Optical diagnosis of colorectal polyp images using a newly developed computer-aided diagnosis system (CADx) compared with intuitive optical diagnosis.

BACKGROUND: Optical diagnosis of colorectal polyps remains challenging. Image-enhancement techniques such as narrow-band imaging and blue-light imaging (BLI) can improve optical diagnosis. We developed and prospectively validated a computer-aided diagnosis system (CADx) using high-definition white-light (HDWL) and BLI images, and compared the system with the optical diagnosis of expert and novice endoscopists. METHODS: CADx characterized colorectal polyps by exploiting artificial neural networks. Six experts and 13 novices optically diagnosed 60 colorectal polyps based on intuition. After 4 weeks, the same set of images was permuted and optically diagnosed using the BLI Adenoma Serrated International Classification (BASIC). RESULTS: CADx had a diagnostic accuracy of 88.3 % using HDWL images and 86.7 % using BLI images. The overall diagnostic accuracy combining HDWL and BLI (multimodal imaging) was 95.0 %, which was significantly higher than that of experts (81.7 %, P = 0.03) and novices (66.7 %, P < 0.001). Sensitivity was also higher for CADx (95.6 % vs. 61.1 % and 55.4 %), whereas specificity was higher for experts compared with CADx and novices (95.6 % vs. 93.3 % and 93.2 %). For endoscopists, diagnostic accuracy did not increase when using BASIC, either for experts (intuition 79.5 % vs. BASIC 81.7 %, P = 0.14) or for novices (intuition 66.7 % vs. BASIC 66.5 %, P = 0.95). CONCLUSION: CADx had a significantly higher diagnostic accuracy than experts and novices for the optical diagnosis of colorectal polyps. Multimodal imaging, incorporating both HDWL and BLI, improved the diagnostic accuracy of CADx. BASIC did not increase the diagnostic accuracy of endoscopists compared with intuitive optical diagnosis.

Development and validation of the international Blue Light Imaging for Barrett's Neoplasia Classification.

BACKGROUND AND AIMS: Detecting subtle Barrett's neoplasia during surveillance endoscopy can be challenging. Blue-light imaging (BLI) is a novel advanced endoscopic technology with high-intensity contrast imaging that may improve the identification of Barrett's neoplasia. The aim of this study was to develop and validate the first classification to enable characterization of neoplastic and non-neoplastic Barrett's esophagus using BLI. METHODS: In phase 1, descriptors pertaining to neoplastic and non-neoplastic Barrett's esophagus were identified to form the classification, named the Blue Light Imaging for Barrett's Neoplasia Classification (BLINC). Phase 2 involved validation of these component criteria by 10 expert endoscopists assessing 50 BLI images. In phase 3, a web-based training module was developed to enable 15 general (nonexpert) endoscopists to use BLINC. They then validated the classification with an image assessment exercise in phase 4, and their pre- and post-training results were compared. RESULTS: In phase 1 the descriptors were grouped into color, pit, and vessel pattern categories to form the classification. In phase 2 the sensitivity of neoplasia identification was 96.0% with a very good level of agreement among the experts (κ = .83). In phase 3, 15 general endoscopists completed the training module. In phase 4 their pretraining sensitivity (85.3%) improved significantly to 95.7% post-training with a good level of agreement (κ = .67). CONCLUSIONS: We developed and validated a new classification system (BLINC) for the optical diagnosis of Barrett's neoplasia using BLI. Despite the limitations of this image-based study with a high prevalence of neoplasia, we believe it has the potential to improve the optical diagnosis of Barrett's neoplasia given the high degree of sensitivity (96%) noted. It is also a promising tool for training in Barrett's esophagus optical diagnosis using BLI.

Best practice in placement of percutaneous endoscopic gastrostomy with jejunal extension tube for continuous infusion of levodopa carbidopa intestinal gel in the treatment of selected patients with Parkinson's disease in the Nordic region.

OBJECTIVE: Continuous infusion of levodopa carbidopa intestinal gel (LCIG) is associated with a significant improvement in the symptoms and quality of life of selected patients with advanced Parkinson's disease. Percutaneous endoscopic gastrostomy with jejunal extension (PEG/J) was first described in 1998 and has become the most common and standard technique for fixing the tubing in place for LCIG infusion. MATERIAL AND METHODS: A workshop was held in Stockholm, Sweden, to discuss the PEG/J placement for the delivery of LCIG in Parkinson's disease patients with the primary goal of providing guidance on best practice for the Nordic countries. RESULTS: Suggested procedures for preparation of patients for PEG/J placement, aftercare, troubleshooting and redo-procedures for use in the Nordic region are described and discussed. CONCLUSIONS: LCIG treatment administered through PEG/J-tubes gives a significant increase in quality of life for selected patients with advanced Parkinson's disease. Although minor complications are common, serious complications are infrequent, and the tube insertion procedures have a good safety record. Further development of delivery systems and evaluation of approaches designed to reduce the demand for redo endoscopy are required.

Once-only colonoscopy or two rounds of faecal immunochemical testing 2 years apart for colorectal cancer screening (SCREESCO): preliminary report of a randomised controlled trial.

