Automated air region delineation on MRI for synthetic CT creation

PURPOSE Automatically and accurately separating air from other low signal regions (especially bone, liver, etc.) in an MRI is difficult because these tissues produce similar MR intensities, resulting in errors in synthetic CT generation for MRI-based radiation therapy planning. This work aims to develop a technique to accurately and automatically determine air-regions for MR-guided adaptive radiation therapy. METHODS CT and MRI scans (T2-weighted) of phantoms with fabricated air-cavities and abdominal cancer patients were used to establish an MR intensity threshold for air delineation. From the phantom data, air/tissue boundaries in MRI were identified by CT-MRI registration. A formula relating the MRI intensities of air and surrounding materials was established to auto-threshold air-regions. The air-regions were further refined by using quantitative image texture features. A naive Bayesian classifier was trained using the extracted features with a leave-one-out cross validation technique to differentiate air from non-air voxels. The multi-step air auto-segmentation method was tested against the manually segmented air-regions. The dosimetry impacts of the air-segmentation methods were studied. RESULTS Air-regions in the abdomen can be segmented on MRI within 1mm accuracy using a multi-step auto-segmentation method as compared to manually delineated contours. The air delineation based on the MR threshold formula was improved using the MRI texture differences between air and tissues, as judged by the area under the receiver operating characteristic curve of 81% when two texture features (autocorrelation and contrast) were used. The performance increased to 82% with using three features (autocorrelation, sum-variance, and contrast). Dosimetric analysis showed no significant difference between the auto-segmentation and manual MR air delineation on commonly used dose volume parameters. CONCLUSIONS The proposed techniques consisting of intensity-based auto-thresholding and image texture-based voxel classification can automatically and accurately segment air-regions on MRI, allowing synthetic CT to be generated quickly and precisely for MR-guided adaptive radiation therapy.

[1]  S. Ourselin,et al.  Evaluation of a multi-atlas CT synthesis approach for MRI-only radiotherapy treatment planning , 2017, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[2]  D. Louis Collins,et al.  Evaluating intensity normalization on MRIs of human brain with multiple sclerosis , 2011, Medical Image Anal..

[3]  Mary Feng,et al.  Investigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapy , 2013, Physics in medicine and biology.

[4]  Fredrik Nordström,et al.  Technical Note: MRI only prostate radiotherapy planning using the statistical decomposition algorithm. , 2015, Medical physics.

[5]  Allan Hanbury,et al.  An Efficient Algorithm for Calculating the Exact Hausdorff Distance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  P E Metcalfe,et al.  High resolution entry and exit Monte Carlo dose calculations from a linear accelerator 6 MV beam under the influence of transverse magnetic fields. , 2009, Medical physics.

[7]  David H. Miller,et al.  Correction for variations in MRI scanner sensitivity in brain studies with histogram matching , 1998, Magnetic resonance in medicine.

[8]  Jan J W Lagendijk,et al.  The magnetic resonance imaging-linac system. , 2014, Seminars in radiation oncology.

[9]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[10]  Lei Xing,et al.  A unifying probabilistic Bayesian approach to derive electron density from MRI for radiation therapy treatment planning , 2014, Physics in medicine and biology.

[11]  Mark Bydder,et al.  Magnetic Resonance: An Introduction to Ultrashort TE (UTE) Imaging , 2003, Journal of computer assisted tomography.

[12]  Russell T. Shinohara,et al.  Removing inter-subject technical variability in magnetic resonance imaging studies , 2016, NeuroImage.

[13]  Tiina Seppälä,et al.  A dual model HU conversion from MRI intensity values within and outside of bone segment for MRI-based radiotherapy treatment planning of prostate cancer. , 2013, Medical physics.

[14]  Gaspar Delso,et al.  Anatomic Evaluation of 3-Dimensional Ultrashort-Echo-Time Bone Maps for PET/MR Attenuation Correction , 2014, The Journal of Nuclear Medicine.

[15]  F. Cendes,et al.  Texture analysis of medical images. , 2004, Clinical radiology.

[16]  A N T J Kotte,et al.  Integrating a MRI scanner with a 6 MV radiotherapy accelerator: dose deposition in a transverse magnetic field. , 2004, Physics in medicine and biology.

[17]  B W Raaymakers,et al.  Integrating a MRI scanner with a 6 MV radiotherapy accelerator: dose increase at tissue–air interfaces in a lateral magnetic field due to returning electrons , 2005, Physics in medicine and biology.

