@misc{MeinikheimMendelProbstetal., author = {Meinikheim, Michael and Mendel, Robert and Probst, Andreas and Scheppach, Markus W. and Nagl, Sandra and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Prinz, Friederike and Schlottmann, Jakob and Messmann, Helmut and Palm, Christoph and Ebigbo, Alanna}, title = {Einfluss von K{\"u}nstlicher Intelligenz auf die Performance von niedergelassenen Gastroenterolog:innen bei der Beurteilung von Barrett-{\"O}sophagus}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {61}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {8}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0043-1771711}, abstract = {Einleitung Die Differenzierung zwischen nicht dysplastischem Barrett-{\"O}sophagus (NDBE) und mit Barrett-{\"O}sophagus assoziierten Neoplasien (BERN) w{\"a}hrend der endoskopischen Inspektion erfordert viel Expertise. Die fr{\"u}he Diagnosestellung ist wichtig f{\"u}r die weitere Prognose des Barrett-Karzinoms. In Deutschland werden Patient:innen mit einem Barrett-{\"O}sophagus (BE) in der Regel im niedergelassenen Sektor {\"u}berwacht. Ziele Ziel ist es, den Einfluss von einem auf K{\"u}nstlicher Intelligenz (KI) basierenden klinischen Entscheidungsunterst{\"u}tzungssystems (CDSS) auf die Performance von niedergelassenen Gastroenterolog:innen (NG) bei der Evaluation von Barrett-{\"O}sophagus (BE) zu untersuchen. Methodik Es erfolgte die prospektive Sammlung von 96 unver{\"a}nderten hochaufl{\"o}senden Videos mit F{\"a}llen von Patient:innen mit histologisch best{\"a}tigtem NDBE und BERN. Alle eingeschlossenen F{\"a}lle enthielten mindestens zwei der folgenden Darstellungsmethoden: HD-Weißlichtendoskopie, Narrow Band Imaging oder Texture and Color Enhancement Imaging. Sechs NG von sechs unterschiedlichen Praxen wurden als Proband:innen eingeschlossen. Es erfolgte eine permutierte Block-Randomisierung der Videof{\"a}lle in entweder Gruppe A oder Gruppe B. Gruppe A implizierte eine Evaluation des Falls durch Proband:innen zun{\"a}chst ohne KI und anschließend mit KI als CDSS. In Gruppe B erfolgte die Evaluation in umgekehrter Reihenfolge. Anschließend erfolgte eine zuf{\"a}llige Wiedergabe der so entstandenen Subgruppen im Rahmen des Tests. Ergebnis In diesem Test konnte ein von uns entwickeltes KI-System (Barrett-Ampel) eine Sensitivit{\"a}t von 92,2\%, eine Spezifit{\"a}t von 68,9\% und eine Accuracy von 81,3\% erreichen. Mit der Hilfe von KI verbesserte sich die Sensitivit{\"a}t der NG von 64,1\% auf 71,2\% (p<0,001) und die Accuracy von 66,3\% auf 70,8\% (p=0,006) signifikant. Eine signifikante Verbesserung dieser Parameter zeigte sich ebenfalls, wenn die Proband:innen die F{\"a}lle zun{\"a}chst ohne KI evaluierten (Gruppe A). Wurde der Fall jedoch als Erstes mit der Hilfe von KI evaluiert (Gruppe B), blieb die Performance nahezu konstant. Schlussfolgerung Es konnte ein performantes KI-System zur Evaluation von BE entwickelt werden. NG verbessern sich bei der Evaluation von BE durch den Einsatz von KI.}, language = {de} } @misc{ScheppachMendelProbstetal., author = {Scheppach, Markus W. and Mendel, Robert and Probst, Andreas and Nagl, Sandra and Meinikheim, Michael and Yip, Hon Chi and Lau, Louis Ho Shing and Chiu, Philip Wai Yan and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Effekt eines K{\"u}nstliche Intelligenz (KI) - Algorithmus auf die Gef{\"a}ßdetektion bei third space Endoskopien}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {61}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {08}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0043-1771980}, pages = {e528-e529}, abstract = {Einleitung Third space Endoskopieprozeduren wie die endoskopische Submukosadissektion (ESD) und die perorale endoskopische Myotomie (POEM) sind technisch anspruchsvoll und gehen mit untersucherabh{\"a}ngigen Komplikationen wie Blutungen und Perforationen einher. Grund hierf{\"u}r ist die unabsichtliche Durchschneidung von submukosalen Blutgef{\"a}ßen ohne pr{\"a}emptive Koagulation. Ziele Die Forschungsfrage, ob ein KI-Algorithmus die intraprozedurale Gef{\"a}ßerkennung bei ESD und POEM unterst{\"u}tzen und damit Komplikationen wie Blutungen verhindern k{\"o}nnte, erscheint in Anbetracht des