BACKGROUND: Screening for colorectal cancer is done with lower gastrointestinal endoscopy or stool-based tests. There is little evidence from randomised trials to show primary colonoscopy reduces mortality in colorectal cancer. We aimed to investigate the effect of screening with once-only colonoscopy or two rounds of faecal immunochemical test screening on colorectal cancer mortality and incidence. METHODS: We did a randomised controlled trial in Sweden (SCREESCO). Residents in 18 of 21 regions who were age 60 years in the year of randomisation were identified from a population register maintained by the Swedish Tax Agency. A statistician with no further involvement in the trial used a randomised block method to assign individuals to once-only colonoscopy, two rounds of faecal immunochemical testing (OC-Sensor; 2 years apart), or a control group (no intervention; standard diagnostic pathways), in a ratio of 1:6 for colonoscopy versus control and 1:2 for faecal immunochemical testing versus control. Masking was not possible due to the nature of the trial. The primary endpoints of the trial are colorectal cancer mortality and colorectal cancer incidence. Here, we report preliminary participation rates, baseline findings, and adverse events from March, 2014, to December, 2020, in the two intervention groups after completion of recruitment and screening, up to the completion of the second faecal immunochemical testing round. Analyses were done in the intention-to-screen population, defined as all individuals who were randomly assigned to the respective study group. This study is registered with ClinicalTrials.gov, NCT02078804. FINDINGS: Between March 1, 2014, and Dec 31, 2020, 278 280 people were included in the study; 31 140 were assigned to the colonoscopy group, 60 300 to the faecal immunochemical test group, and 186 840 to the control group. 10 679 (35·1%) of 30 400 people who received an invitation for colonoscopy participated. 33 383 (55·5%) of 60 137 people who received a postal faecal immunochemical test participated. In the intention-to-screen analysis, colorectal cancer was detected in 49 (0·16%) of 31 140 people in the colonoscopy group versus 121 (0·20%) of 60 300 in the faecal immunochemical test group (relative risk [RR] 0·78, 95% CI 0·56-1·09). Advanced adenomas were detected in 637 (2·05%) people in the colonoscopy group and 968 (1·61%) in the faecal immunochemical test group (RR 1·27, 95% CI 1·15-1·41). Colonoscopy detected more right-sided advanced adenomas than faecal immunochemical testing. There were two perforations and 15 major bleeds in 16 555 colonoscopies. No intervention-related deaths occurred. INTERPRETATION: The diagnostic yield and the low number of adverse events indicate that the design from this trial, both for once-only colonoscopy and faecal immunochemical test screening, could be transferred to a population-based screening service if a benefit in disease-specific mortality is subsequently shown. FUNDING: Swedish regions, County Council, Regional Cancer Center Mellansverige, Swedish Cancer Society, Aleris Research and Development Fund, Eiken Chemical.

The diagnostic value of a change in bowel habit for colorectal cancer within different age groups.

BACKGROUND: Change in bowel habit as a sole alarm symptom for colorectal cancer is disputed. OBJECTIVE: We investigated the diagnostic value of change in bowel habit for colorectal cancer, particularly as a single symptom and within different age groups. METHODS: This retrospective cohort study examined colorectal cancer fast track referrals and outcomes across four Swedish hospitals (April 2016-May 2017). Entry criteria constituted one or more of three alarm features: anaemia, visible rectal bleeding, or change in bowel habit for more than 4 weeks in patients over 40 years of age. Patients were grouped as having only change in bowel habit, change in bowel habit plus anaemia/bleeding or anaemia/bleeding only. RESULTS: Of 628 patients, 22% were diagnosed with colorectal cancer. There were no cases of colorectal cancer in the only change in bowel habit group under 55 years, while this was 6% for 55-64 years, 8% for 65-74 years and 14% for 75 years and older. Among subjects under 55 years, 2% with anaemia/bleeding had colorectal cancer, this increased to 34% for 55 years and older (P < 0.0001). Change in bowel habit plus anaemia/bleeding gave a colorectal cancer prevalence of 16% in under 55 years and increased to 30% for 55 years and older (P = 0.07). CONCLUSION: Change in bowel habit as the only alarm feature has a low diagnostic yield for colorectal cancer in patients under 55 years.

Initial Experience of Video Capsule Endoscopy After Intestinal Transplantation.

BACKGROUND: Intestinal transplantation is a procedure which inflicts immunological and infectious complications that affect the transplanted graft, posing both diagnostic and therapeutic challenges. Video capsule endoscopy (VCE) offers easy access to the entire small intestine and presents itself as an interesting option. However, at present, no studies evaluating the usefulness of video capsule endoscopies in this setting have been published. Our aim was to evaluate the usefulness of VCE in detecting complications that arise after intestinal transplantation. METHODS: We included 7 adult patients with either isolated intestine (n = 1) or multivisceral grafts (n = 6). These patients underwent 12 VCE between 2004 and 2015 at the Sahlgrenska University Hospital. The median age was 42 (21-67) years (4 women/3 men). VCE was used in clinical situations where the conventional diagnostic methods failed to provide answers to the clinical question. RESULTS: Indications for the procedure were: suspicion of rejection (n = 4 examinations), gastrointestinal dysmotility (n = 4 examinations), high stomal output (n = 2 examinations), suspicion of lymphoproliferative disease in the transplanted graft (n = 1 examination), and clinical surveillance (n = 1 examination). The median time after transplantation for performing an examination was 740 (26-3059) days. VCE was useful in 83% of the examinations and the results influenced the planned management. The overall agreement between VCE findings and biopsies was moderate (κ = 0.54, P = 0.05) but increased when comparing the presence of inflammation/rejection (κ = 0.79, P < 0.001). CONCLUSIONS: VCE is a promising diagnostic method after intestinal transplantation. However, larger studies are needed to evaluate its potential risks and gains.