Fredrik Andreas Dahl
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
Fredrik Andreas Dahl has a total of 84 co-authors. Here are the top co-authors by number of shared publications:
- Kashif Waqar Faiz
Department of Neurology Akershus University Hospital Lørenskog Norway
3 shared publications - Line Eikvil
Norwegian Computing Center
3 shared publications - Mathias Barra
Akershus University Hospital, The Health Services Research Unit (HØKH), Lørenskog, Norway
3 shared publications - Solveig Hofvind
Norwegian Institute of Public Health
3 shared publications - Adrian Jäggi
Astronomical Institute of the University of Bern Bern Switzerland
2 shared publications - Anders U. Waldeland
Norwegian Computing Center
2 shared publications
Latest Publications
- Open Access
- 30 January 2026
- Published by Springer Nature in Surveys in Geophysics
- Vol. 47 (4) , 1057-1117
Uncertainty Quantification of Satellite-Based Essential Climate Variables Derived from Deep Learning
Accurate uncertainty information associated with essential climate variables (ECVs) is crucial for reliable climate modeling and understanding the spatiotemporal evolution of the Earth system. Recent developments in deep learning have remarkably advanced the estimation of ECVs with improved accuracy. However, the quantification of uncertainties associated with outputs of such deep learning models has yet to be widely adopted. This survey explores the types of uncertainties associated with ECVs derived from deep learning methods, including aleatoric (data) and epistemic (model) uncertainty, and the techniques to quantify them. The focus is on highlighting the importance of considering uncertainty associated with inputs in the deep learning models to account for the dynamic and multifaceted nature of satellite observations. The survey starts by clarifying the definitions of aleatoric and epistemic uncertainties and their roles in a typical satellite observation processing workflow, followed by bridging the gap between conventional statistical and deep learning views on uncertainties. Then, we comprehensively review the existing uncertainty quantification methods for deep learning algorithms and discuss their strengths and limitations. A comprehensive literature review about quantifying uncertainties in the deep learning estimates of ECVs follows the theoretical survey, covering a wide range of ECVs. The specific need for modification to fit the requirements from both the Earth observation side and the deep learning side in such interdisciplinary tasks is highlighted. We further demonstrate our findings with two selected ECV examples, snow cover and terrestrial water storage, to provide clear insights into different methods by promoting quantitative comparison. In the end, we summarize our findings and provide perspectives for future research.
- 30 January 2026
- Published by Springer Nature in Surveys in Geophysics
- Vol. 47 (4) , 1057-1117
Open AccessUncertainty Quantification of Satellite-Based Essential Climate Variables Derived from Deep Learning
Accurate uncertainty information associated with essential climate variables (ECVs) is crucial for reliable climate modeling and understanding the spatiotemporal evolution of the Earth system. Recent developments in deep learning have remarkably advanced the estimation of ECVs with improved accuracy. However, the quantification of uncertainties associated with outputs of such deep learning models has yet to be widely adopted. This survey explores the types of uncertainties associated with ECVs derived from deep learning methods, including aleatoric (data) and epistemic (model) uncertainty, and the techniques to quantify them. The focus is on highlighting the importance of considering uncertainty associated with inputs in the deep learning models to account for the dynamic and multifaceted nature of satellite observations. The survey starts by clarifying the definitions of aleatoric and epistemic uncertainties and their roles in a typical satellite observation processing workflow, followed by bridging the gap between conventional statistical and deep learning views on uncertainties. Then, we comprehensively review the existing uncertainty quantification methods for deep learning algorithms and discuss their strengths and limitations. A comprehensive literature review about quantifying uncertainties in the deep learning estimates of ECVs follows the theoretical survey, covering a wide range of ECVs. The specific need for modification to fit the requirements from both the Earth observation side and the deep learning side in such interdisciplinary tasks is highlighted. We further demonstrate our findings with two selected ECV examples, snow cover and terrestrial water storage, to provide clear insights into different methods by promoting quantitative comparison. In the end, we summarize our findings and provide perspectives for future research.