erfolgreichen Einsatzes von KI bei der Erkennung von Kolonpolypen interessant. Methoden Auf 5470 Einzelbildern von 59 third space Endoscopievideos wurden submukosale Blutgef{\"a}ße annotiert. Zusammen mit weiteren 179.681 nicht-annotierten Bildern wurde ein DeepLabv3+neuronales Netzwerk mit dem ECMT-Verfahren f{\"u}r semi-supervised learning trainiert, um Blutgef{\"a}ße in Echtzeit erkennen zu k{\"o}nnen. F{\"u}r die Evaluation wurde ein Videotest mit 101 Videoclips aus 15 vom Trainingsdatensatz separaten Prozeduren mit 200 vordefinierten Gef{\"a}ßen erstellt. Die Gef{\"a}ßdetektionsrate, -zeit und -dauer, definiert als der Prozentsatz an Einzelbildern eines Videos bezogen auf den Goldstandard, auf denen ein definiertes Gef{\"a}ß erkannt wurde, wurden erhoben. Acht erfahrene Endoskopiker wurden mithilfe dieses Videotests im Hinblick auf Gef{\"a}ßdetektion getestet, wobei eine H{\"a}lfte der Videos nativ, die andere H{\"a}lfte nach Markierung durch den KI-Algorithmus angesehen wurde. Ergebnisse Der mittlere Dice Score des Algorithmus f{\"u}r Blutgef{\"a}ße war 68\%. Die mittlere Gef{\"a}ßdetektionsrate im Videotest lag bei 94\% (96\% f{\"u}r ESD; 74\% f{\"u}r POEM). Die mediane Gef{\"a}ßdetektionszeit des Algorithmus lag bei 0,32 Sekunden (0,3 Sekunden f{\"u}r ESD; 0,62 Sekunden f{\"u}r POEM). Die mittlere Gef{\"a}ßdetektionsdauer lag bei 59,1\% (60,6\% f{\"u}r ESD; 44,8\% f{\"u}r POEM) des Goldstandards. Alle Endoskopiker hatten mit KI-Unterst{\"u}tzung eine h{\"o}here Gef{\"a}ßdetektionsrate als ohne KI. Die mittlere Gef{\"a}ßdetektionsrate ohne KI lag bei 56,4\%, mit KI bei 71,2\% (p<0.001). Schlussfolgerung KI-Unterst{\"u}tzung war mit einer statistisch signifikant h{\"o}heren Gef{\"a}ßdetektionsrate vergesellschaftet. Die mediane Gef{\"a}ßdetektionszeit von deutlich unter einer Sekunde sowie eine Gef{\"a}ßdetektionsdauer von gr{\"o}ßer 50\% des Goldstandards wurden f{\"u}r den klinischen Einsatz als ausreichend erachtet. In prospektiven Anwendungsstudien sollte der KI-Algorithmus auf klinische Relevanz getestet werden.}, language = {de} } @misc{ZellmerRauberProbstetal., author = {Zellmer, Stephan and Rauber, David and Probst, Andreas and Weber, Tobias and Nagl, Sandra and R{\"o}mmele, Christoph and Schnoy, Elisabeth and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Verwendung k{\"u}nstlicher Intelligenz bei der Detektion der Papilla duodeni major}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {61}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {08}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0043-1772000}, pages = {e539 -- e540}, abstract = {Einleitung Die Endoskopische Retrograde Cholangiopankreatikographie (ERCP) ist der Goldstandard in der Diagnostik und Therapie von Erkrankungen des pankreatobili{\"a}ren Trakts. Jedoch ist sie technisch sehr anspruchsvoll und weist eine vergleichsweise hohe Komplikationsrate auf. Ziele In der vorliegenden Machbarkeitsstudie soll gepr{\"u}ft werden, ob mithilfe eines Deep-learning-Algorithmus die Papille und das Ostium zuverl{\"a}ssig detektiert werden k{\"o}nnen und somit f{\"u}r Endoskopiker mit geringer Erfahrung ein geeignetes Hilfsmittel, insbesondere f{\"u}r die Ausbildungssituation, darstellen k{\"o}nnten. Methodik Wir betrachteten insgesamt 606 Bilddatens{\"a}tze von 65 Patienten. In diesen wurde sowohl die Papilla duodeni major als auch das Ostium segmentiert. Anschließend wurde eine neuronales Netz mittels eines Deep-learning-Algorithmus trainiert. Außerdem erfolgte eine 5-fache Kreuzvaldierung. Ergebnisse Bei einer 5-fachen Kreuzvaldierung auf den 606 gelabelten Daten konnte f{\"u}r die Klasse Papille eine F1-Wert von 0,7908, eine Sensitivit{\"a}t von 0,7943 und eine Spezifit{\"a}t von 0,9785 erreicht werden, f{\"u}r die Klasse Ostium eine F1-Wert von 0,5538, eine Sensitivit{\"a}t von 0,5094 und eine Spezifit{\"a}t von 0,9970 (vgl. [Tab. 1]). Unabh{\"a}ngig von der Klasse zeigte sich gemittelt (Klasse Papille und Klasse Ostium) ein F1-Wert von 0,6673, eine Sensitivit{\"a}t von 0,6519 und eine Spezifit{\"a}t von 0,9877 (vgl. [Tab. 2]). Schlussfolgerung In vorliegende Machbarkeitsstudie konnte das neuronale Netz die Papilla duodeni major mit einer hohen Sensitivit{\"a}t und sehr hohen Spezifit{\"a}t identifizieren. Bei der Detektion des Ostiums war die Sensitivit{\"a}t deutlich geringer. Zuk{\"u}nftig soll das das neuronale Netz mit mehr Daten trainiert werden. Außerdem ist geplant, den Algorithmus auch auf Videos anzuwenden. Somit k{\"o}nnte langfristig ein geeignetes Hilfsmittel f{\"u}r die ERCP etabliert werden.