Multi-modal deep learning for joint prediction of otitis media and diagnostic difficulty
Josefine Vilsbøll Sundgaard, Morten Rieger Hannemose, Søren Laugesen, Peter Bray, James Harte, Yosuke Kamide, Chiemi Tanaka, Rasmus R. Paulsen, and Anders Nymark Christensen
@article{sundgaard2024multimodal,author={Sundgaard, Josefine Vilsbøll and Hannemose, Morten Rieger and Laugesen, Søren and Bray, Peter and Harte, James and Kamide, Yosuke and Tanaka, Chiemi and Paulsen, Rasmus R. and Christensen, Anders Nymark},title={Multi-modal deep learning for joint prediction of otitis media and diagnostic difficulty},journal={Laryngoscope Investigative Otolaryngology},volume={9},number={1},pages={e1199},year={2024},doi={https://doi.org/10.1002/lio2.1199},}
2023
Video-based Skill Assessment for Golf: Estimating Golf Handicap
Christian Keilstrup Ingwersen, Artur Xarles Esparraguera, Albert Clapés, Meysam Madadi, Janus Nørtoft Jensen, Morten Rieger Hannemose, Anders Bjorholm Dahl, and Sergio Escalera
In Proceedings of the 6th International ACM Workshop on Multimedia Content Analysis in Sports, 2023
@inproceedings{ingwersen2023video,title={Video-based Skill Assessment for Golf: Estimating Golf Handicap},author={Ingwersen, Christian Keilstrup and Esparraguera, Artur Xarles and Clap{\'e}s, Albert and Madadi, Meysam and Jensen, Janus N{\o}rtoft and Hannemose, Morten Rieger and Dahl, Anders Bjorholm and Escalera, Sergio},booktitle={Proceedings of the 6th International ACM Workshop on Multimedia Content Analysis in Sports},year={2023},organization={Association for Computing Machinery},doi={https://doi.org/10.1145/3606038.3616150},}
Neural Representation of Open Surfaces
T. V. Christiansen, J. A. Bærentzen, R. R. Paulsen, and M. R. Hannemose
@inproceedings{christiansen2023neural,title={Neural Representation of Open Surfaces },author={Christiansen, T. V. and Bærentzen, J. A. and Paulsen, R. R. and Hannemose, M. R.},booktitle={Computer Graphics Forum},volume={42},number={5},year={2023},organization={Wiley Online Library},doi={http://doi.org/10.1111/cgf.14916},}
SportsPose: A Dynamic 3D Sports Pose Dataset
Christian Keilstrup Ingwersen, Christian Mikkelstrup, Janus Nørtoft Jensen, Morten Rieger Hannemose, and Anders Bjorholm Dahl
In Proceedings of the IEEE/CVF International Workshop on Computer Vision in Sports, 2023
@inproceedings{ingwersen2023sportspose,title={SportsPose: A Dynamic 3D Sports Pose Dataset},author={Ingwersen, Christian Keilstrup and Mikkelstrup, Christian and Jensen, Janus N{\o}rtoft and Hannemose, Morten Rieger and Dahl, Anders Bjorholm},booktitle={Proceedings of the IEEE/CVF International Workshop on Computer Vision in Sports},year={2023},}
Multi-modal data generation with a deep metric variational autoencoder
Josefine V. Sundgaard, Morten R. Hannemose, Søren Laugesen, Peter Bray, James Harte, Yosuke Kamide, Chiemi Tanaka, Rasmus R. Paulsen, and Anders N. Christensen
In Proceedings of the Northern Lights Deep Learning Workshop, 2023
@inproceedings{sundgaard2023multi,author={Sundgaard, Josefine V. and Hannemose, Morten R. and Laugesen, S{\o}ren and Bray, Peter and Harte, James and Kamide, Yosuke and Tanaka, Chiemi and Paulsen, Rasmus R. and Christensen, Anders N.},booktitle={Proceedings of the Northern Lights Deep Learning Workshop},volume={4},year={2023},doi={https://doi.org/10.7557/18.6803},}
