Artificial intelligence-aided diagnostic imaging: A state-of-the-art technique in precancerous screening.

BACKGROUND AND AIM: Chromoendoscopy with the use of indigo carmine (IC) dye is a crucial endoscopic technique to identify gastrointestinal neoplasms. However, its performance is limited by the endoscopist's skill, and no standards are available for lesion identification. Thus, we developed an artificial intelligence (AI) model to replace chromoendoscopy. METHODS: This pilot study assessed the feasibility of our novel AI model in the conversion of white-light images (WLI) into virtual IC-dyed images based on a generative adversarial network. The predictions of our AI model were evaluated against the assessments of five endoscopic experts who were blinded to the purpose of this study with a staining quality rating from 1 (unacceptable) to 4 (excellent). RESULTS: The AI model successfully transformed the WLI of polyps with different morphologies and different types of lesions in the gastrointestinal tract into virtual IC-dyed images. The quality ratings of the real IC-dyed and AI images did not significantly differ concerning surface structure (AI vs IC: 3.08 vs 3.00), lesion border (3.04 vs 2.98), and overall contrast (3.14 vs 3.02) from 10 sets of images (10 AI images and 10 real IC-dyed images). Although the score depended significantly on the evaluator, the staining methods (AI or real IC) and evaluators had no significant interaction (P > 0.05) with each other. CONCLUSION: Our results demonstrated the feasibility of employing AI model's virtual IC staining, increasing the possibility of being employed in daily practice. This novel technology may facilitate gastrointestinal lesion identification in the future.

A Novel Convolutional Neural Network Model as an Alternative Approach to Bowel Preparation Evaluation Before Colonoscopy in the COVID-19 Era: A Multicenter, Single-Blinded, Randomized Study.

INTRODUCTION: Adequate bowel preparation is key to a successful colonoscopy, which is necessary for detecting adenomas and preventing colorectal cancer. We developed an artificial intelligence (AI) platform using a convolutional neural network (CNN) model (AI-CNN model) to evaluate the quality of bowel preparation before colonoscopy. METHODS: This was a colonoscopist-blinded, randomized study. Enrolled patients were randomized into an experimental group, in which our AI-CNN model was used to evaluate the quality of bowel preparation (AI-CNN group), or a control group, which performed self-evaluation per routine practice (control group). The primary outcome was the consistency (homogeneity) between the results of the 2 methods. The secondary outcomes included the quality of bowel preparation according to the Boston Bowel Preparation Scale (BBPS), polyp detection rate, and adenoma detection rate. RESULTS: A total of 1,434 patients were enrolled (AI-CNN, n = 730; control, n = 704). No significant difference was observed between the evaluation results ("pass" or "not pass") of the groups in the adequacy of bowel preparation as represented by BBPS scores. The mean BBPS scores, polyp detection rate, and adenoma detection rate were similar between the groups. These results indicated that the AI-CNN model and routine practice were generally consistent in the evaluation of bowel preparation quality. However, the mean BBPS score of patients with "pass" results were significantly higher in the AI-CNN group than in the control group, indicating that the AI-CNN model may further improve the quality of bowel preparation in patients exhibiting adequate bowel preparation. DISCUSSION: The novel AI-CNN model, which demonstrated comparable outcomes to the routine practice, may serve as an alternative approach for evaluating bowel preparation quality before colonoscopy.

Faecal microbiome and metabolic signatures in rectal neuroendocrine tumors.

Background: The prevalence of rectal neuroendocrine tumors (RNET) has increased substantially over the past decades. Little is known on mechanistic alteration in the pathogenesis of such disease. We postulate that perturbations of human gut microbiome-metabolome interface influentially affect the development of RNET. The study aims to characterize the composition and function of faecal microbiome and metabolites in RNET individuals. Methods: We performed deep shotgun metagenomic sequencing and untargeted liquid chromatography-mass spectrometry (LC-MS) metabolomic profiling of faecal samples from the discovery cohort (18 RNET patients, 40 controls), and validated the microbiome and metabolite-based classifiers in an independent cohort (15 RNET participants, 19 controls). Results: We uncovered a dysbiotic gut ecological microenvironment in RNET patients, characterized by aberrant depletion and attenuated connection of microbial species, and abnormally aggregated lipids and lipid-like molecules. Functional characterization based on our in-house and Human Project Unified Metabolic Analysis Network 2 (HUMAnN2) pipelines further indicated a nutrient deficient gut microenvironment in RNET individuals, evidenced by diminished activities such as energy metabolism, vitamin biosynthesis and transportation. By integrating these data, we revealed 291 robust associations between representative differentially abundant taxonomic species and metabolites, indicating a tight interaction of gut microbiome with metabolites in RNET pathogenesis. Finally, we identified a cluster of gut microbiome and metabolite-based signatures, and replicated them in an independent cohort, showing accurate prediction of such neoplasm from healthy people. Conclusions: Our current study is the first to comprehensively characterize the perturbed interface of gut microbiome and metabolites in RNET patients, which may provide promising targets for microbiome-based diagnostics and therapies for this disorder.