@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{SouzaJrPalmMendeletal., author = {Souza Jr., Luis Antonio de and Palm, Christoph and Mendel, Robert and Hook, Christian and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Weber, Silke A. T. and Papa, Jo{\~a}o Paulo}, title = {A survey on Barrett's esophagus analysis using machine learning}, series = {Computers in Biology and Medicine}, volume = {96}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, doi = {10.1016/j.compbiomed.2018.03.014}, pages = {203 -- 213}, abstract = {This work presents a systematic review concerning recent studies and technologies of machine learning for Barrett's esophagus (BE) diagnosis and treatment. The use of artificial intelligence is a brand new and promising way to evaluate such disease. We compile some works published at some well-established databases, such as Science Direct, IEEEXplore, PubMed, Plos One, Multidisciplinary Digital Publishing Institute (MDPI), Association for Computing Machinery (ACM), Springer, and Hindawi Publishing Corporation. Each selected work has been analyzed to present its objective, methodology, and results. The BE progression to dysplasia or adenocarcinoma shows a complex pattern to be detected during endoscopic surveillance. Therefore, it is valuable to assist its diagnosis and automatic identification using computer analysis. The evaluation of the BE dysplasia can be performed through manual or automated segmentation through machine learning techniques. Finally, in this survey, we reviewed recent studies focused on the automatic detection of the neoplastic region for classification purposes using machine learning methods.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @article{EbigboPalmProbstetal., author = {Ebigbo, Alanna and Palm, Christoph and Probst, Andreas and Mendel, Robert and Manzeneder, Johannes and Prinz, Friederike and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Siersema, Peter and Messmann, Helmut}, title = {A technical review of artificial intelligence as applied to gastrointestinal endoscopy: clarifying the terminology}, series = {Endoscopy International Open}, volume = {07}, journal = {Endoscopy International Open}, number = {12}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/a-1010-5705}, pages = {1616 -- 1623}, abstract = {The growing number of publications on the application of artificial intelligence (AI) in medicine underlines the enormous importance and potential of this emerging field of research. In gastrointestinal endoscopy, AI has been applied to all segments of the gastrointestinal tract most importantly in the detection and characterization of colorectal polyps. However, AI research has been published also in the stomach and esophagus for both neoplastic and non-neoplastic disorders. The various technical as well as medical aspects of AI, however, remain confusing especially for non-expert physicians. This physician-engineer co-authored review explains the basic technical aspects of AI and provides a comprehensive overview of recent publications on AI in gastrointestinal endoscopy. Finally, a basic insight is offered into understanding publications on AI in gastrointestinal endoscopy.}, subject = {Diagnose}, 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{ScheppachRauberStallhoferetal., author = {Scheppach, Markus W. and Rauber, David and Stallhofer, Johannes and Muzalyova, Anna and Otten, Vera and Manzeneder, Carolin and Schwamberger, Tanja and Wanzl, Julia and Schlottmann, Jakob and Tadic, Vidan and Probst, Andreas and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Fleischmann, Carola and Meinikheim, Michael and Miller, Silvia and M{\"a}rkl, Bruno and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Performance comparison of a deep learning algorithm with endoscopists in the detection of duodenal villous atrophy (VA)}, series = {Endoscopy}, volume = {55}, journal = {Endoscopy}, number = {S02}, publisher = {Thieme}, doi = {10.1055/s-0043-1765421}, pages = {S165}, abstract = {Aims VA is an endoscopic finding of celiac disease (CD), which can easily be missed if pretest probability is low. In this study, we aimed to develop an artificial intelligence (AI) algorithm for the detection of villous atrophy on endoscopic images. Methods 858 images from 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa were used for training and internal validation of an AI algorithm (ResNet18). A separate dataset was used