@article{Schoenwolf:2022:MIHDetection,

title = {Artificial intelligence-based diagnostics of molar-incisor-hypomineralization (MIH) on intraoral photographs},

author = {Jule Schönewolf and Ole Meyer and Paula Engels and Anne Schlickenrieder and Reinhard Hickel and Volker Gruhn and Marc Hesenius and Jan Kühnisch},

doi = {10.1007/s00784-022-04552-4},

year  = {2022},

date = {2022-05-24},

urldate = {2022-01-01},

journal = {Clinical Oral Investigations},

abstract = {The aim of this study was to develop and validate a deep learning--based convolutional neural network (CNN) for the automated detection and categorization of teeth affected by molar-incisor-hypomineralization (MIH) on intraoral photographs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Engels:2022:PosteriorRestorationsAI,

title = {Automated detection of posterior restorations in permanent teeth using artificial intelligence on intraoral photographs},

author = {Paula Engels and Ole Meyer and Jule Schönewolf and Anne Schlickenrieder and Reinhard Hickel and Marc Hesenius and Volker Gruhn and Jan Kühnisch},

url = {https://www.sciencedirect.com/science/article/pii/S0300571222001737},

doi = {https://doi.org/10.1016/j.jdent.2022.104124},

issn = {0300-5712},

year  = {2022},

date = {2022-04-05},

urldate = {2022-01-02},

journal = {Journal of Dentistry},

volume = {121},

pages = {104124},

abstract = {Objectives 

Intraoral photographs might be considered the machine-readable equivalent of a clinical-based visual examination and can potentially be used to detect and categorize dental restorations. The first objective of this study was to develop a deep learning-based convolutional neural network (CNN) for automated detection and categorization of posterior composite, cement, amalgam, gold and ceramic restorations on clinical photographs. Second, this study aimed to determine the diagnostic accuracy for the developed CNN (test method) compared to that of an expert evaluation (reference standard). 

Methods The whole image set of 1761 images (483 of unrestored teeth, 570 of composite restorations, 213 of cements, 278 of amalgam restorations, 125 of gold restorations and 92 of ceramic restorations) was divided into a training set (N = 1407, 401, 447, 66, 231, 93, and 169, respectively) and a test set (N = 354, 82, 123, 26, 47, 32, and 44). The expert diagnoses served as a reference standard for cyclic training and repeated evaluation of the CNN (ResNeXt-101--32 × 8d), which was trained by using image augmentation and transfer learning. Statistical analysis included the calculation of contingency tables, areas under the receiver operating characteristic curve and saliency maps. 

Results 

After training was complete, the CNN was able to categorize restorations correctly with the following diagnostic accuracy values: 94.9% for unrestored teeth, 92.9% for composites, 98.3% for cements, 99.2% for amalgam restorations, 99.4% for gold restorations and 97.8% for ceramic restorations. 

Conclusions 

It was possible to categorize different types of posterior restorations on intraoral photographs automatically with a good diagnostic accuracy. 

Clinical significance 

Dental diagnostics might be supported by artificial intelligence-based algorithms in the future. However, further improvements are needed to increase accuracy and practicability.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kühnisch2022,

title = {Caries Detection on Intraoral Images Using Artificial Intelligence},

author = {Jan Kühnisch and Ole Meyer and Marc Hesenius and Volker Gruhn},

url = {https://doi.org/10.1177/00220345211032524},

doi = {10.1177/00220345211032524},

year  = {2022},

date = {2022-01-02},

urldate = {2022-01-01},

journal = {Journal of Dental Research},

volume = {101},

number = {2},

pages = {158-165},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kuehnisch:2022:AutomatMIH,

title = {Automatisierte Erkennung von Molaren-Inzisiven- Hypomineralisationen (MIH) mithilfe künstlicher Intelligenz},

author = {Jan Kühnisch and Marc Hesenius and Ole Meyer},

year  = {2022},

date = {2022-01-01},

journal = {Quintessenz Zahnmedizin},

volume = {73},

number = {12},

pages = {1094-1096},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ruiner:2022:HCITypology,

title = {Job demands and resources when using technologies at work -- development of a digital work typology},

author = {Caroline Ruiner and Christina Debbing and Vera Hagemann and Martina Schaper and Matthias Klumpp and Marc Hesenius},

url = {https://doi.org/10.1108/ER-11-2021-0468},

doi = {10.1108/ER-11-2021-0468},

isbn = {0142-5455},

year  = {2022},

date = {2022-01-01},

journal = {Employee Relations: The International Journal},

volume = {ahead-of-print},

number = {ahead-of-print},

publisher = {Emerald Publishing Limited},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hagemann:2021:MESTAT,

title = {Mental Stress and Strain Assessment in Digital Work},

author = {Vera Hagemann and Jonathan Meinecke and Martina Schaper and Christina Debbing and Caroline Ruiner and Matthias Klumpp and Marc Hesenius},