}, language = {de} } @article{HartmannNieberlePalmetal., author = {Hartmann, Robin and Nieberle, Felix and Palm, Christoph and Br{\´e}bant, Vanessa and Prantl, Lukas and Kuehle, Reinald and Reichert, Torsten E. and Taxis, Juergen and Ettl, Tobias}, title = {Utility of Smartphone-based Three-dimensional Surface Imaging for Digital Facial Anthropometry}, series = {JPRAS Open}, volume = {39}, journal = {JPRAS Open}, publisher = {Elsevier}, doi = {10.1016/j.jpra.2024.01.014}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70348}, pages = {330 -- 343}, abstract = {Background The utilization of three-dimensional (3D) surface imaging for facial anthropometry is a significant asset for patients undergoing maxillofacial surgery. Notably, there have been recent advancements in smartphone technology that enable 3D surface imaging. In this study, anthropometric assessments of the face were performed using a smartphone and a sophisticated 3D surface imaging system. Methods 30 healthy volunteers (15 females and 15 males) were included in the study. An iPhone 14 Pro (Apple Inc., USA) using the application 3D Scanner App (Laan Consulting Corp., USA) and the Vectra M5 (Canfield Scientific, USA) were employed to create 3D surface models. For each participant, 19 anthropometric measurements were conducted on the 3D surface models. Subsequently, the anthropometric measurements generated by the two approaches were compared. The statistical techniques employed included the paired t-test, paired Wilcoxon signed-rank test, Bland-Altman analysis, and calculation of the intraclass correlation coefficient (ICC). Results All measurements showed excellent agreement between smartphone-based and Vectra M5-based measurements (ICC between 0.85 and 0.97). Statistical analysis revealed no statistically significant differences in the central tendencies for 17 of the 19 linear measurements. Despite the excellent agreement found, Bland-Altman analysis revealed that the 95\% limits of agreement between the two methods exceeded ±3 mm for the majority of measurements. Conclusion Digital facial anthropometry using smartphones can serve as a valuable supplementary tool for surgeons, enhancing their communication with patients. However, the proposed data suggest that digital facial anthropometry using smartphones may not yet be suitable for certain diagnostic purposes that require high accuracy.}, language = {en} } @article{MeinikheimMendelPalmetal., author = {Meinikheim, Michael and Mendel, Robert and Palm, Christoph and Probst, Andreas and Muzalyova, Anna and Scheppach, Markus W. and Nagl, Sandra and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Schulz, Dominik Andreas Helmut Otto and Schlottmann, Jakob and Prinz, Friederike and Rauber, David and R{\"u}ckert, Tobias and Matsumura, Tomoaki and Fern{\´a}ndez-Esparrach, Gl{\`o}ria and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/a-2296-5696}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-72818}, pages = {641 -- 649}, abstract = {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.}, language = {en} } @misc{EbigboRauberAyoubetal., author = {Ebigbo, Alanna and Rauber, David and Ayoub, Mousa and Birzle, Lisa and Matsumura, Tomoaki and Probst, Andreas and Steinbr{\"u}ck, Ingo and Nagl, Sandra and R{\"o}mmele, Christoph and Meinikheim, Michael and Scheppach, Markus W. and Palm, Christoph and Messmann, Helmut}, title = {Early Esophageal Cancer and the Generalizability of Artificial Intelligence}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, number = {S 02}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0044-1783775}, pages = {S428}, abstract = {Aims Artificial Intelligence (AI) systems in gastrointestinal endoscopy are narrow because they are trained to solve only one specific task. Unlike Narrow-AI, general AI systems may be able to solve multiple and unrelated