Visualization & HCI

Office	36-230
Email	leonharv@rptu.de

Publications

2023

A. Schilling et al. Uncertainty-aware spot rejection rate as quality metric for proton therapy using a digital tracking calorimeter. Physics in Medicine & Biology, vol. 68, no. 19, p. 194001, Sep. 2023. 10.1088/1361-6560/acf5c2
```
@article{Schilling_2023,
  doi = {10.1088/1361-6560/acf5c2},
  url = {https://dx.doi.org/10.1088/1361-6560/acf5c2},
  year = {2023},
  month = sep,
  publisher = {IOP Publishing},
  volume = {68},
  number = {19},
  pages = {194001},
  author = {Schilling, Alexander and Aehle, Max and Alme, Johan and Barnaföldi, Gergely Gábor and Bodova, Tea and Borshchov, Vyacheslav and van den Brink, Anthony and Eikeland, Viljar and Feofilov, Gregory and Garth, Christoph and Gauger, Nicolas R and Grøttvik, Ola and Helstrup, Håvard and Igolkin, Sergey and Keidel, Ralf and Kobdaj, Chinorat and Kortus, Tobias and Leonhardt, Viktor and Mehendale, Shruti and Mulawade, Raju Ningappa and Odland, Odd Harald and O’Neill, George and Papp, Gábor and Peitzmann, Thomas and Pettersen, Helge Egil Seime and Piersimoni, Pierluigi and Protsenko, Maksym and Rauch, Max and Rehman, Attiq Ur and Richter, Matthias and Röhrich, Dieter and Santana, Joshua and Seco, Joao and Songmoolnak, Arnon and Sudár, Ákos and Tambave, Ganesh and Tymchuk, Ihor and Ullaland, Kjetil and Varga-Kofarago, Monika and Volz, Lennart and Wagner, Boris and Wendzel, Steffen and Wiebel, Alexander and Xiao, RenZheng and Yang, Shiming and Zillien, Sebastian},
  title = {Uncertainty-aware spot rejection rate as quality metric for proton therapy using a digital tracking calorimeter},
  journal = {Physics in Medicine & Biology}
}
```
Abstract: Objective. Proton therapy is highly sensitive to range uncertainties due to the nature of the dose deposition of charged particles. To ensure treatment quality, range verification methods can be used to verify that the individual spots in a pencil beam scanning treatment fraction match the treatment plan. This study introduces a novel metric for proton therapy quality control based on uncertainties in range verification of individual spots. Approach. We employ uncertainty-aware deep neural networks to predict the Bragg peak depth in an anthropomorphic phantom based on secondary charged particle detection in a silicon pixel telescope designed for proton computed tomography. The subsequently predicted Bragg peak positions, along with their uncertainties, are compared to the treatment plan, rejecting spots which are predicted to be outside the 95% confidence interval. The such-produced spot rejection rate presents a metric for the quality of the treatment fraction. Main results. The introduced spot rejection rate metric is shown to be well-defined for range predictors with well-calibrated uncertainties. Using this method, treatment errors in the form of lateral shifts can be detected down to 1 mm after around 1400 treated spots with spot intensities of 1 × 107 protons. The range verification model used in this metric predicts the Bragg peak depth to a mean absolute error of 1.107 ± 0.015 mm. Significance. Uncertainty-aware machine learning has potential applications in proton therapy quality control. This work presents the foundation for future developments in this area.

2022

P. Rüdiger, F. Claus, V. Leonhardt, H. Hagen, J. C. Aurich, and C. Garth. PREVIS - A Combined Machine Learning and Visual Interpolation Approach for Interactive Reverse Engineering in Assembly Quality Control. CoRR, vol. abs/2201.10257, 2022. arXiv:2201.10257

@article{DBLP:journals/corr/abs-2201-10257,
  author = {R{\"{u}}diger, Patrick and Claus, Felix and Leonhardt, Viktor and Hagen, Hans and Aurich, Jan C. and Garth, Christoph},
  title = {{PREVIS} - {A} Combined Machine Learning and Visual Interpolation
                 Approach for Interactive Reverse Engineering in Assembly Quality Control},
  journal = {CoRR},
  volume = {abs/2201.10257},
  year = {2022},
  url = {https://arxiv.org/abs/2201.10257},
  eprinttype = {arXiv},
  eprint = {2201.10257},
  timestamp = {Tue, 01 Feb 2022 14:59:01 +0100},
  biburl = {https://dblp.org/rec/journals/corr/abs-2201-10257.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

V. Leonhardt, F. Claus, and C. Garth. PEN: Process Estimator neural Network for root cause analysis using graph convolution. Journal of Manufacturing Systems, vol. 62, pp. 886–902, 2022. 10.1016/j.jmsy.2021.11.008

