Fabian Wagner
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fabian Wagner has a total of 123 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Maier
Friedrich-Alexander-Universität Erlangen-Nürnberg, Pattern Recognition Lab, Erlangen, Germany
3 shared publications - Mareike Thies
Pattern Recognition Lab, FAU Erlangen-Nürnberg
3 shared publications - Mingxuan Gu
State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing 102249, China; Key Laboratory of Earth Prospecting and Information Technology, China University of Petroleum (Beijing), Beijing 102249, China
3 shared publications - Pallav Purohit
International Institute for Applied Systems Analysis (IIASA)
3 shared publications - Wilfried Winiwarter
International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria
3 shared publications - Wolfgang Schöpp
Air Quality and Greenhouse Gases (AIR) Program, International Institute for Applied Systems Analysis (IIASA), Schlossplatz 1, 2361, Laxenburg, Austria
3 shared publications
Latest Publications
- Top Cited Papers
- 1 July 2024
- Published by Springer Nature in Nature Energy
- Vol. 9 (8) , 1021-1031
Diversifying heat sources in China’s urban district heating systems will reduce risk of carbon lock-in
- 1 July 2024
- Published by Springer Nature in Nature Energy
- Vol. 9 (8) , 1021-1031
Top Cited PapersDiversifying heat sources in China’s urban district heating systems will reduce risk of carbon lock-in
- Open Access
On the Benefit of Dual-domain Denoising in a Self-supervised Low-dose CT Setting
Computed tomography (CT) is routinely used for three-dimensional non-invasive imaging. Numerous data-driven image denoising algorithms were proposed to restore image quality in low-dose acquisitions. However, considerably less research investigates methods already intervening in the raw detector data due to limited access to suitable projection data or correct reconstruction algorithms. In this work, we present an end-to-end trainable CT reconstruction pipeline that contains denoising operators in both the projection and the image domain and that are optimized simultaneously without requiring ground-truth high-dose CT data. Our experiments demonstrate that including an additional projection denoising operator improved the overall denoising performance by 82.4-94.1%/12.5-41.7% (PSNR/SSIM) on abdomen CT and 1.5-2.9%/0.4-0.5% (PSNR/SSIM) on XRM data relative to the low-dose baseline. We make our entire helical CT reconstruction framework publicly available that contains a raw projection rebinning step to render helical projection data suitable for differentiable fan-beam reconstruction operators and end-to-end learning.
Open AccessOn the Benefit of Dual-domain Denoising in a Self-supervised Low-dose CT Setting
Computed tomography (CT) is routinely used for three-dimensional non-invasive imaging. Numerous data-driven image denoising algorithms were proposed to restore image quality in low-dose acquisitions. However, considerably less research investigates methods already intervening in the raw detector data due to limited access to suitable projection data or correct reconstruction algorithms. In this work, we present an end-to-end trainable CT reconstruction pipeline that contains denoising operators in both the projection and the image domain and that are optimized simultaneously without requiring ground-truth high-dose CT data. Our experiments demonstrate that including an additional projection denoising operator improved the overall denoising performance by 82.4-94.1%/12.5-41.7% (PSNR/SSIM) on abdomen CT and 1.5-2.9%/0.4-0.5% (PSNR/SSIM) on XRM data relative to the low-dose baseline. We make our entire helical CT reconstruction framework publicly available that contains a raw projection rebinning step to render helical projection data suitable for differentiable fan-beam reconstruction operators and end-to-end learning.