tasks. We aimed to understand whether an AI system trained to detect, characterize, and segment early Barrett's neoplasia (Barrett's AI) is only capable of detecting this pathology or can also detect and segment other diseases like early squamous cell cancer (SCC). Methods 120 white light (WL) and narrow-band endoscopic images (NBI) from 60 patients (1 WL and 1 NBI image per patient) were extracted from the endoscopic database of the University Hospital Augsburg. Images were annotated by three expert endoscopists with extensive experience in the diagnosis and endoscopic resection of early esophageal neoplasias. An AI system based on DeepLabV3+architecture dedicated to early Barrett's neoplasia was tested on these images. The AI system was neither trained with SCC images nor had it seen the test images prior to evaluation. The overlap between the three expert annotations („expert-agreement") was the ground truth for evaluating AI performance. Results Barrett's AI detected early SCC with a mean intersection over reference (IoR) of 92\% when at least 1 pixel of the AI prediction overlapped with the expert-agreement. When the threshold was increased to 5\%, 10\%, and 20\% overlap with the expert-agreement, the IoR was 88\%, 85\% and 82\%, respectively. The mean Intersection Over Union (IoU) - a metric according to segmentation quality between the AI prediction and the expert-agreement - was 0.45. The mean expert IoU as a measure of agreement between the three experts was 0.60. Conclusions In the context of this pilot study, the predictions of SCC by a Barrett's dedicated AI showed some overlap to the expert-agreement. Therefore, features learned from Barrett's cancer-related training might be helpful also for SCC prediction. Our results allow different possible explanations. On the one hand, some Barrett's cancer features generalize toward the related task of assessing early SCC. On the other hand, the Barrett's AI is less specific to Barrett's cancer than a general predictor of pathological tissue. However, we expect to enhance the detection quality significantly by extending the training to SCC-specific data. The insight of this study opens the way towards a transfer learning approach for more efficient training of AI to solve tasks in other domains.}, language = {en} } @misc{ScheppachMendelRauberetal., author = {Scheppach, Markus W. and Mendel, Robert and Rauber, David and Probst, Andreas and Nagl, Sandra and R{\"o}mmele, Christoph and Meinikheim, Michael and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Artificial Intelligence (AI) improves endoscopists' vessel detection during endoscopic submucosal dissection (ESD)}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, number = {S 02}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0044-1782891}, pages = {S93}, abstract = {Aims While AI has been successfully implemented in detecting and characterizing colonic polyps, its role in therapeutic endoscopy remains to be elucidated. Especially third space endoscopy procedures like ESD and peroral endoscopic myotomy (POEM) pose a technical challenge and the risk of operator-dependent complications like intraprocedural bleeding and perforation. Therefore, we aimed at developing an AI-algorithm for intraprocedural real time vessel detection during ESD and POEM. Methods A training dataset consisting of 5470 annotated still images from 59 full-length videos (47 ESD, 12 POEM) and 179681 unlabeled images was used to train a DeepLabV3+neural network with the ECMT semi-supervised learning method. Evaluation for vessel detection rate (VDR) and time (VDT) of 19 endoscopists with and without AI-support was performed using a testing dataset of 101 standardized video clips with 200 predefined blood vessels. Endoscopists were stratified into trainees and experts in third space endoscopy. Results The AI algorithm had a mean VDR of 93.5\% and a median VDT of 0.32 seconds. AI support was associated with a statistically significant increase in VDR from 54.9\% to 73.0\% and from 59.0\% to 74.1\% for trainees and experts, respectively. VDT significantly decreased from 7.21 sec to 5.09 sec for trainees and from 6.10 sec to 5.38 sec for experts in the AI-support group. False positive (FP) readings occurred in 4.5\% of frames. FP structures were detected significantly shorter than true positives (0.71 sec vs. 5.99 sec). Conclusions AI improved VDR and VDT of trainees and experts in third space endoscopy and may reduce performance variability during training. Further research is needed to evaluate the clinical impact of this new technology.