@article{HammerNunesHammeretal., author = {Hammer, Simone and Nunes, Danilo Weber and Hammer, Michael and Zeman, Florian and Akers, Michael and G{\"o}tz, Andrea and Balla, Annika and Doppler, Michael Christian and Fellner, Claudia and Da Platz Batista Silva, Natascha and Thurn, Sylvia and Verloh, Niklas and Stroszczynski, Christian and Wohlgemuth, Walter Alexander and Palm, Christoph and Uller, Wibke}, title = {Deep learning-based differentiation of peripheral high-flow and low-flow vascular malformations in T2-weighted short tau inversion recovery MRI}, series = {Clinical hemorheology and microcirculation}, journal = {Clinical hemorheology and microcirculation}, edition = {Pre-press}, publisher = {IOP Press}, doi = {10.3233/CH-232071}, pages = {1 -- 15}, abstract = {BACKGROUND Differentiation of high-flow from low-flow vascular malformations (VMs) is crucial for therapeutic management of this orphan disease. OBJECTIVE A convolutional neural network (CNN) was evaluated for differentiation of peripheral vascular malformations (VMs) on T2-weighted short tau inversion recovery (STIR) MRI. METHODS 527 MRIs (386 low-flow and 141 high-flow VMs) were randomly divided into training, validation and test set for this single-center study. 1) Results of the CNN's diagnostic performance were compared with that of two expert and four junior radiologists. 2) The influence of CNN's prediction on the radiologists' performance and diagnostic certainty was evaluated. 3) Junior radiologists' performance after self-training was compared with that of the CNN. RESULTS Compared with the expert radiologists the CNN achieved similar accuracy (92\% vs. 97\%, p = 0.11), sensitivity (80\% vs. 93\%, p = 0.16) and specificity (97\% vs. 100\%, p = 0.50). In comparison to the junior radiologists, the CNN had a higher specificity and accuracy (97\% vs. 80\%, p <  0.001; 92\% vs. 77\%, p <  0.001). CNN assistance had no significant influence on their diagnostic performance and certainty. After self-training, the junior radiologists' specificity and accuracy improved and were comparable to that of the CNN. CONCLUSIONS Diagnostic performance of the CNN for differentiating high-flow from low-flow VM was comparable to that of expert radiologists. CNN did not significantly improve the simulated daily practice of junior radiologists, self-training was more effective.}, language = {en} } @article{RueckertRueckertPalm, author = {R{\"u}ckert, Tobias and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art}, series = {Computers in Biology and Medicine}, volume = {169}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, address = {Amsterdam}, doi = {10.1016/j.compbiomed.2024.107929}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-69830}, pages = {24}, abstract = {In the field of computer- and robot-assisted minimally invasive surgery, enormous progress has been made in recent years based on the recognition of surgical instruments in endoscopic images and videos. In particular, the determination of the position and type of instruments is of great interest. Current work involves both spatial and temporal information, with the idea that predicting the movement of surgical tools over time may improve the quality of the final segmentations. The provision of publicly available datasets has recently encouraged the development of new methods, mainly based on deep learning. In this review, we identify and characterize datasets used for method development and evaluation and quantify their frequency of use in the literature. We further present an overview of the current state of research regarding the segmentation and tracking of minimally invasive surgical instruments in endoscopic images and videos. The paper focuses on methods that work purely visually, without markers of any kind attached to the instruments, considering both single-frame semantic and instance segmentation approaches, as well as those that incorporate temporal information. The publications analyzed were identified through the platforms Google Scholar, Web of Science, and PubMed. The search terms used were "instrument segmentation", "instrument tracking", "surgical tool segmentation", and "surgical tool tracking", resulting in a total of 741 articles published between 01/2015 and 07/2023, of which 123 were included using systematic selection criteria. A discussion of the reviewed literature is provided, highlighting existing shortcomings and emphasizing the available potential for future developments.}, subject = {Deep Learning}, language = {en} } @article{SouzaJrPachecoPassosetal., author = {Souza Jr., Luis Antonio and Pacheco, Andr{\´e} G.C. and Passos, Leandro A. and Santana, Marcos C. S. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {DeepCraftFuse: visual and deeply-learnable features work better together for esophageal cancer detection in patients with Barrett's esophagus}, series = {Neural Computing and Applications}, journal = {Neural Computing and Applications}, publisher = {Springer}, address = {London}, doi = {10.1007/s00521-024-09615-z}, pages = {15}, abstract = {Limitations in computer-assisted diagnosis include lack of labeled data and inability to model the relation between what experts see and what computers learn. Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis. While deep learning techniques are broad so that unseen information might help learn patterns of interest, human insights to describe objects of interest help in decision-making. This paper proposes a novel approach, DeepCraftFuse, to address the challenge of combining information provided by deep networks with visual-based features to significantly enhance the correct identification of cancerous tissues in patients affected with Barrett's esophagus (BE). We demonstrate that DeepCraftFuse outperforms state-of-the-art techniques on private and public datasets, reaching results of around 95\% when distinguishing patients affected by BE that is either positive or negative to esophageal cancer.