- 15 July 2025
- Published by Springer Nature
- p. 261-275
Modelling Uncertainty in Graph Convolutional Networks for Edge Detection in Mammograms
- 15 July 2025
- Published by Springer Nature
- p. 261-275
Modelling Uncertainty in Graph Convolutional Networks for Edge Detection in Mammograms
- 15 July 2025
- Published by Springer Nature
- p. 31-42
Self-guided SwinTransformer Improves Breast Cancer Detection Through Iterative Attention-Based Zooming
- 15 July 2025
- Published by Springer Nature
- p. 31-42
Self-guided SwinTransformer Improves Breast Cancer Detection Through Iterative Attention-Based Zooming
- 23 June 2025
- Published by Springer Nature
- p. 355-364
Unsupervised Domain Adaptation for Breast Cancer Detection in a Multi-Scanner Environment: A Case-Study from Norway
- 23 June 2025
- Published by Springer Nature
- p. 355-364
Unsupervised Domain Adaptation for Breast Cancer Detection in a Multi-Scanner Environment: A Case-Study from Norway
- 1 May 2025
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 7 (3) , e240039
Performance of Two Deep Learning–based AI Models for Breast Cancer Detection and Localization on Screening Mammograms from BreastScreen Norway
Two deep learning–based artificial intelligence (AI) models, one commercially available and one in-house, showed good performance for stand-alone cancer detection on retrospective mammography screening data. AI markings on the mammograms corresponded well to the true cancer location.
- 1 May 2025
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 7 (3) , e240039
Performance of Two Deep Learning–based AI Models for Breast Cancer Detection and Localization on Screening Mammograms from BreastScreen Norway
Two deep learning–based artificial intelligence (AI) models, one commercially available and one in-house, showed good performance for stand-alone cancer detection on retrospective mammography screening data. AI markings on the mammograms corresponded well to the true cancer location.
- Open Access
Uncertainties of Satellite-based Essential Climate Variables from Deep Learning
Accurate uncertainty information associated with essential climate variables (ECVs) is crucial for reliable climate modeling and understanding the spatiotemporal evolution of the Earth system. In recent years, geoscience and climate scientists have benefited from rapid progress in deep learning to advance the estimation of ECV products with improved accuracy. However, the quantification of uncertainties associated with the output of such deep learning models has yet to be thoroughly adopted. This survey explores the types of uncertainties associated with ECVs estimated from deep learning and the techniques to quantify them. The focus is on highlighting the importance of quantifying uncertainties inherent in ECV estimates, considering the dynamic and multifaceted nature of climate data. The survey starts by clarifying the definition of aleatoric and epistemic uncertainties and their roles in a typical satellite observation processing workflow, followed by bridging the gap between conventional statistical and deep learning views on uncertainties. Then, we comprehensively review the existing techniques for quantifying uncertainties associated with deep learning algorithms, focusing on their application in ECV studies. The specific need for modification to fit the requirements from both the Earth observation side and the deep learning side in such interdisciplinary tasks is discussed. Finally, we demonstrate our findings with two ECV examples, snow cover and terrestrial water storage, and provide our perspectives for future research.
Open AccessUncertainties of Satellite-based Essential Climate Variables from Deep Learning
Accurate uncertainty information associated with essential climate variables (ECVs) is crucial for reliable climate modeling and understanding the spatiotemporal evolution of the Earth system. In recent years, geoscience and climate scientists have benefited from rapid progress in deep learning to advance the estimation of ECV products with improved accuracy. However, the quantification of uncertainties associated with the output of such deep learning models has yet to be thoroughly adopted. This survey explores the types of uncertainties associated with ECVs estimated from deep learning and the techniques to quantify them. The focus is on highlighting the importance of quantifying uncertainties inherent in ECV estimates, considering the dynamic and multifaceted nature of climate data. The survey starts by clarifying the definition of aleatoric and epistemic uncertainties and their roles in a typical satellite observation processing workflow, followed by bridging the gap between conventional statistical and deep learning views on uncertainties. Then, we comprehensively review the existing techniques for quantifying uncertainties associated with deep learning algorithms, focusing on their application in ECV studies. The specific need for modification to fit the requirements from both the Earth observation side and the deep learning side in such interdisciplinary tasks is discussed. Finally, we demonstrate our findings with two ECV examples, snow cover and terrestrial water storage, and provide our perspectives for future research.