for external validation, as well as determination of detection performance of experts, trainees and trainees with AI support. According to the AI consultation distribution, images were stratified into "easy" and "difficult". Results Internal validation showed 82\%, 85\% and 84\% for sensitivity, specificity and accuracy. External validation showed 90\%, 76\% and 84\%. The algorithm was significantly more sensitive and accurate than trainees, trainees with AI support and experts in endoscopy. AI support in trainees was associated with significantly improved performance. While all endoscopists showed significantly lower detection for "difficult" images, AI performance remained stable. Conclusions The algorithm outperformed trainees and experts in sensitivity and accuracy for VA detection. The significant improvement with AI support suggests a potential clinical benefit. Stable performance of the algorithm in "easy" and "difficult" test images may indicate an advantage in macroscopically challenging cases.}, language = {en} } @misc{ScheppachWeberNunesArizietal., author = {Scheppach, Markus W. and Weber Nunes, Danilo and Arizi, X. and Rauber, David and Probst, Andreas and Nagl, Sandra and R{\"o}mmele, Christoph and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Single frame workflow recognition during endoscopic submucosal dissection (ESD) using artificial intelligence (AI)}, series = {Endoscopy}, volume = {57}, journal = {Endoscopy}, number = {S 02}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0045-1806324}, pages = {S511}, abstract = {Aims Precise surgical phase recognition and evaluation may improve our understanding of complex endoscopic procedures. Furthermore, quality control measurements and endoscopy training could benefit from objective descriptions of surgical phase distributions. Therefore, we aimed to develop an artificial intelligence algorithm for frame-by-frame operational phase recognition during endoscopic submucosal dissection (ESD). Methods Full length ESD-videos from 31 patients comprising 6.297.782 single images were collected retrospectively. Videos were annotated on a frame-by-frame basis for the operational macro-phases diagnostics, marking, injection, dissection and bleeding. Further subphases were the application of electrical current, visible injection of fluid into the submucosal space and scope manipulation, leading to 11 phases in total. 4.975.699 frames (21 patients) were used for training of a video swin transformer using uniform frame sampling for temporal information. Hyperparameter tuning was performed with 897.325 further frames (6 patients), while 424.758 frames (4 patients) were used for validation. Results The overall F1 scores on the test dataset for the macro-phases and all 11 phases were 0.96 and 0.90, respectively. The recall values for diagnostics, marking, injection, dissection and bleeding were 1.00, 1.00, 0.95, 0.96 and 0.93, respectively. Conclusions The algorithm classified operational phases during ESD with high accuracy. A precise evaluation of phase distribution may allow for the development of objective quality metrics for quality control and training.}, 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} } @misc{ZellmerRauberProbstetal., author = {Zellmer, Stephan and Rauber, David and Probst, Andreas and Weber, Tobias and Braun, Georg and Nagl, Sandra and R{\"o}mmele, Christoph and Schnoy, Elisabeth and Birzle, Lisa and Aehling, Niklas and Schulz, Dominik Andreas Helmut Otto and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {K{\"u}nstliche Intelligenz als Hilfsmittel zur Detektion der Papilla duodeni major und des papill{\"a}ren Ostiums w{\"a}hrend der ERCP}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {63}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {5}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0045-1806882}, pages = {e295}, abstract = {Einleitung Die Endoskopische Retrograde Cholangiopankreatikographie (ERCP) ist der Goldstandard in der endoskopischen Therapie von Erkrankungen des pankreatobili{\"a}ren Trakts. Allerdings ist sie technisch anspruchsvoll, schwer zu erlernen und mit einer relativ hohen Komplikationsrate assoziiert. Daher soll in der vorliegenden Machbarkeitsstudie gepr{\"u}ft werden, ob mithilfe eines Deeplearning- Algorithmus die Papille und das Ostium zuverl{\"a}ssig detektiert werden k{\"o}nnen und dieser f{\"u}r Endoskopiker, insbesondere in der Ausbildungssituation, ein