MRI-based treatment planning for liver stereotactic body radiotherapy: validation of a deep learning-based synthetic CT generation method

Liu, Yingzi; Lei, Yang; Wang, Tonghe; Kayode, Oluwatosin; Tian, Sibo; Tian, Lu; Patel, Pretesh; Curran, Walter J.; Ren, Lei; Yang, Xiaofeng

doi:10.1259/bjr.20190067

Cited by 63 publications

(50 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the sCT dose calculation accuracy for liver radiotherapy, we compared the dCT-based and sCT-based dose distributions for 8 liver cancer patients. In both models, the average MAE between dCT and sCT images is of similar magnitude to that previously reported for sCT abdominal generation using high-field MR images (Liu et al 2019). The average gamma passing rates were above 99% using a 3%, 3 mm criterion in both models.…”

Section: Discussionsupporting

confidence: 84%

Generation of abdominal synthetic CTs from 0.35T MR images using generative adversarial networks for MR-only liver radiotherapy

Fu¹,

Singhrao²,

Cao³

et al. 2020

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Electron density maps must be accurately estimated to achieve valid dose calculation in MR-only radiotherapy. The goal of this study is to assess whether two deep learning models, the conditional generative adversarial network (cGAN) and the cycle-consistent generative adversarial network (cycleGAN), can generate accurate abdominal synthetic CT (sCT) images from 0.35T MR images for MR-only liver radiotherapy.A retrospective study was performed using CT images and 0.35T MR images of 12 patients with liver (n=8) and non-liver abdominal (n=4) cancer. CT images were deformably registered to the corresponding MR images to generate deformed CT (dCT) images for treatment planning. Both cGAN and cycleGAN were trained using MR and dCT transverse slices. Four-fold cross-validation testing was conducted to generate sCT images for all patients. The HU prediction accuracy was evaluated by voxel-wise similarity metric between each dCT and sCT image for all 12 patients. dCT-based and sCT-based dose distributions were compared using gamma and dose-volume histogram (DVH) metric analysis for 8 liver patients. sCTcycleGAN achieved the average mean absolute error (MAE) of 94.1 HU, while sCTcGAN achieved 89.8 HU. In both models, the average gamma passing rates within all volumes of interest were higher than 95% using a 2%, 2 mm criterion, and 99% using a 3%, 3 mm criterion. The average differences in the mean dose and DVH metrics were within ±0.6% for the planning target volume and within ±0.15% for evaluated organs in both models.Results demonstrated that abdominal sCT images generated by both cGAN and cycleGAN achieved accurate dose calculation for 8 liver radiotherapy plans. sCTcGAN images had smaller average MAE and achieved better dose calculation accuracy than sCTcyleGAN images. More abdominal patients will be enrolled in the future to further evaluate two models. Keywords: Generative adversarial network, Synthetic CT, MR-guided radiotherapy planning workflows for pelvic or abdominal cancer radiotherapy (Villeirs et al 2005, Lim et al 2011, Heerkens et al 2017, Mittauer et al 2018. Since there is no direct relationship between MR intensity values and electron densities, the standard MR-guided radiotherapy workflow still requires the acquisition of a CT image for dose calculation. However, registration between CT and MR images for transferring target delineations introduces systematic uncertainties that propagate throughout the treatment (Edmund and Nyholm 2017). Acquiring an additional CT image also increases unwanted radiation exposure, clinical workload, and financial cost (Karlsson et al 2009). MR-only radiotherapy can avoid these downsides.A few methods have been proposed to generate synthetic CT (sCT) images from MR images. These methods include atlas-based methods, voxel-based methods, and hybrid methods (Edmund and Nyholm 2017). In atlas-based methods (Sjölund et al 2015, Dowling et al 2015, the target MR image was first deformably registered to atlas-MR images to acquire deformation vector fields. The acquired vector fi...

show abstract

Section: Discussionsupporting

confidence: 84%

Generation of abdominal synthetic CTs from 0.35T MR images using generative adversarial networks for MR-only liver radiotherapy

Fu¹,

Singhrao²,

Cao³

et al. 2020

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

show abstract

“…The field of medical image registration has been evolving rapidly with hundreds of papers published each year. Recently, DL-based methods have changed the landscape of medical image processing research and achieved the-state-of-art performances in many applications [25,27,45,58,84,85,86,88,89,97,98,156,157,158,160,161]. However, deep learning in medical image registration has not been extensively studied until the past three to four years.…”

