@article{WurmStarkZhuetal.2019, author = {Wurm, Michael and Stark, Thomas and Zhu, Xiao Xiang and Weigand, Matthias and Taubenb{\"o}ck, Hannes}, title = {Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks}, series = {ISPRS Journal of Photogrammetry and Remote Sensing}, volume = {150}, journal = {ISPRS Journal of Photogrammetry and Remote Sensing}, doi = {10.1016/j.isprsjprs.2019.02.006}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-233799}, pages = {59-69}, year = {2019}, abstract = {Unprecedented urbanization in particular in countries of the global south result in informal urban development processes, especially in mega cities. With an estimated 1 billion slum dwellers globally, the United Nations have made the fight against poverty the number one sustainable development goal. To provide better infrastructure and thus a better life to slum dwellers, detailed information on the spatial location and size of slums is of crucial importance. In the past, remote sensing has proven to be an extremely valuable and effective tool for mapping slums. The nature of used mapping approaches by machine learning, however, made it necessary to invest a lot of effort in training the models. Recent advances in deep learning allow for transferring trained fully convolutional networks (FCN) from one data set to another. Thus, in our study we aim at analyzing transfer learning capabilities of FCNs to slum mapping in various satellite images. A model trained on very high resolution optical satellite imagery from QuickBird is transferred to Sentinel-2 and TerraSAR-X data. While free-of-charge Sentinel-2 data is widely available, its comparably lower resolution makes slum mapping a challenging task. TerraSAR-X data on the other hand, has a higher resolution and is considered a powerful data source for intra-urban structure analysis. Due to the different image characteristics of SAR compared to optical data, however, transferring the model could not improve the performance of semantic segmentation but we observe very high accuracies for mapped slums in the optical data: QuickBird image obtains 86-88\% (positive prediction value and sensitivity) and a significant increase for Sentinel-2 applying transfer learning can be observed (from 38 to 55\% and from 79 to 85\% for PPV and sensitivity, respectively). Using transfer learning proofs extremely valuable in retrieving information on small-scaled urban structures such as slum patches even in satellite images of decametric resolution.}, language = {en} } @article{SondermannUtikalEnketal.2019, author = {Sondermann, Wiebke and Utikal, Jochen Sven and Enk, Alexander H. and Schadendorf, Dirk and Klode, Joachim and Hauschild, Axel and Weichenthal, Michael and French, Lars E. and Berking, Carola and Schilling, Bastian and Haferkamp, Sebastian and Fr{\"o}hling, Stefan and von Kalle, Christof and Brinker, Titus J.}, title = {Prediction of melanoma evolution in melanocytic nevi via artificial intelligence: A call for prospective data}, series = {European Journal of Cancer}, volume = {119}, journal = {European Journal of Cancer}, doi = {10.1016/j.ejca.2019.07.009}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-239263}, pages = {30-34}, year = {2019}, abstract = {Recent research revealed the superiority of artificial intelligence over dermatologists to diagnose melanoma from images. However, 30-50\% of all melanomas and more than half of those in young patients evolve from initially benign lesions. Despite its high relevance for melanoma screening, neither clinicians nor computers are yet able to reliably predict a nevus' oncologic transformation. The cause of this lies in the static nature of lesion presentation in the current standard of care, both for clinicians and algorithms. The status quo makes it difficult to train algorithms (and clinicians) to precisely assess the likelihood of a benign skin lesion to transform into melanoma. In addition, it inhibits the precision of current algorithms since 'evolution' image features may not be part of their decision. The current literature reveals certain types of melanocytic nevi (i.e. 'spitzoid' or 'dysplastic' nevi) and criteria (i.e. visible vasculature) that, in general, appear to have a higher chance to transform into melanoma. However, owing to the cumulative nature of oncogenic mutations in melanoma, a more fine-grained early morphologic footprint is likely to be detectable by an algorithm. In this perspective article, the concept of melanoma prediction is further explored by the discussion of the evolution of melanoma, the concept for training of such a nevi classifier and the implications of early melanoma prediction for clinical practice. In conclusion, the authors believe that artificial intelligence trained on prospective image data could be transformative for skin cancer diagnostics by (a) predicting melanoma before it occurs (i.e. pre-in situ) and (b) further enhancing the accuracy of current melanoma classifiers. Necessary prospective images for this research are obtained via free mole-monitoring mobile apps.}, language = {en} } @article{BrinkerHeklerEnketal.2019, author = {Brinker, Titus J. and Hekler, Achim and Enk, Alexander H. and Berking, Carola and Haferkamp, Sebastian and Hauschild, Axel and Weichenthal, Michael and Klode, Joachim and Schadendorf, Dirk and Holland-Letz, Tim and von Kalle, Christof and Fr{\"o}hling, Stefan and Schilling, Bastian and Utikal, Jochen S.