgeons who're perhaps less experienced in advising them what to do next." MARCUS DISCUSSING THE OPERATION AS HE TRAINS KHAN SURGEON'S HANDS REALTIME VIDEO FEED OF OPERATION NEXT TO AI-ENHANCED VIDEO FEED AI-ENHANCED VIDEO FEED (SOUNDBITE) (English) HANI MARCUS, CONSULTANT NEUROSURGEON, SAYING: "So we do these operations with a tiny camera and look at a video feed of the operation in real-time. There's also a second screen next to it which provides AI assistance and that might be delineating structures that you need to either see or avoid and it might be advising you what to do next." KHAN DESCRIBING ANATOMY HE EXPECTS TO SEE DURING THE PROCEDURE HANI'S HANDS DURING THE PROCEDURE REALTIME VIDEO FEED OF OPERATION (SOUNDBITE) (English) HANI MARCUS, CONSULTANT NEUROSURGEON, SAYING: "What we're trying to plan for is AI is analogous to having a very senior surgeon standing next to you. He might just sit quietly but if he sees you doing something he doesn't agree with you he might gently suggest that there's another way of doing things. And that's the kind of experience you have as a trainee, building your surgical experience. And even as a consultant, there's scope to further improve the quality of the surgery by having this extra AI assistance." HANI AND KHAN SWAP PLACES VARIOUS OF KHAN PERFORMING THE PROCEDURE WITH HANI TRAINING HIM / KHAN'S HANDS VARIOUS OF THE AI-ENHANCED VIDEO FEED (SOUNDBITE) (English) DANYAL KHAN, NEUROSURGERY TRAINEE, SAYING: "I think as I progress as a surgeon, there might be stages where I wonder, you know, have I done enough of a particular part of the procedure and should I move on? And actually having that sort of assistant in the background as a reassurance to look at and say, 'well, yeah, actually, at this stage, out of the hundreds of videos of experts that this algorithm has watched, the experts would probably start moving on to the next phase'. It's a useful double check." VARIOUS OF SOPHIA BANO, ASSISTANT PROFESSOR OF ROBOTICS & AI AT UCL DISCUSSING THE VIDEO FEEDS WITH A PHD STUDENT (SOUNDBITE) (English) SOPHIA BANO, ASSOCIATE PROFESSOR OF ROBOTICS AND AI, SAYING: "There can be scenarios where clinicians, unintentionally, are very close to a very critical structure such as the optic nerve. This can have, any damage or a slight more pressure on the optic nerve, can have long-term complications on the patient's side. So, this whole tool will alert the surgeon during the procedure if there is any risk of potential complication so they can recalibrate themselves during the procedure." VARIOUS OF KHAN BEING TRAINED BY HANI / VIDEO FEEDS (SOUNDBITE) (English) HANI MARCUS, CONSULTANT NEUROSURGEON, SAYING: "So I'm very bullish that in the medium to long term, the AI will be helping lots of surgeons do lots of operations better than they otherwise can." VARIOUS OF THE AI-ENHANCED VIDEO FEED / NORMAL FEED
- Embargoed: 31st October 2023 07:24
- Keywords: AI
- Location: LONDON, ENGLAND, UK / SEATTLE, WASHINGTON, USA
- City: LONDON, ENGLAND, UK / SEATTLE, WASHINGTON, USA
- Country: UK
- Topics: Europe,Information Technologies / Computer Sciences,Science
- Reuters ID: LVA001918211102023RP1
- Aspect Ratio: 16:9
- Story Text: Artificial intelligence (AI) is helping to train brain surgeons to perform critical operations more effectively and safely, according to the UK's National Hospital for Neurology and Neurosurgery (NHNN).
The system, under development at University College London (UCL), highlights sensitive or critical structures in the brain, to bring them to the surgeon’s attention.
“What we're really trying to do is apply AI or artificial intelligence to support surgeons doing brain tumour surgery at the base of the brain,” Hani Marcus, Deputy Director of Wellcome/EPSRC Centre for Interventional and Surgical Sciences, told Reuters.
Brain surgery is always conducted with a real-time video feed from the point of surgery.
That video feed is now processed by the AI and augmented in a way that helps the surgeon understand what they are seeing.
“Even as a consultant, there's scope to further improve the quality of the surgery by having this extra AI assistance," Marcus said.
The AI system analysed video of more than 200 pituitary gland tumour operations, and accumulated approximately 10 years worth of experience in a fraction of the time, according to Marcus.
That knowledge means the AI can now not only help navigate to the correct area of the brain but also knows what should be happening at any stage of the procedure, making it a valuable training aid, according to Danyal Khan, a trainee neurosurgeon who is also an AI research Fellow at UCL and has been involved in developing the software that is now helping him.
"Having that sort of assistant in the background as a reassurance to look at and say, 'well, yeah, actually, at this stage, out of the hundreds of videos of experts that this algorithm has watched, the experts would probably start moving on to the next phase'. It's a useful double check," Khan told Reuters.
The system could be in use in operating theatres with two years, according to UCL.
(Production: Stuart McDill) - Copyright Holder: REUTERS
- Copyright Notice: (c) Copyright Thomson Reuters 2023. Open For Restrictions - http://about.reuters.com/fulllegal.asp
- Usage Terms/Restrictions: None