Hybrid Open Access - OA-Veröffentlichung in einer Subskriptionszeitschrift/-medium
Refine
Is part of the Bibliography
- no (47)
Keywords
- Artificial Intelligence (3)
- Maschinelles Lernen (3)
- Medical Image Computing (3)
- 3D volumetry (2)
- Business-managed IT (2)
- Chief Information Officer (2)
- Diagnose (2)
- Endoscopy (2)
- Fractional CIO (2)
- Shadow IT (2)
Institute
- Fakultät Informatik und Mathematik (47) (remove)
Begutachtungsstatus
- peer-reviewed (42)
Background
This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett’s esophagus (BE).
Methods
96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett’s esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level.
Results
AI had a stand-alone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.3%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1%, and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8% [95%CI 65.2%–74.2%] to 78.0% [95%CI 74.0%–82.0%]; specificity 67.3% [95%CI 62.5%–72.2%] to 72.7% [95%CI 68.2%–77.3%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI.
Conclusion
BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists’ decisions to follow or discard AI advice.
Case study research is one of the most widely used research methods in Information Systems (IS). In recent years, an increasing number of publications have used case studies with few sources of evidence, such as single interviews per case. While there is much methodological guidance on rigorously conducting multiple case studies, it remains unclear how researchers can achieve an acceptable level of rigour for this emerging type of multiple case study with few sources of evidence, i.e., multiple mini case studies. In this context, we synthesise methodological guidance for multiple case study research from a cross-disciplinary perspective to develop an analytical framework. Furthermore, we calibrate this analytical framework to multiple mini case studies by reviewing previous IS publications that use multiple mini case studies to provide guidelines to conduct multiple mini case studies rigorously. We also offer a conceptual definition of multiple mini case studies, distinguish them from other research approaches, and position multiple mini case studies as a pragmatic and rigorous approach to research emerging and innovative phenomena in IS.
Effect of AI on performance of endoscopists to detect Barrett neoplasia: A Randomized Tandem Trial
()
Background and study aims
To evaluate the effect of an AI-based clinical decision support system (AI) on the performance and diagnostic confidence of endoscopists during the assessment of Barrett's esophagus (BE).
Patients and Methods
Ninety-six standardized endoscopy videos were assessed by 22 endoscopists from 12 different centers with varying degrees of BE experience.
The assessment was randomized into two video sets: Group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level.
Results
AI had a standalone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.6%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1 and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.7% (95% CI, 65.2% - 74.2%) to 78.0% (95% CI, 74.0% - 82.0%); specificity 67.3% (95% CI, 62.5% - 72.2%) to 72.7% (95 CI, 68.2% - 77.3%). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI.
Conclusion
BE nonexperts benefitted significantly from the additional AI. BE experts and nonexperts remained below the standalone performance of AI, suggesting that there may be other factors influencing endoscopists to follow or discard AI advice.
In the field of computer- and robot-assisted minimally invasive surgery, enormous progress has been made in recent years based on the recognition of surgical instruments in endoscopic images and videos. In particular, the determination of the position and type of instruments is of great interest. Current work involves both spatial and temporal information, with the idea that predicting the movement of surgical tools over time may improve the quality of the final segmentations. The provision of publicly available datasets has recently encouraged the development of new methods, mainly based on deep learning. In this review, we identify and characterize datasets used for method development and evaluation and quantify their frequency of use in the literature. We further present an overview of the current state of research regarding the segmentation and tracking of minimally invasive surgical instruments in endoscopic images and videos. The paper focuses on methods that work purely visually, without markers of any kind attached to the instruments, considering both single-frame semantic and instance segmentation approaches, as well as those that incorporate temporal information. The publications analyzed were identified through the platforms Google Scholar, Web of Science, and PubMed. The search terms used were “instrument segmentation”, “instrument tracking”, “surgical tool segmentation”, and “surgical tool tracking”, resulting in a total of 741 articles published between 01/2015 and 07/2023, of which 123 were included using systematic selection criteria. A discussion of the reviewed literature is provided, highlighting existing shortcomings and emphasizing the available potential for future developments.