}, title = {Deep neural networks are superior to dermatologists in melanoma image classification}, series = {European Journal of Cancer}, volume = {119}, journal = {European Journal of Cancer}, doi = {10.1016/j.ejca.2019.05.023}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-220539}, pages = {11-17}, year = {2019}, abstract = {Background Melanoma is the most dangerous type of skin cancer but is curable if detected early. Recent publications demonstrated that artificial intelligence is capable in classifying images of benign nevi and melanoma with dermatologist-level precision. However, a statistically significant improvement compared with dermatologist classification has not been reported to date. Methods For this comparative study, 4204 biopsy-proven images of melanoma and nevi (1:1) were used for the training of a convolutional neural network (CNN). New techniques of deep learning were integrated. For the experiment, an additional 804 biopsy-proven dermoscopic images of melanoma and nevi (1:1) were randomly presented to dermatologists of nine German university hospitals, who evaluated the quality of each image and stated their recommended treatment (19,296 recommendations in total). Three McNemar's tests comparing the results of the CNN's test runs in terms of sensitivity, specificity and overall correctness were predefined as the main outcomes. Findings The respective sensitivity and specificity of lesion classification by the dermatologists were 67.2\% (95\% confidence interval [CI]: 62.6\%-71.7\%) and 62.2\% (95\% CI: 57.6\%-66.9\%). In comparison, the trained CNN achieved a higher sensitivity of 82.3\% (95\% CI: 78.3\%-85.7\%) and a higher specificity of 77.9\% (95\% CI: 73.8\%-81.8\%). The three McNemar's tests in 2 × 2 tables all reached a significance level of p < 0.001. This significance level was sustained for both subgroups. Interpretation For the first time, automated dermoscopic melanoma image classification was shown to be significantly superior to both junior and board-certified dermatologists (p < 0.001).}, language = {en} } @article{BrinkerHeklerHauschildetal.2019, author = {Brinker, Titus J. and Hekler, Achim and Hauschild, Axel and Berking, Carola and Schilling, Bastian and Enk, Alexander H. and Haferkamp, Sebastian and Karoglan, Ante and von Kalle, Christof and Weichenthal, Michael and Sattler, Elke and Schadendorf, Dirk and Gaiser, Maria R. and Klode, Joachim and Utikal, Jochen S.}, title = {Comparing artificial intelligence algorithms to 157 German dermatologists: the melanoma classification benchmark}, series = {European Journal of Cancer}, volume = {111}, journal = {European Journal of Cancer}, doi = {10.1016/j.ejca.2018.12.016}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-220569}, pages = {30-37}, year = {2019}, abstract = {Background Several recent publications have demonstrated the use of convolutional neural networks to classify images of melanoma at par with board-certified dermatologists. However, the non-availability of a public human benchmark restricts the comparability of the performance of these algorithms and thereby the technical progress in this field. Methods An electronic questionnaire was sent to dermatologists at 12 German university hospitals. Each questionnaire comprised 100 dermoscopic and 100 clinical images (80 nevi images and 20 biopsy-verified melanoma images, each), all open-source. The questionnaire recorded factors such as the years of experience in dermatology, performed skin checks, age, sex and the rank within the university hospital or the status as resident physician. For each image, the dermatologists were asked to provide a management decision (treat/biopsy lesion or reassure the patient). Main outcome measures were sensitivity, specificity and the receiver operating characteristics (ROC). Results Total 157 dermatologists assessed all 100 dermoscopic images with an overall sensitivity of 74.1\%, specificity of 60.0\% and an ROC of 0.67 (range = 0.538-0.769); 145 dermatologists assessed all 100 clinical images with an overall sensitivity of 89.4\%, specificity of 64.4\% and an ROC of 0.769 (range = 0.613-0.9). Results between test-sets were significantly different (P < 0.05) confirming the need for a standardised benchmark. Conclusions We present the first public melanoma classification benchmark for both non-dermoscopic and dermoscopic images for comparing artificial intelligence algorithms with diagnostic performance of 145 or 157 dermatologists. Melanoma Classification Benchmark should be considered as a reference standard for white-skinned Western populations in the field of binary algorithmic melanoma classification.}, language = {en} } @article{KrenzerHeilFittingetal., author = {Krenzer, Adrian and Heil, Stefan and Fitting, Daniel and Matti, Safa and Zoller, Wolfram G. and Hann, Alexander and Puppe, Frank}, title = {Automated classification of polyps using deep learning architectures and few-shot learning}, series = {BMC Medical Imaging}, volume = {23}, journal = {BMC Medical Imaging}, doi = {10.1186/s12880-023-01007-4}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-357465}, abstract = {Background Colorectal cancer is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is a colonoscopy. However, not all colon polyps have the risk of becoming cancerous. Therefore, polyps are classified using different classification systems. After the classification, further treatment and procedures are based on the classification of the polyp. Nevertheless, classification is not easy. Therefore, we suggest two novel automated classifications system assisting gastroenterologists in classifying polyps based on the NICE and Paris classification. Methods We build two classification systems. One is classifying polyps based on their shape (Paris). The other classifies polyps based on their texture and surface patterns (NICE). A two-step process for the Paris classification is introduced: First, detecting and cropping the polyp on the image, and secondly, classifying the polyp based on the cropped area with a