Application of Denoising Diffusion Probabilistic Methods in Fetal MRI

Ana Claudia Souza Vidal de Negreiros; Gilson Giraldi; Heron Werner

doi:10.22456/2175-2745.143785

Authors

Ana Claudia Souza Vidal de Negreiros Federal Rural University of the Semi-Arid (UFERSA) https://orcid.org/0000-0002-6003-5876
Gilson Giraldi National Laboratory for Cientific Computing (LNCC)
Heron Werner Pontifícia Universidade Católica of Rio de Janeiro (PUCRJ) https://orcid.org/0000-0002-8620-7293

DOI:

https://doi.org/10.22456/2175-2745.143785

Keywords:

Image Denoising, DDPM-Based Approaches, Medical Area, Fetal MRI

Abstract

Magnetic resonance imaging (MRI) is a common type of medical image acquisition that can also be used to diagnose early diseases. In this sense, fetal MRI is a non-invasive method to generate high-quality fetal volumes and to perform important clinical analysis. However, image denoising is necessary in many situations to ensure accurate evaluations. Thus, approaches such as Denoising Diffusion Probabilistic Methods (DDPM) have emerged and reached great results in this kind of task. In this work, we applied two DDPM-based approaches (an original and an improved one) besides two self-supervised deep models in a fetal MRI dataset. The results showed that, for the used fetal MRI dataset, the improved DDPM, named I-DDPM outperformed the counterparts considering two evaluation metrics for image quality, the Peak Signal-to-Noise Ratio (PSNR) and Root Mean Squared Error (RMSE).

Downloads

Download data is not yet available.

References

HO, J.; JAIN, A.; ABBEEL, P. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, v. 33, p. 6840–6851, 2020.

CHANG, C.-W. et al. High-resolution MRI synthesis using a data-driven framework with denoising diffusion probabilistic modeling. Physics in Medicine & Biology, IOP Publishing, v. 69, n. 4, p. 045001, 2024.

GONG, K. et al. PET image denoising based on denoising diffusion probabilistic model. European Journal of Nuclear Medicine and Molecular Imaging, Springer, v. 51, n. 2, p. 358–368, 2024.

DURRER, A.; CATTIN, P. C.; WOLLEB, J. Denoising diffusion models for inpainting of healthy brain tissue. arXiv preprint, arXiv:2402.17307, 2024.

KIM, J.-Y. et al. Denoising task difficulty-based curriculum for training diffusion models. arXiv preprint, arXiv:2403.10348, 2024.

BROWNE, A. W. et al. Deep learning-assisted imaging methods to facilitate access to ophthalmic telepathology. Ophthalmology Science, Elsevier, v. 4, n. 3, p. 100450, 2024.

ZHANG, M. et al. FetalDiffusion: Pose-controllable 3D fetal MRI synthesis with conditional diffusion model. arXiv preprint, arXiv:2404.00132, 2024.

DASH, D.; KUMAR, M. An ensemble-based stage-prediction machine learning approach for classifying fetal disease. Healthcare Analytics, Elsevier, v. 5, p. 100322, 2024.

UNGUREANU, A. et al. Learning deep architectures for the interpretation of first-trimester fetal echocardiography (LIFE)—a study protocol for developing an automated intelligent decision support system for early fetal echocardiography. BMC Pregnancy and Childbirth, Springer, v. 23, n. 1, p. 20, 2023.

NICHOL, A. Q.; DHARIWAL, P. Improved denoising diffusion probabilistic models. In: PMLR. International Conference on Machine Learning, [S.l.], 2021. p. 8162–8171.

LEHTINEN, J. et al. Noise2Noise: Learning image restoration without clean data. arXiv preprint, arXiv:1803.04189, 2018.

KRULL, A.; BUCHHOLZ, T.-O.; JUG, F. Noise2Void—learning denoising from single noisy images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, [S.l.: s.n.], 2019. p. 2129–2137.

NEGREIROS, A. C. S. V. de et al. Self-supervised image denoising methods: An application in fetal MRI. In: SBC. Anais do XVIII Workshop de Visão Computacional, [S.l.], 2023. p. 137–141.

MÜLLER-FRANZES, G. et al. Diffusion probabilistic versus generative adversarial models to reduce contrast agent dose in breast MRI. European Radiology Experimental, Springer, v. 8, n. 1, p. 53, 2024.

PENG, J. et al. CBCT-based synthetic CT image generation using conditional denoising diffusion probabilistic model. Medical Physics, Wiley Online Library, v. 51, n. 3, p. 1847–1859, 2024.

LYU, X.; REN, X. Microstructure reconstruction of 2D/3D random materials via diffusion-based deep generative models. Scientific Reports, Nature Publishing Group UK London, v. 14, n. 1, p. 5041, 2024.

MUELLER, P. N. Attention-enhanced conditional-diffusion-based data synthesis for data augmentation in machine fault diagnosis. Engineering Applications of Artificial Intelligence, Elsevier, v. 131, p. 107696, 2024.

SUI, J.; WU, Q.; PUN, M.-O. Denoising diffusion probabilistic model with adversarial learning for remote sensing super-resolution. Remote Sensing, MDPI, v. 16, n. 7, p. 1219, 2024.

LI, G. et al. A generic plug & play diffusion-based denoising module for medical image segmentation. Neural Networks, Elsevier, v. 172, p. 106096, 2024.

MYKULA, H. et al. Diffusion models for unsupervised anomaly detection in fetal brain ultrasound. In: SPRINGER. International Workshop on Advances in Simplifying Medical Ultrasound, [S.l.], 2024. p. 220–230.

KHMAG, A. Additive Gaussian noise removal based on generative adversarial network model and semi-soft thresholding approach. Multimedia Tools and Applications, Springer, v. 82, n. 5, p. 7757–7777, 2023.

KINGMA, D. P. Auto-Encoding Variational Bayes. arXiv preprint, arXiv:1312.6114, 2013.

PASZKE, A. et al. PyTorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, v. 32, 2019.

ABADI, M. et al. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint, arXiv:1603.04467, 2016.

KETKAR, N. Introduction to Keras. [S.l.]: Springer, 2017.

KINGMA, D. P. Adam: A method for stochastic optimization. arXiv preprint, arXiv:1412.6980, 2014.

SHAH, A. et al. Comparative analysis of median filter and its variants for removal of impulse noise from grayscale images. Journal of King Saud University - Computer and Information Sciences, Elsevier, v. 34, n. 3, p. 505–519, 2022.