Atjaunināt sīkdatņu piekrišanu

Prediction and Classification of Respiratory Motion 2014 ed. [Hardback]

,
  • Formāts: Hardback, 167 pages, height x width: 235x155 mm, weight: 3967 g, 65 Illustrations, color; 2 Illustrations, black and white; IX, 167 p. 67 illus., 65 illus. in color., 1 Hardback
  • Sērija : Studies in Computational Intelligence 525
  • Izdošanas datums: 12-Nov-2013
  • Izdevniecība: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3642415083
  • ISBN-13: 9783642415081
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 91,53 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Standarta cena: 107,69 €
  • Ietaupiet 15%
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
Prediction and Classification of Respiratory Motion 2014 ed.Palielināt
  • Formāts: Hardback, 167 pages, height x width: 235x155 mm, weight: 3967 g, 65 Illustrations, color; 2 Illustrations, black and white; IX, 167 p. 67 illus., 65 illus. in color., 1 Hardback
  • Sērija : Studies in Computational Intelligence 525
  • Izdošanas datums: 12-Nov-2013
  • Izdevniecība: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3642415083
  • ISBN-13: 9783642415081
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9783642415081.html
Keywords:
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 studyprediction of human motion with distributed body sensorsusing 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 thetracking estimation value. The experimental results of 448 patients breathing patterns validated the proposed irregular breathing classifier in the last chapter.
1 Introduction 1(6)
References
3(4)
2 Review: Prediction of Respiratory Motion 7(32)
2.1 Tools for Measuring Target Position During Radiotherapy
7(3)
2.1.1 Radiographs
8(1)
2.1.2 Fiducial Markers
8(1)
2.1.3 Fluoroscopy
8(1)
2.1.4 Computed Tomography
8(1)
2.1.5 Magnetic Resonance Imaging
9(1)
2.1.6 Optical Imaging
9(1)
2.2 Tracking-Based Delivery Systems
10(3)
2.2.1 Linear Accelerator
10(1)
2.2.2 Multileaf Collimator
11(1)
2.2.3 Robotic Couch
12(1)
2.3 Prediction Algorithms for Respiratory Motion
13(17)
2.3.1 Model-Based Prediction Algorithms
14(8)
2.3.2 Model-Free Prediction Algorithms
22(3)
2.3.3 Hybrid Prediction Algorithms
25(5)
2.4 Open Questions for Prediction of Respiratory Motion
30(1)
2.4.1 Changes of Respiratory Patterns
31(1)
2.4.2 Tumor Deformation and Target Dosimetry
31(1)
2.4.3 Irregular Pattern Detection
31(1)
2.5 Summary
31(1)
References
32(7)
3 Phantom: Prediction of Human Motion with Distributed Body Sensors 39(28)
3.1 Introduction
39(2)
3.2 Related Work
41(4)
3.2.1 Kalman Filter
41(1)
3.2.2 Interacting Multiple Model Framework
42(1)
3.2.3 Cluster Number Selection Using Gaussian Mixture Model and Expectation-Maximization Algorithm
43(2)
3.3 Proposed Grouping Criteria with Distributed Sensors
45(3)
3.3.1 Collaborative Grouping with Distributed Body Sensors
45(2)
3.3.2 Estimated Parameters Used for Interacting Multiple Model Estimator
47(1)
3.4 Sensors Multi-Channel IMME: Proposed System Design
48(4)
3.4.1 MC Mixed Initial Condition and the Associated Covariance
49(1)
3.4.2 MC Likelihood Update
50(1)
3.4.3 Switching Probability Update
50(1)
3.4.4 Feedback from Switching Probability Update to Stage 1 for Grouping Criteria with Distributed Sensors