}, subject = {Deep Learning}, language = {en} } @inproceedings{RueckertRiederFeussneretal., author = {Rueckert, Tobias and Rieder, Maximilian and Feussner, Hubertus and Wilhelm, Dirk and Rueckert, Daniel and Palm, Christoph}, title = {Smoke Classification in Laparoscopic Cholecystectomy Videos Incorporating Spatio-temporal Information}, series = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springeer}, address = {Wiesbaden}, doi = {10.1007/978-3-658-44037-4_78}, pages = {298 -- 303}, abstract = {Heavy smoke development represents an important challenge for operating physicians during laparoscopic procedures and can potentially affect the success of an intervention due to reduced visibility and orientation. Reliable and accurate recognition of smoke is therefore a prerequisite for the use of downstream systems such as automated smoke evacuation systems. Current approaches distinguish between non-smoked and smoked frames but often ignore the temporal context inherent in endoscopic video data. In this work, we therefore present a method that utilizes the pixel-wise displacement from randomly sampled images to the preceding frames determined using the optical flow algorithm by providing the transformed magnitude of the displacement as an additional input to the network. Further, we incorporate the temporal context at evaluation time by applying an exponential moving average on the estimated class probabilities of the model output to obtain more stable and robust results over time. We evaluate our method on two convolutional-based and one state-of-the-art transformer architecture and show improvements in the classification results over a baseline approach, regardless of the network used.}, language = {en} } @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{TobiasDanielPalm, author = {Tobias, Rueckert and Daniel, Rueckert and Palm, Christoph}, title = {Corrigendum to "Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art" [Comput. Biol. Med. 169 (2024) 107929]}, series = {Computers in Biology and Medicine}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, doi = {10.1016/j.compbiomed.2024.108027}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70337}, pages = {1}, abstract = {The authors regret that the SAR-RARP50 dataset is missing from the description of publicly available datasets presented in Chapter 4.}, language = {en} } @unpublished{MendelRueckertWilhelmetal., author = {Mendel, Robert and Rueckert, Tobias and Wilhelm, Dirk and Rueckert, Daniel and Palm, Christoph}, title = {Motion-Corrected Moving Average: Including Post-Hoc Temporal Information for Improved Video Segmentation}, doi = {10.48550/arXiv.2403.03120}, pages = {9}, abstract = {Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise. Existing approaches can reduce inconsistencies by including temporal information but often impose requirements on the architecture or dataset. This paper proposes a method to include temporal information in any segmentation model and, thus, a technique to improve video segmentation performance without alterations during training or additional labeling. With Motion-Corrected Moving Average, we refine the exponential moving average between the current and previous predictions. Using optical flow to estimate the movement between consecutive frames, we can shift the prior term in the moving-average calculation to align with the geometry of the current frame. The optical flow calculation does not require the output of the model and can therefore be performed in parallel, leading to no significant runtime penalty for our approach. We evaluate our approach on two publicly available segmentation datasets and two proprietary endoscopic datasets and show improvements over a baseline approach.}, subject = {Deep Learning}, language = {en} } @misc{OPUS4-7115, title = {Bildverarbeitung f{\"u}r die Medizin 2024}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer}, address = {Wiesbaden}, isbn = {978-3-658-44037-4}, issn = {1431-472X}, doi = {10.1007/978-3-658-44037-4}, pages = {370}, abstract = {Seit mehr als 25 Jahren ist der Workshop "Bildverarbeitung f{\"u}r die Medizin" als erfolgreiche Veranstaltung etabliert. Ziel ist auch 2024 wieder die Darstellung aktueller Forschungsergebnisse und die Vertiefung der Gespr{\"a}che zwischen Wissenschaftlern, Industrie und Anwendern. Die Beitr{\"a}ge dieses Bandes - viele davon in englischer Sprache - umfassen alle Bereiche der medizinischen Bildverarbeitung, insbesondere die Bildgebung und -akquisition, Segmentierung und Analyse, Visualisierung und Animation, computerunterst{\"u}tzte Diagnose sowie bildgest{\"u}tzte Therapieplanung und Therapie. Hierbei kommen Methoden des maschinelles Lernens, der biomechanischen Modellierung sowie der Validierung und Qualit{\"a}tssicherung zum Einsatz.}, subject = {Bildverarbeitung}, language = {de} } @inproceedings{GutbrodGeislerRauberetal., author = {Gutbrod, Max and Geisler, Benedikt and Rauber, David and Palm, Christoph}, title = {Data Augmentation for Images of Chronic Foot Wounds}, series = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer}, address = {Wiesbaden}, doi = {10.1007/978-3-658-44037-4_71}, pages = {261 -- 266}, abstract = {Training data for Neural Networks is often scarce in the medical domain, which often results in models that struggle to generalize and consequently showpoor performance on unseen datasets. Generally, adding augmentation methods to the training pipeline considerably enhances a model's performance. Using the dataset of the Foot Ulcer Segmentation Challenge, we analyze two additional augmentation methods in the domain of chronic foot wounds - local warping of wound edges along with projection and blurring of shapes inside wounds. Our experiments show that improvements in the Dice similarity coefficient and Normalized Surface Distance metrics depend on a sensible selection of those augmentation methods.}, 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} } @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 A. H. and Schlottmann, Jakob and Prinz, Friederike and Rauber, David and Rueckert, 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}, 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 = {9}, 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{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 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} }