The potential benefit of artificial intelligence (AI) in optimizing the quality of care provided to patients has generated significant interest among gastroenterologists. ...incorporation of AI in ...the clinical workflow (R1-2) is a challenge because it is not yet clear whether its implementation will lead to better outcomes for the patients, practitioners, and the healthcare system. Because new medical interventions generally have both positive and negative consequences, it is important that the rightful enthusiasm toward an innovation such as AI does not make us overlook potential downfalls. Benchmark testing results of several AI devices have shown an accuracy exceeding 90% for the detection and differentiation of upper and lower GI neoplasia (Figure 1), which is equivalent to expert and superior gastroenterologists (3,4). Besides the clinical utility for GI neoplasia detection and characterization, AI tools have been shown to objectively estimate the level of bowel cleansing and grade both inflammatory activity and polyp sizing in patients with inflammatory bowel disease (IBD) (R1-1) (5). ...a microsimulation study that projected outcomes of randomized trials on the natural history of colorectal neoplasia showed that the use of AI contributed to an absolute reduction of 3%–5% in colorectal cancer incidence and mortality when compared with more than 60% achieved by unassisted screening colonoscopy (12) (R1-3).
Background and Aims Endoscopic submucosal dissection (ESD) is an endoscopic resection technique for lesions suspicious of superficial malignancy. It is performed using an ESD knife on its own ...(standard technique) or by the sequential use of a knife and a snare (hybrid technique). The experience with these techniques is different in Asian and non-Asian countries. We performed a systematic review and meta-analysis of available evidence on colorectal ESD. Methods Electronic databases were searched up to August 2016 for studies evaluating R0, en bloc resection, and adverse event rates of both techniques for the treatment of colorectal lesions. Proportions were pooled by a random effects model. Results Ninety-seven studies (71 performed in Asia) evaluated the standard technique and 12 studies (7 in Asia) the hybrid technique. The R0 resection rate of the standard technique was 82.9%, and it was significantly lower in non-Asian versus Asian countries: 71.3% versus 85.6%. The en bloc resection rate was 91% and was significantly lower in non-Asian versus Asian countries (81.2% vs 93%, respectively). Surgery was needed in 1.1% of the ESD-related adverse events, with a significant difference between non-Asian and Asian countries (3.1% vs 0.8%). The R0 and en bloc resection rates with the hybrid technique were significantly lower than those achieved with the standard technique: 60.6% and 68.4%, respectively, with similar adverse event rates. Conclusions In non-Asian countries the standard ESD technique is still failing to achieve acceptable levels of performance. The hybrid technique showed low R0 resection rates and should not be considered as an adequate alternative to the standard technique.
...miss rate by a human endoscopist has been strictly associated with one or more of these factors.1 As only one every two lesions was rated as adenomatous by centralised pathology in the original ...study3 (see online supplementary data), AI may result in the useless removal of hyperplastic polyps. ...a leave in situ strategy at least for distal non-adenomatous lesions is critical for AI not to increase false-positive rate at colonoscopy. Despite the general enthusiasm, prospective series are affected by ineludible operator-related bias, as the endoscopist cannot be blinded in most of the cases to the innovative technique. ...retrospective reassessment of whole colonoscopy videos, such as those in our series, owns the unique advantage of eliminating all of these subjective biases, objectively exposing independent videos to the new technologies. ...a possible bias that we could not eliminate is the fact that AI had in each video clip a relatively long interval between a few seconds before polyp appearance and the use of snare or another device. ...we could not exclude in principle that AI was somewhat facilitated by the fact that the polyp is usually put in a better and close position to the endoscope before resection. ...AI cannot compensate for lesions missed for a suboptimal exploration of colorectal mucosa. ...an adequate level of cleansing, a longer than 6 min withdrawal time and a good withdrawal technique remain prerequisites to maximise the performance of AI.6 We limited our study to white-light high definition colonoscopy.
