Endoscopy AI

AI enabled real time assessment of endoscopic video for accurate colorectal polyp detection

Challenge


Colorectal cancer (CRC) is one of the most common causes of cancer mortality in the world. Early detection through screening by colonoscopy has been proven to effectively reduce disease-related mortality. Therefore, an annual check-up is recommended. However, if cancerous colonic polyps are missed in the first meeting, the situation gets worse as it metastasizes and reaches other organs.

Missed polyps could lead to something as serious as tumours.

Discrepancies between endoscopy reports and subsequent patient outcomes are inevitable errors.

Also, gaps in skills among endoscopists, primarily due to experience, have been identified, and solutions are critically needed.

Solution


ZASTI AI proprietary neural networks are continuously being trained on ever growing dataset of endoscopy videos, acquired from our institutional and academic partners, for early detection of polyps.

The AI model is used for real-time assessment of endoscopic video images of colorectal polyps. This solution has helped detect & differentiate between adenomas or hyperplastic polyps with higher accuracy than traditional methods. The model is equipped with our proprietary explainable AI capability to provide factors contributing to the detection. This helps in making endoscopic procedures more efficient and of higher quality.