geeignetes Hilfsmittel darstellen k{\"o}nnte. Material und Methodik Insgesamt wurden 1534 ERCP-Bilder von 134 Patienten analysiert, wobei sowohl die Papilla duodeni major als auch das Ostium segmentiert wurden. Anschließend erfolgte das Training eines neuronalen Netzes unter Verwendung eines Deep-Learning-Algorithmus. F{\"u}r den Test des Algorithmus erfolgte eine f{\"u}nffache Kreuzvalidierung. Ergebnisse Auf den 1534 gelabelten Bildern wurden f{\"u}r die Klasse Papille ein F1-Wert von 0,7996, eine Sensitivit{\"a}t von 0,8488 und eine Spezifit{\"a}t von 0,9822 erzielt. F{\"u}r die Klasse Ostium ergaben sich ein F1-Wert von 0,5198, eine Sensitivit{\"a}t von 0,5945 und eine Spezifit{\"a}t von 0,9974. Klassen{\"u}bergreifend (Klasse Papille und Klasse Ostium) betrug der F1-Wert 0,6593, die Sensitivit{\"a}t 0,7216 und f{\"u}r die Spezifit{\"a}t 0,9898. Zusammenfassung In der vorliegenden Machbarkeitsstudie zeigte das neuronale Netz eine hohe Sensitivit{\"a}t und eine sehr hohe Spezifit{\"a}t bei der Identifikation der Papilla duodeni major. Die Detektion des Ostiums erfolgte hingegen mit einer deutlich geringeren Sensitivit{\"a}t. Zuk{\"u}nftig ist eine Erweiterung des Trainingsdatensatzes um Videos und klinische Daten vorgesehen, um die Leistungsf{\"a}higkeit des Netzwerks zu verbessern. Hierdurch k{\"o}nnte langfristig ein geeignetes Assistenzsystem f{\"u}r die ERCP, insbesondere in der Ausbildungssituation etabliert werden.}, language = {de} } @article{SouzaJrMendelStrasseretal., author = {Souza Jr., Luis Antonio de and Mendel, Robert and Strasser, Sophia and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Convolutional Neural Networks for the evaluation of cancer in Barrett's esophagus: Explainable AI to lighten up the black-box}, series = {Computers in Biology and Medicine}, volume = {135}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, issn = {0010-4825}, doi = {10.1016/j.compbiomed.2021.104578}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-20126}, pages = {1 -- 14}, abstract = {Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their level of accountability and transparency must be provided in such evaluations. The reliability related to machine learning predictions must be explained and interpreted, especially if diagnosis support is addressed. For this task, the black-box nature of deep learning techniques must be lightened up to transfer its promising results into clinical practice. Hence, we aim to investigate the use of explainable artificial intelligence techniques to quantitatively highlight discriminative regions during the classification of earlycancerous tissues in Barrett's esophagus-diagnosed patients. Four Convolutional Neural Network models (AlexNet, SqueezeNet, ResNet50, and VGG16) were analyzed using five different interpretation techniques (saliency, guided backpropagation, integrated gradients, input × gradients, and DeepLIFT) to compare their agreement with experts' previous annotations of cancerous tissue. We could show that saliency attributes match best with the manual experts' delineations. Moreover, there is moderate to high correlation between the sensitivity of a model and the human-and-computer agreement. The results also lightened that the higher the model's sensitivity, the stronger the correlation of human and computational segmentation agreement. We observed a relevant relation between computational learning and experts' insights, demonstrating how human knowledge may influence the correct computational learning.}, subject = {Deep Learning}, language = {en} } @misc{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Manzeneder, Johannes and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Palm, Christoph and Messmann, Helmut}, title = {Artificial Intelligence in Early Barrett's Cancer: The Segmentation Task}, series = {Endoscopy}, volume = {51}, journal = {Endoscopy}, number = {04}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/s-0039-1681187}, pages = {6}, abstract = {Aims: The delineation of outer margins of early Barrett's cancer can be challenging even for experienced endoscopists. Artificial intelligence (AI) could assist endoscopists faced with this task. As of date, there is very limited experience in this domain. In this study, we demonstrate the measure of overlap (Dice coefficient = D) between highly experienced Barrett endoscopists and an AI system in the delineation of cancer margins (segmentation task). Methods: An