One-fourth of colorectal neoplasia are missed at screening colonoscopy, representing the main cause of interval colorectal cancer. Deep learning systems with real-time computer-aided polyp detection ...(CADe) showed high accuracy in artificial settings, and preliminary randomized controlled trials (RCTs) reported favorable outcomes in the clinical setting. The aim of this meta-analysis was to summarize available RCTs on the performance of CADe systems in colorectal neoplasia detection.
We searched MEDLINE, EMBASE, and Cochrane Central databases until March 2020 for RCTs reporting diagnostic accuracy of CADe systems in the detection of colorectal neoplasia. The primary outcome was pooled adenoma detection rate (ADR), and secondary outcomes were adenoma per colonoscopy (APC) according to size, morphology, and location; advanced APC; polyp detection rate; polyps per colonoscopy; and sessile serrated lesions per colonoscopy. We calculated risk ratios (RRs), performed subgroup and sensitivity analyses, and assessed heterogeneity and publication bias.
Overall, 5 randomized controlled trials (4354 patients) were included in the final analysis. Pooled ADR was significantly higher in the CADe group than in the control group (791/2163 36.6% vs 558/2191 25.2%; RR, 1.44; 95% confidence interval CI, 1.27-1.62; P < .01; I2 = 42%). APC was also higher in the CADe group compared with control (1249/2163 .58 vs 779/2191 .36; RR, 1.70; 95% CI, 1.53-1.89; P < .01; I2 = 33%). APC was higher for ≤5-mm (RR, 1.69; 95% CI, 1.48-1.84), 6- to 9-mm (RR, 1.44; 95% CI, 1.19-1.75), and ≥10-mm adenomas (RR, 1.46; 95% CI, 1.04-2.06) and for proximal (RR, 1.59; 95% CI, 1.34-1.88), distal (RR, 1.68; 95% CI, 1.50-1.88), flat (RR, 1.78; 95% CI, 1.47-2.15), and polypoid morphology (RR, 1.54; 95% CI, 1.40-1.68). Regarding histology, CADe resulted in a higher sessile serrated lesion per colonoscopy (RR, 1.52; 95% CI, 1.14-2.02), whereas a nonsignificant trend for advanced ADR was found (RR, 1.35; 95% CI, .74-2.47; P = .33; I2 = 69%). Level of evidence for RCTs was graded as moderate.
According to available evidence, the incorporation of artificial intelligence as aid for detection of colorectal neoplasia results in a significant increase in the detection of colorectal neoplasia, and such effect is independent from main adenoma characteristics.
Display omitted
Abstract
Current practices for the management of Barrett’s esophagus (BE) vary across Europe, as several national European guidelines exist. This Position Statement from the European Society of ...Gastrointestinal Endoscopy (ESGE) is an attempt to homogenize recommendations and, hence, patient management according to the best scientific evidence and other considerations (e.g. health policy). A Working Group developed consensus statements, using the existing national guidelines as a starting point and considering new evidence in the literature. The Position Statement wishes to contribute to a more cost-effective approach to the care of patients with BE by reducing the number of surveillance endoscopies for patients with a low risk of malignant progression and centralizing care in expert centers for those with high progression rates.
Main statements
MS1
The diagnosis of BE is made if the distal esophagus is lined with columnar epithelium with a minimum length of 1 cm (tongues or circular) containing specialized intestinal metaplasia at histopathological examination.
MS2
The ESGE recommends varying surveillance intervals for different BE lengths. For patients with an irregular Z-line/columnar-lined esophagus of < 1 cm, no routine biopsies or endoscopic surveillance is advised. For BE ≥ 1 cm and < 3 cm, BE surveillance should be repeated every 5 years. For BE ≥ 3 cm and < 10 cm, the interval for endoscopic surveillance should be 3 years. Patients with BE with a maximum extent ≥ 10 cm should be referred to a BE expert center for surveillance endoscopies. Patients with limited life expectancy and advanced age should be discharged from endoscopic surveillance.
