A multidisciplinary team of researchers has developed a deep-learning framework to improve endoscopy for cancer detection.
Cancers detected at an early stage have a much higher chance of being treated successfully. Those of the gastrointestinal tract can be detected through endoscopy, in which a flexible tube with a camera at its tip is inserted into the oesophagus, stomach or colon to pick up on abnormalities in the tissues that line the organs. Endoscopic methods such as radiofrequency ablation can also be used to prevent pre-cancerous regions from progressing to cancer if they are detected in time.
Unfortunately, the more easily treated pre-cancerous conditions and early stage cancers are harder to spot and often missed with conventional endoscopy, especially if it’s conducted by less experienced endoscopists. Cancer detection is made even more challenging by artefacts, such as bubbles, debris, overexposure, light reflection and blurring, which can obscure or distort key features and hinder efforts to automatically analyse endoscopy videos.
In an effort to improve the quality of video endoscopy, a team of researchers from the Ludwig Institute for Cancer Research (Jens Rittscher, Felix Zhou and Xin Lu), the Institute for Biomedical Engineering (Sharib Ali and Jens Rittscher) and the Translational Gastroenterology Unit (Barbara Braden, Adam Bailey and James East) developed a deep-learning framework for quality assessment of endoscopy videos in near real-time. This framework, reported in the journal Medical Image Analysis, can reliably identify six different types of artefacts in the video, generate a quality score for each frame and restore mildly corrupted frames. Frame restoration can help in building visually coherent 2D or 3D maps for further analysis. In addition, providing quality scores can help trainees assess and improve their screening performance.
Future work aims to employ real-time computer algorithm-aided analysis of endoscopic images and videos, which will enable earlier identification of potentially cancerous changes automatically during endoscopy.
This work was supported by the NIHR Oxford Biomedical Research Centre, the EPSRC, the Ludwig Institute for Cancer Research and Health Data Research UK.