Early diagnosis of colorectal cancer significantly improves survival. However, over half of cases are diagnosed late due to demand exceeding the capacity for colonoscopy – the “gold standard” for screening. Colonoscopy is limited by the outdated design of conventional endoscopes, associated with high complexity of use, cost and pain.
Magnetic endoscopes represent a promising alternative, overcoming drawbacks of pain and cost, but struggle to reach the translational stage as magnetic manipulation is complex and unintuitive. A new study published in Nature Machine Intelligence focused on machine vision to develop intelligent and autonomous control of a magnetic endoscope, for the first time enabling non-expert users to effectively perform magnetic colonoscopy in-vivo.
The researchers combined robotics, computer vision and advanced control to offer an intuitive and effective endoscopic system. Moreover, they defined the characteristics required to achieve autonomy in robotic endoscopy. The paradigm described in this study can be adopted in a variety of applications where navigation in unstructured environments is required, such as catheters, pancreatic endoscopy, bronchoscopy, and gastroscopy.
The work brings alternative endoscopic technologies closer to the translational phase, enabling earlier detection of cancer.
Martin JW, Scaglioni B, Norton JC et al. Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation. Nat Mach Intell. 2020 Oct;2(10):595-606. doi: 10.1038/s42256-020-00231-9.