}, language = {en} } @misc{ZellmerRauberProbstetal., author = {Zellmer, Stephan and Rauber, David and Probst, Andreas and Weber, Tobias and Braun, Georg and R{\"o}mmele, Christoph and Nagl, Sandra and Schnoy, Elisabeth and Messmann, Helmut and Ebigbo, Alanna and Palm, Christoph}, title = {Artificial intelligence as a tool in the detection of the papillary ostium during ERCP}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, number = {S 02}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0044-1783138}, pages = {S198}, abstract = {Aims Endoscopic retrograde cholangiopancreaticography (ERCP) is the gold standard in the diagnosis as well as treatment of diseases of the pancreatobiliary tract. However, it is technically complex and has a relatively high complication rate. In particular, cannulation of the papillary ostium remains challenging. The aim of this study is to examine whether a deep-learning algorithm can be used to detect the major duodenal papilla and in particular the papillary ostium reliably and could therefore be a valuable tool for inexperienced endoscopists, particularly in training situation. Methods We analyzed a total of 654 retrospectively collected images of 85 patients. Both the major duodenal papilla and the ostium were then segmented. Afterwards, a neural network was trained using a deep-learning algorithm. A 5-fold cross-validation was performed. Subsequently, we ran the algorithm on 5 prospectively collected videos of ERCPs. Results 5-fold cross-validation on the 654 labeled data resulted in an F1 value of 0.8007, a sensitivity of 0.8409 and a specificity of 0.9757 for the class papilla, and an F1 value of 0.5724, a sensitivity of 0.5456 and a specificity of 0.9966 for the class ostium. Regardless of the class, the average F1 value (class papilla and class ostium) was 0.6866, the sensitivity 0.6933 and the specificity 0.9861. In 100\% of cases the AI-detected localization of the papillary ostium in the prospectively collected videos corresponded to the localization of the cannulation performed by the endoscopist. Conclusions In the present study, the neural network was able to identify the major duodenal papilla with a high sensitivity and high specificity. In detecting the papillary ostium, the sensitivity was notably lower. However, when used on videos, the AI was able to identify the location of the subsequent cannulation with 100\% accuracy. In the future, the neural network will be trained with more data. Thus, a suitable tool for ERCP could be established, especially in the training situation.}, language = {en} } @misc{ScheppachNunesArizietal., author = {Scheppach, Markus W. and Nunes, Danilo Weber and Arizi, X. and Rauber, David and Probst, Andreas and Nagl, Sandra and R{\"o}mmele, Christoph and Meinikheim, Michael and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Procedural phase recognition in endoscopic submucosal dissection (ESD) using artificial intelligence (AI)}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, number = {S 02}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0044-1783804}, pages = {S439}, abstract = {Aims Recent evidence suggests the possibility of intraprocedural phase recognition in surgical operations as well as endoscopic interventions such as peroral endoscopic myotomy and endoscopic submucosal dissection (ESD) by AI-algorithms. The intricate measurement of intraprocedural phase distribution may deepen the understanding of the procedure. Furthermore, real-time quality assessment as well as automation of reporting may become possible. Therefore, we aimed to develop an AI-algorithm for intraprocedural phase recognition during ESD. Methods A training dataset of 364385 single images from 9 full-length ESD videos was compiled. Each frame was classified into one procedural phase. Phases included scope