transformer network. For the NICE classification, we design a few-shot learning algorithm based on the Deep Metric Learning approach. The algorithm creates an embedding space for polyps, which allows classification from a few examples to account for the data scarcity of NICE annotated images in our database. Results For the Paris classification, we achieve an accuracy of 89.35 \%, surpassing all papers in the literature and establishing a new state-of-the-art and baseline accuracy for other publications on a public data set. For the NICE classification, we achieve a competitive accuracy of 81.13 \% and demonstrate thereby the viability of the few-shot learning paradigm in polyp classification in data-scarce environments. Additionally, we show different ablations of the algorithms. Finally, we further elaborate on the explainability of the system by showing heat maps of the neural network explaining neural activations. Conclusion Overall we introduce two polyp classification systems to assist gastroenterologists. We achieve state-of-the-art performance in the Paris classification and demonstrate the viability of the few-shot learning paradigm in the NICE classification, addressing the prevalent data scarcity issues faced in medical machine learning.}, language = {en} } @article{RackFernandoYalcinetal.2023, author = {Rack, Christian and Fernando, Tamara and Yalcin, Murat and Hotho, Andreas and Latoschik, Marc Erich}, title = {Who is Alyx? A new behavioral biometric dataset for user identification in XR}, series = {Frontiers in Virtual Reality}, volume = {4}, journal = {Frontiers in Virtual Reality}, issn = {2673-4192}, doi = {10.3389/frvir.2023.1272234}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-353979}, year = {2023}, abstract = {Introduction: This paper addresses the need for reliable user identification in Extended Reality (XR), focusing on the scarcity of public datasets in this area. Methods: We present a new dataset collected from 71 users who played the game "Half-Life: Alyx" on an HTC Vive Pro for 45 min across two separate sessions. The dataset includes motion and eye-tracking data, along with physiological data from a subset of 31 users. Benchmark performance is established using two state-of-the-art deep learning architectures, Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). Results: The best model achieved a mean accuracy of 95\% for user identification within 2 min when trained on the first session and tested on the second. Discussion: The dataset is freely available and serves as a resource for future research in XR user identification, thereby addressing a significant gap in the field. Its release aims to facilitate advancements in user identification methods and promote reproducibility in XR research.}, language = {en} } @article{VollmerNaglerHoerneretal.2023, author = {Vollmer, Andreas and Nagler, Simon and H{\"o}rner, Marius and Hartmann, Stefan and Brands, Roman C. and Breitenb{\"u}cher, Niko and Straub, Anton and K{\"u}bler, Alexander and Vollmer, Michael and Gubik, Sebastian and Lang, Gernot and Wollborn, Jakob and Saravi, Babak}, title = {Performance of artificial intelligence-based algorithms to predict prolonged length of stay after head and neck cancer surgery}, series = {Heliyon}, volume = {9}, journal = {Heliyon}, number = {11}, issn = {2405-8440}, doi = {10.1016/j.heliyon.2023.e20752}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-350416}, year = {2023}, abstract = {Background Medical resource management can be improved by assessing the likelihood of prolonged length of stay (LOS) for head and neck cancer surgery patients. The objective of this study was to develop predictive models that could be used to determine whether a patient's LOS after cancer surgery falls within the normal range of the cohort. Methods We conducted a retrospective analysis of a dataset consisting of 300 consecutive patients who underwent head and neck cancer surgery between 2017 and 2022 at a single university medical center. Prolonged LOS was defined as LOS exceeding the 75th percentile of the cohort. Feature importance analysis was performed to evaluate the most important predictors for prolonged LOS. We then constructed 7 machine learning and deep learning algorithms for the prediction modeling of prolonged LOS. Results The algorithms reached accuracy values of 75.40 (radial basis function neural network) to 97.92 (Random Trees) for the training set and 64.90 (multilayer perceptron neural network) to 84.14 (Random Trees) for the testing set. The leading parameters predicting prolonged LOS were operation time, ischemia time, the graft used, the ASA score, the intensive care stay, and the pathological stages. The results revealed that patients who had a higher number of harvested lymph nodes (LN) had a lower probability of recurrence but also a greater LOS. However, patients with prolonged LOS were also at greater risk of recurrence, particularly when fewer (LN) were extracted. Further, LOS was more strongly correlated with the overall number of extracted lymph nodes than with the number of positive lymph nodes or the ratio of positive to overall extracted lymph nodes, indicating that particularly unnecessary lymph node extraction might be associated with prolonged LOS. Conclusions The results emphasize the need for a closer follow-up of patients who experience prolonged LOS. Prospective trials are warranted to validate the present results.