Pseudo CT Image Synthesis and Bone Segmentation From MR Images Using Adversarial Networks With Residual Blocks for MR-Based Attenuation Correction of Brain PET Data

Tao, Li; Fisher, Jonathan; Anaya, Emily; Li, Xin; Levin, Craig S.

doi:10.1109/trpms.2020.2989073

Cited by 22 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results show that UNet AC models generally provide an estimate of 18F-FDG uptake with a lower bias than state-ofthe-art atlas-based or segmentation-based AC methods. This confirms the results previously obtained by other authors [4,8,[12][13][14]. As for the best point in the AC pipeline to insert the synthetic map, results show that it is nearly equivalent to generate synthetic CT or directly LRAM after bilinear scaling and low pass filtering.…”

Section: Discussionsupporting

confidence: 90%

“…Most of the DL approaches presented so far in literature for AC correction in PET/MR brain studies aim to construct synthetic CT images starting from diagnostic [12,13] or nondiagnostic [4,14,15] MR images. These methods outperform conventional synthetic CT construction methods, reducing the average bias in PET quantification from about 5% to about 2% [8,9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of a 2D UNet-Based Attenuation Correction Methodology for PET/MR Brain Studies

et al. 2022

View full text Add to dashboard Cite

Deep learning (DL) strategies applied to magnetic resonance (MR) images in positron emission tomography (PET)/MR can provide synthetic attenuation correction (AC) maps, and consequently PET images, more accurate than segmentation or atlas-registration strategies. As first objective, we aim to investigate the best MR image to be used and the best point of the AC pipeline to insert the synthetic map in. Sixteen patients underwent a 18F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) and a PET/MR brain study in the same day. PET/CT images were reconstructed with attenuation maps obtained: (1) from CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with a 2D UNet trained on MR image/attenuation map pairs. As for MR, T1-weighted and Zero Time Echo (ZTE) images were considered; as for attenuation maps, CTs and 511 keV low-resolution attenuation maps were assessed. As second objective, we assessed the ability of DL strategies to provide proper AC maps in presence of cranial anatomy alterations due to surgery. Three 11C-methionine (METH) PET/MR studies were considered. PET images were reconstructed with attenuation maps obtained: (1) from diagnostic coregistered CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with 2D UNets trained on the sixteen FDG anatomically normal patients. Only UNets taking ZTE images in input were considered. FDG and METH PET images were quantitatively evaluated. As for anatomically normal FDG patients, UNet AC models generally provide an uptake estimate with lower bias than atlas-based or segmentation-based methods. The intersubject average bias on images corrected with UNet AC maps is always smaller than 1.5%, except for AC maps generated on too coarse grids. The intersubject bias variability is the lowest (always lower than 2%) for UNet AC maps coming from ZTE images, larger for other methods. UNet models working on MR ZTE images and generating synthetic CT or 511 keV low-resolution attenuation maps therefore provide the best results in terms of both accuracy and variability. As for METH anatomically altered patients, DL properly reconstructs anatomical alterations. Quantitative results on PET images confirm those found on anatomically normal FDG patients.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Evaluation of a 2D UNet-Based Attenuation Correction Methodology for PET/MR Brain Studies

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Among these approaches, deep learning (DL)-based methods have attracted significant research attention as alternatives to conventional AC methods. Many DL studies were focused on the transformation of MR images into a synthetic pseudo-CT or μ-map [34][35][36][37][38][39][40][41][42][43][44]52]. Other approaches that are not dependent on the anatomical images (CT or MRI) can overcome limitations with respect to current CT-and MRI-based ACs and allow for more accurate PET quantification in stand-alone PET scanners for the realization of low radiation doses [25][26][27][28][29][30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

A Review of Deep-Learning-Based Approaches for Attenuation Correction in Positron Emission Tomography

Lee

2021

IEEE Trans. Radiat. Plasma Med. Sci.

View full text Add to dashboard Cite

Attenuation correction (AC) is essential for the generation of artifact-free and quantitaAtively accurate positron emission tomography (PET) images. PET AC based on computed tomography (CT) frequently results in artifacts in attenuationcorrected PET images, and these artifacts mainly originate from CT artifacts and PET-CT mismatches. The AC in PET combined with a magnetic resonance imaging (MRI) scanner (PET/MRI) is more complex than PET/CT, given that MR images do not provide direct information on high energy photon attenuation. Deep learning (DL)-based methods for the improvement of PET AC have received significant research attention as alternatives to conventional AC methods. Many DL studies were focused on the transformation of MR images into synthetic pseudo-CT or attenuation maps. Alternative approaches that are not dependent on the anatomical images (CT or MRI) can overcome the limitations related to current CT-and MRI-based ACs and allow for more accurate PET quantification in stand-alone PET scanners for the realization of low radiation doses. In this article, a review is presented on the limitations of the PET AC in current dual-modality PET/CT and PET/MRI scanners, in addition to the current status and progress of DL-based approaches, for the realization of improved performance of PET AC.

show abstract

“…The networks that containing residual block has the main features that have enabled it to perform better. The feature maintains a steady data flow between both the incoming and outgoing images [21,22]. These methods are among the most effective architectures in this medical field [23].…”

Section: Literature Reviewmentioning

confidence: 99%

Multi-Scale Network for Thoracic Organs Segmentation

Khalil¹,

Tehsin²,

Humayun³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Medical Imaging Segmentation is an essential technique for modern medical applications. It is the foundation of many aspects of clinical diagnosis, oncology, and computer-integrated surgical intervention. Although significant successes have been achieved in the segmentation of medical images, DL (deep learning) approaches. Manual delineation of OARs (organs at risk) is vastly dominant but it is prone to errors given the complex irregularities in shape, low texture diversity between tissues and adjacent blood area, patientwide location of organisms, and weak soft tissue contrast across adjacent organs in CT images. Till now several models have been implemented on multi organs segmentation but not caters to the problem of imbalanced classes some organs have relatively small pixels as compared to others. To segment OARs in thoracic CT images, we proposed the model based on the encoder-decoder approach using transfer learning with the efficientnetB7 DL model. We have built a fully connected CNN (Convolutional Neural network) having 5 layers of encoding and 5 layers of decoding with efficientnetB7 specifically to tackle imbalance class pixels in an accurate way for the segmentation of OARs. Proposed methodology achieves 0.93405 IOU score, 0.95138 F1 score and class-wise dice score for esophagus 0.92466, trachea 0.94257, heart 0.95038, aorta 0.9351 and background 0.99891. The results showed that our proposed framework can be segmented organs accurately.

show abstract

Pseudo CT Image Synthesis and Bone Segmentation From MR Images Using Adversarial Networks With Residual Blocks for MR-Based Attenuation Correction of Brain PET Data

Cited by 22 publications

References 28 publications

Evaluation of a 2D UNet-Based Attenuation Correction Methodology for PET/MR Brain Studies

Evaluation of a 2D UNet-Based Attenuation Correction Methodology for PET/MR Brain Studies

A Review of Deep-Learning-Based Approaches for Attenuation Correction in Positron Emission Tomography

Multi-Scale Network for Thoracic Organs Segmentation

Contact Info

Product

Resources

About