Johannes Hofmanninger
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Johannes Hofmanninger has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Georg Langs
Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria
8 shared publications Helmut Prosch
Medical University of Vienna
3 shared publications- Matthias Perkonigg
Medical University of Vienna
3 shared publications Christian Herold
Medical University of Vienna
2 shared publications- Helmut Prosch
Medical University of Vienna, Austria
2 shared publications Sebastian Röhrich
Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria
2 shared publications
Latest Publications
- Open Access
- 16 March 2022
- Published by Machine Learning for Biomedical Imaging in Machine Learning for Biomedical Imaging
- Vol. 1 (IPMI 2021) , 1-28
Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristics
Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial static training set, model performance and reliability suffer from changes of acquisition characteristics as data and targets may become inconsistent. Continual learning can help to adapt models to the changing environment by training on a continuous data stream. However, continual manual expert labelling of medical imaging requires substantial effort. Thus, ways to use labelling resources efficiently on a well chosen sub-set of new examples is necessary to render this strategy feasible. Here, we propose a method for continual active learning operating on a stream of medical images in a multi-scanner setting. The approach automatically recognizes shifts in image acquisition characteristics – new domains –, selects optimal examples for labelling and adapts training accordingly. Labelling is subject to a limited budget, resembling typical real world scenarios. In order to avoid catastrophic forgetting while learning on new domains the proposed method utilizes a rehearsal memory. To demonstrate generalizability, we evaluate the effectiveness of our method on three tasks: cardiac segmentation, lung nodule detection and brain age estimation. Results show that the proposed approach outperforms other active learning methods on a continuous data stream with domain shifts.
- 16 March 2022
- Published by Machine Learning for Biomedical Imaging in Machine Learning for Biomedical Imaging
- Vol. 1 (IPMI 2021) , 1-28
Open AccessContinual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristics
Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial static training set, model performance and reliability suffer from changes of acquisition characteristics as data and targets may become inconsistent. Continual learning can help to adapt models to the changing environment by training on a continuous data stream. However, continual manual expert labelling of medical imaging requires substantial effort. Thus, ways to use labelling resources efficiently on a well chosen sub-set of new examples is necessary to render this strategy feasible. Here, we propose a method for continual active learning operating on a stream of medical images in a multi-scanner setting. The approach automatically recognizes shifts in image acquisition characteristics – new domains –, selects optimal examples for labelling and adapts training accordingly. Labelling is subject to a limited budget, resembling typical real world scenarios. In order to avoid catastrophic forgetting while learning on new domains the proposed method utilizes a rehearsal memory. To demonstrate generalizability, we evaluate the effectiveness of our method on three tasks: cardiac segmentation, lung nodule detection and brain age estimation. Results show that the proposed approach outperforms other active learning methods on a continuous data stream with domain shifts.
- 14 June 2021
- Published by Springer Nature
- p. 649-660
Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition
- 14 June 2021
- Published by Springer Nature
- p. 649-660
Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition
- Open Access
- 4 May 2021
- Published by Springer Nature in European Radiology
- Vol. 31 (11) , 8818-8819
Correction to: Radiomics score predicts acute respiratory distress syndrome based on the initial CT scan after trauma
A Correction to this paper has been published: https://doi.org/ 10.1007/s00330-021-07995-7
- 4 May 2021
- Published by Springer Nature in European Radiology
- Vol. 31 (11) , 8818-8819
Open AccessCorrection to: Radiomics score predicts acute respiratory distress syndrome based on the initial CT scan after trauma
A Correction to this paper has been published: https://doi.org/ 10.1007/s00330-021-07995-7
- Top Cited PapersOpen Access
- 20 August 2020
- Published by Springer Nature in European Radiology Experimental
- Vol. 4 (1) , 1-13
Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
Background: Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exists, involving sophisticated pipelines trained and validated on different datasets. However, the clinical applicability of these approaches across diseases remains limited. Methods: We compared four generic deep learning approaches trained on various datasets and two readily available lung segmentation algorithms. We performed evaluation on routine imaging data with more than six different disease patterns and three published data sets. Results: Using different deep learning approaches, mean Dice similarity coefficients (DSCs) on test datasets varied not over 0.02. When trained on a diverse routine dataset (n = 36), a standard approach (U-net) yields a higher DSC (0.97 ± 0.05) compared to training on public datasets such as the Lung Tissue Research Consortium (0.94 ± 0.13, p = 0.024) or Anatomy 3 (0.92 ± 0.15, p = 0.001). Trained on routine data (n = 231) covering multiple diseases, U-net compared to reference methods yields a DSC of 0.98 ± 0.03 versus 0.94 ± 0.12 (p = 0.024). Conclusions: The accuracy and reliability of lung segmentation algorithms on demanding cases primarily relies on the diversity of the training data, highlighting the importance of data diversity compared to model choice. Efforts in developing new datasets and providing trained models to the public are critical. By releasing the trained model under General Public License 3.0, we aim to foster research on lung diseases by providing a readily available tool for segmentation of pathological lungs.