}, language = {en} } @article{PennigHoyerKrauskopfetal.2021, author = {Pennig, Lenhard and Hoyer, Ulrike Cornelia Isabel and Krauskopf, Alexandra and Shahzad, Rahil and J{\"u}nger, Stephanie T. and Thiele, Frank and Laukamp, Kai Roman and Grunz, Jan-Peter and Perkuhn, Michael and Schlamann, Marc and Kabbasch, Christoph and Borggrefe, Jan and Goertz, Lukas}, title = {Deep learning assistance increases the detection sensitivity of radiologists for secondary intracranial aneurysms in subarachnoid hemorrhage}, series = {Neuroradiology}, volume = {63}, journal = {Neuroradiology}, number = {12}, issn = {0028-3940}, doi = {10.1007/s00234-021-02697-9}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-308117}, pages = {1985-1994}, year = {2021}, abstract = {Purpose To evaluate whether a deep learning model (DLM) could increase the detection sensitivity of radiologists for intracranial aneurysms on CT angiography (CTA) in aneurysmal subarachnoid hemorrhage (aSAH). Methods Three different DLMs were trained on CTA datasets of 68 aSAH patients with 79 aneurysms with their outputs being combined applying ensemble learning (DLM-Ens). The DLM-Ens was evaluated on an independent test set of 104 aSAH patients with 126 aneuryms (mean volume 129.2 ± 185.4 mm3, 13.0\% at the posterior circulation), which were determined by two radiologists and one neurosurgeon in consensus using CTA and digital subtraction angiography scans. CTA scans of the test set were then presented to three blinded radiologists (reader 1: 13, reader 2: 4, and reader 3: 3 years of experience in diagnostic neuroradiology), who assessed them individually for aneurysms. Detection sensitivities for aneurysms of the readers with and without the assistance of the DLM were compared. Results In the test set, the detection sensitivity of the DLM-Ens (85.7\%) was comparable to the radiologists (reader 1: 91.2\%, reader 2: 86.5\%, and reader 3: 86.5\%; Fleiss κ of 0.502). DLM-assistance significantly increased the detection sensitivity (reader 1: 97.6\%, reader 2: 97.6\%,and reader 3: 96.0\%; overall P=.024; Fleiss κ of 0.878), especially for secondary aneurysms (88.2\% of the additional aneurysms provided by the DLM). Conclusion Deep learning significantly improved the detection sensitivity of radiologists for aneurysms in aSAH, especially for secondary aneurysms. It therefore represents a valuable adjunct for physicians to establish an accurate diagnosis in order to optimize patient treatment.}, language = {en} } @article{DirkFischerSchardtetal.2023, author = {Dirk, Robin and Fischer, Jonas L. and Schardt, Simon and Ankenbrand, Markus J. and Fischer, Sabine C.}, title = {Recognition and reconstruction of cell differentiation patterns with deep learning}, series = {PLoS Computational Biology}, volume = {19}, journal = {PLoS Computational Biology}, number = {10}, doi = {10.1371/journal.pcbi.1011582}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-350167}, year = {2023}, abstract = {Abstract Cell lineage decisions occur in three-dimensional spatial patterns that are difficult to identify by eye. There is an ongoing effort to replicate such patterns using mathematical modeling. One approach uses long ranging cell-cell communication to replicate common spatial arrangements like checkerboard and engulfing patterns. In this model, the cell-cell communication has been implemented as a signal that disperses throughout the tissue. On the other hand, machine learning models have been developed for pattern recognition and pattern reconstruction tasks. We combined synthetic data generated by the mathematical model with spatial summary statistics and deep learning algorithms to recognize and reconstruct cell fate patterns in organoids of mouse embryonic stem cells. Application of Moran's index and pair correlation functions for in vitro and synthetic data from the model showed local clustering and radial segregation. To assess the patterns as a whole, a graph neural network was developed and trained on synthetic data from the model. Application to in vitro data predicted a low signal dispersion value. To test this result, we implemented a multilayer perceptron for the prediction of a given cell fate based on the fates of the neighboring cells. The results show a 70\% accuracy of cell fate imputation based on the nine nearest neighbors of a cell. Overall, our approach combines deep learning with mathematical modeling to link cell fate patterns with potential underlying mechanisms. Author summary Mammalian embryo development relies on organized differentiation of stem cells into different lineages. Particularly at the early stages of embryogenesis, cells of different fates form three-dimensional spatial patterns that are difficult to identify by eye. Pattern quantification and mathematical modeling have produced first insights into potential mechanisms for the cell fate arrangements. However, these approaches have relied on classifications of the patterns such as inside-out or random, or used summary statistics such as pair correlation functions or cluster radii. Deep neural networks allow characterizing patterns directly. Since the tissue context can be readily reproduced by a graph, we implemented a graph neural network to characterize the patterns of embryonic stem cell organoids as a whole. In addition, we implemented a multilayer perceptron model to reconstruct the fate of a given cell based on its neighbors. To train and test the models, we used synthetic data generated by our mathematical model for cell-cell communication. This interplay of deep learning and mathematical modeling in combination with summary statistics allowed us to identify a potential mechanism for cell fate determination in mouse embryonic stem cells. Our results agree with a mechanism with a dispersion of the intercellular signal that links a cell's fate to those of the local neighborhood.