4D Modeling and Estimation of Respiratory Motion for Radiation Therapy PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download 4D Modeling and Estimation of Respiratory Motion for Radiation Therapy PDF full book. Access full book title 4D Modeling and Estimation of Respiratory Motion for Radiation Therapy by Jan Ehrhardt. Download full books in PDF and EPUB format.
Author: Jan Ehrhardt Publisher: Springer Science & Business Media ISBN: 3642364411 Category : Science Languages : en Pages : 352
Book Description
Respiratory motion causes an important uncertainty in radiotherapy planning of the thorax and upper abdomen. The main objective of radiation therapy is to eradicate or shrink tumor cells without damaging the surrounding tissue by delivering a high radiation dose to the tumor region and a dose as low as possible to healthy organ tissues. Meeting this demand remains a challenge especially in case of lung tumors due to breathing-induced tumor and organ motion where motion amplitudes can measure up to several centimeters. Therefore, modeling of respiratory motion has become increasingly important in radiation therapy. With 4D imaging techniques spatiotemporal image sequences can be acquired to investigate dynamic processes in the patient’s body. Furthermore, image registration enables the estimation of the breathing-induced motion and the description of the temporal change in position and shape of the structures of interest by establishing the correspondence between images acquired at different phases of the breathing cycle. In radiation therapy these motion estimations are used to define accurate treatment margins, e.g. to calculate dose distributions and to develop prediction models for gated or robotic radiotherapy. In this book, the increasing role of image registration and motion estimation algorithms for the interpretation of complex 4D medical image sequences is illustrated. Different 4D CT image acquisition techniques and conceptually different motion estimation algorithms are presented. The clinical relevance is demonstrated by means of example applications which are related to the radiation therapy of thoracic and abdominal tumors. The state of the art and perspectives are shown by an insight into the current field of research. The book is addressed to biomedical engineers, medical physicists, researchers and physicians working in the fields of medical image analysis, radiology and radiation therapy.
Author: Jan Ehrhardt Publisher: Springer Science & Business Media ISBN: 3642364411 Category : Science Languages : en Pages : 352
Book Description
Respiratory motion causes an important uncertainty in radiotherapy planning of the thorax and upper abdomen. The main objective of radiation therapy is to eradicate or shrink tumor cells without damaging the surrounding tissue by delivering a high radiation dose to the tumor region and a dose as low as possible to healthy organ tissues. Meeting this demand remains a challenge especially in case of lung tumors due to breathing-induced tumor and organ motion where motion amplitudes can measure up to several centimeters. Therefore, modeling of respiratory motion has become increasingly important in radiation therapy. With 4D imaging techniques spatiotemporal image sequences can be acquired to investigate dynamic processes in the patient’s body. Furthermore, image registration enables the estimation of the breathing-induced motion and the description of the temporal change in position and shape of the structures of interest by establishing the correspondence between images acquired at different phases of the breathing cycle. In radiation therapy these motion estimations are used to define accurate treatment margins, e.g. to calculate dose distributions and to develop prediction models for gated or robotic radiotherapy. In this book, the increasing role of image registration and motion estimation algorithms for the interpretation of complex 4D medical image sequences is illustrated. Different 4D CT image acquisition techniques and conceptually different motion estimation algorithms are presented. The clinical relevance is demonstrated by means of example applications which are related to the radiation therapy of thoracic and abdominal tumors. The state of the art and perspectives are shown by an insight into the current field of research. The book is addressed to biomedical engineers, medical physicists, researchers and physicians working in the fields of medical image analysis, radiology and radiation therapy.
Author: Yugang Min Publisher: ISBN: Category : Languages : en Pages : 83
Book Description
Radiation therapy has been successful in treating lung cancer patients, but its efficacy is limited by the inability to account for the respiratory motion during treatment planning and radiation dose delivery. Physics-based lung deformation models facilitate the motion computation of both tumor and local lung tissue during radiation therapy. In this dissertation, a novel method is discussed to accurately register 3D lungs across the respiratory phases from 4D-CT datasets, which facilitates the estimation of the volumetric lung deformation models. This method uses multi-level and multi-resolution optical flow registration coupled with thin plate splines (TPS), to address registration issue of inconsistent intensity across respiratory phases. It achieves higher accuracy as compared to multi-resolution optical flow registration and other commonly used registration methods. Results of validation show that the lung registration is computed with 3 mm Target Registration Error (TRE) and approximately 3 mm Inverse Consistency Error (ICE). This registration method is further implemented in GPU based real time dose delivery simulation to assist radiation therapy planning.
