@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{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} } @article{RoserMeinikheimMuzalyovaetal., author = {Roser, David and Meinikheim, Michael and Muzalyova, Anna and Mendel, Robert and Palm, Christoph and Probst, Andreas and Nagl, Sandra and Scheppach, Markus W. and R{\"o}mmele, Christoph and Schnoy, Elisabeth and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Artificial intelligence-assisted endoscopy and examiner confidence : a study on human-artificial intelligence interaction in Barrett's Esophagus (With Video)}, series = {DEN Open}, volume = {6}, journal = {DEN Open}, number = {1}, publisher = {Wiley}, doi = {10.1002/deo2.70150}, pages = {8}, abstract = {Objective Despite high stand-alone performance, studies demonstrate that artificial intelligence (AI)-supported endoscopic diagnostics often fall short in clinical applications due to human-AI interaction factors. This video-based trial on Barrett's esophagus aimed to investigate how examiner behavior, their levels of confidence, and system usability influence the diagnostic outcomes of AI-assisted endoscopy. Methods The present analysis employed data from a multicenter randomized controlled tandem video trial involving 22 endoscopists with varying degrees of expertise. Participants were tasked with evaluating a set of 96 endoscopic videos of Barrett's esophagus in two distinct rounds, with and without AI assistance. Diagnostic confidence levels were recorded, and decision changes were categorized according to the AI prediction. Additional surveys assessed user experience and system usability ratings. Results AI assistance significantly increased examiner confidence levels (p < 0.001) and accuracy. Withdrawing AI assistance decreased confidence (p < 0.001), but not accuracy. Experts consistently reported higher confidence than non-experts (p < 0.001), regardless of performance. Despite improved confidence, correct AI guidance was disregarded in 16\% of all cases, and 9\% of initially correct diagnoses were changed to incorrect ones. Overreliance on AI, algorithm aversion, and uncertainty in AI predictions were identified as key factors influencing outcomes. The System Usability Scale questionnaire scores indicated good to excellent usability, with non-experts scoring 73.5 and experts 85.6. Conclusions Our findings highlight the pivotal function of examiner behavior in AI-assisted endoscopy. To fully realize the benefits of AI, implementing explainable AI, improving user interfaces, and providing targeted training are essential. Addressing these factors could enhance diagnostic accuracy and confidence in clinical practice.}, language = {en} } @article{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Meinikheim, Michael and Byrne, Michael F. and Messmann, Helmut and Palm, Christoph}, title = {Multimodal imaging for detection and segmentation of Barrett's esophagus-related neoplasia using artificial intelligence}, series = {Endoscopy}, volume = {54}, journal = {Endoscopy}, number = {10}, edition = {E-Video}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/a-1704-7885}, pages = {1}, abstract = {The early diagnosis of cancer in Barrett's esophagus is crucial for improving the prognosis. However, identifying Barrett's esophagus-related neoplasia (BERN) is challenging, even for experts [1]. Four-quadrant biopsies may improve the detection of neoplasia, but they can be associated with sampling errors. The application of artificial intelligence (AI) to the assessment of Barrett's esophagus could improve the diagnosis of BERN, and this has been demonstrated in both preclinical and clinical studies [2] [3]. In this video demonstration, we show the accurate detection and delineation of BERN in two patients ([Video 1]). In part 1, the AI system detects a mucosal cancer about 20 mm in size and accurately delineates the lesion in both white-light and narrow-band imaging. In part 2, a small island of BERN with high-grade dysplasia is detected and delineated in white-light, narrow-band, and texture and color enhancement imaging. The video shows the results using a transparent overlay of the mucosal cancer in real time as well as a full segmentation preview. Additionally, the optical flow allows for the assessment of endoscope movement, something which is inversely related to the reliability of the AI prediction. We demonstrate that multimodal imaging can be applied to the AI-assisted detection and segmentation of even small focal lesions in real time.