Leveraging deep neural networks to improve numerical and perceptual image quality in low-dose preclinical PET imaging

Amirrashedi, Mahsa; Sarkar, Saeed; Mami-Zadeh, H.; Ghadiri, Hossein; Ghafarian, Pardis; Zaidi, Habib; Ay, Mohammad Reza

doi:10.1016/j.compmedimag.2021.102010

Cited by 6 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the clinic, DL denoising techniques have increasingly gained in popularity thanks to their promising potential to improve image quality with clear bene ts for dose reduction. However, there has been very little effort to translate such frameworks to the preclinical imaging eld [14,15].…”

Section: Discussionmentioning

confidence: 99%

“…For early, very short (2-10s) frames during fast dynamic studies, or for imaging studies with short-lived isotopes (e.g. 15 O, 11 C, 82 Rb) which decay very fast during scanning, or with long-lived isotopes (e.g. 89 Zr) which exhibit low positron fraction, even higher noise levels of varying textures will corrupt the data.…”

Section: Discussionmentioning

confidence: 99%

“…However, while there are clear driving factors for low dose imaging in preclinical set-ups, the incentive for DL-based denoising of low-count micro-PET has been lacking compared to the extensive research efforts spent on clinical low dose PET. To our knowledge, only two previous studies have investigated the use of DL for denoising low dose micro-PET data [14,15], and both studies showed that the DL approach achieved lower bias in 18 F-FDG quanti cation than non-DL denoising techniques, but they did not consider cross-tracer applicability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image Denoising of Low Dose PET Mouse Scans with Deep Learning: Validation Study for Cross-Tracer Preclinical Imaging Applicability

Muller

Vervenne

Maebe

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose: Positron Emission Tomography (PET) image quality can be improved by higher injected activity and/or longer acquisition time, but both may often not be practical in preclinical imaging. Common preclinical radioactive doses (10 MBq) have been shown to cause deterministic changes in biological pathways. Reducing the injected tracer activity and/or shortening the scan time inevitably results in low-count acquisitions which poses a challenge because of the inherent noise introduction. We present an image-based deep learning (DL) framework for denoising lower count micro-PET images. Procedures: For 36 mice, a 15-min 18F-FDG (8.15 ± 1.34 MBq) PET scan was acquired at 40 min post-injection on the Molecubes b-CUBE (in list mode). The 15-min acquisition (high-count) was parsed into smaller time fractions of 7.50, 3.75, 1.50 and 0.75 mins to emulate images reconstructed at 50, 25, 10 and 5% of the full counts, respectively. A 2D U-Net was trained with mean-squared-error loss on 28 high-low count image pairs. Results: The DL algorithms were visually and quantitatively compared to spatial and edge-preserving denoising filters; the DL-based methods effectively removed image noise and recovered image details much better while keeping quantitative (SUV) accuracy. The largest improvement in image quality was seen in the images reconstructed with 10 and 5% of the counts (equivalent to sub-1-MBq or sub-1-min mouse imaging). The DL-based denoising framework was also successfully applied on the NEMA-NU4 phantom and different tracer studies (18F-PSMA, 18F-FAPI and 68Ga-FAPI). Conclusion: Visual and quantitative results support the superior performance and robustness in image denoising of the implemented DL models for low statistics micro-PET. This offers tremendous flexibility in optimizing scan protocols with reduced tracer doses or shorter durations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image Denoising of Low Dose PET Mouse Scans with Deep Learning: Validation Study for Cross-Tracer Preclinical Imaging Applicability

Muller

Vervenne

Maebe

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Most of these studies are concentrated on clinical PET images, and have solved many problems related to PET imaging such as image reconstruction, 32,33 image denoising, 34–36 PET attenuation correction, 37–39 PET image quality, 40 and so forth. Very few studies have been conducted on preclinical PET imaging using DL methods 41,42 . Compared with clinical PET systems, preclinical PET systems have several advantages, including high spatial resolution, high sensitivity, and lower scattering and attenuation issues due to the smaller size of the objects being imaged.…”

