Artificial intelligence for characterization of diminutive colorectal polyps:A feasibility study comparing two computer-aided diagnosis systems

BACKGROUND Artificial intelligence(AI)has potential in the optical diagnosis of colorectal polyps.AIM To evaluate the feasibility of the real-time use of the computer-aided diagnosis system(CADx)AI for ColoRectal Polyps(AI4CRP)for the optical diagnosis of diminutive colorectal polyps and to compare the performance with CAD EYE^(TM)(Fujifilm,Tokyo,Japan).CADx influence on the optical diagnosis of an expert endoscopist was also investigated.METHODS AI4CRP was developed in-house and CAD EYE was proprietary software provided by Fujifilm.Both CADxsystems exploit convolutional neural networks.Colorectal polyps were characterized as benign or premalignant and histopathology was used as gold standard.AI4CRP provided an objective assessment of its characterization by presenting a calibrated confidence characterization value(range 0.0-1.0).A predefined cut-off value of 0.6 was set with values<0.6 indicating benign and values≥0.6 indicating premalignant colorectal polyps.Low confidence characterizations were defined as values 40%around the cut-off value of 0.6(<0.36 and>0.76).Self-critical AI4CRP’s diagnostic performances excluded low confidence characterizations.RESULTS AI4CRP use was feasible and performed on 30 patients with 51 colorectal polyps.Self-critical AI4CRP,excluding 14 low confidence characterizations[27.5%(14/51)],had a diagnostic accuracy of 89.2%,sensitivity of 89.7%,and specificity of 87.5%,which was higher compared to AI4CRP.CAD EYE had a 83.7%diagnostic accuracy,74.2%sensitivity,and 100.0%specificity.Diagnostic performances of the endoscopist alone(before AI)increased nonsignificantly after reviewing the CADx characterizations of both AI4CRP and CAD EYE(AI-assisted endoscopist).Diagnostic performances of the AI-assisted endoscopist were higher compared to both CADx-systems,except for specificity for which CAD EYE performed best.CONCLUSION Real-time use of AI4CRP was feasible.Objective confidence values provided by a CADx is novel and self-critical AI4CRP showed higher diagnostic performances compared to AI4CRP.

Barrett's esophagus with high grade dysplasia is associated with non-esophageal cancer

AIM To study factors associated with esophageal and nonesophageal cancer morbidity among Barrett's esophagus(BE) patients. METHODS A cohort study within a single tertiary center included 386 consecutive patients with biopsy proven BE, who were recruited between 2004-2014. Endoscopic and histologic data were prospectively recorded. Cancer morbidity was obtained from the national cancer registry. Main outcomes were BE related(defined as esophagus and cardia) and non-BE related cancers(all other cancers). Cancer incidence and all-causemortality were compared between patients with highgrade dysplasia(HGD) and with low-grade or no dysplasia(non-HGD) using Kaplan-Meier curves and cox regression models.RESULTS Of the 386 patients, 12 had HGD, 7 had a BE related cancer. There were 75(19.4%) patients with 86 cases of lifetime cancers, 76 of these cases were non-BE cancers. Seven(1.8%) and 18(4.7%) patients had BE and non-BE incident cancers, respectively. Twelve(3.1%) patients had HGD as worst histologic result. Two(16.7%) and 16(4.4%) incident non-BE cancers occurred in the HGD and non-HGD group, respectively. Ten-year any cancer and non-BE cancer free survival was 63% and 82% in the HGD group compared to 93% and 95% at the non-HGD group, respectively. Log-rank test for patients with more than one endoscopy, assuring longer follow up, showed a significant difference(P < 0.001 and P = 0.017 respectively). All-cause mortality was not significantly associated with BE HGD.CONCLUSION Patients with BE and HGD, may have a higher risk for all-cause cancer morbidity. The implications on cancer prevention recommendations should be further studied.

Architectural factors influencing the sense of home in nursing homes： An operationalization for practice

Various studies have shown that the architecture and design of a nursing home can have a profound impact on the sense of home of old people residing in the nursing home, next to psychological and social factors. However, adequate guidance on how these factors can be operationalized in practice is not provided for architects and interior designers. This study investigated which architectural factors contribute to a sense of home and how these can be implemented in the design guidelines. Two existing data sets were used, combining the most recent evidence from the literature and experiences of residents, family caregivers, and professional staff of Dutch nursing homes. These analyses resulted in theoretical implications for the private space, quasi-public space, the took and feel of the nursing home, and the outdoors. Furthermore, these analyses were used for the design of a demonstration apartment that integrates the factors of the sense of home. This description was concluded by a checklist for practice, in which design guidelines were formulated. A holistic understanding of which factors influence the sense of home could tead to improvements of the sense of home of nursing home residents.