}, language = {en} } @article{LuxBanckSassmannshausenetal.2022, author = {Lux, Thomas J. and Banck, Michael and Saßmannshausen, Zita and Troya, Joel and Krenzer, Adrian and Fitting, Daniel and Sudarevic, Boban and Zoller, Wolfram G. and Puppe, Frank and Meining, Alexander and Hann, Alexander}, title = {Pilot study of a new freely available computer-aided polyp detection system in clinical practice}, series = {International Journal of Colorectal Disease}, volume = {37}, journal = {International Journal of Colorectal Disease}, number = {6}, doi = {10.1007/s00384-022-04178-8}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324459}, pages = {1349-1354}, year = {2022}, abstract = {Purpose Computer-aided polyp detection (CADe) systems for colonoscopy are already presented to increase adenoma detection rate (ADR) in randomized clinical trials. Those commercially available closed systems often do not allow for data collection and algorithm optimization, for example regarding the usage of different endoscopy processors. Here, we present the first clinical experiences of a, for research purposes publicly available, CADe system. Methods We developed an end-to-end data acquisition and polyp detection system named EndoMind. Examiners of four centers utilizing four different endoscopy processors used EndoMind during their clinical routine. Detected polyps, ADR, time to first detection of a polyp (TFD), and system usability were evaluated (NCT05006092). Results During 41 colonoscopies, EndoMind detected 29 of 29 adenomas in 66 of 66 polyps resulting in an ADR of 41.5\%. Median TFD was 130 ms (95\%-CI, 80-200 ms) while maintaining a median false positive rate of 2.2\% (95\%-CI, 1.7-2.8\%). The four participating centers rated the system using the System Usability Scale with a median of 96.3 (95\%-CI, 70-100). Conclusion EndoMind's ability to acquire data, detect polyps in real-time, and high usability score indicate substantial practical value for research and clinical practice. Still, clinical benefit, measured by ADR, has to be determined in a prospective randomized controlled trial.}, language = {en} } @article{PhilippDietzUllmannetal.2023, author = {Philipp, Marius and Dietz, Andreas and Ullmann, Tobias and Kuenzer, Claudia}, title = {A circum-Arctic monitoring framework for quantifying annual erosion rates of permafrost coasts}, series = {Remote Sensing}, volume = {15}, journal = {Remote Sensing}, number = {3}, issn = {2072-4292}, doi = {10.3390/rs15030818}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-304447}, year = {2023}, abstract = {This study demonstrates a circum-Arctic monitoring framework for quantifying annual change of permafrost-affected coasts at a spatial resolution of 10 m. Frequent cloud coverage and challenging lighting conditions, including polar night, limit the usability of optical data in Arctic regions. For this reason, Synthetic Aperture RADAR (SAR) data in the form of annual median and standard deviation (sd) Sentinel-1 (S1) backscatter images covering the months June-September for the years 2017-2021 were computed. Annual composites for the year 2020 were hereby utilized as input for the generation of a high-quality coastline product via a Deep Learning (DL) workflow, covering 161,600 km of the Arctic coastline. The previously computed annual S1 composites for the years 2017 and 2021 were employed as input data for the Change Vector Analysis (CVA)-based coastal change investigation. The generated DL coastline product served hereby as a reference. Maximum erosion rates of up to 67 m per year could be observed based on 400 m coastline segments. Overall highest average annual erosion can be reported for the United States (Alaska) with 0.75 m per year, followed by Russia with 0.62 m per year. Out of all seas covered in this study, the Beaufort Sea featured the overall strongest average annual coastal erosion of 1.12 m. Several quality layers are provided for both the DL coastline product and the CVA-based coastal change analysis to assess the applicability and accuracy of the output products. The predicted coastal change rates show good agreement with findings published in previous literature. The proposed methods and data may act as a valuable tool for future analysis of permafrost loss and carbon emissions in Arctic coastal environments.}, language = {en} } @article{KunzStellzigEisenhauerBoldt2023, author = {Kunz, Felix and Stellzig-Eisenhauer, Angelika and Boldt, Julian}, title = {Applications of artificial intelligence in orthodontics — an overview and perspective based on the current state of the art}, series = {Applied Sciences}, volume = {13}, journal = {Applied Sciences}, number = {6}, issn = {2076-3417}, doi = {10.3390/app13063850}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-310940}, year = {2023}, abstract = {Artificial intelligence (AI) has already arrived in many areas of our lives and, because of the increasing availability of computing power, can now be used for complex tasks in medicine and dentistry. This is reflected by an exponential increase in scientific publications aiming to integrate AI into everyday clinical routines. Applications of AI in orthodontics are already manifold and range from the identification of anatomical/pathological structures or reference points in imaging to the support of complex decision-making in orthodontic treatment planning. The aim of this article is to give the reader an overview of the current state of the art regarding applications of AI in orthodontics and to provide a perspective for the use of such AI solutions in clinical routine. For this purpose, we present various use cases for AI in orthodontics, for which research is already available. Considering the current scientific progress, it is not unreasonable to assume that AI will become an integral part of orthodontic diagnostics and treatment planning in the near future. Although AI will equally likely not be able to replace the knowledge and experience of human experts in the not-too-distant future, it probably will be able to support practitioners, thus serving as a quality-assuring component in orthodontic patient care.