Author: Elizabeth Shobha Zachariah Publisher: ISBN: Category : Anatomy Languages : en Pages : 172
Book Description
In radiation therapy, it is imperative to deliver high doses of radiation to the tumor while reducing radiation to the healthy tissue. Respiratory motion is the most significant source of errors during treatment. Therefore, it is essential to accurately model respiratory motion for precise and effective radiation delivery. Many approaches exist to account for respiratory motion, such as controlled breath hold and respiratory gating, and they have been relatively successful. They still present many drawbacks. Thus, research has been expanded to tumor tracking. The overall goal of 4D-CT is to predict tumor motion in real time, and this work attempts to move in that direction. The following work addresses both the temporal and the spatial aspects of four-dimensional CT reconstruction. The aims of the paper are to (1) estimate the temporal parameters of 4D models for anatomy deformation using a novel neural network approach and (2) to use intelligently chosen non-uniform, non-separable splines to improve the spatial resolution of the deformation models in image registration.
Author: Hadi Fayad Publisher: ISBN: Category : Languages : en Pages : 198
Book Description
One of the most important parameters reducing the sensitivity and specificity in the thoracic and abdominal areas is respiratory motion and associated deformations which represent today an important challenge in medical imaging. In addition, respiratory motion reduces accuracy in image fusion from combined positron emission tomography computed tomography (PET/CT) systems. Solutions presented to date include respiratory synchronized PET and CT acquisitions. However, differences between acquired 4D PET and corresponding CT image series have been reported due to differences in respiration conditions during PET and CT acquisitions. In addition, the radiation dose burden resulting from a 4D CT acquisition may not be justifiable for every patient. The first objective of this thesis was to generate dynamic CT images from one reference CT image; based on deformation matrices obtained from the elastic registration of 4D non attenuation corrected PET images. Such an approach eliminates, on one hand the need for the acquisition of dynamic CT, while at the same time ensuring the good matching between CT and PET images. The second objective was to develop and evaluate methods of building patient specific respiratory motion models and at as a second step more developed generic respiratory motion models. These models relate the internal motion to the parameters of an external surrogate signal (PET respiratory signal or patient's surface) that can be acquired during data acquisition and treatment delivery. Finally, the two developed models were validated and used in the PET respiratory motion and attenuation correction and in radiation therapy applications.
Author: Jef Vandemeulebroucke Publisher: ISBN: Category : Languages : en Pages :
Book Description
The principal aim of this work is to provide methodological contributions for the quantification, characterization and representation of lung motion, in order to facilitate its inclusion in the radiotherapy treatment process. We describe a method for automatically extracting a motion mask, which divides the thorax into moving and less-moving regions. By providing an interface where sliding motion occurs, the discontinuity in the motion fields is preserved and registration is facilitated. Stronger smoothness constraints can be applied for each region separately while maintaining matching accuracy. Next, a spatio-temporal registration framework for respiratory-correlated imaging of the lungs is developed. A spatial transformation based on B-splines is extended to the temporal domain by coupling it to a cyclic trajectory model with suitable smoothness constraints. The obtained deformation model is shown to be capable of accurately representing respiratory motion while using a more compact and restrictive parameterisation. By enforcing the temporal coherence of the deformation across the breathing cycle, robustness to artefacts of subsequent deformable registration is improved. Finally, we investigated the feasibility of performing respiratory motion estimation from a cone-beam projection sequence. A prior is introduced in the form of a patient-specific model built from a previously acquired 4D~CT image. Motion estimation is accomplished by comparing the cone-beam projection sequence to projection views of the patient model. A semi-global optimisation approach is utilized, considering the entire breathing cycle and providing smooth motion estimates per cycle.
Author: Suk Jin Lee Publisher: Springer ISBN: 3642415091 Category : Technology & Engineering Languages : en Pages : 171
Book Description
This book describes recent radiotherapy technologies including tools for measuring target position during radiotherapy and tracking-based delivery systems. This book presents a customized prediction of respiratory motion with clustering from multiple patient interactions. The proposed method contributes to the improvement of patient treatments by considering breathing pattern for the accurate dose calculation in radiotherapy systems. Real-time tumor-tracking, where the prediction of irregularities becomes relevant, has yet to be clinically established. The statistical quantitative modeling for irregular breathing classification, in which commercial respiration traces are retrospectively categorized into several classes based on breathing pattern are discussed as well. The proposed statistical classification may provide clinical advantages to adjust the dose rate before and during the external beam radiotherapy for minimizing the safety margin. In the first chapter following the Introduction to this book, we review three prediction approaches of respiratory motion: model-based methods, model-free heuristic learning algorithms, and hybrid methods. In the following chapter, we present a phantom study—prediction of human motion with distributed body sensors—using a Polhemus Liberty AC magnetic tracker. Next we describe respiratory motion estimation with hybrid implementation of extended Kalman filter. The given method assigns the recurrent neural network the role of the predictor and the extended Kalman filter the role of the corrector. After that, we present customized prediction of respiratory motion with clustering from multiple patient interactions. For the customized prediction, we construct the clustering based on breathing patterns of multiple patients using the feature selection metrics that are composed of a variety of breathing features. We have evaluated the new algorithm by comparing the prediction overshoot and the tracking estimation value. The experimental results of 448 patients’ breathing patterns validated the proposed irregular breathing classifier in the last chapter.
