Hanna Siebert
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hanna Siebert has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Mattias Paul Heinrich
Institute of Medical Informatics, University of Lübeck, Lübeck, Germany
8 shared publications - Lasse Hansen
EchoScout GmbH, Lübeck, Germany
4 shared publications Mattias P. Heinrich
Univ. zu Lübeck (Germany)
3 shared publications- Kumar Rajamani
Sathya Sai Institute of Higher Medical Sciences
2 shared publications Andreas Genz
MeVis Medical Solutions AG, Bremen
1 shared publication- Christoph Großbröhmer
Institute of Medical Informatics, University of Lübeck, Lübeck, Germany
1 shared publication
Latest Publications
- 3 April 2023
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12464, 496-500
Highly accurate deep registration networks for large deformation estimation in compression ultrasound
AI guidance on compression ultrasound is a problem for 2D segmentation networks, which produce inconsistent labels. This is aided by registration but classical untrained approaches cannot handle the large deformations and the noisy background movement and convolutional models like VoxelMorph do not reach the robust accuracy required. Meanwhile, large deformations are typically estimated with multi-warp networks that comprise "correlation layers", but they are resource-intensive and not easily applicable on end-devices in clinical context. We propose to replace the "correlation layer" with a differentiable convex optimisation block and perform end-to-end training of the convolutional feature backbone for improved performance.
- 3 April 2023
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12464, 496-500
Highly accurate deep registration networks for large deformation estimation in compression ultrasound
AI guidance on compression ultrasound is a problem for 2D segmentation networks, which produce inconsistent labels. This is aided by registration but classical untrained approaches cannot handle the large deformations and the noisy background movement and convolutional models like VoxelMorph do not reach the robust accuracy required. Meanwhile, large deformations are typically estimated with multi-warp networks that comprise "correlation layers", but they are resource-intensive and not easily applicable on end-devices in clinical context. We propose to replace the "correlation layer" with a differentiable convex optimisation block and perform end-to-end training of the convolutional feature backbone for improved performance.
- Open Access
Robust and Realtime Large Deformation Ultrasound Registration Using End-to-End Differentiable Displacement Optimisation
Image registration for temporal ultrasound sequences can be very beneficial for image-guided diagnostics and interventions. Cooperative human–machine systems that enable seamless assistance for both inexperienced and expert users during ultrasound examinations rely on robust, realtime motion estimation. Yet rapid and irregular motion patterns, varying image contrast and domain shifts in imaging devices pose a severe challenge to conventional realtime registration approaches. While learning-based registration networks have the promise of abstracting relevant features and delivering very fast inference times, they come at the potential risk of limited generalisation and robustness for unseen data; in particular, when trained with limited supervision. In this work, we demonstrate that these issues can be overcome by using end-to-end differentiable displacement optimisation. Our method involves a trainable feature backbone, a correlation layer that evaluates a large range of displacement options simultaneously and a differentiable regularisation module that ensures smooth and plausible deformation. In extensive experiments on public and private ultrasound datasets with very sparse ground truth annotation the method showed better generalisation abilities and overall accuracy than a VoxelMorph network with the same feature backbone, while being two times faster at inference.
Open AccessRobust and Realtime Large Deformation Ultrasound Registration Using End-to-End Differentiable Displacement Optimisation
Image registration for temporal ultrasound sequences can be very beneficial for image-guided diagnostics and interventions. Cooperative human–machine systems that enable seamless assistance for both inexperienced and expert users during ultrasound examinations rely on robust, realtime motion estimation. Yet rapid and irregular motion patterns, varying image contrast and domain shifts in imaging devices pose a severe challenge to conventional realtime registration approaches. While learning-based registration networks have the promise of abstracting relevant features and delivering very fast inference times, they come at the potential risk of limited generalisation and robustness for unseen data; in particular, when trained with limited supervision. In this work, we demonstrate that these issues can be overcome by using end-to-end differentiable displacement optimisation. Our method involves a trainable feature backbone, a correlation layer that evaluates a large range of displacement options simultaneously and a differentiable regularisation module that ensures smooth and plausible deformation. In extensive experiments on public and private ultrasound datasets with very sparse ground truth annotation the method showed better generalisation abilities and overall accuracy than a VoxelMorph network with the same feature backbone, while being two times faster at inference.