}, language = {en} } @article{VollmerVollmerLangetal.2023, author = {Vollmer, Andreas and Vollmer, Michael and Lang, Gernot and Straub, Anton and K{\"u}bler, Alexander and Gubik, Sebastian and Brands, Roman C. and Hartmann, Stefan and Saravi, Babak}, title = {Automated assessment of radiographic bone loss in the posterior maxilla utilizing a multi-object detection artificial intelligence algorithm}, series = {Applied Sciences}, volume = {13}, journal = {Applied Sciences}, number = {3}, issn = {2076-3417}, doi = {10.3390/app13031858}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-305050}, year = {2023}, abstract = {Periodontitis is one of the most prevalent diseases worldwide. The degree of radiographic bone loss can be used to assess the course of therapy or the severity of the disease. Since automated bone loss detection has many benefits, our goal was to develop a multi-object detection algorithm based on artificial intelligence that would be able to detect and quantify radiographic bone loss using standard two-dimensional radiographic images in the maxillary posterior region. This study was conducted by combining three recent online databases and validating the results using an external validation dataset from our organization. There were 1414 images for training and testing and 341 for external validation in the final dataset. We applied a Keypoint RCNN with a ResNet-50-FPN backbone network for both boundary box and keypoint detection. The intersection over union (IoU) and the object keypoint similarity (OKS) were used for model evaluation. The evaluation of the boundary box metrics showed a moderate overlapping with the ground truth, revealing an average precision of up to 0.758. The average precision and recall over all five folds were 0.694 and 0.611, respectively. Mean average precision and recall for the keypoint detection were 0.632 and 0.579, respectively. Despite only using a small and heterogeneous set of images for training, our results indicate that the algorithm is able to learn the objects of interest, although without sufficient accuracy due to the limited number of images and a large amount of information available in panoramic radiographs. Considering the widespread availability of panoramic radiographs as well as the increasing use of online databases, the presented model can be further improved in the future to facilitate its implementation in clinics.}, language = {en} } @article{OberdorfSchaschekWeinzierletal.2023, author = {Oberdorf, Felix and Schaschek, Myriam and Weinzierl, Sven and Stein, Nikolai and Matzner, Martin and Flath, Christoph M.}, title = {Predictive end-to-end enterprise process network monitoring}, series = {Business \& Information Systems Engineering}, volume = {65}, journal = {Business \& Information Systems Engineering}, number = {1}, issn = {2363-7005}, doi = {10.1007/s12599-022-00778-4}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-323814}, pages = {49-64}, year = {2023}, abstract = {Ever-growing data availability combined with rapid progress in analytics has laid the foundation for the emergence of business process analytics. Organizations strive to leverage predictive process analytics to obtain insights. However, current implementations are designed to deal with homogeneous data. Consequently, there is limited practical use in an organization with heterogeneous data sources. The paper proposes a method for predictive end-to-end enterprise process network monitoring leveraging multi-headed deep neural networks to overcome this limitation. A case study performed with a medium-sized German manufacturing company highlights the method's utility for organizations.}, language = {en} } @article{DawoodBreuerStebanietal.2023, author = {Dawood, Peter and Breuer, Felix and Stebani, Jannik and Burd, Paul and Homolya, Istv{\´a}n and Oberberger, Johannes and Jakob, Peter M. and Blaimer, Martin}, title = {Iterative training of robust k-space interpolation networks for improved image reconstruction with limited scan specific training samples}, series = {Magnetic Resonance in Medicine}, volume = {89}, journal = {Magnetic Resonance in Medicine}, number = {2}, doi = {10.1002/mrm.29482}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-312306}, pages = {812 -- 827}, year = {2023}, abstract = {To evaluate an iterative learning approach for enhanced performance of robust artificial-neural-networks for k-space interpolation (RAKI), when only a limited amount of training data (auto-calibration signals [ACS]) are available for accelerated standard 2D imaging. Methods In a first step, the RAKI model was tailored for the case of limited training data amount. In the iterative learning approach (termed iterative RAKI [iRAKI]), the tailored RAKI model is initially trained using original and augmented ACS obtained from a linear parallel imaging reconstruction. Subsequently, the RAKI convolution filters are refined iteratively using original and augmented ACS extracted from the previous RAKI reconstruction. Evaluation was carried out on 200 retrospectively undersampled in vivo datasets from the fastMRI neuro database with different contrast settings. Results For limited training data (18 and 22 ACS lines for R = 4 and R = 5, respectively), iRAKI outperforms standard RAKI by reducing residual artifacts and yields better noise suppression when compared to standard parallel imaging, underlined by quantitative reconstruction quality metrics. Additionally, iRAKI shows better performance than both GRAPPA and standard RAKI in case of pre-scan calibration with varying contrast between training- and undersampled data. Conclusion RAKI benefits from the iterative learning approach, which preserves the noise suppression feature, but requires less original training data for the accurate reconstruction of standard 2D images thereby improving net acceleration.