A deep learning system for detection of early Barrett's neoplasia: a model development and validation study.

BACKGROUND: Computer-aided detection (CADe) systems could assist endoscopists in detecting early neoplasia in Barrett's oesophagus, which could be difficult to detect in endoscopic images. The aim of this study was to develop, test, and benchmark a CADe system for early neoplasia in Barrett's oesophagus. METHODS: The CADe system was first pretrained with ImageNet followed by domain-specific pretraining with GastroNet. We trained the CADe system on a dataset of 14 046 images (2506 patients) of confirmed Barrett's oesophagus neoplasia and non-dysplastic Barrett's oesophagus from 15 centres. Neoplasia was delineated by 14 Barrett's oesophagus experts for all datasets. We tested the performance of the CADe system on two independent test sets. The all-comers test set comprised 327 (73 patients) non-dysplastic Barrett's oesophagus images, 82 (46 patients) neoplastic images, 180 (66 of the same patients) non-dysplastic Barrett's oesophagus videos, and 71 (45 of the same patients) neoplastic videos. The benchmarking test set comprised 100 (50 patients) neoplastic images, 300 (125 patients) non-dysplastic images, 47 (47 of the same patients) neoplastic videos, and 141 (82 of the same patients) non-dysplastic videos, and was enriched with subtle neoplasia cases. The benchmarking test set was evaluated by 112 endoscopists from six countries (first without CADe and, after 6 weeks, with CADe) and by 28 external international Barrett's oesophagus experts. The primary outcome was the sensitivity of Barrett's neoplasia detection by general endoscopists without CADe assistance versus with CADe assistance on the benchmarking test set. We compared sensitivity using a mixed-effects logistic regression model with conditional odds ratios (ORs; likelihood profile 95% CIs). FINDINGS: Sensitivity for neoplasia detection among endoscopists increased from 74% to 88% with CADe assistance (OR 2·04; 95% CI 1·73-2·42; p<0·0001 for images and from 67% to 79% [2·35; 1·90-2·94; p<0·0001] for video) without compromising specificity (from 89% to 90% [1·07; 0·96-1·19; p=0·20] for images and from 96% to 94% [0·94; 0·79-1·11; ] for video; p=0·46). In the all-comers test set, CADe detected neoplastic lesions in 95% (88-98) of images and 97% (90-99) of videos. In the benchmarking test set, the CADe system was superior to endoscopists in detecting neoplasia (90% vs 74% [OR 3·75; 95% CI 1·93-8·05; p=0·0002] for images and 91% vs 67% [11·68; 3·85-47·53; p<0·0001] for video) and non-inferior to Barrett's oesophagus experts (90% vs 87% [OR 1·74; 95% CI 0·83-3·65] for images and 91% vs 86% [2·94; 0·99-11·40] for video). INTERPRETATION: CADe outperformed endoscopists in detecting Barrett's oesophagus neoplasia and, when used as an assistive tool, it improved their detection rate. CADe detected virtually all neoplasia in a test set of consecutive cases. FUNDING: Olympus.

Endoscopic Resection Without Subsequent Ablation Therapy for Early Barrett's Neoplasia: Endoscopic Findings and Long-Term Mortality.

INTRODUCTION: After endoscopic resection (ER) of neoplasia in Barrett's esophagus (BE), it is recommended to ablate the remaining BE to minimize the risk for metachronous disease. However, we report long-term outcomes for a nationwide cohort of all patients who did not undergo ablation of the remaining BE after ER for early BE neoplasia, due to clinical reasons or performance status. METHODS: Endoscopic therapy for BE neoplasia in the Netherlands is centralized in 8 expert centers with specifically trained endoscopists and pathologists. Uniformity is ensured by a joint protocol and regular group meetings. We report all patients who underwent ER for a neoplastic lesion between 2008 and 2018, without further ablation therapy. Outcomes include progression during endoscopic FU and all-cause mortality. RESULTS: Ninety-four patients were included with mean age 74 (± 10) years. ER was performed for low-grade dysplasia (LGD) (10%), high-grade dysplasia (HGD) (25%), or low-risk esophageal adenocarcinoma (EAC) (65%). No additional ablation was performed for several reasons; in 73 patients (78%), the main argument was expected limited life expectancy. Median C2M5 BE persisted after ER, and during median 21 months (IQR 11-51) with 4 endoscopies per patient, no patient progressed to advanced cancer. Seventeen patients (18%) developed HGD/EAC: all were curatively treated endoscopically. In total, 29/73 patients (40%) with expected limited life expectancy died due to unrelated causes during FU, none of EAC. CONCLUSION: In selected patients, ER monotherapy with endoscopic surveillance of the residual BE is a valid alternative to eradication therapy with ablation.