- 9 July 2022
- Published by Springer Nature
- p. 119-123
Learn to Fuse Input Features for Large-Deformation Registration with Differentiable Convex-Discrete Optimisation
- 9 July 2022
- Published by Springer Nature
- p. 119-123
Learn to Fuse Input Features for Large-Deformation Registration with Differentiable Convex-Discrete Optimisation
- 1 July 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (04) , 044001-10
Learning-based three-dimensional registration with weak bounding box supervision
Purpose: Image registration is the process of aligning images, and it is a fundamental task in medical image analysis. While many tasks in the field of image analysis, such as image segmentation, are handled almost entirely with deep learning and exceed the accuracy of conventional algorithms, currently available deformable image registration methods are often still conventional. Deep learning methods for medical image registration have recently reached the accuracy of conventional algorithms. However, they are often based on a weakly supervised learning scheme using multilabel image segmentations during training. The creation of such detailed annotations is very time-consuming. Approach: We propose a weakly supervised learning scheme for deformable image registration. By calculating the loss function based on only bounding box labels, we are able to train an image registration network for large displacement deformations without using densely labeled images. We evaluate our model on interpatient three-dimensional abdominal CT and MRI images. Results: The results show an improvement of ∼10 % (for CT images) and 20% (for MRI images) in comparison to the unsupervised method. When taking into account the reduced annotation effort, the performance also exceeds the performance of weakly supervised training using detailed image segmentations. Conclusion: We show that the performance of image registration methods can be enhanced with little annotation effort using our proposed method.
- 1 July 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (04) , 044001-10
Learning-based three-dimensional registration with weak bounding box supervision
Purpose: Image registration is the process of aligning images, and it is a fundamental task in medical image analysis. While many tasks in the field of image analysis, such as image segmentation, are handled almost entirely with deep learning and exceed the accuracy of conventional algorithms, currently available deformable image registration methods are often still conventional. Deep learning methods for medical image registration have recently reached the accuracy of conventional algorithms. However, they are often based on a weakly supervised learning scheme using multilabel image segmentations during training. The creation of such detailed annotations is very time-consuming. Approach: We propose a weakly supervised learning scheme for deformable image registration. By calculating the loss function based on only bounding box labels, we are able to train an image registration network for large displacement deformations without using densely labeled images. We evaluate our model on interpatient three-dimensional abdominal CT and MRI images. Results: The results show an improvement of ∼10 % (for CT images) and 20% (for MRI images) in comparison to the unsupervised method. When taking into account the reduced annotation effort, the performance also exceeds the performance of weakly supervised training using detailed image segmentations. Conclusion: We show that the performance of image registration methods can be enhanced with little annotation effort using our proposed method.
- 2 March 2022
- Published by Springer Nature
- p. 174-179
Fast 3D Registration with Accurate Optimisation and Little Learning for Learn2Reg 2021
- 2 March 2022
- Published by Springer Nature
- p. 174-179
Fast 3D Registration with Accurate Optimisation and Little Learning for Learn2Reg 2021
- Open Access
Learning a Metric for Multimodal Medical Image Registration without Supervision Based on Cycle Constraints
Deep learning based medical image registration remains very difficult and often fails to improve over its classical counterparts where comprehensive supervision is not available, in particular for large transformations—including rigid alignment. The use of unsupervised, metric-based registration networks has become popular, but so far no universally applicable similarity metric is available for multimodal medical registration, requiring a trade-off between local contrast-invariant edge features or more global statistical metrics. In this work, we aim to improve over the use of handcrafted metric-based losses. We propose to use synthetic three-way (triangular) cycles that for each pair of images comprise two multimodal transformations to be estimated and one known synthetic monomodal transform. Additionally, we present a robust method for estimating large rigid transformations that is differentiable in end-to-end learning. By minimising the cycle discrepancy and adapting the synthetic transformation to be close to the real geometric difference of the image pairs during training, we successfully tackle intra-patient abdominal CT-MRI registration and reach performance on par with state-of-the-art metric-supervision and classic methods. Cyclic constraints enable the learning of cross-modality features that excel at accurate anatomical alignment of abdominal CT and MRI scans.