- Open Access
- 17 November 2023
- Published by University of Oslo Library in Nordic Machine Intelligence
- Vol. 3 (2) , 1-7
Two-stage mammography classification model using explainable-AI for ROI detection
This study introduces an enhanced version of a two-stage modelling approach using artificial intelligence (AI) for breast cancer detection in mammography screening. Leveraging a large dataset of 2,863,175 mammograms from the Norwegian breast cancer screening program, the approach uses two convolutional neural networks. A key enhancement over the prior methodology is the application of the explainable-AI method Layered GradCam for identifying regions of interest (ROIs) within the mammograms. The second neural network subsequently classifies these ROIs for malignancy. Layered GradCam is also used to display identified cancers to the user. By the AUC criterion, our model performs well, 0.974 for screen-detected and 0.931 for all cancers (screen-detected and interval), compared to a commercial program; 0.959 and 0.918, respectively. Comparisons with the radiologist cores indicates that the model has equal performance with two radiologists, and superior performance to one, for the detection of all cancers (screening- and interval type). Our tests indicate that our model generalizes well for different breast centers, but so far only images from a single manufacturer have been tested.
- 17 November 2023
- Published by University of Oslo Library in Nordic Machine Intelligence
- Vol. 3 (2) , 1-7
Open AccessTwo-stage mammography classification model using explainable-AI for ROI detection
This study introduces an enhanced version of a two-stage modelling approach using artificial intelligence (AI) for breast cancer detection in mammography screening. Leveraging a large dataset of 2,863,175 mammograms from the Norwegian breast cancer screening program, the approach uses two convolutional neural networks. A key enhancement over the prior methodology is the application of the explainable-AI method Layered GradCam for identifying regions of interest (ROIs) within the mammograms. The second neural network subsequently classifies these ROIs for malignancy. Layered GradCam is also used to display identified cancers to the user. By the AUC criterion, our model performs well, 0.974 for screen-detected and 0.931 for all cancers (screen-detected and interval), compared to a commercial program; 0.959 and 0.918, respectively. Comparisons with the radiologist cores indicates that the model has equal performance with two radiologists, and superior performance to one, for the detection of all cancers (screening- and interval type). Our tests indicate that our model generalizes well for different breast centers, but so far only images from a single manufacturer have been tested.
- Open Access
- 15 February 2023
- Published by Taylor & Francis in Health Systems
- Vol. 12 (3) , 317-331
Using stochastic simulation modelling to study occupancy levels of decentralised admission avoidance units in Norway
Identifying alternatives to acute hospital admission is a priority for many countries. Over 200 decentralised municipal acute units (MAUs) were established in Norway to divert low-acuity patients away from hospitals. MAUs have faced criticism for low mean occupancy and not relieving pressures on hospitals. We developed a discrete time simulation model of admissions and discharges to MAUs to test scenarios for increasing absolute mean occupancy. We also used the model to estimate the number of patients turned away as historical data was unavailable. Our experiments suggest that mergers alone are unlikely to substantially increase MAU absolute mean occupancy as unmet demand is generally low. However, merging MAUs offers scope for up to 20% reduction in bed capacity, without affecting service provision. Our work has relevance for other admissions avoidance units and provides a method for estimating unconstrained demand for beds in the absence of historical data.
- 15 February 2023
- Published by Taylor & Francis in Health Systems
- Vol. 12 (3) , 317-331
Open AccessUsing stochastic simulation modelling to study occupancy levels of decentralised admission avoidance units in Norway
Identifying alternatives to acute hospital admission is a priority for many countries. Over 200 decentralised municipal acute units (MAUs) were established in Norway to divert low-acuity patients away from hospitals. MAUs have faced criticism for low mean occupancy and not relieving pressures on hospitals. We developed a discrete time simulation model of admissions and discharges to MAUs to test scenarios for increasing absolute mean occupancy. We also used the model to estimate the number of patients turned away as historical data was unavailable. Our experiments suggest that mergers alone are unlikely to substantially increase MAU absolute mean occupancy as unmet demand is generally low. However, merging MAUs offers scope for up to 20% reduction in bed capacity, without affecting service provision. Our work has relevance for other admissions avoidance units and provides a method for estimating unconstrained demand for beds in the absence of historical data.