Author: Dragan Indjin Publisher: MDPI ISBN: 303897370X Category : Engineering (General). Civil engineering (General) Languages : en Pages : 289
Book Description
This book is a printed edition of the Special Issue "Optical Methods in Sensing and Imaging for Medical and Biological Applications" that was published in Sensors
Author: Maxime Descoteaux Publisher: Springer ISBN: 331966185X Category : Computers Languages : en Pages : 803
Book Description
The three-volume set LNCS 10433, 10434, and 10435 constitutes the refereed proceedings of the 20th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2017, held inQuebec City, Canada, in September 2017. The 255 revised full papers presented were carefully reviewed and selected from 800 submissions in a two-phase review process. The papers have been organized in the following topical sections: Part I: atlas and surface-based techniques; shape and patch-based techniques; registration techniques, functional imaging, connectivity, and brain parcellation; diffusion magnetic resonance imaging (dMRI) and tensor/fiber processing; and image segmentation and modelling. Part II: optical imaging; airway and vessel analysis; motion and cardiac analysis; tumor processing; planning and simulation for medical interventions; interventional imaging and navigation; and medical image computing. Part III: feature extraction and classification techniques; and machine learning in medical image computing.
Author: J.D. Westwood Publisher: IOS Press ISBN: 1614996253 Category : Medical Languages : en Pages : 496
Book Description
In the early 1990s, a small group of individuals recognized how virtual reality (VR) could transform medicine by immersing physicians, students and patients in data more completely. Technical obstacles delayed progress but VR is now enjoying a renaissance, with breakthrough applications available for healthcare. This book presents papers from the Medicine Meets Virtual Reality 22 conference, held in Los Angeles, California, USA, in April 2016. Engineers, physicians, scientists, educators, students, industry, military, and futurists participated in its creative mix of unorthodox thinking and validated investigation. The topics covered include medical simulation and modeling, imaging and visualization, robotics, haptics, sensors, physical and mental rehabilitation tools, and more. Providing an overview of the state-of-the-art, this book will interest all those involved in medical VR and in innovative healthcare, generally.
Author: Marleen de Bruijne Publisher: Springer Nature ISBN: 3030872025 Category : Computers Languages : en Pages : 711
Book Description
The eight-volume set LNCS 12901, 12902, 12903, 12904, 12905, 12906, 12907, and 12908 constitutes the refereed proceedings of the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2021, held in Strasbourg, France, in September/October 2021.* The 531 revised full papers presented were carefully reviewed and selected from 1630 submissions in a double-blind review process. The papers are organized in the following topical sections: Part I: image segmentation Part II: machine learning - self-supervised learning; machine learning - semi-supervised learning; and machine learning - weakly supervised learning Part III: machine learning - advances in machine learning theory; machine learning - attention models; machine learning - domain adaptation; machine learning - federated learning; machine learning - interpretability / explainability; and machine learning - uncertainty Part IV: image registration; image-guided interventions and surgery; surgical data science; surgical planning and simulation; surgical skill and work flow analysis; and surgical visualization and mixed, augmented and virtual reality Part V: computer aided diagnosis; integration of imaging with non-imaging biomarkers; and outcome/disease prediction Part VI: image reconstruction; clinical applications - cardiac; and clinical applications - vascular Part VII: clinical applications - abdomen; clinical applications - breast; clinical applications - dermatology; clinical applications - fetal imaging; clinical applications - lung; clinical applications - neuroimaging - brain development; clinical applications - neuroimaging - DWI and tractography; clinical applications - neuroimaging - functional brain networks; clinical applications - neuroimaging – others; and clinical applications - oncology Part VIII: clinical applications - ophthalmology; computational (integrative) pathology; modalities - microscopy; modalities - histopathology; and modalities - ultrasound *The conference was held virtually.
Author: Jan Ehrhardt
Author: Jan Ehrhardt
Author: Yugang Min
Author: Elizabeth Shobha Zachariah
Author: Hadi Fayad
Author: Jef Vandemeulebroucke
Author: Suk Jin Lee
Author: Dragan Indjin
Author: Maxime Descoteaux
Author: J.D. Westwood
Author: Marleen de Bruijne