Georg Langs - Selected Publications#

Overall more than 200 peer reviewed papers, > 15.000 citations ( 3.400 citations in 2023), h-factor: 47

Schwartz, E., Nenning, K. H., Heuer, K., Jeffery, N., Bertrand, O. C., Toro, R., Kasprian, G., Prayer, D., Langs, G. (2023). Evolution of cortical geometry and its link to function, behaviour and ecology. Nature communications, 14(1), 2252.
https://doi.org/10.1038/s41467-023-37574-x

Impact: Linking brain imaging data of 90 species, this paper reconstructs the evolution of the human brain over more than 70 million years. The paper established new evidence for the tethering hypothesis of the brain, and the linked cortical maps form a basis for translating insights across species.

Burger, B., Nenning, K. H., Schwartz, E., Margulies, D. S., Goulas, A., Liu, H., Neubauer, S., Dauwels, J., Prayer, D., Langs, G. (2022). Disentangling cortical functional connectivity strength and topography reveals divergent roles of genes and environment. NeuroImage, 247, 118770.
https://doi.org/10.1016/j.neuroimage.2021.118770

Impact: This paper showed that individual brain variability of anatomy, and function can be disentangled. Prior approaches to study variability were not able to resolve how genes and environment shape the functional network architecture, and its spatial layout on the cortex differently. In contrast, this work could show that disentangling reveals a heterogeneous landscape of genetic and environmental influence on the human cortical architecture.

Taymourtash, A., Schwartz, E., Nenning, K. H., Sobotka, D., Licandro, R., Glatter, S., Diogo, M., Golland, P., Grant, E., Prayer, D., Kasprian, G., Langs, G. (2023). Fetal development of functional thalamocortical and cortico–cortical connectivity. Cerebral Cortex, 33(9), 5613-5624.
https://doi.org/10.1093/cercor/bhac446

Hofmanninger, J., Prayer, F., Pan, J., Röhrich, S., Prosch, H. and Langs, G., 2020. Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. European Radiology Experimental, 4(1), pp.1-13.
https://doi.org/10.1186/s41747-020-00173-2

Impact: Introduced a lung segmentation model that can cope with substantial disease in a robust way. It was most downloaded and most cited paper of Eur. Rad. Exp. 2020. The open source code published together with the paper, enabling lung segmentation was downloaded more than 10.000 times.

Perkonigg, M., Hofmanninger, J., Herold, C.J., Brink, J.A., Pianykh, O., Prosch, H., Langs, G., 2021. Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging. Nature Communications 12, 5678.
https://doi.org/10.1038/s41467-021-25858-z

Impact: Paper introduced novel methodology for continual machine learning in medicine, to adapt to new technologies, and avoiding catastrophic forgetting of prior data characteristics.

Xu, T., Nenning, K. H., Schwartz, E., Hong, S. J., Vogelstein, J. T., Goulas, A., Fair, D., Schroeder, C., Margulies, D., Smallwood, J., Milham, M., Langs, G. (2020). Cross-species functional alignment reveals evolutionary hierarchy within the connectome. Neuroimage, 223, 117346.
https://doi.org/10.1016/j.neuroimage.2020.117346

Impact: This work linked functional brain maps across species, finding evidence for a gradient of similarity across different brain areas.

Voted best paper in NeuroImage 2020 by the editorial board.

Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G., 2017. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In Advances in information processing in medical imaging (pp. 146-157)
https://doi.org/10.1007/978-3-319-59050-9_12

Impact: The paper introduced the method of anomaly detection to identify novel biomarkers with generative deep learning models. 2490 citations

Holzinger, A., Langs, G., Denk, H., Zatloukal, K., & Müller, H. (2019). Causability and explainability of artificial intelligence in medicine. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(4), e1312.

Impact: The paper established novel concepts to assess explainability of artificial intelligence models. 1087 citations.