Evaluating current state of monocular 3D pose models for golf
Christian Keilstrup Ingwersen, Janus Nørtoft Jensen, Morten Rieger Hannemose, and Anders B. Dahl
In Proceedings of the Northern Lights Deep Learning Workshop, 2023
@inproceedings{ingwersen2023evaluating,title={Evaluating current state of monocular 3D pose models for golf},author={Ingwersen, Christian Keilstrup and Jensen, Janus N{\o}rtoft and Hannemose, Morten Rieger and Dahl, Anders B.},booktitle={Proceedings of the Northern Lights Deep Learning Workshop},volume={4},year={2023},doi={https://doi.org/10.7557/18.6793},}
Interactive Scribble Segmentation
Mathias M. Lowes, Jakob L. Christensen, Bjørn Schreblowski Hansen, Morten Rieger Hannemose, Anders B. Dahl, and Vedrana Dahl
In Proceedings of the Northern Lights Deep Learning Workshop, 2023
@inproceedings{lowes2023interactive,title={Interactive Scribble Segmentation},author={Lowes, Mathias M. and Christensen, Jakob L. and Hansen, Bj{\o}rn Schreblowski and Hannemose, Morten Rieger and Dahl, Anders B. and Dahl, Vedrana},booktitle={Proceedings of the Northern Lights Deep Learning Workshop},volume={4},year={2023},doi={https://doi.org/10.7557/18.6823},}
2022
Generalizability and usefulness of artificial intelligence for skin cancer diagnostics: An algorithm validation study
Niels K. Ternov, Anders N. Christensen, Peter J. T. Kampen, Gustav Als, Tine Vestergaard, Lars Konge, Martin Tolsgaard, Lisbet R. Hölmich, Pascale Guitera, Annette H. Chakera, and Morten R. Hannemose
Artificial intelligence can be trained to outperform dermatologists in image-based skin cancer diagnostics. However, the networks’ sensitivity to biases and overfitting may hamper their clinical applicability. Objectives The aim of this study was to explain the potential consequences of implementing convolutional neural networks for stand-alone melanoma diagnostics and skin lesion triage. Methods In this algorithm validation study on retrospective data, we reproduced and evaluated the performance of state-of-the-art artificial intelligence (convolutional neural networks) for skin cancer diagnostics. The networks were trained on 25,331 annotated dermoscopic skin lesion images from an open-source data set (ISIC-2019) and tested using a novel data set (AISC-2021) consisting of 26,591 annotated dermoscopic skin lesion images. We tested the trained algorithms’ ability to generalize to new data and their diagnostic performance in two simulations (melanoma diagnostics and skin lesion triage). Results The trained algorithms performed significantly less accurate diagnostics on images of nevi, melanomas and actinic keratoses from the AISC-2021 data set than the ISIC-2019 data set (p < 0.003). Almost one-third (31.1%) of the melanomas were misclassified during the melanoma diagnostics simulation, irrespective of their Breslow thickness. Furthermore, the algorithms marked 92.7% of the lesions ‘suspicious’ during the triage simulation, which yielded a triage sensitivity and specificity of 99.7% and 8.2%, respectively. Conclusions Although state-of-the-art artificial intelligence outperforms dermatologists on image-based skin lesion classification within an artificial setting, additional data and technological advances are needed before clinical implementation.