AI system with a deep convolutional neural network (CNN) was trained and tested on high-definition endoscopic images of early Barrett's cancer (n = 33) and normal Barrett's mucosa (n = 41). The reference standard for the segmentation task were the manual delineations of tumor margins by three highly experienced Barrett endoscopists. Training of the AI system included patch generation, patch augmentation and adjustment of the CNN weights. Then, the segmentation results from patch classification and thresholding of the class probabilities. Segmentation results were evaluated using the Dice coefficient (D). Results: The Dice coefficient (D) which can range between 0 (no overlap) and 1 (complete overlap) was computed only for images correctly classified by the AI-system as cancerous. At a threshold of t = 0.5, a mean value of D = 0.72 was computed. Conclusions: AI with CNN performed reasonably well in the segmentation of the tumor region in Barrett's cancer, at least when compared with expert Barrett's endoscopists. AI holds a lot of promise as a tool for better visualization of tumor margins but may need further improvement and enhancement especially in real-time settings.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @inproceedings{SouzaJrEbigboProbstetal., author = {Souza Jr., Luis Antonio de and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Papa, Jo{\~a}o Paulo and Mendel, Robert and Palm, Christoph}, title = {Barrett's Esophagus Identification Using Color Co-occurrence Matrices}, series = {31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Parana, 2018}, booktitle = {31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Parana, 2018}, doi = {10.1109/SIBGRAPI.2018.00028}, pages = {166 -- 173}, abstract = {In this work, we propose the use of single channel Color Co-occurrence Matrices for texture description of Barrett'sEsophagus (BE)and adenocarcinoma images. Further classification using supervised learning techniques, such as Optimum-Path Forest (OPF), Support Vector Machines with Radial Basisunction (SVM-RBF) and Bayesian classifier supports the contextof automatic BE and adenocarcinoma diagnosis. We validated three approaches of classification based on patches, patients and images in two datasets (MICCAI 2015 and Augsburg) using the color-and-texture descriptors and the machine learning techniques. Concerning MICCAI 2015 dataset, the best results were obtained using the blue channel for the descriptors and the supervised OPF for classification purposes in the patch-based approach, with sensitivity nearly to 73\% for positive adenocarcinoma identification and specificity close to 77\% for BE (non-cancerous) patch classification. Regarding the Augsburg dataset, the most accurate results were also obtained using both OPF classifier and blue channel descriptor for the feature extraction, with sensitivity close to 67\% and specificity around to76\%. Our work highlights new advances in the related research area and provides a promising technique that combines color and texture information, allied to three different approaches of dataset pre-processing aiming to configure robust scenarios for the classification step.}, language = {en} } @article{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Manzeneder, Johannes and Prinz, Friederike and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Palm, Christoph and Messmann, Helmut}, title = {Real-time use of artificial intelligence in the evaluation of cancer in Barrett's oesophagus}, series = {Gut}, volume = {69}, journal = {Gut}, number = {4}, publisher = {BMJ}, address = {London}, doi = {10.1136/gutjnl-2019-319460}, pages = {615 -- 616}, abstract = {Based on previous work by our group with manual annotation of visible Barrett oesophagus (BE) cancer images, a real-time deep learning artificial intelligence (AI) system was developed. While an expert endoscopist conducts the endoscopic assessment of BE, our AI system captures random images from the real-time camera livestream and provides a global prediction (classification), as well as a dense prediction (segmentation) differentiating accurately between normal BE and early oesophageal adenocarcinoma (EAC). The AI system showed an accuracy of 89.9\% on 14 cases with neoplastic BE.