}, language = {en} } @misc{RoserMeinikheimMendeletal., author = {Roser, David and Meinikheim, Michael and Mendel, Robert and Palm, Christoph and Muzalyova, Anna and Rauber, David and R{\"u}ckert, Tobias and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Mensch-Maschine-Interaktion: Einfluss k{\"u}nstlicher Intelligenz auf das diagnostische Vertrauen von Endoskopikern bei der Beurteilung des Barrett-{\"O}sophagus}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {62}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {09}, publisher = {Georg Thieme Verlag KG}, doi = {10.1055/s-0044-1789656}, pages = {e575 -- e576}, abstract = {Ziele: Das Ziel der Studie war es, den Einfluss von KI auf die diagnostische Sicherheit (Konfidenzniveau) von Endoskopikern anhand von B{\"O}-Videos zu untersuchen und m{\"o}gliche Korrelationen mit der Untersuchungsqualit{\"a}t zu erforschen. Methodik: 22 Endoskopiker aus zw{\"o}lf Zentren mit unterschiedlicher Barrett-Erfahrung untersuchten 96 standardisierte Endoskopievideos. Die Untersucher wurden in Experten und Nicht-Experten eingeteilt und nach dem Zufallsprinzip f{\"u}r die Bewertung der Videos mit oder ohne KI eingeteilt. Die Teilnehmer wurden in zwei Gruppen aufgeteilt: Arm A bewertete zun{\"a}chst Videos ohne KI und dann mit KI, w{\"a}hrend Arm B die umgekehrte Reihenfolge einhielt. Die Untersucher hatten die Aufgabe, B{\"O}-assoziierte Neoplasien zu erkennen und ihr Konfidenzniveau sowohl mit als auch ohne KI auf einer Skala von 0 bis 9 anzugeben. Ergebnis: In Arm A erh{\"o}hte der Einsatz von KI das Konfidenzniveau bei beiden signifikant (p<0.001). Bemerkenswert ist, dass jedoch nur Nicht-Experten durch die KI eine signifikante Verbesserung der Sensitivit{\"a}t und Spezifit{\"a}t (p<0.001 bzw. p<0.05) erfuhren. W{\"a}hrend Experten ohne KI im Vergleich zu Nicht-Experten mit KI ein h{\"o}heres Konfidenzniveau aufwiesen, gab es keinen signifikanten Unterschied in der Genauigkeit. In Arm B zeigten beide Gruppen eine signifikante Abnahme des Konfidenzniveaus (p<0.001) bei gleichbleibender Genauigkeit. Dar{\"u}ber hinaus wurden in 9\% der Entscheidungen trotz korrekter KI eine falsche Wahl getroffen. Schlussfolgerung: Der Einsatz k{\"u}nstlicher Intelligenz steigerte das Konfidenzniveau sowohl bei Experten als auch bei Nicht-Experten signifikant - ein Effekt, der im Studienmodell reversibel war. Dar{\"u}ber hinaus wiesen Experten mit oder ohne KI durchweg h{\"o}here Konfidenzniveaus auf als Nicht-Experten mit KI, trotz vergleichbarer Ergebnisse. Zudem konnte beobachtet werden, dass die Untersucher in 9\% der F{\"a}lle die KI zuungunsten des Patienten ignorierten.}, language = {de} } @article{EbigboMendelScheppachetal., author = {Ebigbo, Alanna and Mendel, Robert and Scheppach, Markus W. and Probst, Andreas and Shahidi, Neal and Prinz, Friederike and Fleischmann, Carola and R{\"o}mmele, Christoph and G{\"o}lder, Stefan Karl and Braun, Georg and Rauber, David and R{\"u}ckert, Tobias and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Byrne, Michael F. and Palm, Christoph and Messmann, Helmut}, title = {Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm}, series = {Gut}, volume = {71}, journal = {Gut}, number = {12}, publisher = {BMJ}, address = {London}, doi = {10.1136/gutjnl-2021-326470}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-54293}, pages = {2388 -- 2390}, abstract = {In this study, we aimed to develop an artificial intelligence clinical decision support solution to mitigate operator-dependent limitations during complex endoscopic procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy, for example, bleeding and perforation. A DeepLabv3-based model was trained to delineate vessels, tissue structures and instruments on endoscopic still images from such procedures. The mean cross-validated Intersection over Union and Dice Score were 63\% and 76\%, respectively. Applied to standardised video clips from third-space endoscopic procedures, the algorithm showed a mean vessel detection rate of 85\% with a false-positive rate of 0.75/min. These performance statistics suggest a potential clinical benefit for procedure safety, time and also training.}, language = {en} } @article{EbigboMendelRueckertetal., author = {Ebigbo, Alanna and Mendel, Robert and R{\"u}ckert, Tobias and Schuster, Laurin and Probst, Andreas and Manzeneder, Johannes and Prinz, Friederike and Mende, Matthias and Steinbr{\"u}ck, Ingo and Faiss, Siegbert and Rauber, David and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Deprez, Pierre and Oyama, Tsuneo and Takahashi, Akiko and Seewald, Stefan and Sharma, Prateek and Byrne, Michael F. and Palm, Christoph and Messmann, Helmut}, title = {Endoscopic prediction of submucosal invasion in Barrett's cancer with the use of Artificial Intelligence: A pilot Study}, series = {Endoscopy}, volume = {53}, journal = {Endoscopy}, number = {09}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/a-1311-8570}, pages = {878 -- 883}, abstract = {Background and aims: The accurate differentiation between T1a and T1b Barrett's cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an Artificial Intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett's cancer white-light images. Methods: Endoscopic images from three tertiary care centres in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross-validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) was evaluated with the AI-system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett's cancer. Results: The sensitivity, specificity, F1 and accuracy of the AI-system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.73 and 0.71, respectively. There was no statistically significant difference between the performance of the AI-system and that of human experts with sensitivity, specificity, F1 and accuracy of 0.63, 0.78, 0.67 and 0.70 respectively. Conclusion: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett's cancer. AI scored equal to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and in a real-life setting. Nevertheless, the correct prediction of submucosal invasion in Barret´s cancer remains challenging for both experts and AI.