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
Linked color imaging (LCI) is a newly developed image-enhancing endoscopy technology that provides bright endoscopic images and increases color contrast. We investigated whether LCI improves the ...detection of neoplastic lesions in the right colon when compared with high definition white-light imaging (WLI).
Consecutive patients undergoing colonoscopy were randomized (1:1) after cecal intubation into right colon inspection at first pass by LCI or by WLI. At the hepatic flexure, the scope was reintroduced to the cecum under LCI and a second right colon inspection was performed under WLI in previously LCI-scoped patients (LCI-WLI group) and vice versa (WLI-LCI group). Lesions detected on first- and second-pass examinations were used to calculate detection and miss rates, respectively. The primary outcome was the right colon adenoma miss rate.
Of the 600 patients enrolled, 142 had at least one adenoma in the right colon, with similar right colon adenoma detection rates (r-ADR) in the two groups (22.7 % in LCI-WLI and 24.7 % in WLI-LCI). At per-polyp analysis, double inspection of the right colon in the LCI-WLI and WLI-LCI groups resulted in an 11.8 % and 30.6 % adenoma miss rate, respectively (
< 0.001). No significant difference in miss rate was found for advanced adenomas or sessile serrated lesions. At per-patient analysis, at least one adenoma was identified in the second pass only (incremental ADR) in 2 of 300 patients (0.7 %) in the LCI - WLI group and in 13 of 300 patients (4.3 %) in the WLI - LCI group (
= 0.01).
LCI could reduce the miss rate of neoplastic lesions in the right colon.
Abstract
Background
Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence ...(AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs).
Methods
Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations PIVI-1 threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines.
Results
Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %–93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %–98.9 %) and 92.6 % (95 %CI 90.0 %–95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %–87.3 %) than for experts (91.9 %, 95 %CI 88.5 %–94.5 %); however, nonexperts quickly approached the performance levels of experts over time.
Conclusion
AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopistsʼ high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.
False positive (FP) results by computer-aided detection (CADe) hamper the efficiency of colonoscopy by extending examination time. Our aim was to develop a classification of the causes and clinical ...relevance of CADe FPs, and to assess the relative distribution of FPs in a real-life setting.
In a post-hoc analysis of a randomized trial comparing colonoscopy with and without CADe (NCT: 04079478), we extracted 40 CADe colonoscopy videos. Using a modified Delphi process, 4 expert endoscopists identified the main domains for the reasons and clinical relevance of FPs. Then, 2 expert endoscopists manually examined each FP and classified it according to the proposed domains. The analysis was limited to the withdrawal phase.
The 2 main domains for the causes of CADe FPs were identified as artifacts due to either the mucosal wall or bowel content, and clinical relevance was defined as the time spent on FPs and the FP rate per minute. The mean number of FPs per colonoscopy was 27.3 ± 13.1, of which 24 ± 12 (88%) and 3.2 ± 2.6 (12%) were due to artifacts in the bowel wall and bowel content, respectively. Of the 27.3 FPs per colonoscopy, 1.6 (5.7%) required additional exploration time of 4.8 ± 6.2 seconds per FP (ie, 0.7% of the mean withdrawal time). In detail, 15 (24.2%), 33 (53.2%), and 14 (22.6%) FPs were classified as being of mild, moderate, or severe clinical relevance. The rate of FPs per minute of withdrawal time was 2.4 ± 1.2, and was higher for FPs due to artifacts from the bowel wall than for those from bowel content (2.4 ± 0.6 vs 0.3 ± 0.2, P < .001).
FPs by CADe are primarily due to artifacts from the bowel wall. Despite a high frequency, FPs result in a negligible 1% increase in the total withdrawal time because most of them are immediately discarded by the endoscopist.
Blue-light imaging (BLI) is a chromoendoscopy technique that uses direct (not filtered) emission of blue light with short wavelength (410 nm) to increase visibility of microvascular pattern and ...superficial mucosa. A BLI-based classification system for colorectal polyps (also called BLI Adenomas Serrated International Classification, BASIC) has been created and was validated using still images or short videos. We aimed to validate BASIC in a clinical practice setting, using thresholds recommended by the American Society for Gastrointestinal Endoscopy for the resect and discard strategy as the reference standard.
We studied 333 patients (mean age, 62.7±8.1 y; 176 men) who underwent screening colonoscopy from January through July 2019. Six endoscopists trained in BASIC participated in the study. All detected diminutive polyps were characterized by real-time BLI and categorized as adenoma or non-adenoma according to BASIC. All polyps were removed and evaluated by histopathology. The BLI-directed surveillance intervals (based on high-confidence characterization of polyps 5 mm or smaller and pathology feature for others) were compared with histology-directed surveillance intervals, according to United States Multi-society Task Force and European Society of Gastrointestinal Endoscopy recommendations. We calculated negative-predictive values of optical real-time analysis of diminutive rectosigmoid adenomas.
