Optical Biopsy of Dysplasia in Barrett's Oesophagus Assisted by Artificial Intelligence

Simple Summary: Advanced endoscopy techniques that generate microscopic images can be used to optimize cancer screening in patients with an increased risk of oesophageal cancer. However, these microscopic endoscopy images are highly detailed and difficult for doctors to interpret. Support by artificial intelligence (AI) could be useful when the image is too complex for human interpretation. Therefore, this study investigated whether AI as second assessor can assist doctors in assessing complex, microscopic endoscopy images for the presence of oesophageal cancer. To investigate this, we developed online training and testing modules for doctors to learn to classify these novel images, and to assess the potential of AI assistance in analysing the oesophageal microscopy images. Our data showed that the best diagnostic scores for cancer recognition emerged through the collaboration between doctors and AI as the second assessor. Therefore, AI could be used to support the clinical implementation of endoscopy techniques that generate microscopic images. Optical biopsy in Barrett's oesophagus (BE) using endocytoscopy (EC) could optimize endoscopic screening. However, the identification of dysplasia is challenging due to the complex interpretation of the highly detailed images. Therefore, we assessed whether using artificial intelligence (AI) as second assessor could help gastroenterologists in interpreting endocytoscopic BE images. First, we prospectively videotaped 52 BE patients with EC. Then we trained and tested the AI pm distinct datasets drawn from 83,277 frames, developed an endocytoscopic BE classification system, and designed online training and testing modules. We invited two successive cohorts for these online modules: 10 endoscopists to validate the classification system and 12 gastroenterologists to evaluate AI as second assessor by providing six of them with the option to request AI assistance. Training the endoscopists in the classification system established an improved sensitivity of 90.0% (+32.67%, p < 0.001) and an accuracy of 77.67% (+13.0%, p = 0.020) compared with the baseline. However, these values deteriorated at follow-up ( 16.67%, p < 0.001 and -8.0%, p = 0.009). Contrastingly, AI-assisted gastroenterologists maintained high sensitivity and accuracy at follow-up, subsequently outperforming the unassisted gastroenterologists (+20.0%, p = 0.025 and +12.22%, p = 0.05). Thus, best diagnostic scores for the identification of dysplasia emerged through human-machine collaboration between trained gastroenterologists with AI as the second assessor. Therefore, AI could support clinical implementation of optical biopsies through EC.