- 20 August 2020
- Published by Springer Nature in European Radiology Experimental
- Vol. 4 (1) , 1-13
Top Cited PapersOpen AccessAutomatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
Background: Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exists, involving sophisticated pipelines trained and validated on different datasets. However, the clinical applicability of these approaches across diseases remains limited. Methods: We compared four generic deep learning approaches trained on various datasets and two readily available lung segmentation algorithms. We performed evaluation on routine imaging data with more than six different disease patterns and three published data sets. Results: Using different deep learning approaches, mean Dice similarity coefficients (DSCs) on test datasets varied not over 0.02. When trained on a diverse routine dataset (n = 36), a standard approach (U-net) yields a higher DSC (0.97 ± 0.05) compared to training on public datasets such as the Lung Tissue Research Consortium (0.94 ± 0.13, p = 0.024) or Anatomy 3 (0.92 ± 0.15, p = 0.001). Trained on routine data (n = 231) covering multiple diseases, U-net compared to reference methods yields a DSC of 0.98 ± 0.03 versus 0.94 ± 0.12 (p = 0.024). Conclusions: The accuracy and reliability of lung segmentation algorithms on demanding cases primarily relies on the diversity of the training data, highlighting the importance of data diversity compared to model choice. Efforts in developing new datasets and providing trained models to the public are critical. By releasing the trained model under General Public License 3.0, we aim to foster research on lung diseases by providing a readily available tool for segmentation of pathological lungs.
- 1 August 2020
- Published by Radiological Society of North America (RSNA) in Radiology: Cardiothoracic Imaging
- Vol. 2 (4) , e190190
Prospects and Challenges of Radiomics by Using Nononcologic Routine Chest CT
This review describes challenges and solutions of a radiomics analysis of chronic obstructive pulmonary disease, osteoporosis, sarcopenia, interstitial lung disease, and coronary artery calcificati... Chest CT scans are one of the most common medical imaging procedures. The automatic extraction and quantification of imaging features may help in diagnosis, prognosis of, or treatment decision in c...
- 1 August 2020
- Published by Radiological Society of North America (RSNA) in Radiology: Cardiothoracic Imaging
- Vol. 2 (4) , e190190
Prospects and Challenges of Radiomics by Using Nononcologic Routine Chest CT
This review describes challenges and solutions of a radiomics analysis of chronic obstructive pulmonary disease, osteoporosis, sarcopenia, interstitial lung disease, and coronary artery calcificati... Chest CT scans are one of the most common medical imaging procedures. The automatic extraction and quantification of imaging features may help in diagnosis, prognosis of, or treatment decision in c...
- Open Access
Dynamic memory to alleviate catastrophic forgetting in continuous learning settings
In medical imaging, technical progress or changes in diagnostic procedures lead to a continuous change in image appearance. Scanner manufacturer, reconstruction kernel, dose, other protocol specific settings or administering of contrast agents are examples that influence image content independent of the scanned biology. Such domain and task shifts limit the applicability of machine learning algorithms in the clinical routine by rendering models obsolete over time. Here, we address the problem of data shifts in a continuous learning scenario by adapting a model to unseen variations in the source domain while counteracting catastrophic forgetting effects. Our method uses a dynamic memory to facilitate rehearsal of a diverse training data subset to mitigate forgetting. We evaluated our approach on routine clinical CT data obtained with two different scanner protocols and synthetic classification tasks. Experiments show that dynamic memory counters catastrophic forgetting in a setting with multiple data shifts without the necessity for explicit knowledge about when these shifts occur.
