Attenuation correction for brain PET imaging using deep neural network based on Dixon and ZTE MR images

Gong, Kuang; Yang, Jaewon; Kim, Kyungsang; Fakhri, Georges El; Seo, Youngho; Li, Quanzheng

doi:10.1088/1361-6560/aac763

Cited by 96 publications

(103 citation statements)

References 52 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The fuzzy c-means clustering method implemented on UTE MR sequences by Su et al [39] resulted in a MAE of 130 HU whereas the multiatlas method developed by Burgos et al [13] produced a MAE of 102 HU on 17 head and neck studies in the context of radiotherapy planning. The deep neural network based on Dixon and ZTE MR images built by Gong et al [40] achieved a bone extraction accuracy of DSC = 0.76 on 40 clinical studies (vs. DSC = 0.77 achieved by DL-AdvSS). The data-driven deep learning approach for PET AC without anatomical imaging was developed by Liu et al [41] to continuously generate sCT images from uncorrected PET images.…”

Section: Discussionmentioning

confidence: 99%

“…The different observed PET quantification bias might be partly due to different validation strategies. Gong et al [43] reported a mean PET quantification bias up 3% using a convolutional neural network trained with Dixon and ZTE MR sequences. The additional ZTE sequence, providing complementary information about bone tissue, supports the deep learning network to better extract the bony tissue.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI

Arabi

Zeng

Zheng

et al. 2019

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

Objective Quantitative PET/MR imaging is challenged by the accuracy of synthetic CT (sCT) generation from MR images. Deep learning-based algorithms have recently gained momentum for a number of medical image analysis applications. In this work, a novel sCT generation algorithm based on deep learning adversarial semantic structure (DL-AdvSS) is proposed for MRI-guided attenuation correction in brain PET/MRI. Materials and methods The proposed DL-AdvSS algorithm exploits the ASS learning framework to constrain the synthetic CT generation process to comply with the extracted structural features from CT images. The proposed technique was evaluated through comparison to an atlas-based sCT generation method (Atlas), previously developed for MRI-only or PET/MRI-guided radiation planning. Moreover, the commercial segmentation-based approach (Segm) implemented on the Philips TF PET/MRI system was included in the evaluation. Clinical brain studies of 40 patients who underwent PET/CT and MR imaging were used for the evaluation of the proposed method under a twofold cross validation scheme. Results The accuracy of cortical bone extraction and CT value estimation were investigated for the three different methods. Atlas and DL-AdvSS exhibited similar cortical bone extraction accuracy resulting in a Dice coefficient of 0.78 ± 0.07 and 0.77 ± 0.07, respectively. Likewise, DL-AdvSS and Atlas techniques performed similarly in terms of CT value estimation in the cortical bone region where a mean error (ME) of less than −11 HU was obtained. The Segm approach led to a ME of −1025 HU. Furthermore, the quantitative analysis of corresponding PET images using the three approaches assuming the CT-based attenuation corrected PET (PET CTAC) as reference demonstrated comparative performance of DL-AdvSS and Atlas techniques with a mean standardized uptake value (SUV) bias less than 4% in 63 brain regions. In addition, less that 2% SUV bias was observed in the cortical bone when using Atlas and DL-AdvSS approaches. However, Segm resulted in 14.7 ± 8.9% SUV underestimation in the cortical bone. Conclusion The proposed DL-AdvSS approach demonstrated competitive performance with respect to the state-of-the-art atlasbased technique achieving clinically tolerable errors, thus outperforming the commercial segmentation approach used in the clinic.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI

Arabi

Zeng

Zheng

et al. 2019

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

show abstract

“…Santos Ribeiro et al [101] proposed a feed-forward neural network to directly output a continuous-valued head attenuation map by nonlinear regression of several UTE images and a template-based MRAC map. Gong et al [102] used a convolutional neural network with Dixon images only or in a combination of Dixon and ZTE images to generate a continuous valued attenuation map. Similarly, a deep convolutional neural network that derived attenuation maps based on ZTE images was shown to outperform both ZTE and atlas-based method in Blanc-Durand et al [43].…”

Section: Methods Based On Atlas or Database Approaches Including Machmentioning

confidence: 99%

Magnetic Resonance-Based Attenuation Correction and Scatter Correction in Neurological Positron Emission Tomography/Magnetic Resonance Imaging—Current Status With Emerging Applications

Teuho

Torrado‐Carvajal

Herzog³

et al. 2020

Front. Phys.

