Direct image-based attenuation correction using conditional generative adversarial network for SPECT myocardial perfusion imaging

Torkaman, Mahsa; Yang, Jaewon; Shi, Luyao; Wang, Rui; Miller, Edward J.; Sinusas, Albert J.; Liu, Chi; Gullberg, Grant T.; Seo, Youngho

doi:10.1117/12.2580922

Cited by 11 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the superiority of U‐NetAC over AutoencoderAC was suggested in these brain regions, the small percentage error suggests that these differences would unlikely affect the clinical diagnosis. The possibility of direct AC from NAC images of the trunk has been reported for whole‐body PET 34,35 and myocardial‐perfusion SPECT 23,25 . The application of AC in the trunk should be the focus of future research.…”

Section: Discussionmentioning

confidence: 97%

“…However, because attenuation map generation requires cross‐modality transformation, one must be aware of potential pitfalls such as misalignment between subjects, field‐of‐view differences between modalities, modality‐specific artifacts, positional differences, and organ displacement during the scan 22 . For myocardial‐perfusion SPECT 23–25 and brain PET, 26 there have been reports of AC images being generated directly from NAC images. These studies were able to achieve highly accurate AC using GAN and CNN‐based networks, and thus suggested that accurate AC could be achieved using deep learning without the need for generating an attenuation map.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of attenuation correction methods using deep learning in brain‐perfusion single‐photon emission computed tomography

et al. 2021

View full text Add to dashboard Cite

Purpose Computed tomography (CT)‐based attenuation correction (CTAC) in single‐photon emission computed tomography (SPECT) is highly accurate, but it requires hybrid SPECT/CT instruments and additional radiation exposure. To obtain attenuation correction (AC) without the need for additional CT images, a deep learning method was used to generate pseudo‐CT images has previously been reported, but it is limited because of cross‐modality transformation, resulting in misalignment and modality‐specific artifacts. This study aimed to develop a deep learning‐based approach using non‐attenuation‐corrected (NAC) images and CTAC‐based images for training to yield AC images in brain‐perfusion SPECT. This study also investigated whether the proposed approach is superior to conventional Chang’s AC (ChangAC). Methods In total, 236 patients who underwent brain‐perfusion SPECT were randomly divided into two groups: the training group (189 patients; 80%) and the test group (47 patients; 20%). Two models were constructed using Autoencoder (AutoencoderAC) and U‐Net (U‐NetAC), respectively. ChangAC, AutoencoderAC, and U‐NetAC approaches were compared with CTAC using qualitative analysis (visual evaluation) and quantitative analysis (normalized mean squared error [NMSE] and the percentage error in each brain region). Statistical analyses were performed using the Wilcoxon signed‐rank sum test and Bland‐Altman analysis. Results U‐NetAC had the highest visual evaluation score. The NMSE results for the U‐NetAC were the lowest, followed by AutoencoderAC and ChangAC (P < 0.001). Bland‐Altman analysis showed a fixed bias for ChangAC and AutoencoderAC and a proportional bias for ChangAC. ChangAC underestimated counts by 30–40% in all brain regions. AutoencoderAC and U‐NetAC produced mean errors of <1% and maximum errors of 3%, respectively. Conclusion New deep learning‐based AC methods for AutoencoderAC and U‐NetAC were developed. Their accuracy was higher than that obtained by ChangAC. U‐NetAC exhibited higher qualitative and quantitative accuracy than AutoencoderAC. We generated highly accurate AC images directly from NAC images without the need for intermediate pseudo‐CT images. To verify our models’ generalizability, external validation is required.

show abstract

Section: Discussionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Development of attenuation correction methods using deep learning in brain‐perfusion single‐photon emission computed tomography

et al. 2021

View full text Add to dashboard Cite

show abstract

“…End-to-end methods might be valid alternatives for SPECT AC alternative to the CNN μ-map estimation approach proposed in this study. Such methods as proposed in Yang et al (2019), ( 2020), ( 2021), Dong et al (2020), Torkaman et al (2021) directly generate attenuation corrected SPECT/PET images as output, and thus eliminate the procedure of performing an AC using the μ-map. We opted for a two-step strategy with an intermediate μ-map estimation step as it is less of a black box compared to the end-to-end approach.…”

Section: Discussionmentioning

confidence: 99%

Convolutional neural network based attenuation correction for ¹²³I-FP-CIT SPECT with focused striatum imaging

