nn-UNet Training on CycleGAN-Translated Images for Cross-modal Domain Adaptation in Biomedical Imaging

Joshi, Smriti; Osuala, Richard; Martín-Isla, Carlos; Campello, Víctor M.; Sendra-Balcells, Carla; Lekadir, Karim; Escalera, Sérgio

doi:10.1007/978-3-031-09002-8_47

Cited by 4 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…85 For downstream task evaluation, we generally note the importance of avoiding data leakage between training, validation, and test sets by training the The approaches displayed in Table 6 represent the application, where synthetic data is used instead of real data to train downstream task models. Despite an observable performance decrease when training on synthetic data only, the results 51,91,92 demonstrate the usefulness of synthetic data if none or only limited real training data is available or shareable. For example, if labels or annotations in a target domain are scarce but present in a source domain, a generative model can translate annotated data from the source domain to the target domain to enable supervised training of downstream task models.…”

Section: Improving Clinical Medical Image Analysismentioning

confidence: 88%

“…For example, if labels or annotations in a target domain are scarce but present in a source domain, a generative model can translate annotated data from the source domain to the target domain to enable supervised training of downstream task models. 92,93 5 Discussion and Future Work…”

Section: Improving Clinical Medical Image Analysismentioning

confidence: 99%

“…We would like to thank all model contributors, such as Alyafi et al., 11 Szafranowska et al., 14 Thambawita et al., 51 Kim et al., 84 Segal et al., 91 Joshi et al., 92 and Garrucho et al. 50 This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreements No.…”

Section: Acknowledgmentsmentioning

confidence: 99%

See 2 more Smart Citations

medigan: a Python library of pretrained generative models for medical image synthesis

et al. 2023

Self Cite

View full text Add to dashboard Cite

Purpose: Deep learning has shown great promise as the backbone of clinical decision support systems. Synthetic data generated by generative models can enhance the performance and capabilities of data-hungry deep learning models. However, there is (1) limited availability of (synthetic) datasets and (2) generative models are complex to train, which hinders their adoption in research and clinical applications. To reduce this entry barrier, we explore generative model sharing to allow more researchers to access, generate, and benefit from synthetic data.Approach: We propose medigan, a one-stop shop for pretrained generative models implemented as an open-source framework-agnostic Python library. After gathering end-user requirements, design decisions based on usability, technical feasibility, and scalability are formulated. Subsequently, we implement medigan based on modular components for generative model (i) execution, (ii) visualization, (iii) search & ranking, and (iv) contribution. We integrate pretrained models with applications across modalities such as mammography, endoscopy, x-ray, and MRI. Results:The scalability and design of the library are demonstrated by its growing number of integrated and readily-usable pretrained generative models, which include 21 models utilizing nine different generative adversarial network architectures trained on 11 different datasets. We further analyze three medigan applications, which include (a) enabling community-wide sharing of restricted data, (b) investigating generative model evaluation metrics, and (c) improving clinical downstream tasks. In (b), we extract Fréchet inception distances (FID) demonstrating FID variability based on image normalization and radiology-specific feature extractors.Conclusion: medigan allows researchers and developers to create, increase, and domain-adapt their training data in just a few lines of code. Capable of enriching and accelerating the development of clinical machine learning models, we show medigan's viability as platform for generative model sharing. Our multimodel synthetic data experiments uncover standards for assessing and reporting metrics, such as FID, in image synthesis studies.

show abstract

Section: Improving Clinical Medical Image Analysismentioning

confidence: 88%

Section: Improving Clinical Medical Image Analysismentioning

confidence: 99%

See 1 more Smart Citation

medigan: a Python library of pretrained generative models for medical image synthesis

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…[4] used a register to generate the conditional signal). Some other GANs-based cross-modality data translation methods use cycle consistency training to swap the features between different domains [52,29,21,50].…”

Section: Related Workmentioning

confidence: 99%

Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion

Wang¹,

Yingyu²,

Sermesant³

et al. 2023

Preprint

View full text Add to dashboard Cite

Cross-modality data translation has attracted great interest in image computing. Deep generative models (e.g., GANs) show performance improvement in tackling those problems. Nevertheless, as a fundamental challenge in image translation, the problem of Zero-shot-Learning Cross-Modality Data Translation with fidelity remains unanswered. This paper proposes a new unsupervised zero-shot-learning method named Mutual Information guided Diffusion cross-modality data translation Model (MIDiffusion), which learns to translate the unseen source data to the target domain. The MIDiffusion leverages a score-matching-based generative model, which learns the prior knowledge in the target domain. We propose a differentiable local-wise-MI-Layer (LM I) for conditioning the iterative denoising sampling. The LM I captures the identical cross-modality features in the statistical domain for the diffusion guidance; thus, our method does not require retraining when the source domain is changed, as it does not rely on any direct mapping between the source and target domains. This advantage is critical for applying cross-modality data translation methods in practice, as a reasonable amount of source domain dataset is not always available for supervised training. We empirically show the advanced performance of MIDiffusion in comparison with an influential group of generative models, including adversarial-based and other scorematching-based models.

show abstract

BrainDAS: Structure-aware domain adaptation network for multi-site brain network analysis

Song,

Cao,

Wen

et al. 2024

Medical Image Analysis

View full text Add to dashboard Cite

nn-UNet Training on CycleGAN-Translated Images for Cross-modal Domain Adaptation in Biomedical Imaging

Cited by 4 publications

References 16 publications

medigan: a Python library of pretrained generative models for medical image synthesis

medigan: a Python library of pretrained generative models for medical image synthesis

Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion

BrainDAS: Structure-aware domain adaptation network for multi-site brain network analysis

Contact Info

Product

Resources

About