- Open Access
Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT
Low-dose computed tomography (CT) denoising algorithms aim to enable reduced patient dose in routine CT acquisitions while maintaining high image quality. Recently, deep learning~(DL)-based methods were introduced, outperforming conventional denoising algorithms on this task due to their high model capacity. However, for the transition of DL-based denoising to clinical practice, these data-driven approaches must generalize robustly beyond the seen training data. We, therefore, propose a hybrid denoising approach consisting of a set of trainable joint bilateral filters (JBFs) combined with a convolutional DL-based denoising network to predict the guidance image. Our proposed denoising pipeline combines the high model capacity enabled by DL-based feature extraction with the reliability of the conventional JBF. The pipeline's ability to generalize is demonstrated by training on abdomen CT scans without metal implants and testing on abdomen scans with metal implants as well as on head CT data. When embedding two well-established DL-based denoisers (RED-CNN/QAE) in our pipeline, the denoising performance is improved by $10\,\%$/$82\,\%$ (RMSE) and $3\,\%$/$81\,\%$ (PSNR) in regions containing metal and by $6\,\%$/$78\,\%$ (RMSE) and $2\,\%$/$4\,\%$ (PSNR) on head CT data, compared to the respective vanilla model. Concluding, the proposed trainable JBFs limit the error bound of deep neural networks to facilitate the applicability of DL-based denoisers in low-dose CT pipelines.Open AccessTrainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT
Low-dose computed tomography (CT) denoising algorithms aim to enable reduced patient dose in routine CT acquisitions while maintaining high image quality. Recently, deep learning~(DL)-based methods were introduced, outperforming conventional denoising algorithms on this task due to their high model capacity. However, for the transition of DL-based denoising to clinical practice, these data-driven approaches must generalize robustly beyond the seen training data. We, therefore, propose a hybrid denoising approach consisting of a set of trainable joint bilateral filters (JBFs) combined with a convolutional DL-based denoising network to predict the guidance image. Our proposed denoising pipeline combines the high model capacity enabled by DL-based feature extraction with the reliability of the conventional JBF. The pipeline's ability to generalize is demonstrated by training on abdomen CT scans without metal implants and testing on abdomen scans with metal implants as well as on head CT data. When embedding two well-established DL-based denoisers (RED-CNN/QAE) in our pipeline, the denoising performance is improved by $10\,\%$/$82\,\%$ (RMSE) and $3\,\%$/$81\,\%$ (PSNR) in regions containing metal and by $6\,\%$/$78\,\%$ (RMSE) and $2\,\%$/$4\,\%$ (PSNR) on head CT data, compared to the respective vanilla model. Concluding, the proposed trainable JBFs limit the error bound of deep neural networks to facilitate the applicability of DL-based denoisers in low-dose CT pipelines. - Open Access
ConFUDA: Contrastive Fewshot Unsupervised Domain Adaptation for Medical Image Segmentation
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled target domain. Contrastive learning (CL) in the context of UDA can help to better separate classes in feature space. However, in image segmentation, the large memory footprint due to the computation of the pixel-wise contrastive loss makes it prohibitive to use. Furthermore, labeled target data is not easily available in medical imaging, and obtaining new samples is not economical. As a result, in this work, we tackle a more challenging UDA task when there are only a few (fewshot) or a single (oneshot) image available from the target domain. We apply a style transfer module to mitigate the scarcity of target samples. Then, to align the source and target features and tackle the memory issue of the traditional contrastive loss, we propose the centroid-based contrastive learning (CCL) and a centroid norm regularizer (CNR) to optimize the contrastive pairs in both direction and magnitude. In addition, we propose multi-partition centroid contrastive learning (MPCCL) to further reduce the variance in the target features. Fewshot evaluation on MS-CMRSeg dataset demonstrates that ConFUDA improves the segmentation performance by 0.34 of the Dice score on the target domain compared with the baseline, and 0.31 Dice score improvement in a more rigorous oneshot setting.