Section: Introductionmentioning

confidence: 99%

Deep learning in medical image registration: a review

et al. 2020

Self Cite

View full text Add to dashboard Cite

This paper presents a review of deep learning (DL) based medical image registration methods. We summarized the latest developments and applications of DL-based registration methods in the medical field. These methods were classified into seven categories according to their methods, functions and popularity. A detailed review of each category was presented, highlighting important contributions and identifying specific challenges. A short assessment was presented following the detailed review of each category to summarize its achievements and future potentials. We provided a comprehensive comparison among DL-based methods for lung and brain registration using benchmark datasets. Lastly, we analyzed the statistics of all the cited works from various aspects, revealing the popularity and future trend of DL-based medical image registration. 1 arXiv:1912.12318v1 [eess.IV] 27 Dec 2019 1. Summarize the latest developments in DL-based medical image registration. 2. Highlight contributions, identify challenges and outline future trends. 3. Provide detailed statistics on recent publications from different perspectives. 2 Deep Learning 2 Convolutional Neural NetworkConvolutional neural network (CNN) is a class of deep neural networks with regularized multilayer perceptron. CNN uses convolution operation in place of general matrix multiplication in simple neural networks. The convolutional filters and operations in CNN make it suitable for visual imagery signal processing. Because of its excellent feature extraction ability, CNN is one of the most successful models for image analysis. Since the breakthrough of AlexNet [79], many variants of CNN have been proposed and have achieved the-state-of-art performances in various image processing tasks. A typical CNN usually consists of multiple convolutional layers, max pooling layers, batch normalization layers, dropout layers, a sigmoid or softmax layer. In each convolutional layer, multiple channels of feature maps were extracted by sliding trainable convolutional kernels across the input feature maps. Hierarchical features with high-level abstraction are extracted using multiple convolutional layers. These feature maps usually go through multiple fully connected layer before reaching the final decision layer. Max pooling layers are often used to reduce the image sizes and to promote spatial invariance of the network. Batch normalization is used to reduce internal covariate shift among the training samples. Weight regularization and dropout layers are used to alleviate data overfitting. The loss function is defined as the difference between the predicted and the target output. CNN is usually trained by minimizing the loss via gradient back propagation using optimization methods. Many different types of network architectures have been proposed to improve the performance of CNN [93]. U-Net proposed by Ronneberger et al. is among one of the most used network architectures [120]. U-Net was originally used to perform neuronal structures segmentation. U-Net adopts symmetrical contractiv...

show abstract

“…The 3D doses calculated based on the sCT images showed good agreement with those calculated from the pCT images, as assessed by image registration, dosimetric parameters, and gamma analysis. Because of superiority MR for delineation of prostate and normal organs [9], various methodologies generating sCT from MR for implement MR only simulation, such as bulky anatomical density [21][22][23][24], machine learning [25,26] and so on, have been suggested. Usually, process of generating sCT from MRI required a specialist or specific procedure, however, a commercial MRCAT software, used in this study, could generate sCT using the dedicated MR protocol automatically.…”

Section: Discussionmentioning

confidence: 99%

Magnetic resonance image-based tomotherapy planning for prostate cancer

et al. 2020

View full text Add to dashboard Cite

Image-guided intensity-modulated radiotherapy (IG-IMRT) has been widely used in the treatment of prostate cancer, with the goal of reducing acute and late toxicity of adjunct critical organs, e.g., the bladder and rectum [1,2]. Helical tomotherapy is considered a favorable treatment technique for prostate cancer due to its uniformity in treatment and the fact that it is based on computed tomography (CT) simulation [3,4]. Magnetic resonance imaging (MRI) has been shown to be supe-Purpose: To evaluate and compare the feasibilities of magnetic resonance (MR) image-based planning using synthetic computed tomography (sCT) versus CT (pCT)-based planning in helical tomotherapy for prostate cancer. Materials and Methods: A retrospective evaluation was performed in 16 patients with prostate cancer who had been treated with helical tomotherapy. MR images were acquired using a dedicated therapy sequence; sCT images were generated using magnetic resonance for calculating attenuation (MRCAT). The three-dimensional dose distribution according to sCT was recalculated using a previously optimized plan and was compared with the doses calculated using pCT. Results: The mean planning target volume doses calculated by sCT and pCT differed by 0.65% ± 1.11% (p = 0.03). Three-dimensional gamma analysis at a 2%/2 mm dose difference/distance to agreement yielded a pass rate of 0.976 (range, 0.658 to 0.986). Conclusion: The dose distribution results obtained using tomotherapy from MR-only simulations were in good agreement with the dose distribution results from simulation CT, with mean dose differences of less than 1% for target volume and normal organs in patients with prostate cancer.

show abstract

MRI-based treatment planning for liver stereotactic body radiotherapy: validation of a deep learning-based synthetic CT generation method

Cited by 63 publications

References 33 publications

Generation of abdominal synthetic CTs from 0.35T MR images using generative adversarial networks for MR-only liver radiotherapy

Generation of abdominal synthetic CTs from 0.35T MR images using generative adversarial networks for MR-only liver radiotherapy

Deep learning in medical image registration: a review

Magnetic resonance image-based tomotherapy planning for prostate cancer

Contact Info

Product

Resources

About