[18]  Adam Johansson,et al.  CT substitute derived from MRI sequences with ultrashort echo time. , 2011, Medical physics.

[19]  Habib Zaidi,et al.  Atlas-guided generation of pseudo-CT images for MRI-only and hybrid PET–MRI-guided radiotherapy treatment planning , 2016, Physics in medicine and biology.

[20]  Xiao Han,et al.  MR‐based synthetic CT generation using a deep convolutional neural network method , 2017, Medical physics.

[21]  Oliver Jäkel,et al.  Generation of synthetic CT data using patient specific daily MR image data and image registration , 2017, Physics in medicine and biology.

[22]  Oliver Holub,et al.  Quantitative histogram analysis of images , 2006, Comput. Phys. Commun..

[23]  D Forsberg,et al.  Generating patient specific pseudo-CT of the head from MR using atlas-based regression , 2015, Physics in medicine and biology.

[24]  X. Li,et al.  Technical Note: Dose effects of 1.5 T transverse magnetic field on tissue interfaces in MRI-guided radiotherapy. , 2016, Medical physics.

[25]  Jan J W Lagendijk,et al.  MR-guided breast radiotherapy: feasibility and magnetic-field impact on skin dose , 2013, Physics in medicine and biology.

[26]  Ron Kikinis,et al.  Statistical validation of image segmentation quality based on a spatial overlap index. , 2004, Academic radiology.

[27]  B W Raaymakers,et al.  Fast online Monte Carlo-based IMRT planning for the MRI linear accelerator , 2012, Physics in medicine and biology.

[28]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[29]  B W Raaymakers,et al.  Integrating a MRI scanner with a 6 MV radiotherapy accelerator: impact of the surface orientation on the entrance and exit dose due to the transverse magnetic field , 2007, Physics in medicine and biology.

[30]  H. Kjer,et al.  A voxel-based investigation for MRI-only radiotherapy of the brain using ultra short echo times , 2014, Physics in medicine and biology.

[31]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[32]  Koen Van Leemput,et al.  A patch-based pseudo-CT approach for MRI-only radiotherapy in the pelvis. , 2016, Medical physics.

[33]  Carri Glide-Hurst,et al.  Implementation of a novel algorithm for generating synthetic CT images from magnetic resonance imaging data sets for prostate cancer radiation therapy. , 2015, International journal of radiation oncology, biology, physics.

[34]  Olivier Salvado,et al.  An atlas-based electron density mapping method for magnetic resonance imaging (MRI)-alone treatment planning and adaptive MRI-based prostate radiation therapy. , 2012, International journal of radiation oncology, biology, physics.

[35]  X. Li,et al.  A Technique to Rapidly Generate Synthetic Computed Tomography for Magnetic Resonance Imaging-Guided Online Adaptive Replanning: An Exploratory Study. , 2019, International journal of radiation oncology, biology, physics.

[36]  Robert King,et al.  Textural features corresponding to textural properties , 1989, IEEE Trans. Syst. Man Cybern..

[37]  J J W Lagendijk,et al.  Dose optimization for the MRI-accelerator: IMRT in the presence of a magnetic field , 2007, Physics in medicine and biology.

[38]  Jurgen Fripp,et al.  Automatic Substitute Computed Tomography Generation and Contouring for Magnetic Resonance Imaging (MRI)-Alone External Beam Radiation Therapy From Standard MRI Sequences. , 2015, International journal of radiation oncology, biology, physics.

[39]  J. Edmund,et al.  Patch-based generation of a pseudo CT from conventional MRI sequences for MRI-only radiotherapy of the brain. , 2015, Medical physics.

[40]  Siyong Kim,et al.  Deformable image registration in radiation therapy , 2017, Radiation oncology journal.

[41]  Elizabeth Gore,et al.  Technical Note: Is bulk electron density assignment appropriate for MRI‐only based treatment planning for lung cancer?† , 2017, Medical physics.

[42]  T. Nyholm,et al.  A review of substitute CT generation for MRI-only radiation therapy , 2017, Radiation oncology.

[43]  Benjamin M Ellingson,et al.  Comparison between intensity normalization techniques for dynamic susceptibility contrast (DSC)‐MRI estimates of cerebral blood volume (CBV) in human gliomas , 2012, Journal of magnetic resonance imaging : JMRI.