}, language = {en} } @article{VollmerSaraviVollmeretal.2022, author = {Vollmer, Andreas and Saravi, Babak and Vollmer, Michael and Lang, Gernot Michael and Straub, Anton and Brands, Roman C. and K{\"u}bler, Alexander and Gubik, Sebastian and Hartmann, Stefan}, title = {Artificial intelligence-based prediction of oroantral communication after tooth extraction utilizing preoperative panoramic radiography}, series = {Diagnostics}, volume = {12}, journal = {Diagnostics}, number = {6}, issn = {2075-4418}, doi = {10.3390/diagnostics12061406}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-278814}, year = {2022}, abstract = {Oroantral communication (OAC) is a common complication after tooth extraction of upper molars. Profound preoperative panoramic radiography analysis might potentially help predict OAC following tooth extraction. In this exploratory study, we evaluated n = 300 consecutive cases (100 OAC and 200 controls) and trained five machine learning algorithms (VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50) to predict OAC versus non-OAC (binary classification task) from the input images. Further, four oral and maxillofacial experts evaluated the respective panoramic radiography and determined performance metrics (accuracy, area under the curve (AUC), precision, recall, F1-score, and receiver operating characteristics curve) of all diagnostic approaches. Cohen's kappa was used to evaluate the agreement between expert evaluations. The deep learning algorithms reached high specificity (highest specificity 100\% for InceptionV3) but low sensitivity (highest sensitivity 42.86\% for MobileNetV2). The AUCs from VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50 were 0.53, 0.60, 0.67, 0.51, and 0.56, respectively. Expert 1-4 reached an AUC of 0.550, 0.629, 0.500, and 0.579, respectively. The specificity of the expert evaluations ranged from 51.74\% to 95.02\%, whereas sensitivity ranged from 14.14\% to 59.60\%. Cohen's kappa revealed a poor agreement for the oral and maxillofacial expert evaluations (Cohen's kappa: 0.1285). Overall, present data indicate that OAC cannot be sufficiently predicted from preoperative panoramic radiography. The false-negative rate, i.e., the rate of positive cases (OAC) missed by the deep learning algorithms, ranged from 57.14\% to 95.24\%. Surgeons should not solely rely on panoramic radiography when evaluating the probability of OAC occurrence. Clinical testing of OAC is warranted after each upper-molar tooth extraction.}, language = {en} } @article{BrandTroyaKrenzeretal.2022, author = {Brand, Markus and Troya, Joel and Krenzer, Adrian and Saßmannshausen, Zita and Zoller, Wolfram G. and Meining, Alexander and Lux, Thomas J. and Hann, Alexander}, title = {Development and evaluation of a deep learning model to improve the usability of polyp detection systems during interventions}, series = {United European Gastroenterology Journal}, volume = {10}, journal = {United European Gastroenterology Journal}, number = {5}, doi = {10.1002/ueg2.12235}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-312708}, pages = {477-484}, year = {2022}, abstract = {Background The efficiency of artificial intelligence as computer-aided detection (CADe) systems for colorectal polyps has been demonstrated in several randomized trials. However, CADe systems generate many distracting detections, especially during interventions such as polypectomies. Those distracting CADe detections are often induced by the introduction of snares or biopsy forceps as the systems have not been trained for such situations. In addition, there are a significant number of non-false but not relevant detections, since the polyp has already been previously detected. All these detections have the potential to disturb the examiner's work. Objectives Development and evaluation of a convolutional neuronal network that recognizes instruments in the endoscopic image, suppresses distracting CADe detections, and reliably detects endoscopic interventions. Methods A total of 580 different examination videos from 9 different centers using 4 different processor types were screened for instruments and represented the training dataset (519,856 images in total, 144,217 contained a visible instrument). The test dataset included 10 full-colonoscopy videos that were analyzed for the recognition of visible instruments and detections by a commercially available CADe system (GI Genius, Medtronic). Results The test dataset contained 153,623 images, 8.84\% of those presented visible instruments (12 interventions, 19 instruments used). The convolutional neuronal network reached an overall accuracy in the detection of visible instruments of 98.59\%. Sensitivity and specificity were 98.55\% and 98.92\%, respectively. A mean of 462.8 frames containing distracting CADe detections per colonoscopy were avoided using the convolutional neuronal network. This accounted for 95.6\% of all distracting CADe detections. Conclusions Detection of endoscopic instruments in colonoscopy using artificial intelligence technology is reliable and achieves high sensitivity and specificity. Accordingly, the new convolutional neuronal network could be used to reduce distracting CADe detections during endoscopic procedures. Thus, our study demonstrates the great potential of artificial intelligence technology beyond mucosal assessment.