Auch kleine und mittlere Unternehmen (KMUs) benötigen zunehmend ein effektives Informationstechnologie- (IT)-Management, um wettbewerbsfähig zu bleiben. Im Vergleich zu großen Unternehmen verfügen KMUs jedoch oft nicht über die Ressourcen, die Arbeitgeberattraktivität oder den Bedarf, um einen Chief Information Officer (CIO) in Vollzeit zu beschäftigen. Um diese Lücke zu schließen, hat eine wachsende Zahl von Expertinnen und Experten weltweit damit begonnen, CIO-Dienste in Teilzeit anzubieten. Auf diese Weise erhalten KMUs Zugang zu erfahrenen und kompetenten IT-Führungskräften zu einem Bruchteil der Kosten und ohne langfristige Verpflichtungen. Während diese so genannten „Fractional CIOs“ in der Praxis bereits einen Mehrwert schaffen, gibt es noch kaum wissenschaftliche Untersuchungen zu diesem neuen Phänomen. In einem größeren Forschungsprojekt mit insgesamt 62 Fractional CIOs aus 10 Ländern wurden daher eine Definition, Typen verschiedenartiger Engagements und Erfolgsfaktoren abgeleitet. Die vorliegende Studie fasst die Ergebnisse zusammen und setzt sie in Bezug zum deutschen Markt, indem sie drei Fractional CIOs/CTOs aus Deutschland befragt. Es zeigt sich, dass die folgenden vier Engagement-Typen von Fractional CIOs für KMUs in verschiedenen Situationen von Nutzen sind: Strategisches IT-Management, Restrukturierung, Skalierung und Hands-on Support. Darüber hinaus zeigt die Studie, dass Vertrauen, die Unterstützung durch das Top-Management-Team und die Integrität des Fractional CIOs Schlüsselfaktoren für den Erfolg von Fractional CIO-Engagements sind. Für den deutschen Markt werden die Ergebnisse durch drei befragte Fractional CIOs/CTOs weitgehend bestätigt. Die Fractional CIOs/CTOs können zwar keine genauen Gründe für die geringe Akzeptanz der Rolle nennen, betonen aber ihr Wertpotenzial für den deutschen Markt.
Ziel der Studie:
Ziel der Studie ist die Messung des Stands der Digitalisierung und die mit einer Anbindung an die Telematikinfrastruktur verbundenen Chancen und Herausforderungen für Rehabilitationseinrichtungen.
Methodik:
Teilstandardisierte Online-Befragung bei Trägern von Rehabilitationseinrichtungen in Bayern (n=33). Der Fragebogen mit 36 Fragen beinhaltet eine leicht veränderte Skala auf Basis des „Electronic Medical Record Adoption Model (EMRAM)“.
Ergebnisse:
Der Digitalisierungsgrad wurde in 70 Prozent der Rehabilitationseinrichtungen mit Stufe 0 angegeben (Stufenmodell bis 7). Die Übermittlung patientenbezogener Daten (Eingang und Ausgang) erfolgt häufig analog, wohingegen die Verarbeitung innerhalb der Einrichtung in vielen Fällen bereits überwiegend digital ist. Beim Anschluss an die Telematikinfrastruktur wird hoher Aufwand bei der Installation, aber auch der Schulung des Personals und der Anpassung der Arbeitsorganisation gesehen.
Schlussfolgerung:
Durch Änderung der gesetzlich-finanziellen Lage in Deutschland eröffnen sich für Rehabilitationseinrichtungen neue Möglichkeiten einer verstärkten Digitalisierung. Hürden hängen mit Anforderungen an IT-Sicherheit, Schulung des Personals und sowie dem ebenfalls geringen Digitalisierungsstand bei Krankenhäusern und Ärzt*innen sowie Patient*innen zusammen, die eine digitale Datenübermittlung erschweren.
Let G⊊C be a bounded, simply connected domain in C, and denote by
Q(G):={f:G⟶G | f is a quasiconformal mapping of G onto G } the quasiconformal automorphism group of G. In a canonical manner, the set Q(G) carries the structure of a (non–abelian) group with respect to composition of mappings. Moreover, we endow the set Q(G) with the topology of uniform convergence by the supremum metric dsup(f,g):=supz∈G|f(z)−g(z)|,f,g∈Q(G).