@article{LEONHARDT2022886,
  title = {PEN: Process Estimator neural Network for root cause analysis using graph convolution},
  journal = {Journal of Manufacturing Systems},
  volume = {62},
  pages = {886-902},
  year = {2022},
  issn = {0278-6125},
  doi = {10.1016/j.jmsy.2021.11.008},
  url = {https://www.sciencedirect.com/science/article/pii/S0278612521002363},
  author = {Leonhardt, Viktor and Claus, Felix and Garth, Christoph}
}

M. Aehle et al. Derivatives in Proton CT. CoRR, vol. abs/2202.05551, 2022. arXiv:2202.05551

@article{DBLP:journals/corr/abs-2202-05551,
  author = {Aehle, Max and Alme, Johan and Barnaf{\"{o}}ldi, Gergely G{\'{a}}bor and Bl{\"{u}}hdorn, Johannes and Bodova, Tea and Borshchov, Vyacheslav and van den Brink, Anthony and Chaar, Mamdouh and Eikeland, Viljar and Feofilov, Gregory and Garth, Christoph and Gauger, Nicolas R. and Genov, Georgi and Gr{\o}ttvik, Ola and Helstrup, H{\aa}vard and Igolkin, Sergey and Keidel, Ralf and Kobdaj, Chinorat and Kortus, Tobias and Leonhardt, Viktor and Mehendale, Shruti and Mulawade, Raju Ningappa and Odland, Odd Harald and O'Neill, George and Papp, G{\'{a}}bor and Peitzmann, Thomas and Pettersen, Helge Egil Seime and Piersimoni, Pierluigi and Pochampalli, Rohit and Protsenko, Maksym and Rauch, Max and Rehman, Attiq Ur and Richter, Matthias and R{\"{o}}hrich, Dieter and Sagebaum, Max and Santana, Joshua and Schilling, Alexander and Seco, Joao and Songmoolnak, Arnon and S{\o}lie, Jarle Rambo and Tambave, Ganesh and Tymchuk, Ihor and Ullaland, Kjetil and Varga{-}Kofarago, Monika and Volz, Lennart and Wagner, Boris and Wendzel, Steffen and Wiebel, Alexander and Xiao, RenZheng and Yang, Shiming and Yokoyama, Hiroki and Zillien, Sebastian},
  title = {Derivatives in Proton {CT}},
  journal = {CoRR},
  volume = {abs/2202.05551},
  year = {2022},
  url = {https://arxiv.org/abs/2202.05551},
  eprinttype = {arXiv},
  eprint = {2202.05551},
  timestamp = {Tue, 01 Mar 2022 14:36:22 +0100},
  biburl = {https://dblp.org/rec/journals/corr/abs-2202-05551.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

2021

H. E. S. Pettersen et al. Investigating particle track topology for range telescopes in particle radiography using convolutional neural networks. Acta Oncologica, 2021. 10.1080/0284186X.2021.1949037

@article{paa+21,
  author = {Pettersen, Helge Egil Seime and Aehle, Max and Alme, Johan and Barnaf{\"{o}}ldi, Gergely G{\'{a}}bor and Borshchov, Vyacheslav and van den Brink, Anthony and Chaar, Mamdouh and Eikeland, Viljar and Feofilov, Grigory and Garth, Christoph and Gauger, Nicolas R. and Genov, Georgi and Gr{\o}ttvik, Ola and Helstrup, H{\aa}vard and Igolkin, Sergey and Keidel, Ralf and Kobdaj, Chinorat and Kortus, Tobias and Leonhardt, Viktor and Mehendale, Shruti and Mulawade, Raju Ningappa and Odland, Odd Harald and Papp, G{\'{a}}bor and Peitzmann, Thomas and Piersimoni, Pierluigi and Protsenko, Maksym and Rehman, Attiq Ur and Richter, Matthias and Santana, Joshua and Schilling, Alexander and Seco, Joao and Songmoolnak, Arnon and S{\o}lie, Jarle Rambo and Tambave, Ganesh and Tymchuk, Ihor and Ullaland, Kjetil and Varga-Kofarago, Monika and Volz, Lennart and Wagner, Boris and Wendzel, Steffen and Wiebel, Alexander and Xiao, RenZheng and Yang, Shiming and Yokoyama, Hiroki and Zillien, Sebastian and R{\"{o}}hrich, Dieter},
  title = {Investigating particle track topology for range telescopes in particle radiography using convolutional neural networks},
  journal = {Acta Oncologica},
  year = {2021},
  publisher = {Taylor & Francis},
  doi = {10.1080/0284186X.2021.1949037}
}

Department of Computer Science