Comparison of different deep learning architectures for synthetic CT generation from MR images

Bahrami, Abbas; Karimian, Alireza; Arabi, Hossein

doi:10.1016/j.ejmp.2021.09.006

Cited by 62 publications

(14 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of deep learning models were implemented/compared for synthetic CT estimation from MR images, wherein the HighResNet model exhibited superior performance, hence motivating its selection for this study (Supporting Information Table S2 ). 32 , 33 HighResNet consists of 20 convolutional layers wherein the first seven layers are equipped with 3 × 3 × 3 voxel convolution kernels. The first seven layers were designed to depict the low‐level image features from the input images.…”

Section: Methodsmentioning

confidence: 99%

“…The HighResNet model, in comparison with other similar architectures, has the merit of high resolution (using dilated convolution kernels instead of max‐pooling layers) image processing and feature extraction within the different layers of the network, which render this architecture a powerful model for image translation/regression and segmentation/classification tasks. 30 Although the HighResNet model was previously used for synthetic CT generation in head and pelvis imaging or PET AC, 32 , 34 , 35 , 36 this work used this model for the first time for synthetic CT generation from torso MR images.…”

Section: Methodsmentioning

confidence: 99%

“…The residual deep learning model, referred to as HighResNet, 30 implemented in Python library of the Niftynet platform, 31 was configured in a 2D manner to convert transaxial slices of the IP Dixon images into corresponding sCT slices. A number of deep learning models were implemented/compared for synthetic CT estimation from MR images, wherein the HighResNet model exhibited superior performance, hence motivating its selection for this study (Supporting Information Table ) 32,33 . HighResNet consists of 20 convolutional layers wherein the first seven layers are equipped with 3 × 3 × 3 voxel convolution kernels.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

MRI‐guided attenuation correction in torso PET/MRI: Assessment of segmentation‐, atlas‐, and deep learning‐based approaches in the presence of outliers

Arabi

Zaidi

2021

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Purpose We compare the performance of three commonly used MRI‐guided attenuation correction approaches in torso PET/MRI, namely segmentation‐, atlas‐, and deep learning‐based algorithms. Methods Twenty‐five co‐registered torso 18F‐FDG PET/CT and PET/MR images were enrolled. PET attenuation maps were generated from in‐phase Dixon MRI using a three‐tissue class segmentation‐based approach (soft‐tissue, lung, and background air), voxel‐wise weighting atlas‐based approach, and a residual convolutional neural network. The bias in standardized uptake value (SUV) was calculated for each approach considering CT‐based attenuation corrected PET images as reference. In addition to the overall performance assessment of these approaches, the primary focus of this work was on recognizing the origins of potential outliers, notably body truncation, metal‐artifacts, abnormal anatomy, and small malignant lesions in the lungs. Results The deep learning approach outperformed both atlas‐ and segmentation‐based methods resulting in less than 4% SUV bias across 25 patients compared to the segmentation‐based method with up to 20% SUV bias in bony structures and the atlas‐based method with 9% bias in the lung. The deep learning‐based method exhibited superior performance. Yet, in case of sever truncation and metallic‐artifacts in the input MRI, this approach was outperformed by the atlas‐based method, exhibiting suboptimal performance in the affected regions. Conversely, for abnormal anatomies, such as a patient presenting with one lung or small malignant lesion in the lung, the deep learning algorithm exhibited promising performance compared to other methods. Conclusion The deep learning‐based method provides promising outcome for synthetic CT generation from MRI. However, metal‐artifact and body truncation should be specifically addressed.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MRI‐guided attenuation correction in torso PET/MRI: Assessment of segmentation‐, atlas‐, and deep learning‐based approaches in the presence of outliers

Arabi

Zaidi

2021

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…The most common are intensity-based ( 14 ) metrics, like the mean absolute error (MAE), mean error (ME), mean squared error (MSE), and peak signal-to-noise ratio (PSNR). Structural similarity (SSIM) ( 15 , 16 ) is also often computed. These metrics have been reported at a global level, restricted to a single value describing the agreement within the body contour of the patient or within an organ ( 12 ).…”

Section: Introductionmentioning

confidence: 99%

“…For sCT evaluations, each patient is usually assessed in isolation and the results are then combined. However, it has been reported that errors might appear heterogeneously distributed across different tissue densities ( 6 , 16 , 21 – 24 ).…”

