Posterior temperature optimized Bayesian models for inverse problems in medical imaging

Laves, Max-Heinrich; Tölle, Malte; Schlaefer, Alexander; Engelhardt, Sandy

doi:10.1016/j.media.2022.102382

Cited by 5 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the current study, POTOBIM, an unsupervised approach of Bayesian CNNs, was applied as a new method to counter the problem described above. As already shown in the study of Laves et al [ 24 ], POTOBIM is a method that shows a lower reconstruction error in the region of interest compared to other unsupervised methods aiming to prevent hallucinations during reconstruction.…”

Section: Discussionmentioning

confidence: 87%

“…Sparse-view CT slices were then reconstructed from the simulated sinograms using POTOBIM and FBP with a Shepp–Logan filter. For the former, configurations for temperature candidates and iteration cycles were used as suggested by Laves et al [ 24 ] for the task of sparse-view CT reconstruction.…”

Section: Methodsmentioning

confidence: 99%

“…Consequently, a Bayesian neural network (BNN) approach to DIP has been considered to automate the prevention of overfitting [ 22 , 23 ]. Outperforming previous approaches, Posterior Temperature Optimized Bayesian Inverse Models (POTOBIM) have recently shown the most successful application of Bayesian DIP in the context of sparse-view reconstruction [ 24 ]. However, a clinical test of its applicability in routine CT scans has not yet been investigated.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bayesian Reconstruction Algorithms for Low-Dose Computed Tomography Are Not Yet Suitable in Clinical Context

Kniep,

Mieling,

Gerling

et al. 2023

J. Imaging

Self Cite

View full text Add to dashboard Cite

Computed tomography (CT) is a widely used examination technique that usually requires a compromise between image quality and radiation exposure. Reconstruction algorithms aim to reduce radiation exposure while maintaining comparable image quality. Recently, unsupervised deep learning methods have been proposed for this purpose. In this study, a promising sparse-view reconstruction method (posterior temperature optimized Bayesian inverse model; POTOBIM) is tested for its clinical applicability. For this study, 17 whole-body CTs of deceased were performed. In addition to POTOBIM, reconstruction was performed using filtered back projection (FBP). An evaluation was conducted by simulating sinograms and comparing the reconstruction with the original CT slice for each case. A quantitative analysis was performed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). The quality was assessed visually using a modified Ludewig’s scale. In the qualitative evaluation, POTOBIM was rated worse than the reference images in most cases. A partially equivalent image quality could only be achieved with 80 projections per rotation. Quantitatively, POTOBIM does not seem to benefit from more than 60 projections. Although deep learning methods seem suitable to produce better image quality, the investigated algorithm (POTOBIM) is not yet suitable for clinical routine.

show abstract

Section: Discussionmentioning

confidence: 87%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian Reconstruction Algorithms for Low-Dose Computed Tomography Are Not Yet Suitable in Clinical Context

Kniep,

Mieling,

Gerling

et al. 2023

J. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…The relevant research of Bayesian theory begins to grow in a blowout mode at the beginning of the 21st century. Meanwhile, Bayesian theory is also widely applied in finance, 98 medical, 99,100 marketing, 101 transportation, 102 and many other fields. Bayesian theory can make full use of the damage information of the structures, speed up the evaluation process and improve the evaluation efficiency.…”

Section: Structure Health Monitoring Of Offshore Jacket Structuresmentioning

confidence: 99%

Condition-based structural health monitoring of offshore wind jacket structures: Opportunities, challenges, and perspectives

Leng

Gardoni

Wang

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

Structural health monitoring (SHM) has been recognized as a useful tool for safety management and risk reduction of offshore wind farms. In complex offshore environment, jacket structures of offshore wind turbines are prone to damages due to corrosion and fatigue. Effective SHM on jacket structures can substantially reduce their operation risk and costs. This work reviews the latest progress on the SHM of offshore wind jacket structures. The achievements in the structural damage identification, location, quantification, and remaining useful life (RUL) estimation are respectively introduced in detail, and existing challenges are discussed. Possible solutions to the challenges using the Digital Twin (DT) technology are put forward. The DT is able to mirror a real jacket structure into a virtual model, and Bayesian updating can refresh the virtual model parameters in real-time to keep consistency between virtual model and physical structure; then, just-in-time SHM can be carried out for jacket structures by performing damage detection, location, quantification, and RUL estimation using the virtual model. As a result, the DT may provide engineers and researchers a practicable tool for safety monitoring and risk reduction of fixed foundation offshore wind structures.

show abstract

“…erefore, the proposed method can be well applied to deep neural network models that are optimized based on training data. In addition, the proposed method can be applied not only to deep neural networks but also to support vector machines [27] and Bayesian models [28] that predict based on training data.…”

Section: Target Modelmentioning

confidence: 99%

Toward Backdoor Attacks for Image Captioning Model in Deep Neural Networks

Kwon

Lee

2022

Security and Communication Networks

View full text Add to dashboard Cite

Deep neural networks perform well in image recognition, speech recognition, and text recognition fields. The image caption model provides captions for images by generating text after image recognition. After extracting features from the original image, this model generates a representation vector and provides captions for the image by generating text through a recursive neural network. However, this image caption model has weaknesses in the backdoor sample. In this paper, we propose a method for generating backdoor samples for image caption models. By adding a specific trigger to the original sample, this proposed method creates a backdoor sample that is misrecognized as a target class by the target model. The MS-COCO dataset was used as the experimental dataset, and Tensorflow was used as the machine learning library. When the trigger size of the backdoor sample is 4%, experimental results show that the average attack success rate of the backdoor sample is 96.67%, and the average error rate of the original sample is 9.65%.

show abstract

Posterior temperature optimized Bayesian models for inverse problems in medical imaging

Cited by 5 publications

References 29 publications

Bayesian Reconstruction Algorithms for Low-Dose Computed Tomography Are Not Yet Suitable in Clinical Context

Bayesian Reconstruction Algorithms for Low-Dose Computed Tomography Are Not Yet Suitable in Clinical Context

Condition-based structural health monitoring of offshore wind jacket structures: Opportunities, challenges, and perspectives

Toward Backdoor Attacks for Image Captioning Model in Deep Neural Networks

Contact Info

Product

Resources

About