50(1)
3.4.5 Combination of MC Conditioned Estimates and Covariance
51(1)
3.4.6 Computational Time
51(1)
3.5 Experimental Results
52(12)
3.5.1 Motion Data
53(1)
3.5.2 Collaborative Grouping Initialization
53(4)
3.5.3 Comparison of Grouping Methods with Other Techniques
57(1)
3.5.4 Multi-Channel IMME
58(3)
3.5.5 Prediction Overshoot
61(1)
3.5.6 Computational Time
62(2)
3.6 Summary
64(1)
References
64(3)
4 Respiratory Motion Estimation with Hybrid Implementation 67(24)
4.1 Introduction
67(2)
4.2 Related Work
69(3)
4.2.1 Recurrent Neural Network
69(2)
4.2.2 Extended Kalman Filter for Recurrent Neural Networks
71(1)
4.3 Multi-Channel Coupled EKF-RNN
72(7)
4.3.1 Decoupled Extended Kalman Filter
72(2)
4.3.2 Hybrid Estimation Based on EKF for Neural Network
74(1)
4.3.3 Optimized Group Number for Recurrent Multilayer Perceptron
75(2)
4.3.4 Prediction Overshoot Analysis
77(1)
4.3.5 Comparisons on Computational Complexity and Storage Requirement
78(1)
4.4 Experimental Results
79(7)
4.4.1 Motion Data Captured
79(1)
4.4.2 Optimized Group Number for RMLP
80(1)
4.4.3 Prediction Overshoot Analysis
81(1)
4.4.4 Comparison on Estimation Performance
82(2)
4.4.5 Error Performance Over Prediction Time Horizon
84(1)
4.4.6 Comparisons on Computational Complexity
84(2)
4.5 Summary
86(1)
References
87(4)
5 Customized Prediction of Respiratory Motion 91(18)
5.1 Introduction
91(1)
5.2 Prediction Process for Each Patient
92(2)
5.3 Proposed Filter Design for Multiple Patients
94(4)
5.3.1 Grouping Breathing Pattern for Prediction Process
95(2)
5.3.2 Neuron Number Selection
97(1)
5.4 Experimental Results
98(6)
5.4.1 Breathing Motion Data
98(1)
5.4.2 Feature Selection Metrics
98(1)
5.4.3 Comparison on Estimation Performance
99(1)
5.4.4 Prediction Accuracy with Time Horizontal Window
100(2)
5.4.5 Prediction Overshoot Analysis
102(2)
5.4.6 Comparisons on Computational Complexity
104(1)
5.5 Summary
104(1)
References
105(4)
6 Irregular Breathing Classification from Multiple Patient Datasets 109(26)
6.1 Introduction
109(2)
6.2 Related Work
111(2)
6.2.1 Expectation-Maximization Based on Gaussian Mixture Model
111(1)
6.2.2 Neural Network
112(1)
6.3 Proposed Algorithms on Irregular Breathing Classifier
113(6)
6.3.1 Feature Extraction from Breathing Analysis
113(2)
6.3.2 Clustering of Respiratory Patterns Based on EM
115(1)
6.3.3 Reconstruction Error for Each Cluster Using NN
116(1)
6.3.4 Detection of Irregularity Based on Reconstruction Error
117(2)
6.4 Evaluation Criteria for Irregular Breathing Classifier
119(2)
6.4.1 Sensitivity and Specificity
119(1)
6.4.2 Receiver Operating Characteristics
120(1)
6.5 Experimental Results
121(9)
6.5.1 Breathing Motion Data
121(1)
6.5.2 Selection of the Estimated Feature Metrics (x)
122(1)
6.5.3 Clustering of Respiratory Patterns Based on EM
123(1)
6.5.4 Breathing Pattern Analysis to Detect Irregular Pattern
123(4)
6.5.5 Classifier Performance
127(3)
6.6 Summary
130(1)
References
131(4)
7 Conclusions and Contributions 135(4)
7.1 Conclusions
135(1)
7.1.1 Hybrid Implementation of Extended Kalman Filter
135(1)
7.1.2 Customized Prediction of Respiratory Motion with Clustering
135(1)
7.1.3 Irregular Breathing Classification from Multiple Patient Datasets
136(1)
7.2 Contributions
136(3)
Appendix A 139(6)
Appendix B 145