Open AccessConFUDA: Contrastive Fewshot Unsupervised Domain Adaptation for Medical Image Segmentation
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled target domain. Contrastive learning (CL) in the context of UDA can help to better separate classes in feature space. However, in image segmentation, the large memory footprint due to the computation of the pixel-wise contrastive loss makes it prohibitive to use. Furthermore, labeled target data is not easily available in medical imaging, and obtaining new samples is not economical. As a result, in this work, we tackle a more challenging UDA task when there are only a few (fewshot) or a single (oneshot) image available from the target domain. We apply a style transfer module to mitigate the scarcity of target samples. Then, to align the source and target features and tackle the memory issue of the traditional contrastive loss, we propose the centroid-based contrastive learning (CCL) and a centroid norm regularizer (CNR) to optimize the contrastive pairs in both direction and magnitude. In addition, we propose multi-partition centroid contrastive learning (MPCCL) to further reduce the variance in the target features. Fewshot evaluation on MS-CMRSeg dataset demonstrates that ConFUDA improves the segmentation performance by 0.34 of the Dice score on the target domain compared with the baseline, and 0.31 Dice score improvement in a more rigorous oneshot setting.
- 9 May 2022
- Published by Springer Nature in Nature Climate Change
- Vol. 12 (5) , 428-435
Using large ensembles of climate change mitigation scenarios for robust insights
- 9 May 2022
- Published by Springer Nature in Nature Climate Change
- Vol. 12 (5) , 428-435
Using large ensembles of climate change mitigation scenarios for robust insights
- 26 July 2021
- Published by Springer Nature in Nature Sustainability
- Vol. 4 (10) , 859-867
Household contributions to and impacts from air pollution in India
- 26 July 2021
- Published by Springer Nature in Nature Sustainability
- Vol. 4 (10) , 859-867
Household contributions to and impacts from air pollution in India
- Open Access
- 29 December 2020
- Published by Springer Nature in Research Square
Who pollutes and who suffers from air pollution in India
Airborne fine particulate matter (PM2.5) is the most important environmental risk factor for premature mortality worldwide, and the likely cause of several hundred thousand premature deaths every year in India. Indian households also contribute to ambient PM2.5 to different extents from a number of sources, including biomass-burning cook stoves, transport and industrial manufacturing triggered by household consumption. In this study, we quantify the PM2.5 contributions by source from, as well as the mortality burden suffered by, individual urban and rural income deciles. We find that the impacts are distributed differently from contributions. Indirect emissions associated with household consumption contribute almost twice as much to ambient PM2.5 concentrations as direct emissions from biomass cook stoves. We show that the mortality risk from these indirect sources fall disproportionately on lower-income households, exacerbating the mortality risks they already face from using biomass-burning cook stoves. As a result, economy-wide end-of-pipe controls can reduce inequity in contributions to ambient air pollution. However, due to the overwhelming role of household indoor air pollution in premature deaths among the low-income population, clean cook stoves reduce overall inequality in terms of mortality risks to a far greater extent.
- 29 December 2020
- Published by Springer Nature in Research Square
Open AccessWho pollutes and who suffers from air pollution in India
Airborne fine particulate matter (PM2.5) is the most important environmental risk factor for premature mortality worldwide, and the likely cause of several hundred thousand premature deaths every year in India. Indian households also contribute to ambient PM2.5 to different extents from a number of sources, including biomass-burning cook stoves, transport and industrial manufacturing triggered by household consumption. In this study, we quantify the PM2.5 contributions by source from, as well as the mortality burden suffered by, individual urban and rural income deciles. We find that the impacts are distributed differently from contributions. Indirect emissions associated with household consumption contribute almost twice as much to ambient PM2.5 concentrations as direct emissions from biomass cook stoves. We show that the mortality risk from these indirect sources fall disproportionately on lower-income households, exacerbating the mortality risks they already face from using biomass-burning cook stoves. As a result, economy-wide end-of-pipe controls can reduce inequity in contributions to ambient air pollution. However, due to the overwhelming role of household indoor air pollution in premature deaths among the low-income population, clean cook stoves reduce overall inequality in terms of mortality risks to a far greater extent.
- 1 September 2019
- Published by Elsevier in Journal of Cleaner Production
- Vol. 232, 235-249
Integrated assessment of resource-energy-environment nexus in China's iron and steel industry
- 1 September 2019
- Published by Elsevier in Journal of Cleaner Production
- Vol. 232, 235-249
Integrated assessment of resource-energy-environment nexus in China's iron and steel industry