@article{ternov2022generalizability,author={Ternov, Niels K. and Christensen, Anders N. and Kampen, Peter J. T. and Als, Gustav and Vestergaard, Tine and Konge, Lars and Tolsgaard, Martin and Hölmich, Lisbet R. and Guitera, Pascale and Chakera, Annette H. and Hannemose, Morten R.},title={Generalizability and usefulness of artificial intelligence for skin cancer diagnostics: An algorithm validation study},journal={JEADV Clinical Practice},year={2022},keywords={artificial intelligence, melanoma, skin cancer, skin cancer prevention and early detection},doi={https://doi.org/10.1002/jvc2.59},publisher={Wiley Online Library},}
Was that so Hard? Estimating Human Classification Difficulty
Morten Rieger Hannemose*, Josefine Vilsbøll Sundgaard*, Niels Kvorning Ternov, Rasmus R. Paulsen, and Anders Nymark Christensen
Applications of Medical Artificial Intelligence, 2022
@article{hannemose2022so,title={Was that so Hard? Estimating Human Classification Difficulty},author={Hannemose*, Morten Rieger and Sundgaard*, Josefine Vilsb{\o}ll and Ternov, Niels Kvorning and Paulsen, Rasmus R. and Christensen, Anders Nymark},journal={Applications of Medical Artificial Intelligence},volume={13540},pages={88},year={2022},doi={https://doi.org/10.1007/978-3-031-17721-7_10},publisher={Springer Nature},}
LayeredCNN: Segmenting Layers with Autoregressive Models
Jakob L. Christensen, Patrick Møller Jensen, Morten Rieger Hannemose, Anders B. Dahl, and Vedrana Andersen Dahl
@inproceedings{christensen2022layeredcnn,title={LayeredCNN: Segmenting Layers with Autoregressive Models},author={Christensen, Jakob L. and Jensen, Patrick Møller and Hannemose, Morten Rieger and Dahl, Anders B. and Dahl, Vedrana Andersen},booktitle={Northern Lights Deep Learning Workshop},volume={3},doi={https://doi.org/10.7557/18.6254},year={2022},}
2021
Surface reconstruction from structured light images using differentiable rendering
Janus Nørtoft Jensen*, Morten Hannemose*, Jakob Andreas Bærentzen, Jakob Wilm, Jeppe Revall Frisvad, and Anders B. Dahl
@article{jensen2021surface,title={Surface reconstruction from structured light images using differentiable rendering},author={Jensen*, Janus N{\o}rtoft and Hannemose*, Morten and B{\ae}rentzen, Jakob Andreas and Wilm, Jakob and Frisvad, Jeppe Revall and Dahl, Anders B.},journal={Sensors},volume={21},number={4},pages={1068},year={2021},publisher={Multidisciplinary Digital Publishing Institute},doi={https://doi.org/10.3390/s21041068},}
2020
Design of Automated Robotic System for Draping Prepreg Composite Fabrics
Lars-Peter Ellekilde, Jakob Wilm, Ole W. Nielsen, Christian Krogh, Ewa Kristiansen, Gudmundur G. Gunnarsson, Thor Stærk Stenvang, Johnny Jakobsen, Morten Kristiansen, Jens A. Glud, Morten Hannemose, Henrik Aanæs, Joachim Kruijk, Ingolf Sveidahl, Asim Ikram, and Henrik G. Petersen
@article{ellekilde2020design,title={Design of Automated Robotic System for Draping Prepreg Composite Fabrics},author={Ellekilde, Lars-Peter and Wilm, Jakob and Nielsen, Ole W. and Krogh, Christian and Kristiansen, Ewa and Gunnarsson, Gudmundur G. and Stenvang, Thor Stærk and Jakobsen, Johnny and Kristiansen, Morten and Glud, Jens A. and Hannemose, Morten and Aanæs, Henrik and de Kruijk, Joachim and Sveidahl, Ingolf and Ikram, Asim and Petersen, Henrik G.},journal={Robotica},pages={1--16},year={2020},doi={https://doi.org/10.1017/S0263574720000193},publisher={Cambridge University Press},}
Alignment of rendered images with photographs for testing appearance models
Morten Hannemose, Mads Emil Brix Doest, Andrea Luongo, Søren Kimmer Schou Gregersen, Jakob Wilm, and Jeppe Revall Frisvad