doi = {10.1026/0932-4089/a000387},

year  = {2021},

date = {2021-01-01},

journal = {Zeitschrift für Arbeits- und Organisationspsychologie A&O},

abstract = { Abstract. When digitalizing work, organizations face the challenge of analyzing, evaluating, and mitigating a potential increase in mental workload for employees and managers. This paper presents an instrument to assess mental stress and strain in digital work contexts and the related development process and validation. Based on a literature and instrument review and an interview study, we developed an assessment instrument and validated it in two coordinated studies (N = 245},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{diagnostics11091608,

title = {Automatized Detection and Categorization of Fissure Sealants from Intraoral Digital Photographs Using Artificial Intelligence},

author = {Anne Schlickenrieder and Ole Meyer and Jule Schönewolf and Paula Engels and Reinhard Hickel and Volker Gruhn and Marc Hesenius and Jan Kühnisch},

url = {https://www.mdpi.com/2075-4418/11/9/1608},

doi = {10.3390/diagnostics11091608},

issn = {2075-4418},

year  = {2021},

date = {2021-01-01},

journal = {Diagnostics},

volume = {11},

number = {9},

abstract = {The aim of the present study was to investigate the diagnostic performance of a trained convolutional neural network (CNN) for detecting and categorizing fissure sealants from intraoral photographs using the expert standard as reference. An image set consisting of 2352 digital photographs from permanent posterior teeth (461 unsealed tooth surfaces/1891 sealed surfaces) was divided into a training set (n = 1881/364/1517) and a test set (n = 471/97/374). All the images were scored according to the following categories: unsealed molar, intact, sufficient and insufficient sealant. Expert diagnoses served as the reference standard for cyclic training and repeated evaluation of the CNN (ResNeXt-101-32x8d), which was trained by using image augmentation and transfer learning. A statistical analysis was performed, including the calculation of contingency tables and areas under the receiver operating characteristic curve (AUC). The results showed that the CNN accurately detected sealants in 98.7% of all the test images, corresponding to an AUC of 0.996. The diagnostic accuracy and AUC were 89.6% and 0.951, respectively, for intact sealant; 83.2% and 0.888, respectively, for sufficient sealant; 92.4 and 0.942, respectively, for insufficient sealant. On the basis of the documented results, it was concluded that good agreement with the reference standard could be achieved for automatized sealant detection by using artificial intelligence methods. Nevertheless, further research is necessary to improve the model performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.1093/iwcomp/iwab017,

title = {AugIR Meets GestureCards: A Digital Sketching Environment for Gesture-Based Applications},

author = {Marc Hesenius and Markus Kleffmann and Volker Gruhn},

url = {https://academic.oup.com/iwc/advance-article/doi/10.1093/iwcomp/iwab017/6273339?guestAccessKey=d665bee3-137e-469e-a569-f328e9e2a77a},

doi = {10.1093/iwcomp/iwab017},

issn = {1873-7951},

year  = {2021},

date = {2021-01-01},

journal = {Interacting with Computers},

abstract = {To gain a common understanding of an application's layouts, dialogs and interaction flows, development teams often sketch user interface (UI). Nowadays, they must also define multi-touch gestures, but tools for sketching UIs often lack support for custom gestures and typically just integrate a basic predefined gesture set, which might not suffice to specifically tailor the interaction to the desired use cases. Furthermore, sketching can be enhanced with digital means, but it remains unclear whether digital sketching is actually beneficial when designing gesture-based applications. We extended the AugIR, a digital sketching environment, with GestureCards, a hybrid gesture notation, to allow software engineers to define custom gestures when sketching UIs. We evaluated our approach in a user study contrasting digital and analog sketching of gesture-based UIs.},

note = {iwab017},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{cite-key,

title = {Adaptive Extraction and Refinement of Marine Lanes from Crowdsourced Trajectory Data},

author = {Guiling Wang and Jinlong Meng and Zhuoran Li and Marc Hesenius and Weilong Ding and Yanbo Han and Volker Gruhn},

url = {https://doi.org/10.1007/s11036-019-01454-w},

doi = {10.1007/s11036-019-01454-w},

isbn = {1572-8153},

year  = {2020},

date = {2020-01-01},

journal = {Mobile Networks and Applications},

abstract = {Crowdsourced trajectory data of ships provide the opportunity for extracting marine lane information. However, extracting useful knowledge from massive amounts of trajectory data is a challenging problem. Trajectory data collected from crowdsourcing can be extremely diverse in different areas and its quality might be very low. Moreover, the density distribution of the crowdsourced trajectory points is quite uneven in different areas. Furthermore, it is necessary to extract marine lanes with high extraction precision in offshore and nearshore water areas, but extraction precision can be lower in the open sea. We propose an adaptive approach for marine lane extraction and refinement based on grid merging and filtering to meet the challenges. In this paper, after pre-processing and clustering the trajectory data based on the density value of grids with a parallel GeoHash encoding algorithm, we propose a parallel grid merging and filtering algorithm based on a QuadTree data structure. The algorithm performs grid merging on the simplified grid data according to the density value of grid, then filters the merged grid data based on a local sliding window mechanism to get the marine lane grid data. Applying the Delaunay Triangulation on the marine lane grid data, the marine lane boundary information can be extracted with adaptive extraction precision. Experimental results show that the proposed approach can extract marine lanes with high extraction precision in offshore and nearshore water area and low extraction precision in open sea area.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}