Section: Introductionmentioning

confidence: 99%

“…Very few studies have been conducted on preclinical PET imaging using DL methods. 41,42 Compared with clinical PET systems, preclinical PET systems have several advantages, including high spatial resolution, high sensitivity, and lower scattering and attenuation issues due to the smaller size of the objects being imaged. Images acquired with clinical PET usually exhibit different noise profiles from those obtained with preclinical PET.…”

Section: Introductionmentioning

confidence: 99%

Utilizing deep learning techniques to improve image quality and noise reduction in preclinical low‐dose PET images in the sinogram domain

Manoj Doss,

Chen

2023

Medical Physics

View full text Add to dashboard Cite

BackgroundLow‐dose positron emission tomography (LD‐PET) imaging is commonly employed in preclinical research to minimize radiation exposure to animal subjects. However, LD‐PET images often exhibit poor quality and high noise levels due to the low signal‐to‐noise ratio. Deep learning (DL) techniques such as generative adversarial networks (GANs) and convolutional neural network (CNN) have the capability to enhance the quality of images derived from noisy or low‐quality PET data, which encodes critical information about radioactivity distribution in the body.PurposeOur objective was to optimize the image quality and reduce noise in preclinical PET images by utilizing the sinogram domain as input for DL models, resulting in improved image quality as compared to LD‐PET images.MethodsA GAN and CNN model were utilized to predict high‐dose (HD) preclinical PET sinograms from the corresponding LD preclinical PET sinograms. In order to generate the datasets, experiments were conducted on micro‐phantoms, animal subjects (rats), and virtual simulations. The quality of DL‐generated images was weighted by performing the following quantitative measures: structural similarity index measure (SSIM), root mean squared error (RMSE), peak signal‐to‐noise ratio (PSNR), signal‐to‐noise ratio (SNR), and contrast‐to‐noise ratio (CNR). Additionally, DL input and output were both subjected to a spatial resolution calculation of full width half maximum (FWHM) and full width tenth maximum (FWTM). DL outcomes were then compared with the conventional denoising algorithms such as non‐local means (NLM), block‐matching, and 3D filtering (BM3D).ResultsThe DL models effectively learned image features and produced high‐quality images, as reflected in the quantitative metrics. Notably, the FWHM and FWTM values of DL PET images exhibited significantly improved accuracy compared to LD, NLM, and BM3D PET images, and just as precise as HD PET images. The MSE loss underscored the excellent performance of the models, indicating that the models performed well. To further improve the training, the generator loss (G loss) was increased to a value higher than the discriminator loss (D loss), thereby achieving convergence in the GAN model.ConclusionsThe sinograms generated by the GAN network closely resembled real HD preclinical PET sinograms and were more realistic than LD. There was a noticeable improvement in image quality and noise factor in the predicted HD images. Importantly, DL networks did not fully compromise the spatial resolution of the images.

show abstract

Image Denoising of Low-Dose PET Mouse Scans with Deep Learning: Validation Study for Preclinical Imaging Applicability

Muller,

Vervenne,

Maebe

et al. 2023

Mol Imaging Biol

View full text Add to dashboard Cite

Leveraging deep neural networks to improve numerical and perceptual image quality in low-dose preclinical PET imaging

Cited by 6 publications

References 45 publications

Image Denoising of Low Dose PET Mouse Scans with Deep Learning: Validation Study for Cross-Tracer Preclinical Imaging Applicability

Image Denoising of Low Dose PET Mouse Scans with Deep Learning: Validation Study for Cross-Tracer Preclinical Imaging Applicability

Utilizing deep learning techniques to improve image quality and noise reduction in preclinical low‐dose PET images in the sinogram domain

Image Denoising of Low-Dose PET Mouse Scans with Deep Learning: Validation Study for Preclinical Imaging Applicability

Contact Info

Product

Resources

About