Assisted documentation as a new focus for artificial intelligence in endoscopy: the precedent of reliable withdrawal time and image reporting.

BACKGROUND : Reliable documentation is essential for maintaining quality standards in endoscopy; however, in clinical practice, report quality varies. We developed an artificial intelligence (AI)-based prototype for the measurement of withdrawal and intervention times, and automatic photodocumentation. METHOD: A multiclass deep learning algorithm distinguishing different endoscopic image content was trained with 10 557 images (1300 examinations, nine centers, four processors). Consecutively, the algorithm was used to calculate withdrawal time (AI prediction) and extract relevant images. Validation was performed on 100 colonoscopy videos (five centers). The reported and AI-predicted withdrawal times were compared with video-based measurement; photodocumentation was compared for documented polypectomies. RESULTS: Video-based measurement in 100 colonoscopies revealed a median absolute difference of 2.0 minutes between the measured and reported withdrawal times, compared with 0.4 minutes for AI predictions. The original photodocumentation represented the cecum in 88 examinations compared with 98/100 examinations for the AI-generated documentation. For 39/104 polypectomies, the examiners' photographs included the instrument, compared with 68 for the AI images. Lastly, we demonstrated real-time capability (10 colonoscopies). CONCLUSION : Our AI system calculates withdrawal time, provides an image report, and is real-time ready. After further validation, the system may improve standardized reporting, while decreasing the workload created by routine documentation.

Artificial intelligence-based polyp size measurement in gastrointestinal endoscopy using the auxiliary waterjet as a reference.

BACKGROUND: Measurement of colorectal polyp size during endoscopy is mainly performed visually. In this work, we propose a novel polyp size measurement system (Poseidon) based on artificial intelligence (AI) using the auxiliary waterjet as a measurement reference. METHODS: Visual estimation, biopsy forceps-based estimation, and Poseidon were compared using a computed tomography colonography-based silicone model with 28 polyps of defined sizes. Four experienced gastroenterologists estimated polyp sizes visually and with biopsy forceps. Furthermore, the gastroenterologists recorded images of each polyp with the waterjet in proximity for the application of Poseidon. Additionally, Poseidon's measurements of 29 colorectal polyps during routine clinical practice were compared with visual estimates. RESULTS: In the silicone model, visual estimation had the largest median percentage error of 25.1 % (95 %CI 19.1 %-30.4 %), followed by biopsy forceps-based estimation: median 20.0 % (95 %CI 14.4 %-25.6 %). Poseidon gave a significantly lower median percentage error of 7.4 % (95 %CI 5.0 %-9.4 %) compared with other methods. During routine colonoscopies, Poseidon presented a significantly lower median percentage error (7.7 %, 95 %CI 6.1 %-9.3 %) than visual estimation (22.1 %, 95 %CI 15.1 %-26.9 %). CONCLUSION: In this work, we present a novel AI-based method for measuring colorectal polyp size with significantly higher accuracy than other common sizing methods.

Risk Stratification of SARS-CoV-2 Breakthrough Infections Based on an Outbreak at a Student Festive Event.

In early 2022, the Coronavirus disease 2019 (COVID-19) remains a global challenge. COVID-19 is caused by an increasing number of variants of the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). Here, we report an outbreak of SARS-CoV-2 breakthrough infections related to a student festive event with 100 mostly vaccinated guests, which took place in Northern Bavaria, Germany, in October 2021. The data were obtained by retrospective guest interviews. In total, 95 students participated in the study, with 94 being fully vaccinated and 24 reporting infection by the delta variant. Correlation analyses among 15 examined variables revealed that time spent at the event, conversation with the supposed index person, and a homologous viral vector vaccination regime were significant risk factors for infection. Non-significant observations related to higher rates of infection included time since last vaccination, shared use of drinking vessels, and number of individual person-to-person contacts at the event. Our data suggest that a high rate of breakthrough infections with the delta variant occurs if no preventive measures are practiced. To limit infection risk, high-quality testing of participants should be considered a mandatory measure at gatherings, irrespective of the participants' vaccination status.