Section: Introductionmentioning

confidence: 99%

Quality assurance for MRI-only radiation therapy: A voxel-wise population-based methodology for image and dose assessment of synthetic CT generation methods

et al. 2022

View full text Add to dashboard Cite

The quality assurance of synthetic CT (sCT) is crucial for safe clinical transfer to an MRI-only radiotherapy planning workflow. The aim of this work is to propose a population-based process assessing local errors in the generation of sCTs and their impact on dose distribution. For the analysis to be anatomically meaningful, a customized interpatient registration method brought the population data to the same coordinate system. Then, the voxel-based process was applied on two sCT generation methods: a bulk-density method and a generative adversarial network. The CT and MRI pairs of 39 patients treated by radiotherapy for prostate cancer were used for sCT generation, and 26 of them with delineated structures were selected for analysis. Voxel-wise errors in sCT compared to CT were assessed for image intensities and dose calculation, and a population-based statistical test was applied to identify the regions where discrepancies were significant. The cumulative histograms of the mean absolute dose error per volume of tissue were computed to give a quantitative indication of the error for each generation method. Accurate interpatient registration was achieved, with mean Dice scores higher than 0.91 for all organs. The proposed method produces three-dimensional maps that precisely show the location of the major discrepancies for both sCT generation methods, highlighting the heterogeneity of image and dose errors for sCT generation methods from MRI across the pelvic anatomy. Hence, this method provides additional information that will assist with both sCT development and quality control for MRI-based planning radiotherapy.

show abstract

Bony structure enhanced synthetic CT generation using Dixon sequences for pelvis MR‐only radiotherapy

et al. 2023

View full text Add to dashboard Cite

BackgroundMRI‐only radiotherapy planning (MROP) is beneficial to patients by avoiding MRI/CT registration errors, simplifying the radiation treatment simulation workflow and reducing exposure to ionizing radiation. MRI is the primary imaging modality for soft tissue delineation. Treatment planning CTs (i.e., CT simulation scan) are redundant if a synthetic CT (sCT) can be generated from the MRI to provide the patient positioning and electron density information. Unsupervised deep learning (DL) models like CycleGAN are widely used in MR‐to‐sCT conversion, when paired patient CT and MR image datasets are not available for model training. However, compared to supervised DL models, they cannot guarantee anatomic consistency, especially around bone.PurposeThe purpose of this work was to improve the sCT accuracy generated from MRI around bone for MROP.MethodsTo generate more reliable bony structures on sCT images, we proposed to add bony structure constraints in the unsupervised CycleGAN model's loss function and leverage Dixon constructed fat and in‐phase (IP) MR images. Dixon images provide better bone contrast than T2‐weighted images as inputs to a modified multi‐channel CycleGAN. A private dataset with a total of 31 prostate cancer patients were used for training (20) and testing (11).ResultsWe compared model performance with and without bony structure constraints using single‐ and multi‐channel inputs. Among all the models, multi‐channel CycleGAN with bony structure constraints had the lowest mean absolute error, both inside the bone and whole body (50.7 and 145.2 HU). This approach also resulted in the highest Dice similarity coefficient (0.88) of all bony structures compared with the planning CT.ConclusionModified multi‐channel CycleGAN with bony structure constraints, taking Dixon‐constructed fat and IP images as inputs, can generate clinically suitable sCT images in both bone and soft tissue. The generated sCT images have the potential to be used for accurate dose calculation and patient positioning in MROP radiation therapy.

show abstract

Comparison of different deep learning architectures for synthetic CT generation from MR images

Cited by 62 publications

References 56 publications

MRI‐guided attenuation correction in torso PET/MRI: Assessment of segmentation‐, atlas‐, and deep learning‐based approaches in the presence of outliers

MRI‐guided attenuation correction in torso PET/MRI: Assessment of segmentation‐, atlas‐, and deep learning‐based approaches in the presence of outliers

Quality assurance for MRI-only radiation therapy: A voxel-wise population-based methodology for image and dose assessment of synthetic CT generation methods

Bony structure enhanced synthetic CT generation using Dixon sequences for pelvis MR‐only radiotherapy

Contact Info

Product

Resources

About