View full text Add to dashboard Cite

In this review, we will summarize the past and current state-of-the-art developments in attenuation and scatter correction approaches for hybrid positron emission tomography (PET) and magnetic resonance (MR) imaging. The current status of the methodological advances for producing accurate attenuation and scatter corrections on PET/MR systems are described, in addition to emerging clinical and research applications. Future prospects and potential applications that benefit from accurate data corrections to improve the quantitative accuracy and clinical applicability of PET/MR are also discussed. Novel clinical and research applications where improved attenuation and scatter correction methods are beneficial are highlighted.

show abstract

“…[19][20][21][22][23][24][25] DLMs have been primarily proposed for pCT generation from magnetic resonance imaging (MRI). [26][27][28][29][30][31] They are particularly appealing owing to their fast computation time. One of the first DLMs for pCT generation was based on the U-Net architecture.…”

Section: Introductionmentioning

confidence: 99%

Comparison of CBCT‐based dose calculation methods in head and neck cancer radiotherapy: from Hounsfield unit to density calibration curve to deep learning

et al. 2020

View full text Add to dashboard Cite

Purpose: Anatomical variations occur during head and neck (H&N) radiotherapy treatment. kV cone-beam computed tomography (CBCT) images can be used for daily dose monitoring to assess dose variations owing to anatomic changes. Deep learning methods (DLMs) have recently been proposed to generate pseudo-CT (pCT) from CBCT to perform dose calculation. This study aims to evaluate the accuracy of a DLM and to compare this method with three existing methods of dose calculation from CBCT in H&N cancer radiotherapy. Methods: Forty-four patients received VMAT for H&N cancer (70-63-56 Gy). For each patient, reference CT (Bigbore, Philips) and CBCT images (XVI, Elekta) were acquired. The DLM was based on a generative adversarial network. The three compared methods were: (a) a method using a density to Hounsfield Unit (HU) relation from phantom CBCT image (HU-D curve method), (b) a water-airbone density assignment method (DAM), and iii) a method using deformable image registration (DIR). The imaging endpoints were the mean absolute error (MAE) and mean error (ME) of HU from pCT and reference CT (CT ref). The dosimetric endpoints were dose discrepancies and 3D gamma analyses (local, 2%/2 mm, 30% dose threshold). Dose discrepancies were defined as the mean absolute differences between DVHs calculated from the CT ref and pCT of each method. Results: In the entire body, the MAEs and MEs of the DLM, HU-D curve method, DAM, and DIR method were 82.4 and 17.1 HU, 266.6 and 208.9 HU, 113.2 and 14.2 HU, and 95.5 and −36.6 HU, respectively. The MAE obtained using the DLM differed significantly from those of other methods (Wilcoxon, P ≤ 0.05). The DLM dose discrepancies were 7 AE 8 cGy (maximum = 44 cGy) for the ipsilateral parotid gland D mean and 5 AE 6 cGy (max = 26 cGy) for the contralateral parotid gland mean dose (D mean). For the parotid gland D mean , no significant dose difference was observed between the DLM and other methods. The mean 3D gamma pass rate AE standard deviation was 98.1 AE 1.2%, 91.0 AE 5.3%, 97.9 AE 1.6%, and 98.8 AE 0.7% for the DLM, HU-D method, DAM, and DIR method, respectively. The gamma pass rates and mean gamma results of the HU-D curve method, DAM, and DIR method differed significantly from those of the DLM. The mean calculation time to generate one pCT was 30 sec for the deep learning and DIR methods. Conclusions: For H&N radiotherapy, DIR method and DLM appears as the most appealing CBCTbased dose calculation methods among the four methods in terms of dose accuracy as well as calculation time. Using the DIR method or DLM with CBCT images enables dose monitoring in the parotid glands during the treatment course and may be used to trigger replanning.

show abstract

Attenuation correction for brain PET imaging using deep neural network based on Dixon and ZTE MR images

Cited by 96 publications

References 52 publications

Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI

Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI

Magnetic Resonance-Based Attenuation Correction and Scatter Correction in Neurological Positron Emission Tomography/Magnetic Resonance Imaging—Current Status With Emerging Applications

Comparison of CBCT‐based dose calculation methods in head and neck cancer radiotherapy: from Hounsfield unit to density calibration curve to deep learning

Contact Info

Product

Resources

About