}, language = {en} } @article{KrenzerBanckMakowskietal.2023, author = {Krenzer, Adrian and Banck, Michael and Makowski, Kevin and Hekalo, Amar and Fitting, Daniel and Troya, Joel and Sudarevic, Boban and Zoller, Wolfgang G. and Hann, Alexander and Puppe, Frank}, title = {A real-time polyp-detection system with clinical application in colonoscopy using deep convolutional neural networks}, series = {Journal of Imaging}, volume = {9}, journal = {Journal of Imaging}, number = {2}, issn = {2313-433X}, doi = {10.3390/jimaging9020026}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-304454}, year = {2023}, abstract = {Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is with a colonoscopy. During this procedure, the gastroenterologist searches for polyps. However, there is a potential risk of polyps being missed by the gastroenterologist. Automated detection of polyps helps to assist the gastroenterologist during a colonoscopy. There are already publications examining the problem of polyp detection in the literature. Nevertheless, most of these systems are only used in the research context and are not implemented for clinical application. Therefore, we introduce the first fully open-source automated polyp-detection system scoring best on current benchmark data and implementing it ready for clinical application. To create the polyp-detection system (ENDOMIND-Advanced), we combined our own collected data from different hospitals and practices in Germany with open-source datasets to create a dataset with over 500,000 annotated images. ENDOMIND-Advanced leverages a post-processing technique based on video detection to work in real-time with a stream of images. It is integrated into a prototype ready for application in clinical interventions. We achieve better performance compared to the best system in the literature and score a F1-score of 90.24\% on the open-source CVC-VideoClinicDB benchmark.}, language = {en} } @article{PhilippDietzUllmannetal.2022, author = {Philipp, Marius and Dietz, Andreas and Ullmann, Tobias and Kuenzer, Claudia}, title = {Automated extraction of annual erosion rates for Arctic permafrost coasts using Sentinel-1, Deep Learning, and Change Vector Analysis}, series = {Remote Sensing}, volume = {14}, journal = {Remote Sensing}, number = {15}, issn = {2072-4292}, doi = {10.3390/rs14153656}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-281956}, year = {2022}, abstract = {Arctic permafrost coasts become increasingly vulnerable due to environmental drivers such as the reduced sea-ice extent and duration as well as the thawing of permafrost itself. A continuous quantification of the erosion process on large to circum-Arctic scales is required to fully assess the extent and understand the consequences of eroding permafrost coastlines. This study presents a novel approach to quantify annual Arctic coastal erosion and build-up rates based on Sentinel-1 (S1) Synthetic Aperture RADAR (SAR) backscatter data, in combination with Deep Learning (DL) and Change Vector Analysis (CVA). The methodology includes the generation of a high-quality Arctic coastline product via DL, which acted as a reference for quantifying coastal erosion and build-up rates from annual median and standard deviation (sd) backscatter images via CVA. The analysis was applied on ten test sites distributed across the Arctic and covering about 1038 km of coastline. Results revealed maximum erosion rates of up to 160 m for some areas and an average erosion rate of 4.37 m across all test sites within a three-year temporal window from 2017 to 2020. The observed erosion rates within the framework of this study agree with findings published in the previous literature. The proposed methods and data can be applied on large scales and, prospectively, even for the entire Arctic. The generated products may be used for quantifying the loss of frozen ground, estimating the release of stored organic material, and can act as a basis for further related studies in Arctic coastal environments.}, language = {en} } @article{KrenzerMakowskiHekaloetal.2022, author = {Krenzer, Adrian and Makowski, Kevin and Hekalo, Amar and Fitting, Daniel and Troya, Joel and Zoller, Wolfram G. and Hann, Alexander and Puppe, Frank}, title = {Fast machine learning annotation in the medical domain: a semi-automated video annotation tool for gastroenterologists}, series = {BioMedical Engineering OnLine}, volume = {21}, journal = {BioMedical Engineering OnLine}, number = {1}, doi = {10.1186/s12938-022-01001-x}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-300231}, year = {2022}, abstract = {Background Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g., visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between. Methods In our framework, an expert reviews the video and annotates a few video frames to verify the object's annotations for the non-expert. In a second step, a non-expert has visual confirmation of the given object and can annotate all following and preceding frames with AI assistance. After the expert has finished, relevant frames will be selected and passed on to an AI model. This information allows the AI model to detect and mark the desired object on all following and preceding frames with an annotation. Therefore, the non-expert can adjust and modify the AI predictions and export the results, which can then be used to train the AI model. Results Using this framework, we were able to reduce workload of domain experts on average by a factor of 20 on our data. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated AI model enhances the annotation speed further. Through a prospective study with 10 participants, we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool. Conclusion In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.}, language = {en} }