Open AccessLearning a Metric for Multimodal Medical Image Registration without Supervision Based on Cycle Constraints
Deep learning based medical image registration remains very difficult and often fails to improve over its classical counterparts where comprehensive supervision is not available, in particular for large transformations—including rigid alignment. The use of unsupervised, metric-based registration networks has become popular, but so far no universally applicable similarity metric is available for multimodal medical registration, requiring a trade-off between local contrast-invariant edge features or more global statistical metrics. In this work, we aim to improve over the use of handcrafted metric-based losses. We propose to use synthetic three-way (triangular) cycles that for each pair of images comprise two multimodal transformations to be estimated and one known synthetic monomodal transform. Additionally, we present a robust method for estimating large rigid transformations that is differentiable in end-to-end learning. By minimising the cycle discrepancy and adapting the synthetic transformation to be close to the real geometric difference of the image pairs during training, we successfully tackle intra-patient abdominal CT-MRI registration and reach performance on par with state-of-the-art metric-supervision and classic methods. Cyclic constraints enable the learning of cross-modality features that excel at accurate anatomical alignment of abdominal CT and MRI scans.
- 20 May 2021
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 119, 103816
Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation
- 20 May 2021
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 119, 103816
Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation
- 27 February 2021
- Published by Springer Nature
- p. 111-116
Evaluating Design Choices for Deep Learning Registration Networks
- 27 February 2021
- Published by Springer Nature
- p. 111-116
Evaluating Design Choices for Deep Learning Registration Networks
- Open Access
Dynamic deformable attention (DDANet) for semantic segmentation
Deep learning based medical image segmentation is an important step within diagnosis, which relies strongly on capturing sufficient spatial context without requiring too complex models that are hard to train with limited labelled data. Training data is in particular scarce for segmenting infection regions of CT images of COVID-19 patients. Attention models help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent criss-cross-attention module aims to approximate global self-attention while remaining memory and time efficient by separating horizontal and vertical selfsimilarity computations. However, capturing attention from all non-local locations can adversely impact the accuracy of semantic segmentation networks. We propose a new Dynamic Deformable Attention Network (DDANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on a deformable criss-cross attention block that learns both attention coefficients and attention offsets in a continuous way. A deep segmentation network (in our case a U-Net [1]) that employs this attention mechanism is able to capture attention from pertinent non-local locations and also improves the performance on semantic segmentation tasks compared to criss-cross attention within a U-Net on a challenging COVID-19 lesion segmentation task. Our validation experiments show that the performance gain of the recursively applied dynamic deformable attention blocks comes from their ability to capture dynamic and precise (wider) attention context. Our DDANet achieves Dice scores of 73.4% and 61.3% for Ground-Glass-Opacity and Consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.9% points compared to a baseline U-Net.
Open AccessDynamic deformable attention (DDANet) for semantic segmentation
Deep learning based medical image segmentation is an important step within diagnosis, which relies strongly on capturing sufficient spatial context without requiring too complex models that are hard to train with limited labelled data. Training data is in particular scarce for segmenting infection regions of CT images of COVID-19 patients. Attention models help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent criss-cross-attention module aims to approximate global self-attention while remaining memory and time efficient by separating horizontal and vertical selfsimilarity computations. However, capturing attention from all non-local locations can adversely impact the accuracy of semantic segmentation networks. We propose a new Dynamic Deformable Attention Network (DDANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on a deformable criss-cross attention block that learns both attention coefficients and attention offsets in a continuous way. A deep segmentation network (in our case a U-Net [1]) that employs this attention mechanism is able to capture attention from pertinent non-local locations and also improves the performance on semantic segmentation tasks compared to criss-cross attention within a U-Net on a challenging COVID-19 lesion segmentation task. Our validation experiments show that the performance gain of the recursively applied dynamic deformable attention blocks comes from their ability to capture dynamic and precise (wider) attention context. Our DDANet achieves Dice scores of 73.4% and 61.3% for Ground-Glass-Opacity and Consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.9% points compared to a baseline U-Net.