- Open Access
- 28 March 2022
- Published by UiT The Arctic University of Norway in Proceedings of the Northern Lights Deep Learning Workshop
- Vol. 3
mammography classification model trained from image labels only
The Cancer Registry of Norway organises a population-based breast cancer screening program, where 250 000 women participate each year. The interpretation of the screening mammograms is a manual process, but deep neural networks are showing potential in mammographic screening. Most methods focus on methods trained from pixel-level annotations, but these require expertise and are time-consuming to produce. Through the screenings, image level annotations are however readily available. In this work we present a few models trained from image level annotations from the Norwegian dataset: a holistic model, an attention model and an ensemble model. We compared their performance with that of pretrained models based on pixel-level annotations, trained on international datasets. From this we found that models trained on our local data with image-level annotation gave considerably better performance than the pretrained models from external data, although based on pixel-level annotations.
- 28 March 2022
- Published by UiT The Arctic University of Norway in Proceedings of the Northern Lights Deep Learning Workshop
- Vol. 3
Open Accessmammography classification model trained from image labels only
The Cancer Registry of Norway organises a population-based breast cancer screening program, where 250 000 women participate each year. The interpretation of the screening mammograms is a manual process, but deep neural networks are showing potential in mammographic screening. Most methods focus on methods trained from pixel-level annotations, but these require expertise and are time-consuming to produce. Through the screenings, image level annotations are however readily available. In this work we present a few models trained from image level annotations from the Norwegian dataset: a holistic model, an attention model and an ensemble model. We compared their performance with that of pretrained models based on pixel-level annotations, trained on international datasets. From this we found that models trained on our local data with image-level annotation gave considerably better performance than the pretrained models from external data, although based on pixel-level annotations.
- Open Access
- 15 March 2022
- Published by Springer Nature in BMC Health Services Research
- Vol. 22 (1) , 1-10
Stroke unit demand in Norway – present and future estimates
All stroke patients should receive timely admission to a stroke unit (SU). Consequently, most patients with suspected strokes – including stroke mimics (SM) are admitted. The aim of this study was to estimate the current total demand for SU bed capacity today and give estimates for future (2020–2040) demand. Time trend estimates for stroke incidence and time constant estimates for length of stay (LOS) were estimated from the Norwegian Patient Registry (2010–2015). Incidence and LOS models for SMs were based on data from Haukeland University Hospital (2008–2017) and Akershus University Hospital (2020), respectively. The incidence and LOS models were combined with scenarios from Statistic Norway’s population predictions to estimate SU demands for each health region. A telephone survey collected data on the number of currently available SU beds. In 2020, 361 SU beds are available, while demand was estimated to 302. The models predict a reduction in stroke incidence, which offsets projected demographic shifts. Still, the estimated demand for 2040 rose to 316, due to an increase in SMs. A variation of this reference scenario, where stroke incidence was frozen at the 2020-level, gave a 2040-demand of 480 beds. While the stroke incidence is likely to continue to fall, this appears to be balanced by an increase in SMs. An important uncertainty is how long the trend of decreasing stroke incidence can be expected to continue. Since the most important uncertainty factors point toward a potential increase, which may be as large as 50%, we would recommend that the health authorities plan for a potential increase in the demand for SU bed capacity.
- 15 March 2022
- Published by Springer Nature in BMC Health Services Research
- Vol. 22 (1) , 1-10
Open AccessStroke unit demand in Norway – present and future estimates
All stroke patients should receive timely admission to a stroke unit (SU). Consequently, most patients with suspected strokes – including stroke mimics (SM) are admitted. The aim of this study was to estimate the current total demand for SU bed capacity today and give estimates for future (2020–2040) demand. Time trend estimates for stroke incidence and time constant estimates for length of stay (LOS) were estimated from the Norwegian Patient Registry (2010–2015). Incidence and LOS models for SMs were based on data from Haukeland University Hospital (2008–2017) and Akershus University Hospital (2020), respectively. The incidence and LOS models were combined with scenarios from Statistic Norway’s population predictions to estimate SU demands for each health region. A telephone survey collected data on the number of currently available SU beds. In 2020, 361 SU beds are available, while demand was estimated to 302. The models predict a reduction in stroke incidence, which offsets projected demographic shifts. Still, the estimated demand for 2040 rose to 316, due to an increase in SMs. A variation of this reference scenario, where stroke incidence was frozen at the 2020-level, gave a 2040-demand of 480 beds. While the stroke incidence is likely to continue to fall, this appears to be balanced by an increase in SMs. An important uncertainty is how long the trend of decreasing stroke incidence can be expected to continue. Since the most important uncertainty factors point toward a potential increase, which may be as large as 50%, we would recommend that the health authorities plan for a potential increase in the demand for SU bed capacity.