2021

View full text Add to dashboard Cite

SPECT imaging with 123 I-FP-CIT is used for diagnosis of neurodegenerative disorders like Parkinson's disease. Attenuation correction (AC) can be useful for quantitative analysis of 123 I-FP-CIT SPECT. Ideally, AC would be performed based on attenuation maps (m-maps) derived from perfectly registered CT scans. Such m-maps, however, are most times not available and possible errors in image registration can induce quantitative inaccuracies in AC corrected SPECT images. Earlier, we showed that a convolutional neural network (CNN) based approach allows to estimate SPECT-aligned m-maps for full brain perfusion imaging using only emission data. Here we investigate the feasibility of similar CNN methods for axially focused 123 I-FP-CIT scans. We tested our approach on a highresolution multi-pinhole prototype clinical SPECT system in a Monte Carlo simulation study. Three CNNs that estimate m-maps in a voxel-wise, patch-wise and image-wise manner were investigated. As the added value of AC on clinical 123 I-FP-CIT scans is still debatable, the impact of AC was also reported to check in which cases CNN based AC could be beneficial. AC using the ground truth m-maps (GT-AC) and CNN estimated m-maps (CNN-AC) were compared with the case when no AC was done (No-AC). Results show that the effect of using GT-AC versus CNN-AC or No-AC on striatal shape and symmetry is minimal. Specific binding ratios (SBRs) from localized regions show a deviation from GT-AC  2.5% for all three CNN-ACs while No-AC systematically underestimates SBRs by 13.1%. A strong correlation (  r 0.99) was obtained between GT-AC based SBRs and SBRs from CNN-ACs and No-AC. Absolute quantification (in kBq ml −1 ) shows a deviation from GT-AC within 2.2% for all three CNN-ACs and of 71.7% for No-AC. To conclude, all three CNNs show comparable performance in accurate m-map estimation and 123 I-FP-CIT quantification. CNNestimated m-map can be a promising substitute for CT-based m-map.

show abstract

“…Thus, it is important to validate the robustness of DL models to new incoming data toward clinical translation. Previously, we investigated the feasibility of using a DL approach for SPECT AC in the image domain and demonstrated the potential clinical values of the proposed method in the stand-alone SPECT systems that occupy 80% of the current market share [8], [9]. Incorporating the DL-based AC into clinical practice can improve the diagnostic accuracy of MPIs by eliminating the attenuation artifacts [3], [40] and also reduce the radiation dose from CT, which can benefit pediatric patients who are more at risk of radiation [41].…”

Section: ) Similarity Of Data Distribution Between the Test And Thementioning

confidence: 99%

“…Therefore, correcting the attenuation without generating the attenuation maps as an intermediate step is important, especially in stand-alone SPECT systems. As we demonstrated in our previous study, it is feasible to use a deep learning approach to correct the attenuation in the image domain by using only noncorrected SPECT images, which is distinct from conventional approaches using CT data or generating pseudo-CT data as an intermediate step [9]. Recently, deep learning has become an active area of research in different medical imaging applications because of its unprecedented success in various computer vision tasks [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Data Management and Network Architecture Effect on Performance Variability in Direct Attenuation Correction via Deep Learning for Cardiac SPECT: A Feasibility Study

Torkaman¹,

Yang²,

Shi

et al. 2022

IEEE Trans. Radiat. Plasma Med. Sci.

Self Cite

View full text Add to dashboard Cite

Attenuation correction (AC) is important for the accurate interpretation of single-photon computed tomography (SPECT) myocardial perfusion imaging (MPI). However, it is challenging to perform AC in dedicated cardiac systems not equipped with a transmission imaging capability. Previously, we demonstrated the feasibility of generating attenuation-corrected SPECT images using a deep learning technique (SPECT DL ) directly from noncorrected images (SPECT NC ). However, we observed performance variability across patients which is an important factor for clinical translation of the technique. In this study, we investigate the feasibility of overcoming the performance variability across patients for the direct AC in SPECT MPI by proposing to develop an advanced network and a data management strategy. To investigate, we compared the accuracy of the SPECT DL for the conventional U-Net and Wasserstein cycle generative adversarial networks (WCycleGANs). To manage the training data, clustering was applied to a representation of data in the lower dimensional space, and the training data were chosen based on the similarity of data in this space. Quantitative analysis demonstrated that the DL model with an advanced network improves the global performance for the AC task with the limited data. However, the regional results were not improved. The proposed data management strategy demonstrated that the clustered training has a potential benefit for effective training.

show abstract

Direct image-based attenuation correction using conditional generative adversarial network for SPECT myocardial perfusion imaging

Cited by 11 publications

References 0 publications

Development of attenuation correction methods using deep learning in brain‐perfusion single‐photon emission computed tomography

Development of attenuation correction methods using deep learning in brain‐perfusion single‐photon emission computed tomography

Convolutional neural network based attenuation correction for ¹²³I-FP-CIT SPECT with focused striatum imaging

Data Management and Network Architecture Effect on Performance Variability in Direct Attenuation Correction via Deep Learning for Cardiac SPECT: A Feasibility Study

Contact Info

Product

Resources

About

Direct image-based attenuation correction using conditional generative adversarial network for SPECT myocardial perfusion imaging

Cited by 11 publications

References 0 publications

Development of attenuation correction methods using deep learning in brain‐perfusion single‐photon emission computed tomography

Development of attenuation correction methods using deep learning in brain‐perfusion single‐photon emission computed tomography

Convolutional neural network based attenuation correction for 123I-FP-CIT SPECT with focused striatum imaging

Data Management and Network Architecture Effect on Performance Variability in Direct Attenuation Correction via Deep Learning for Cardiac SPECT: A Feasibility Study

Contact Info

Product

Resources

About

Convolutional neural network based attenuation correction for ¹²³I-FP-CIT SPECT with focused striatum imaging