@article{hannemose2020alignment,title={Alignment of rendered images with photographs for testing appearance models},author={Hannemose, Morten and Doest, Mads Emil Brix and Luongo, Andrea and Gregersen, Søren Kimmer Schou and Wilm, Jakob and Frisvad, Jeppe Revall},journal={Applied Optics},year={2020},doi={https://doi.org/10.1364/AO.398055},}
@phdthesis{hannemose2020differentiable,author={Hannemose, Morten},title={Differentiable formulations for inverse rendering},school={Technical University of Denmark},year={2020},}
2019
Video Frame Interpolation via Cyclic Fine-Tuning and Asymmetric Reverse Flow
Morten Hannemose, Janus Nørtoft Jensen, Gudmundur Einarsson, Jakob Wilm, Anders B. Dahl, and Jeppe R. Frisvad
In Scandinavian Conference on Image Analysis, 2019
@inproceedings{hannemose2019video,title={Video Frame Interpolation via Cyclic Fine-Tuning and Asymmetric Reverse Flow},author={Hannemose, Morten and Jensen, Janus N{\o}rtoft and Einarsson, Gudmundur and Wilm, Jakob and Dahl, Anders B. and Frisvad, Jeppe R.},booktitle={Scandinavian Conference on Image Analysis},pages={311--323},year={2019},organization={Springer},doi={https://doi.org/10.1007/978-3-030-20205-7_26},}
Superaccurate camera calibration via inverse rendering
Morten Hannemose, Jakob Wilm, and Jeppe R. Frisvad
In Modeling Aspects in Optical Metrology VII, 2019
@inproceedings{hannemose2019superaccurate,title={Superaccurate camera calibration via inverse rendering},author={Hannemose, Morten and Wilm, Jakob and Frisvad, Jeppe R.},booktitle={Modeling Aspects in Optical Metrology VII},volume={11057},pages={1105717},year={2019},organization={International Society for Optics and Photonics},doi={https://doi.org/10.1117/12.2531769},}
Generating spatial attention cues via illusory motion
Janus Nørtoft Jensen*, Morten Hannemose*, Jakob Wilm, Anders B. Dahl, Jeppe R. Frisvad, and Serge Belongie
In Third Workshop on Computer Vision for AR/VR, 2019
@inproceedings{jensen2019generating,title={Generating spatial attention cues via illusory motion},author={Jensen*, Janus N{\o}rtoft and Hannemose*, Morten and Wilm, Jakob and Dahl, Anders B. and Frisvad, Jeppe R. and Belongie, Serge},booktitle={Third Workshop on Computer Vision for AR/VR},year={2019},}
2017
An image-based method for objectively assessing injection moulded plastic quality
Morten Hannemose, Jannik Boll Nielsen, László Zsíros, and Henrik Aanæs
In Scandinavian Conference on Image Analysis, 2017
@inproceedings{hannemose2017image,author={Hannemose, Morten and Nielsen, Jannik Boll and Zs\'{i}ros, L\'{a}szl\'{o} and Aan{\ae}s, Henrik},title={An image-based method for objectively assessing injection moulded plastic quality},booktitle={Scandinavian Conference on Image Analysis},year={2017},doi={https://doi.org/10.1007/978-3-319-59129-2_36},}
2016
Tunnel Effect in CNNs: Image Reconstruction From Max-Switch Locations
Matthieu de La Roche Saint Andre*, Laura Rieger*, Morten Hannemose*, and Junmo Kim
@article{saint2016tunnel,title={Tunnel Effect in CNNs: Image Reconstruction From Max-Switch Locations},author={Saint Andre*, Matthieu de La Roche and Rieger*, Laura and Hannemose*, Morten and Kim, Junmo},journal={IEEE Signal Processing Letters},year={2016},publisher={IEEE},doi={https://doi.org/10.1109/LSP.2016.2638435},}
MSc Thesis
Automatic Localization of Impact Position in Golf Swing using Computer Vision
@mastersthesis{jensen2016automatic,author={Jensen*, Janus N{\o}rtoft and Hannemose*, Morten},title={Automatic Localization of Impact Position in Golf Swing using Computer Vision},school={Technical University of Denmark},year={2016},}
@mastersthesis{jensen2014camera,author={Jensen*, Janus N{\o}rtoft and Hannemose*, Morten},title={Camera-based Heart Rate Monitoring},school={Technical University of Denmark},year={2014},}