When we applied BASIC, 748 polyps smaller than 5 mm were categorized with 89% accuracy (95% CI, 85.9%-90.6%). BLI-directed surveillance was correct for 90% of patients according to the United States Multi-society task force criteria (95% CI, 86%-93%) and for 96% of patients according to European Society of Gastrointestinal Endoscopy criteria (95% CI, 93%-97%). The negative-predictive value for 302 polyps smaller than 5 mm, located in the rectosigmoid colon and evaluated with high confidence, based on histologic features of adenomatous polyps, was 91% (95% CI, 85%-95%).
Our analysis of data from 333 patients undergoing screen colonoscopies supports the validity of BASIC discriminating diminutive colorectal polyps with histologic features of adenomas from non-adenomas. This allows for the implementation of the resect and discard strategy based on BLI in clinical practice. ClinicalTrials.gov no: NCT03746171.
It has been proposed that the use of narrow-band imaging (NBI) for real-time histological assessment to determine postpolypectomy surveillance intervals is a cost-effective approach to the management ...of diminutive polyps. However, significant discrepancies in NBI performance have been observed among endoscopists; hence, professional societies recommend training, monitoring, and auditing. The aim of the present study was to evaluate the performance of real-time optical diagnosis for diminutive polyps after the inclusion of this approach in an internal quality assurance program, in order to assess its applicability in clinical practice Patients and methods: Four endoscopists attended periodic training sessions on NBI assessment of polyp histology before and during the study. Performance was audited and periodic feedback was provided. The accuracy of high-confidence NBI evaluation for polyps ≤ 5 mm in predicting surveillance intervals according to the European and US guidelines, and the negative predictive value (NPV) for adenoma in the rectosigmoid were calculated and compared with recommended thresholds (90 % agreement and 90 % NPV, respectively).
Overall, 284 outpatients (mean age 61.3 ± 18.2 years; 63 % males) were enrolled. A total of 656 polyps were detected, 465 of which (70.9 %) were diminutive (70.5 % adenomas). Sensitivity, specificity, positive and negative predictive values, and accuracy of high-confidence NBI predictions for adenoma in diminutive lesions were 95.3 %, 83.5 %, 93.5 %, 87.6 %, and 91.9 %, respectively. High-confidence characterization of diminutive polyps predicted the correct surveillance interval in 95.8 % and 93.3 % of cases according to European and American guidelines, respectively. NPV for adenoma in the rectosigmoid was 91.3 %
For community settings in which endoscopists are adequately trained and performance is periodically audited, real-time optical diagnosis for diminutive polyps is sufficiently accurate to avoid postpolypectomy histological examination of resected lesions, or to leave rectosigmoid hyperplastic polyps in place. Trial registered at ClinicalTrials.gov (NCT02196402).
Highlights ► PICD is a frequent and harmful complication of large volume paracentesis in cirrhosis. ► The efficacy of albumin (8 g/L of ascites removed) in preventing it is demonstrated. ► Albumin ...has high costs and limited availability. ► Half doses (4 g/L) were effective in preventing PICD and its clinical complications. ► Achievement: significant costs reduction in the management of ascites in cirrhosis.
It has been shown that mortality rates of coeliac patients correlate with age at diagnosis of coeliac disease, diagnostic delay for coeliac disease, pattern of clinical presentation and HLA typing. ...Our aim was to create a tool that identifies coeliac patients at higher risk of developing complications.
To identify predictors of complications in patients with coeliac disease, we organised an observational multicenter case-control study based on a retrospective collection of clinical data. Clinical data from 116 cases (patients with complicated coeliac disease) and 181 controls (coeliac patients without any complications) were collected from seven European centres. For each case, one or two controls, matched to cases according to the year of assessment, gender and age, were selected. Diagnostic delay, pattern of clinical presentation, HLA typing and age at diagnosis were used as predictors.
Differences between cases and controls were detected for diagnostic delay and classical presentation. Conditional logistic models based on these statistically different predictors allowed the development of a score system. Tertiles analysis showed a relationship between score and risk of developing complications.
A score that shows the risk of a newly diagnosed coeliac patient developing complications was devised for the first time. This will make it possible to set up the follow-up of coeliac patients with great benefits not only for their health but also for management of economic resources.
We think that our results are very encouraging and represent the first attempt to build a prognostic score for coeliac patients.