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @article{ArribasAntonelliFrazzonietal., author = {Arribas, Julia and Antonelli, Giulio and Frazzoni, Leonardo and Fuccio, Lorenzo and Ebigbo, Alanna and van der Sommen, Fons and Ghatwary, Noha and Palm, Christoph and Coimbra, Miguel and Renna, Francesco and Bergman, Jacques J.G.H.M. and Sharma, Prateek and Messmann, Helmut and Hassan, Cesare and Dinis-Ribeiro, Mario J.}, title = {Standalone performance of artificial intelligence for upper GI neoplasia: a meta-analysis}, series = {Gut}, volume = {70}, journal = {Gut}, number = {8}, publisher = {BMJ}, address = {London}, doi = {10.1136/gutjnl-2020-321922}, pages = {1458 -- 1468}, abstract = {Objective: Artificial intelligence (AI) may reduce underdiagnosed or overlooked upper GI (UGI) neoplastic and preneoplastic conditions, due to subtle appearance and low disease prevalence. Only disease-specific AI performances have been reported, generating uncertainty on its clinical value. Design: We searched PubMed, Embase and Scopus until July 2020, for studies on the diagnostic performance of AI in detection and characterisation of UGI lesions. Primary outcomes were pooled diagnostic accuracy, sensitivity and specificity of AI. Secondary outcomes were pooled positive (PPV) and negative (NPV) predictive values. We calculated pooled proportion rates (\%), designed summary receiving operating characteristic curves with respective area under the curves (AUCs) and performed metaregression and sensitivity analysis. Results: Overall, 19 studies on detection of oesophageal squamous cell neoplasia (ESCN) or Barrett's esophagus-related neoplasia (BERN) or gastric adenocarcinoma (GCA) were included with 218, 445, 453 patients and 7976, 2340, 13 562 images, respectively. AI-sensitivity/specificity/PPV/NPV/positive likelihood ratio/negative likelihood ratio for UGI neoplasia detection were 90\% (CI 85\% to 94\%)/89\% (CI 85\% to 92\%)/87\% (CI 83\% to 91\%)/91\% (CI 87\% to 94\%)/8.2 (CI 5.7 to 11.7)/0.111 (CI 0.071 to 0.175), respectively, with an overall AUC of 0.95 (CI 0.93 to 0.97). No difference in AI performance across ESCN, BERN and GCA was found, AUC being 0.94 (CI 0.52 to 0.99), 0.96 (CI 0.95 to 0.98), 0.93 (CI 0.83 to 0.99), respectively. Overall, study quality was low, with high risk of selection bias. No significant publication bias was found. Conclusion: We found a high overall AI accuracy for the diagnosis of any neoplastic lesion of the UGI tract that was independent of the underlying condition. This may be expected to substantially reduce the miss rate of precancerous lesions and early cancer when implemented in clinical practice.}, 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} } @article{SouzaJrPassosMendeletal., author = {Souza Jr., Luis Antonio de and Passos, Leandro A. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Assisting Barrett's esophagus identification using endoscopic data augmentation based on Generative Adversarial Networks}, series = {Computers in Biology and Medicine}, volume = {126}, journal = {Computers in Biology and Medicine}, number = {November}, publisher = {Elsevier}, doi = {10.1016/j.compbiomed.2020.104029}, pages = {12}, abstract = {Barrett's esophagus figured a swift rise in the number of cases in the past years. Although traditional diagnosis methods offered a vital role in early-stage treatment, they are generally time- and resource-consuming. In this context, computer-aided approaches for automatic diagnosis emerged in the literature since early detection is intrinsically related to remission probabilities. However, they still suffer from drawbacks because of the lack of available data for machine learning purposes, thus implying reduced recognition rates. This work introduces Generative Adversarial Networks to generate high-quality endoscopic images, thereby identifying Barrett's esophagus and adenocarcinoma more precisely. Further, Convolution Neural Networks are used for feature extraction and classification purposes. The proposed approach is validated over two datasets of endoscopic images, with the experiments conducted over the full and patch-split images. The application of Deep Convolutional Generative Adversarial Networks for the data augmentation step and LeNet-5 and AlexNet for the classification step allowed us to validate the proposed methodology over an extensive set of datasets (based on original and augmented sets), reaching results of 90\% of accuracy for the patch-based approach and 85\% for the image-based approach. Both results are based on augmented datasets and are statistically different from the ones obtained in the original datasets of the same kind. Moreover, the impact of data augmentation was evaluated in the context of image description and classification, and the results obtained using synthetic images outperformed the ones over the original datasets, as well as other recent approaches from the literature. Such results suggest promising insights related to the importance of proper data for the accurate classification concerning computer-assisted Barrett's esophagus and adenocarcinoma detection.