MS3
The diagnosis of any degree of dysplasia (including “indefinite for dysplasia”) in BE requires confirmation by an expert gastrointestinal pathologist.
MS4
Patients with visible lesions in BE diagnosed as dysplasia or early cancer should be referred to a BE expert center. All visible abnormalities, regardless of the degree of dysplasia, should be removed by means of endoscopic resection techniques in order to obtain optimal histopathological staging
MS5
All patients with a BE ≥ 10 cm, a confirmed diagnosis of low grade dysplasia, high grade dysplasia (HGD), or early cancer should be referred to a BE expert center for surveillance and/or treatment. BE expert centers should meet the following criteria: annual case load of ≥10 new patients undergoing endoscopic treatment for HGD or early carcinoma per BE expert endoscopist; endoscopic and histological care provided by endoscopists and pathologists who have followed additional training; at least 30 supervised endoscopic resection and 30 endoscopic ablation procedures to acquire competence in technical skills, management pathways, and complications; multidisciplinary meetings with gastroenterologists, surgeons, oncologists, and pathologists to discuss patients with Barrett’s neoplasia; access to experienced esophageal surgery; and all BE patients registered prospectively in a database.
An endoscopist with a 50% miss rate of colorectal neoplasia would have the same adenoma detection rate as an endoscopist with no miss rate when a 2-fold gradient of disease prevalence is present. ......it is mandatory to assure a balance in disease prevalence between the intervention and the control when validating any colonoscopy innovation. To incorporate the criticism by the authors on the excessively artificial setting of the controlled trials, new modalities for incorporating randomization in real-life scenarios (e.g., randomized health services studies (3)) should be explored. Design of the polish colonoscopy screening program: A randomized health services study.
One-fourth of colorectal neoplasias are missed during screening colonoscopies; these can develop into colorectal cancer (CRC). Deep learning systems allow for real-time computer-aided detection ...(CADe) of polyps with high accuracy. We performed a multicenter, randomized trial to assess the safety and efficacy of a CADe system in detection of colorectal neoplasias during real-time colonoscopy.
We analyzed data from 685 subjects (61.32 ± 10.2 years old; 337 men) undergoing screening colonoscopies for CRC, post-polypectomy surveillance, or workup due to positive results from a fecal immunochemical test or signs or symptoms of CRC, at 3 centers in Italy from September through November 2019. Patients were randomly assigned (1:1) to groups who underwent high-definition colonoscopies with the CADe system or without (controls). The CADe system included an artificial intelligence–based medical device (GI-Genius, Medtronic) trained to process colonoscopy images and superimpose them, in real time, on the endoscopy display a green box over suspected lesions. A minimum withdrawal time of 6 minutes was required. Lesions were collected and histopathology findings were used as the reference standard. The primary outcome was adenoma detection rate (ADR, the percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, non-neoplastic resection rate, and withdrawal time.
The ADR was significantly higher in the CADe group (54.8%) than in the control group (40.4%) (relative risk RR, 1.30; 95% confidence interval CI, 1.14–1.45). Adenomas detected per colonoscopy were significantly higher in the CADe group (mean, 1.07 ±1.54) than in the control group (mean 0.71 ± 1.20) (incidence rate ratio, 1.46; 95% CI, 1.15–1.86). Adenomas 5 mm or smaller were detected in a significantly higher proportion of subjects in the CADe group (33.7%) than in the control group (26.5%; RR, 1.26; 95% CI, 1.01–1.52), as were adenomas of 6 to 9 mm (detected in 10.6% of subjects in the CADe group vs 5.8% in the control group; RR, 1.78; 95% CI, 1.09–2.86), regardless of morphology or location. There was no significant difference between groups in withdrawal time (417 ± 101 seconds for the CADe group vs 435 ± 149 for controls; P = .1) or proportion of subjects with resection of non-neoplastic lesions (26.0% in the CADe group vs 28.7% of controls; RR, 1.00; 95% CI, 0.90–1.12).
