Cancers of the upper gastrointestinal (GI) tract remain a major contributor to the global cancer risk. This study uses a diffuse reflectance spectroscopic probe for tissue characterisation. Optical tracking of the DRS probe is used to aid histology correlation. Supervised classification algorithms are used for discrimination between tumour and non-tumour tissue and evaluated in terms of accuracy, sensitivity, specificity, and the area under the curve. A live augmented view with all the tracked and classified biopsy sites is presented, providing visual feedback to the surgeons. Thus, the system provides real-time tissue discrimination, whilst clinical outcomes for patients are optimised.
|