In this paper, we present results concerning topological properties of Q(G) such as completeness, separability, path–connectedness, discreteness and compactness.
Semantic segmentation is an essential task in medical imaging research. Many powerful deep-learning-based approaches can be employed for this problem, but they are dependent on the availability of an expansive labeled dataset. In this work, we augment such supervised segmentation models to be suitable for learning from unlabeled data. Our semi-supervised approach, termed Error-Correcting Mean-Teacher, uses an exponential moving average model like the original Mean Teacher but introduces our new paradigm of error correction. The original segmentation network is augmented to handle this secondary correction task. Both tasks build upon the core feature extraction layers of the model. For the correction task, features detected in the input image are fused with features detected in the predicted segmentation and further processed with task-specific decoder layers. The combination of image and segmentation features allows the model to correct present mistakes in the given input pair. The correction task is trained jointly on the labeled data. On unlabeled data, the exponential moving average of the original network corrects the student’s prediction. The combined outputs of the students’ prediction with the teachers’ correction form the basis for the semi-supervised update. We evaluate our method with the 2017 and 2018 Robotic Scene Segmentation data, the ISIC 2017 and the BraTS 2020 Challenges, a proprietary Endoscopic Submucosal Dissection dataset, Cityscapes, and Pascal VOC 2012. Additionally, we analyze the impact of the individual components and examine the behavior when the amount of labeled data varies, with experiments performed on two distinct segmentation architectures. Our method shows improvements in terms of the mean Intersection over Union over the supervised baseline and competing methods. Code is available at https://github.com/CloneRob/ECMT.
Background and aims
Celiac disease with its endoscopic manifestation of villous atrophy is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of villous atrophy at routine esophagogastroduodenoscopy may improve diagnostic performance.
Methods
A dataset of 858 endoscopic images of 182 patients with villous atrophy and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet 18 deep learning model to detect villous atrophy. An external data set was used to test the algorithm, in addition to six fellows and four board certified gastroenterologists. Fellows could consult the AI algorithm’s result during the test. From their consultation distribution, a stratification of test images into “easy” and “difficult” was performed and used for classified performance measurement.
Results
External validation of the AI algorithm yielded values of 90 %, 76 %, and 84 % for sensitivity, specificity, and accuracy, respectively. Fellows scored values of 63 %, 72 % and 67 %, while the corresponding values in experts were 72 %, 69 % and 71 %, respectively. AI consultation significantly improved all trainee performance statistics. While fellows and experts showed significantly lower performance for “difficult” images, the performance of the AI algorithm was stable.
Conclusion
In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of villous atrophy on endoscopic still images. AI decision support significantly improved the performance of non-expert endoscopists. The stable performance on “difficult” images suggests a further positive add-on effect in challenging cases.
The prospect of achieving computational speedups by exploiting quantum phenomena makes the use of quantum processing units (QPUs) attractive for many algorithmic database problems. Query optimisation, which concerns problems that typically need to explore large search spaces, seems like an ideal match for the known quantum algorithms. We present the first quantum implementation of join ordering, which is one of the most investigated and fundamental query optimisation problems, based on a reformulation to quadratic binary unconstrained optimisation problems. We empirically characterise our method on two state-of-the-art approaches (gate-based quantum computing and quantum annealing), and identify speed-ups compared to the best know classical join ordering approaches for input sizes that can be processed with current quantum annealers. However, we also confirm that limits of early-stage technology are quickly reached.
Current QPUs are classified as noisy, intermediate scale quantum computers (NISQ), and are restricted by a variety of limitations that reduce their capabilities as compared to ideal future quantum computers, which prevents us from scaling up problem dimensions and reaching practical utility. To overcome these challenges, our formulation accounts for specific QPU properties and limitations, and allows us to trade between achievable solution quality and possible problem size.
In contrast to all prior work on quantum computing for query optimisation and database-related challenges, we go beyond currently available QPUs, and explicitly target the scalability limitations: Using insights gained from numerical simulations and our experimental analysis, we identify key criteria for co-designing QPUs to improve their usefulness for join ordering, and show how even relatively minor physical architectural improvements can result in substantial enhancements. Finally, we outline a path towards practical utility of custom-designed QPUs.