Open AccessDynamic memory to alleviate catastrophic forgetting in continuous learning settings
In medical imaging, technical progress or changes in diagnostic procedures lead to a continuous change in image appearance. Scanner manufacturer, reconstruction kernel, dose, other protocol specific settings or administering of contrast agents are examples that influence image content independent of the scanned biology. Such domain and task shifts limit the applicability of machine learning algorithms in the clinical routine by rendering models obsolete over time. Here, we address the problem of data shifts in a continuous learning scenario by adapting a model to unseen variations in the source domain while counteracting catastrophic forgetting effects. Our method uses a dynamic memory to facilitate rehearsal of a diverse training data subset to mitigate forgetting. We evaluated our approach on routine clinical CT data obtained with two different scanner protocols and synthetic classification tasks. Experiments show that dynamic memory counters catastrophic forgetting in a setting with multiple data shifts without the necessity for explicit knowledge about when these shifts occur.
- 9 September 2017
- Published by Springer Nature
- p. 341-348
Mapping Multi-Modal Routine Imaging Data to a Single Reference via Multiple Templates
- 9 September 2017
- Published by Springer Nature
- p. 341-348
Mapping Multi-Modal Routine Imaging Data to a Single Reference via Multiple Templates
- 2 October 2016
- Published by Springer Nature
- p. 192-200
Unsupervised Identification of Clinically Relevant Clusters in Routine Imaging Data
- 2 October 2016
- Published by Springer Nature
- p. 192-200
Unsupervised Identification of Clinically Relevant Clusters in Routine Imaging Data
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 457-465
Mapping visual features to semantic profiles for retrieval in medical imaging
Content based image retrieval is highly relevant in medical imaging, since it makes vast amounts of imaging data accessible for comparison during diagnosis. Finding image similarity measures that reflect diagnostically relevant relationships is challenging, since the overall appearance variability is high compared to often subtle signatures of diseases. To learn models that capture the relationship between semantic clinical information and image elements at scale, we have to rely on data generated during clinical routine (images and radiology reports), since expert annotation is prohibitively costly. Here we show that re-mapping visual features extracted from medical imaging data based on weak labels that can be found in corresponding radiology reports creates descriptions of local image content capturing clinically relevant information. We show that these semantic profiles enable higher recall and precision during retrieval compared to visual features, and that we can even map semantic terms describing clinical findings from radiology reports to localized image volume areas.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 457-465
Mapping visual features to semantic profiles for retrieval in medical imaging
Content based image retrieval is highly relevant in medical imaging, since it makes vast amounts of imaging data accessible for comparison during diagnosis. Finding image similarity measures that reflect diagnostically relevant relationships is challenging, since the overall appearance variability is high compared to often subtle signatures of diseases. To learn models that capture the relationship between semantic clinical information and image elements at scale, we have to rely on data generated during clinical routine (images and radiology reports), since expert annotation is prohibitively costly. Here we show that re-mapping visual features extracted from medical imaging data based on weak labels that can be found in corresponding radiology reports creates descriptions of local image content capturing clinically relevant information. We show that these semantic profiles enable higher recall and precision during retrieval compared to visual features, and that we can even map semantic terms describing clinical findings from radiology reports to localized image volume areas.
- 1 December 2013
- Published by Elsevier in Respiratory Physiology & Neurobiology
- Vol. 189 (3) , 594-606
Heterogeneity and matching of ventilation and perfusion within anatomical lung units in rats
- 1 December 2013
- Published by Elsevier in Respiratory Physiology & Neurobiology
- Vol. 189 (3) , 594-606
Heterogeneity and matching of ventilation and perfusion within anatomical lung units in rats