Gastrointestinal (GI) endoscopy is the gold-standard procedure for detection and treatment of dysplastic lesions and early stage GI cancers. Despite its proven effectiveness, its sensitivity remains suboptimal due to the subjective nature of the examination, which is substantially reliant on human-operator skills. For bowel cancer, colonoscopy can miss up to 22% of dysplastic lesions, with even higher miss rates for small (<5 mm diameter) and flat lesions. We propose a robotic hyperspectral (HS) scanning framework that aims to improve the sensitivity of GI endoscopy by automated scanning and real-time classification of wide tissue areas based on their HS features. A “hot-spot” map is generated to highlight dysplastic or cancerous lesions for further scrutiny or concurrent resection. The device works as an add-on accessory to any conventional endoscope, and to our knowledge, is the first of its kind.
This paper focuses on characterising its optical resolution on rigid and deformable colon phantoms. We report for the first time 2D and 3D wide-area reconstruction of endoscopic HS data with sub-millimetre optical resolution. The current setup, compatible with the anatomical dimensions of the colon, could allow the identification of flat and small pre-cancerous lesions that are currently missed. The proposed framework will lay the foundations towards the next generation of augmented reality endoscopy while increasing its sensitivity and specificity.