Second-generation colon capsule endoscopy for detection of colorectal polyps: Systematic review and meta-analysis of clinical trials

Background and study aims Adherence to colorectal cancer (CRC) screening is still unsatisfactory in many countries, thereby limiting prevention of CRC. Colon capsule endoscopy (CCE), a minimally invasive procedure, could be an alternative to fecal immunochemical tests or optical colonoscopy for CRC screening, and might increase adherence in CRC screening. This systematic review and meta-analysis evaluates the diagnostic accuracy of CCE compared to optical colonoscopy (OC) as the gold standard, adequacy of bowel preparation regimes and the patient perspective on diagnostic measures. Methods We conducted a systematic literature search in PubMed, EMBASE and the Cochrane Register for Clinical Trials. Pooled estimates for sensitivity, specificity and the diagnostic odds ratio with their respective 95 % confidence intervals (CI) were calculated for studies providing sufficient data. Results Of 840 initially identified studies, 13 were included in the systematic review and up to 9 in the meta-analysis. The pooled sensitivities and specificities for polyps ≥ 6 mm were 87 % (95 % CI: 83 %–90 %) and 87 % (95 % CI: 76 %–93 %) in 8 studies, respectively. For polyps ≥ 10 mm, the pooled estimates for sensitivities and specificities were 87 % (95 % CI: 83 %–90 %) and 95 % (95 % CI: 92 %–97 %) in 9 studies, respectively. A patients’ perspective was assessed in 31 % (n = 4) of studies, and no preference of CCE over OC was reported. Bowel preparation was adequate in 61 % to 92 % of CCE exams. Conclusions CCE provides high diagnostic accuracy in an adequately cleaned large bowel. Conclusive findings on patient perspectives require further studies to increase acceptance/adherence of CCE for CRC screening.

Development of a real-time endoscopic image diagnosis support system using deep learning technology in colonoscopy

Gaps in colonoscopy skills among endoscopists, primarily due to experience, have been identified, and solutions are critically needed. Hence, the development of a real-time robust detection system for colorectal neoplasms is considered to significantly reduce the risk of missed lesions during colonoscopy. Here, we develop an artificial intelligence (AI) system that automatically detects early signs of colorectal cancer during colonoscopy; the AI system shows the sensitivity and specificity are 97.3% (95% confidence interval [CI] = 95.9%–98.4%) and 99.0% (95% CI = 98.6%–99.2%), respectively, and the area under the curve is 0.975 (95% CI = 0.964–0.986) in the validation set. Moreover, the sensitivities are 98.0% (95% CI = 96.6%–98.8%) in the polypoid subgroup and 93.7% (95% CI = 87.6%–96.9%) in the non-polypoid subgroup; To accelerate the detection, tensor metrics in the trained model was decomposed, and the system can predict cancerous regions 21.9 ms/image on average. These findings suggest that the system is sufficient to support endoscopists in the high detection against non-polypoid lesions, which are frequently missed by optical colonoscopy. This AI system can alert endoscopists in real-time to avoid missing abnormalities such as non-polypoid polyps during colonoscopy, improving the early detection of this disease.