Deep learning–based MR‐to‐CT synthesis: The influence of varying gradient echo–based MR images as input channels
Mateusz C. Florkow,Frank Zijlstra,Koen Willemsen,Matteo Maspero,Cornelis A. T. van den Berg,Linda G W Kerkmeijer,René M. Castelein,Harrie Weinans,Max A. Viergever,Marijn van Stralen,Peter R. Seevinck +10 more
TLDR
To study the influence of gradient echo–based contrasts as input channels to a 3D patch‐based neural network trained for synthetic CT (sCT) generation in canine and human populations, a neural network model is constructed.Abstract:
PURPOSE: To study the influence of gradient echo-based contrasts as input channels to a 3D patch-based neural network trained for synthetic CT (sCT) generation in canine and human populations. METHODS: Magnetic resonance images and CT scans of human and canine pelvic regions were acquired and paired using nonrigid registration. Magnitude MR images and Dixon reconstructed water, fat, in-phase and opposed-phase images were obtained from a single T1 -weighted multi-echo gradient-echo acquisition. From this set, 6 input configurations were defined, each containing 1 to 4 MR images regarded as input channels. For each configuration, a UNet-derived deep learning model was trained for synthetic CT generation. Reconstructed Hounsfield unit maps were evaluated with peak SNR, mean absolute error, and mean error. Dice similarity coefficient and surface distance maps assessed the geometric fidelity of bones. Repeatability was estimated by replicating the training up to 10 times. RESULTS: Seventeen canines and 23 human subjects were included in the study. Performance and repeatability of single-channel models were dependent on the TE-related water-fat interference with variations of up to 17% in mean absolute error, and variations of up to 28% specifically in bones. Repeatability, Dice similarity coefficient, and mean absolute error were statistically significantly better in multichannel models with mean absolute error ranging from 33 to 40 Hounsfield units in humans and from 35 to 47 Hounsfield units in canines. CONCLUSION: Significant differences in performance and robustness of deep learning models for synthetic CT generation were observed depending on the input. In-phase images outperformed opposed-phase images, and Dixon reconstructed multichannel inputs outperformed single-channel inputs.read more
Citations
More filters
Journal ArticleDOI
Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy
Matteo Maspero,Mark H. F. Savenije,Anna M. Dinkla,Peter R. Seevinck,Martijn Intven,Ina M. Jürgenliemk-Schulz,Linda G W Kerkmeijer,Cornelis A. T. van den Berg +7 more
TL;DR: Accurate MR-based dose calculation using sCT images generated with a cGAN trained on prostate cancer patients is feasible for the entire pelvis, and the sCT generation was sufficiently fast for integration in an MR-guided radiotherapy workflow.
Journal ArticleDOI
A review on medical imaging synthesis using deep learning and its clinical applications.
TL;DR: This paper summarized the recent developments of deep learning-based methods in inter- and intra-modality image synthesis by listing and highlighting the proposed methods, study designs, and reported performances with related clinical applications on representative studies.
Journal ArticleDOI
Multi-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapy.
Mengke Qi,Yongbao Li,Aiqian Wu,Qiyuan Jia,Bin Li,Wenzhao Sun,Zhenhui Dai,Xingyu Lu,Linghong Zhou,Xiaowu Deng,Ting Song +10 more
TL;DR: The results show that the cGAN model with multi-channel sequences as input to predict sCT achieves higher accuracy than any single MR sequence model and the T1-weighted MR model achieves better results than T2, T1C and T1DixonC-water models.
Book ChapterDOI
Medical Image Generation Using Generative Adversarial Networks: A Review
TL;DR: In this article, the authors provide state-of-the-art progress in GANs based clinical application in medical image generation and cross-modality synthesis, and future research directions in the area have been covered.
Journal ArticleDOI
Deep learning based synthetic-CT generation in radiotherapy and PET: A review
TL;DR: A systematic review of deep learning-based methods for the generation of synthetic computed tomography (sCT) is presented in this article, where the authors classify the methods into three categories according to their clinical applications: (i) to replace computed tomograms in magnetic resonance (MR) based treatment planning, (ii) facilitate cone-beam computed tomograph based image-guided adaptive radiotherapy, and (iii) derive attenuation maps for the correction of positron emission tomography.
References
More filters
Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
On methods in the analysis of profile data.
TL;DR: In this article, an approximate procedure based on classical analysis of variance is presented, including an adjustment to the degrees of freedom resulting in conservative F tests, which can be applied to the case where the variance covariance matrices differ from group to group.
Proceedings ArticleDOI
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
TL;DR: In this article, a volumetric, fully convolutional neural network (FCN) was proposed to predict segmentation for the whole volume at one time, which can deal with situations where there is a strong imbalance between the number of foreground and background voxels.
Journal ArticleDOI
elastix : A Toolbox for Intensity-Based Medical Image Registration
TL;DR: The software consists of a collection of algorithms that are commonly used to solve medical image registration problems, and allows the user to quickly configure, test, and compare different registration methods for a specific application.