Real-Time Patient-Specific Lung Radiotherapy Targeting using Deep Learning

  title={Real-Time Patient-Specific Lung Radiotherapy Targeting using Deep Learning},
  author={Markus Foote and Blake E. Zimmerman and Amit R. Sawant and Sarang C. Joshi},
Radiation therapy has presented a need for dynamic tracking of a target tumor volume. Fiducial markers such as implanted gold seeds have been used to gate radiation delivery but the markers are invasive and gating significantly increases treatment time. Pretreatment acquisition of a 4DCT allows for the development of accurate motion estimation for treatment planning. A deep convolutional neural network and subspace motion tracking is used to recover anatomical positions from a single radiograph… Expand
Deep learning in medical imaging and radiation therapy.
The general principles of DL and convolutional neural networks are introduced, five major areas of application of DL in medical imaging and radiation therapy are surveyed, common themes are identified, methods for dataset expansion are discussed, and lessons learned, remaining challenges, and future directions are summarized. Expand
Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy
The applications of artificial intelligence in five generic fields of molecular imaging and radiation therapy, including PET instrumentation design, PET image reconstruction quantification and segmentation, image denoising, radiation dosimetry and computer-aided diagnosis, and outcome prediction are discussed. Expand
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 5th International Workshop, BrainLes 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 17, 2019, Revised Selected Papers, Part I
Experimental results on the segmentation of brain tumors in multimodal MRI scans (BraTS’19) demonstrate that the proposed method can efficiently segment the tumor regions. Expand
Estimation of the Principal Ischaemic Stroke Growth Directions for Predicting Tissue Outcomes
The estimates of traditional segmentation networks for the prediction of the follow-up tissue outcome in strokes are not yet accurate enough or capable of properly modeling the growth mechanisms of ischaemic stroke. Expand


Four-dimensional radiotherapy planning for DMLC-based respiratory motion tracking.
4D radiotherapy planning for DMLC-based respiratory motion tracking is feasible and may offer tumor dose escalation and/or a reduction in treatment-related complications, however, 4D planning requires new planning tools, such as deformable registration and automated treatment planning on multiple CT image sets. Expand
Quantifying variability in radiation dose due to respiratory-induced tumor motion
A framework that models both organ displacement in response to respiration and the underlying random variations in patient-specific breathing patterns is developed to predict uncertainties in dose delivery in the presence of organ motion and identify tissues at risk of receiving insufficient or harmful levels of radiation. Expand
Investigating the Feasibility of Rapid MRI for Image-Guided Motion Management in Lung Cancer Radiotherapy
The studies indicate that image quality and acquisition speed of cine-2D MRI were adequate for motion monitoring, however, significant improvements are required to achieve comparable speeds for truly 4D MRI. Expand
Diffeomorphic Density Registration in Thoracic Computed Tomography
It is shown that one can effectively transform a CT image of effective linear attenuation coefficients to act as a density, i.e. exhibiting conservation of mass while undergoing a deformation. Expand
Management of three-dimensional intrafraction motion through real-time DMLC tracking.
Early results indicate that accurate, real-time DMLC tracking of 3D tumor motion is feasible and can potentially result in significant geometric and dosimetric advantages leading to more effective management of intrafraction motion. Expand
Rank Constrained Diffeomorphic Density Motion Estimation for Respiratory Correlated Computed Tomography
A novel motion estimation algorithm is presented that includes the constraint for low-rank motion between the different phases of the RCCT images and is quite general and applicable to various motion estimation problems in medical imaging. Expand
IMRT Treatment Planning on 4D Geometries for the Era of Dynamic MLC Tracking
4D optimization for respiratory phase-dependent treatment planning with dynamic MLC motion tracking improved the 4D treatment plan score by 4–50% compared with 3D optimization. Expand
Motion adaptive x-ray therapy: a feasibility study.
The concept and feasibility of MAX-T and the capability of the treatment machine to deliver such a treatment were investigated by performing measurements for uniform and IMRT fields using a mechanical sinusoidal oscillator to simulate target motion. Expand
On a PCA-based lung motion model.
The goal of this work is to understand the underlying reason why PCA is effective for modeling lung motion and find the optimal number of PCA coefficients for accurate lung motion modeling and propose a new method to derive the entire lung motion using a single internal marker based on the PCA model. Expand
Mobile C-arm 3D Reconstruction in the Presence of Uncertain Geometry
The proposed method reconstructs the 3D image using the expectation maximization (EM) framework while jointly estimating the true geometry, thereby improving the feasibility of 3D imaging on mobile C-arms. Expand