Homeostatic calcium fluxes, ER calcium release, SOCE, and calcium oscillations in cultured astrocytes are interlinked by a small calcium toolkit.

How homeostatic ER calcium fluxes shape cellular calcium signals is still poorly understood. Here we used dual-color calcium imaging (ER-cytosol) and transcriptome analysis to link candidates of the calcium toolkit of astrocytes with homeostatic calcium signals. We found molecular and pharmacological evidence that P/Q-type channel Cacna1a contributes to depolarization-dependent calcium entry in astrocytes. For stimulated ER calcium release, the cells express the phospholipase Cb3, IP3 receptors Itpr1 and Itpr2, but no ryanodine receptors (Ryr1-3). After IP3-induced calcium release, Stim1/2 - Orai1/2/3 most likely mediate SOCE. The Serca2 (Atp2a2) is the candidate for refilling of the ER calcium store. The cells highly express adenosine receptor Adora1a for IP3-induced calcium release. Accordingly, adenosine induces fast ER calcium release and subsequent ER calcium oscillations. After stimulation, calcium refilling of the ER depends on extracellular calcium. In response to SOCE, astrocytes show calcium-induced calcium release, notably even after ER calcium was depleted by extracellular calcium removal in unstimulated cells. In contrast, spontaneous ER-cytosol calcium oscillations were not fully dependent on extracellular calcium, as ER calcium oscillations could persist over minutes in calcium-free solution. Additionally, cell-autonomous calcium oscillations show a second-long spatial and temporal delay in the signal dynamics of ER and cytosolic calcium. Our data reveal a rather strong contribution of homeostatic calcium fluxes in shaping IP3-induced and calcium-induced calcium release as well as spatiotemporal components of intracellular calcium oscillations.

A convolutional neural network for ECG annotation as the basis for classification of cardiac rhythms.

OBJECTIVE: Electrocardiography is the most common tool to diagnose cardiovascular diseases. Annotation, segmentation and rhythm classification of ECGs are challenging tasks, especially in the presence of atrial fibrillation and other arrhythmias. Our aim is to increase the accuracy of heart rhythm estimation by the use of extreme gradient boosting trees and the development of a deep convolutional neural network for ECG segmentation. APPROACH: We trained a convolutional neural network with waveforms from PhysioNet databases to annotate QRS complexes, P waves, T waves, noise and interbeat ECG segments that characterize the essences of normal and irregular heart beats. We evaluated true positive rates, positive predictive values and mean absolute differences of our annotation based on reference annotations of the QT and MIT-BIH P-wave database. Moreover, we compared the results with standard QRS detectors and Ecgpuwave. Extreme gradient boosting trees were used to determine the heart rhythm based on hand-crafted features. More precisely, a noise estimation function was used in combination with heart rate and interval data. Furthermore we defined particular features based on ECG morphology, appearance of P waves and detection of irregular beats. We examined the feature importance and identified key features for normal sinus rhythm, atrial fibrillation, alternative rhythm and noisy recordings. The classification performance was evaluated externally using F 1 scores by applying the algorithm to the hidden test set provided by the PhysioNet/CinC Challenge 2017. MAIN RESULTS: The true positive rate of the convolutional neural network in detection of manually revised R peaks in the QT database was [Formula: see text] and the positive predictive value was [Formula: see text]. The detection of P and T waves reached a true positive rate of [Formula: see text] and [Formula: see text] respectively, given a 50 ms tolerance when comparing the reference to the test annotation set. The rhythm classification performance reached an overall F 1 score of 0.82 when applying the algorithm to the hidden test set. SIGNIFICANCE: We achieved a shared rank #9 in the post-challenge phase of the PhysioNet/CinC Challenge 2017.