[Motivation of High-risk Patients to Stop Smoking in the DMP]. / Motivation von Risikopatienten zum Rauchstopp im DMP.

AIM OF THE STUDY: Patients in disease management programmes (DMP) have a high overall cardiovascular risk. Smoking is the most important preventable risk factor. A reduction in the overall risk could be achieved in studies by multiple risk consulting. Direct influence on the smoking behaviour has not been investigated. ARRBIA heart is a risk calculator that can represent mainly the possible risk reduction through a change in behaviour such as smoking cessation. The MOTOR study should therefore review the possibility of integrating ARRBIA heart DMP in order to increase the motivation to stop smoking. METHODOLOGY: As part of the usual consultation DMP 47 patients were informed about their personal overall cardiovascular risk. Then a smoking brief intervention was performed depending on the predetermined motivation stage and handed out in a self-help manual at the end of the consultation. In the control group, 33 patients were treated as usual in the DMP. RESULTS: The integration of a risk consulting with ARRIBA heart is possible at a mean intervention period of 10 min in the regular DMP. Most doctors want to continue to work with ARRIBA heart. A change in smoking behaviour could not be determined by a single risk consulting. It was found, however, that the perception of risk increased with increasing motivation to stop smoking. CONCLUSIONS: In a subsequent study, the effectiveness of multiple risk consulting on the smoking behaviour and the overall risk must now be checked. The integration of ARRIBA heart is a possible approach to achieve regular smoking brief interventions in the DMP.

A new role for the neuronal ubiquitin C-terminal hydrolase-L1 (UCH-L1) in podocyte process formation and podocyte injury in human glomerulopathies.

Glomerular epithelial cell (podocyte) injury is characterized by foot process retraction, slit diaphragm reorganization, and degradation of podocyte-specific proteins. However, the mechanisms underlying podocyte injury are largely unknown. The ubiquitin C-terminal hydrolase-L1 (UCH-L1) is a key modulator of ubiquitin modification in neurons. Like neurons, UCH-L1 expression was associated with an undifferentiated status in cultured human podocytes, whereas differentiation and arborization decreased UCH-L1 and monoUb expression. Inhibition of UCH-L1 induced time and concentration-dependent process formation with alpha-actinin-4 distribution to the cell membrane and processes. An immunohistochemical approach was used to evaluate whether UCH-L1 expression was associated with podocyte injury in 15 different human glomerular diseases. Whereas normal kidneys expressed no UCH-L1 and little ubiquitin, a subset of human glomerulopathies associated with podocyte foot process effacement (membranous nephropathy, SLE class V, FSGS) de novo expressed UCH-L1 in podocyte cell bodies, nuclei, and processes. Interestingly, UCH-L1 expression correlated with podocyte ubiquitin content and internalization of the podocyte-specific proteins nephrin and alpha-actinin-4. In contrast, minimal change glomerulonephritis, a reversible disease, demonstrated minimal UCH-L1 and ubiquitin expression with intact alpha-actinin-4 but internalized nephrin. Glomerular kidney diseases typically not associated with foot process effacement (SLE class IV, ANCA+ necrotizing GN, amyloidosis, IgA nephritis) expressed intermediate to no UCH-L1 and ubiquitin. These studies show a role for UCH-L1 and ubiquitin modification in podocyte differentiation and injury.

The genomic response of the Drosophila embryo to JNK signaling.

During Drosophila development, the Jun N-terminal kinase signal transduction pathway regulates morphogenetic tissue closure movements that involve cell shape changes and reorganization of the actin cytoskeleton. We analyzed the genome-wide transcriptional response to activation of the JNK pathway in the Drosophila embryo by serial analysis of gene expression (SAGE) and identified loci encoding cell adhesion molecules and cytoskeletal regulators as JNK responsive genes. The role of one of the upregulated genes, chickadee (chic), encoding a Drosophila profilin, in embryogenesis was analyzed genetically. chic-deficient embryos fail to execute the JNK-mediated cytoskeletal rearrangements during dorsal closure. This study demonstrates a transcriptional mechanism of cytoskeletal regulation and establishes SAGE as an advantageous approach for genomic experiments in the fruitfly.