In a multicenter, randomized trial, we found that including CADe in real-time colonoscopy significantly increases ADR and adenomas detected per colonoscopy without increasing withdrawal time. ClinicalTrials.gov no: 04079478
Display omitted
Main Recommendations
The following recommendations for post-polypectomy colonoscopic surveillance apply to all patients who had one or more polyps that were completely removed during a high quality ...baseline colonoscopy.
1
ESGE recommends that patients with complete removal of 1 – 4 < 10 mm adenomas with low grade dysplasia, irrespective of villous components, or any serrated polyp < 10 mm without dysplasia, do not require endoscopic surveillance and should be returned to screening.
Strong recommendation, moderate quality evidence.
If organized screening is not available, repetition of colonoscopy 10 years after the index procedure is recommended. Strong recommendation, moderate quality evidence.
2
ESGE recommends surveillance colonoscopy after 3 years for patients with complete removal of at least 1 adenoma ≥ 10 mm or with high grade dysplasia, or ≥ 5 adenomas, or any serrated polyp ≥ 10 mm or with dysplasia.
Strong recommendation, moderate quality evidence.
3
ESGE recommends a 3 – 6-month early repeat colonoscopy following piecemeal endoscopic resection of polyps ≥ 20 mm.
Strong recommendation, moderate quality evidence.
A first surveillance colonoscopy 12 months after the repeat colonoscopy is recommended to detect late recurrence.
Strong recommendation, high quality evidence.
4
If no polyps requiring surveillance are detected at the first surveillance colonoscopy, ESGE suggests to perform a second surveillance colonoscopy after 5 years.
Weak recommendation, low quality evidence.
After that, if no polyps requiring surveillance are detected, patients can be returned to screening.
5
ESGE suggests that, if polyps requiring surveillance are detected at first or subsequent surveillance examinations, surveillance colonoscopy may be performed at 3 years.
Weak recommendation, low quality evidence.
A flowchart showing the recommended surveillance intervals is provided (Fig. 1).
To perform a systematic review and meta-analysis of published studies assessing the sensitivity of both computed tomographic (CT) colonography and optical colonoscopy (OC) for colorectal cancer ...detection.
Analysis followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses recommendations. The primary data source was the results of a detailed PubMed search from 1994 to 2009. Diagnostic studies evaluating CT colonography detection of colorectal cancer were assessed by using predefined inclusion and exclusion criteria, in particular requiring both OC and histologic confirmation of disease. Studies that also included a mechanism to assess true-positive versus false-negative diagnoses at OC (eg, segmental unblinding) were used to calculate OC sensitivity. Assessment and data extraction were performed independently by two authors. Potential bias was ascertained by using Quality Assessment of Diagnostic Accuracy Studies guidelines. Specific CT colonography techniques were cataloged. Forest plots of per-patient sensitivity were produced on the basis of random-effect models. Potential bias across primary studies was assessed by using the I(2) statistic. Original study authors were contacted for data clarification when necessary.
Forty-nine studies provided data on 11,151 patients with a cumulative colorectal cancer prevalence of 3.6% (414 cancers). The sensitivity of CT colonography for colorectal cancer was 96.1% (398 of 414; 95% confidence interval CI: 93.8%, 97.7%). No heterogeneity (I(2) = 0%) was detected. No cancers were missed at CT colonography when both cathartic and tagging agents were combined in the bowel preparation. The sensitivity of OC for colorectal cancer, derived from a subset of 25 studies including 9223 patients, was 94.7% (178 of 188; 95% CI: 90.4%, 97.2%). A moderate degree of heterogeneity (I(2) = 50%) was present.
CT colonography is highly sensitive for colorectal cancer, especially when both cathartic and tagging agents are combined in the bowel preparation. Given the relatively low prevalence of colorectal cancer, primary CT colonography may be more suitable than OC for initial investigation of suspected colorectal cancer, assuming reasonable specificity.
http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.11101887/-/DC1.