}, subject = {Maschinelles Lernen}, language = {en} } @inproceedings{SouzaJrPassosMendeletal., author = {Souza Jr., Luis Antonio de and Passos, Leandro A. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Fine-tuning Generative Adversarial Networks using Metaheuristics}, series = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-33197-9}, doi = {10.1007/978-3-658-33198-6_50}, pages = {205 -- 210}, abstract = {Barrett's esophagus denotes a disorder in the digestive system that affects the esophagus' mucosal cells, causing reflux, and showing potential convergence to esophageal adenocarcinoma if not treated in initial stages. Thus, fast and reliable computer-aided diagnosis becomes considerably welcome. Nevertheless, such approaches usually suffer from imbalanced datasets, which can be addressed through Generative Adversarial Networks (GANs). Such techniques generate realistic images based on observed samples, even though at the cost of a proper selection of its hyperparameters. Many works employed a class of nature-inspired algorithms called metaheuristics to tackle the problem considering distinct deep learning approaches. Therefore, this paper's main contribution is to introduce metaheuristic techniques to fine-tune GANs in the context of Barrett's esophagus identification, as well as to investigate the feasibility of generating high-quality synthetic images for early-cancer assisted identification.}, subject = {Endoskopie}, language = {en} } @article{RoemmeleMendelBarrettetal., author = {R{\"o}mmele, Christoph and Mendel, Robert and Barrett, Caroline and Kiesl, Hans and Rauber, David and R{\"u}ckert, Tobias and Kraus, Lisa and Heinkele, Jakob and Dhillon, Christine and Grosser, Bianca and Prinz, Friederike and Wanzl, Julia and Fleischmann, Carola and Nagl, Sandra and Schnoy, Elisabeth and Schlottmann, Jakob and Dellon, Evan S. and Messmann, Helmut and Palm, Christoph and Ebigbo, Alanna}, title = {An artificial intelligence algorithm is highly accurate for detecting endoscopic features of eosinophilic esophagitis}, series = {Scientific Reports}, volume = {12}, journal = {Scientific Reports}, publisher = {Nature Portfolio}, address = {London}, doi = {10.1038/s41598-022-14605-z}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-46928}, pages = {10}, abstract = {The endoscopic features associated with eosinophilic esophagitis (EoE) may be missed during routine endoscopy. We aimed to develop and evaluate an Artificial Intelligence (AI) algorithm for detecting and quantifying the endoscopic features of EoE in white light images, supplemented by the EoE Endoscopic Reference Score (EREFS). An AI algorithm (AI-EoE) was constructed and trained to differentiate between EoE and normal esophagus using endoscopic white light images extracted from the database of the University Hospital Augsburg. In addition to binary classification, a second algorithm was trained with specific auxiliary branches for each EREFS feature (AI-EoE-EREFS). The AI algorithms were evaluated on an external data set from the University of North Carolina, Chapel Hill (UNC), and compared with the performance of human endoscopists with varying levels of experience. The overall sensitivity, specificity, and accuracy of AI-EoE were 0.93 for all measures, while the AUC was 0.986. With additional auxiliary branches for the EREFS categories, the AI algorithm (AI-EoEEREFS) performance improved to 0.96, 0.94, 0.95, and 0.992 for sensitivity, specificity, accuracy, and AUC, respectively. AI-EoE and AI-EoE-EREFS performed significantly better than endoscopy beginners and senior fellows on the same set of images. An AI algorithm can be trained to detect and quantify endoscopic features of EoE with excellent performance scores. The addition of the EREFS criteria improved the performance of the AI algorithm, which performed significantly better than endoscopists with a lower or medium experience level.}, 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} }