manipulation, marking, injection, application of electrical current and bleeding. Allocation of each frame was only possible to one category. This training dataset was used to train a Video Swin transformer to recognize the phases. Temporal information was included via logarithmic frame sampling. Validation was performed using two separate ESD videos with 29801 single frames. Results The validation yielded sensitivities of 97.81\%, 97.83\%, 95.53\%, 85.01\% and 87.55\% for scope manipulation, marking, injection, electric application and bleeding, respectively. Specificities of 77.78\%, 90.91\%, 95.91\%, 93.65\% and 84.76\% were measured for the same parameters. Conclusions The developed algorithm was able to classify full-length ESD videos on a frame-by-frame basis into the predefined classes with high sensitivities and specificities. Future research will aim at the development of quality metrics based on single-operator phase distribution.}, language = {en} } @misc{RoserMeinikheimMendeletal., author = {Roser, David and Meinikheim, Michael and Mendel, Robert and Palm, Christoph and Probst, Andreas and Muzalyova, Anna and Scheppach, Markus W. and Nagl, Sandra and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Schulz, Dominik Andreas Helmut Otto and Schlottmann, Jakob and Prinz, Friederike and Rauber, David and R{\"u}ckert, Tobias and Matsumura, Tomoaki and Fernandez-Esparrach, G. and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Human-Computer Interaction: Impact of Artificial Intelligence on the diagnostic confidence of endoscopists assessing videos of Barrett's esophagus}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, number = {S 02}, publisher = {Georg Thieme Verlag}, issn = {1438-8812}, doi = {10.1055/s-0044-1782859}, pages = {79}, abstract = {Aims Human-computer interactions (HCI) may have a relevant impact on the performance of Artificial Intelligence (AI). Studies show that although endoscopists assessing Barrett's esophagus (BE) with AI improve their performance significantly, they do not achieve the level of the stand-alone performance of AI. One aspect of HCI is the impact of AI on the degree of certainty and confidence displayed by the endoscopist. Indirectly, diagnostic confidence when using AI may be linked to trust and acceptance of AI. In a BE video study, we aimed to understand the impact of AI on the diagnostic confidence of endoscopists and the possible correlation with diagnostic performance. Methods 22 endoscopists from 12 centers with varying levels of BE experience reviewed ninety-six standardized endoscopy videos. Endoscopists were categorized into experts and non-experts and randomly assigned to assess the videos with and without AI. Participants were randomized in two arms: Arm A assessed videos first without AI and then with AI, while Arm B assessed videos in the opposite order. Evaluators were tasked with identifying BE-related neoplasia and rating their confidence with and without AI on a scale from 0 to 9. Results The utilization of AI in Arm A (without AI first, with AI second) significantly elevated confidence levels for experts and non-experts (7.1 to 8.0 and 6.1 to 6.6, respectively). Only non-experts benefitted from AI with a significant increase in accuracy (68.6\% to 75.5\%). Interestingly, while the confidence levels of experts without AI were higher than those of non-experts with AI, there was no significant difference in accuracy between these two groups (71.3\% vs. 75.5\%). In Arm B (with AI first, without AI second), experts and non-experts experienced a significant reduction in confidence (7.6 to 7.1 and 6.4 to 6.2, respectively), while maintaining consistent accuracy levels (71.8\% to 71.8\% and 67.5\% to 67.1\%, respectively). Conclusions AI significantly enhanced confidence levels for both expert and non-expert endoscopists. Endoscopists felt significantly more uncertain in their assessments without AI. Furthermore, experts with or without AI consistently displayed higher confidence levels than non-experts with AI, irrespective of comparable outcomes. These findings underscore the possible role of AI in improving diagnostic confidence during endoscopic assessment.}, language = {en} }