}, subject = {Maschinelles Lernen}, language = {en} } @misc{RoemmeleMendelRauberetal., author = {R{\"o}mmele, Christoph and Mendel, Robert and Rauber, David and R{\"u}ckert, Tobias and Byrne, Michael F. and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Endoscopic Diagnosis of Eosinophilic Esophagitis Using a deep Learning Algorithm}, series = {Endoscopy}, volume = {53}, journal = {Endoscopy}, number = {S 01}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/s-0041-1724274}, abstract = {Aims Eosinophilic esophagitis (EoE) is easily missed during endoscopy, either because physicians are not familiar with its endoscopic features or the morphologic changes are too subtle. In this preliminary paper, we present the first attempt to detect EoE in endoscopic white light (WL) images using a deep learning network (EoE-AI). Methods 401 WL images of eosinophilic esophagitis and 871 WL images of normal esophageal mucosa were evaluated. All images were assessed for the Endoscopic Reference score (EREFS) (edema, rings, exudates, furrows, strictures). Images with strictures were excluded. EoE was defined as the presence of at least 15 eosinophils per high power field on biopsy. A convolutional neural network based on the ResNet architecture with several five-fold cross-validation runs was used. Adding auxiliary EREFS-classification branches to the neural network allowed the inclusion of the scores as optimization criteria during training. EoE-AI was evaluated for sensitivity, specificity, and F1-score. In addition, two human endoscopists evaluated the images. Results EoE-AI showed a mean sensitivity, specificity, and F1 of 0.759, 0.976, and 0.834 respectively, averaged over the five distinct cross-validation runs. With the EREFS-augmented architecture, a mean sensitivity, specificity, and F1-score of 0.848, 0.945, and 0.861 could be demonstrated respectively. In comparison, the two human endoscopists had an average sensitivity, specificity, and F1-score of 0.718, 0.958, and 0.793. Conclusions To the best of our knowledge, this is the first application of deep learning to endoscopic images of EoE which were also assessed after augmentation with the EREFS-score. The next step is the evaluation of EoE-AI using an external dataset. We then plan to assess the EoE-AI tool on endoscopic videos, and also in real-time. This preliminary work is encouraging regarding the ability for AI to enhance physician detection of EoE, and potentially to do a true "optical biopsy" but more work is needed.}, language = {en} } @misc{ScheppachRauberMendeletal., author = {Scheppach, Markus W. and Rauber, David and Mendel, Robert and Palm, Christoph and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Detection Of Celiac Disease Using A Deep Learning Algorithm}, series = {Endoscopy}, volume = {53}, journal = {Endoscopy}, number = {S 01}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/s-0041-1724970}, abstract = {Aims Celiac disease (CD) is a complex condition caused by an autoimmune reaction to ingested gluten. Due to its polymorphic manifestation and subtle endoscopic presentation, the diagnosis is difficult and thus the disorder is underreported. We aimed to use deep learning to identify celiac disease on endoscopic images of the small bowel. Methods Patients with small intestinal histology compatible with CD (MARSH classification I-III) were extracted retrospectively from the database of Augsburg University hospital. They were compared to patients with no clinical signs of CD and histologically normal small intestinal mucosa. In a first step MARSH III and normal small intestinal mucosa were differentiated with the help of a deep learning algorithm. For this, the endoscopic white light images were divided into five equal-sized subsets. We avoided splitting the images of one patient into several subsets. A ResNet-50 model was trained with the images from four subsets and then validated with the remaining subset. This process was repeated for each subset, such that each subset was validated once. Sensitivity, specificity, and harmonic mean (F1) of the algorithm were determined. Results The algorithm showed values of 0.83, 0.88, and 0.84 for sensitivity, specificity, and F1, respectively. Further data showing a comparison between the detection rate of the AI model and that of experienced endoscopists will be available at the time of the upcoming conference. Conclusions We present the first clinical report on the use of a deep learning algorithm for the detection of celiac disease using endoscopic images. Further evaluation on an external data set, as well as in the detection of CD in real-time, will follow. However, this work at least suggests that AI can assist endoscopists in the endoscopic diagnosis of CD, and ultimately may be able to do a true optical biopsy in live-time.}, language = {en} }