by Kara Quast, Mewburn Ellis LLP
Artificial intelligence (AI) is transforming surgical imaging and with it real-time diagnostics.
Traditionally, surgeons rely on pre-operative scans and visual cues, but AI-assisted imaging reveals details invisible to the human eye, improving identification of critical structures and abnormalities during procedures. This leads to faster, more accurate diagnoses and better-informed treatment decisions. Below, we take a look at some exciting new developments from EnAcuity, Hypervision Surgical, and 3Sonic.
AI imaging for in vivo procedures
One innovation enabling real-time diagnostics is hyperspectral imaging, which captures more light wavelengths than standard cameras.
Hypervision Surgical, a King’s College London spinout, offers a leap forward. Their system combines a hyperspectral camera with real-time AI analytics to deliver tissue-level insights at over 60 frames per second. It uses safe light and requires no dyes or contrast agents. The AI overlays colour-coded maps of tissue oxygenation onto the surgical view, helping identify poor perfusion or tumour margins. In gastrointestinal surgery, it can highlight ischaemic bowel segments; in oncology, it helps distinguish malignant from healthy tissue. Notably, Hypervision has recently secured UKCA certification in the UK and FDA clearance in the US.
EnAcuity, a spin out company from Imperial College London and UCL, has developed the first hardware-free hyperspectral imaging system for surgery without needing expensive hyperspectral cameras. This highlights tissue perfusions and structures such as vessels, nerves and tumours to the surgeon. The system increases the chance of spotting abnormalities that might be missed by standard vision. For example, subtle differences in blood flow or oxygenation in tissues can signal early-stage disease or compromised tissue. By augmenting the surgeon’s view in real time, EnAcuity’s system supports faster and more accurate intraoperative diagnoses, potentially preventing complications through early detection.
AI imaging for ex vivo procedures
Diagnostics also take place outside the body during surgery, for example cancer margin assessment, the removal of cancerous tissue with a safe margin of healthy tissue around the cancer to ensure no cancer cells are left in the body. This highly skilled, detailed work typically takes 20 minutes, prolonging surgery and anaesthesia.
3Sonic addresses this with their cancer tumour imaging platform, which performs ultrasound scans of resected tumours and uses AI to assess whether the surgical margin is sufficient. It delivers margin assessments in under two minutes, allowing surgeons to act immediately if further tissue removal is needed. Tested on oral cancer specimens, the system matches pathologist accuracy without complex preparation. Its portability and speed reduce patient risk and surgical costs.
Such technologies could provide faster intraoperative diagnoses, for example for biopsies. This could allow surgical treatment to be provided immediately rather than requiring further surgery at a later time, reducing patient risk and surgery costs.
Conclusion
AI-assisted imaging is sharpening the diagnostic focus of surgery. As clinical trials and adoption grow, AI imaging is set to redefine surgical diagnostics, making real-time decisions the new standard. The rapid development in this field is also reflected in the patent landscape. The quickly increasing number of patent filings for AI assisted MedTech solutions is further analysed in Mewburn Ellis’ report on AI in MedTech.
Read the full article about AI-assisted imaging here and you can get in touch with Mewburn Ellis if you have any IP-related questions!