Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECT

Sun, Jingzhang; Jiang, Han; Du, Yu; Li, Chien-Ying; Wu, Tsu‐Juey; Liu, Yi-Hwa; Yang, Baofeng; Mok, Greta S. P.

doi:10.1007/s12350-022-03045-x

Cited by 19 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Post-processing-based denoising used in this work is not the only DL denoising option available. Sun et al [ 20 ] compared pre-reconstruction and post-reconstruction denoising. They used cGAN-type denoising model and noticed that pre-reconstruction-based denoising outperformed post-reconstruction denoising in terms of image quality of mathematical phantoms.…”

Section: Discussionmentioning

confidence: 99%

Comparison of deep learning-based denoising methods in cardiac SPECT

et al. 2023

View full text Add to dashboard Cite

Background Myocardial perfusion SPECT (MPS) images often suffer from artefacts caused by low-count statistics. Poor-quality images can lead to misinterpretations of perfusion defects. Deep learning (DL)-based methods have been proposed to overcome the noise artefacts. The aim of this study was to investigate the differences among several DL denoising models. Methods Convolution neural network (CNN), residual neural network (RES), UNET and conditional generative adversarial neural network (cGAN) were generated and trained using ordered subsets expectation maximization (OSEM) reconstructed MPS studies acquired with full, half, three-eighths and quarter acquisition time. All DL methods were compared against each other and also against images without DL-based denoising. Comparisons were made using half and quarter time acquisition data. The methods were evaluated in terms of noise level (coefficient of variation of counts, CoV), structural similarity index measure (SSIM) in the myocardium of normal patients and receiver operating characteristic (ROC) analysis of realistic artificial perfusion defects inserted into normal MPS scans. Total perfusion deficit scores were used as observer rating for the presence of a perfusion defect. Results All the DL denoising methods tested provided statistically significantly lower noise level than OSEM without DL-based denoising with the same acquisition time. CoV of the myocardium counts with the different DL noising methods was on average 7% (CNN), 8% (RES), 7% (UNET) and 14% (cGAN) lower than with OSEM. All DL methods also outperformed full time OSEM without DL-based denoising in terms of noise level with both half and quarter acquisition time, but this difference was not statistically significant. cGAN had the lowest CoV of the DL methods at all noise levels. Image quality and polar map uniformity of DL-denoised images were also better than reduced acquisition time OSEM’s. SSIM of the reduced acquisition time OSEM was overall higher than with the DL methods. The defect detection performance of full time OSEM measured as area under the ROC curve (AUC) was on average 0.97. Half time OSEM, CNN, RES and UNET provided equal or nearly equal AUC. However, with quarter time data CNN, RES and UNET had an average AUC of 0.93, which was lower than full time OSEM’s AUC, but equal to quarter acquisition time OSEM. cGAN did not achieve the defect detection performance of the other DL methods. Its average AUC with half time data was 0.94 and 0.91 with quarter time data. Conclusions DL-based denoising effectively improved noise level with slightly lower perfusion defect detection performance than full time reconstruction. cGAN achieved the lowest noise level, but at the same time the poorest defect detection performance among the studied DL methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of deep learning-based denoising methods in cardiac SPECT

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The decoding layers mirrored the encoding layers, except the up-sample layers replaced the down-sample layers, and skip connection between the encoding and decoding layers was added. The discriminator was a CNN-based network used in our previous study (19).…”

Section: Attention-guided Generative Adversarial Network (Attgan)mentioning

confidence: 99%

“…The L 1 loss (26) and the adversarial loss L ADV were used for training the generator g. The discriminator was trained by a crossentropy loss L D (19). The final objective function of AttGAN was:…”

Section: Attention-guided Generative Adversarial Network (Attgan)mentioning

confidence: 99%

“…The AttGAN was trained by minimizing the loss. The Unet and cGAN structures were the same according to our previous studies (18,19).…”

Section: Attention-guided Generative Adversarial Network (Attgan)mentioning

confidence: 99%

“…Shiri et al (17) proposed a 2D residual CNN (ResNet) to estimate full time (FT) MP-SPECT projection images. Previously, our group implemented a 3D cGAN to denoise fast and low dose MP-SPECT reconstruction (18) and projection (19) images. Our results showed that denoising on the projection domain is superior to the reconstruction domain (19).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast myocardial perfusion SPECT denoising using an attention-guided generative adversarial network

Sun

Yang²,

Li³

et al. 2023

Front. Med.

Self Cite

View full text Add to dashboard Cite

PurposeDeep learning-based denoising is promising for myocardial perfusion (MP) SPECT. However, conventional convolutional neural network (CNN)-based methods use fixed-sized convolutional kernels to convolute one region within the receptive field at a time, which would be ineffective for learning the feature dependencies across large regions. The attention mechanism (Att) is able to learn the relationships between the local receptive field and other voxels in the image. In this study, we propose a 3D attention-guided generative adversarial network (AttGAN) for denoising fast MP-SPECT images.MethodsFifty patients who underwent 1184 MBq 99mTc-sestamibi stress SPECT/CT scan were retrospectively recruited. Sixty projections were acquired over 180° and the acquisition time was 10 s/view for the full time (FT) mode. Fast MP-SPECT projection images (1 s to 7 s) were generated from the FT list mode data. We further incorporated binary patient defect information (0 = without defect, 1 = with defect) into AttGAN (AttGAN-def). AttGAN, AttGAN-def, cGAN, and Unet were implemented using Tensorflow with the Adam optimizer running up to 400 epochs. FT and fast MP-SPECT projection pairs of 35 patients were used for training the networks for each acquisition time, while 5 and 10 patients were applied for validation and testing. Five-fold cross-validation was performed and data for all 50 patients were tested. Voxel-based error indices, joint histogram, linear regression, and perfusion defect size (PDS) were analyzed.ResultsAll quantitative indices of AttGAN-based networks are superior to cGAN and Unet on all acquisition time images. AttGAN-def further improves AttGAN performance. The mean absolute error of PDS by AttcGAN-def was 1.60 on acquisition time of 1 s/prj, as compared to 2.36, 2.76, and 3.02 by AttGAN, cGAN, and Unet.ConclusionDenoising based on AttGAN is superior to conventional CNN-based networks for MP-SPECT.

show abstract