Muutke küpsiste eelistusi

Guide to Outcome Modeling In Radiotherapy and Oncology: Listening to the Data [Kõva köide]

4.00/5 (2 hinnangut Goodreads-ist)
Edited by (University of Michigan, Ann Arbor, USA)
Teised raamatud teemal:
Guide to Outcome Modeling In Radiotherapy and Oncology: Listening to the DataSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781498768054.html
Märksõnad:
This book explores outcome modeling in cancer from a data-centric perspective to enable a better understanding of complex treatment response, to guide the design of advanced clinical trials, and to aid personalized patient care and improve their quality of life. It contains coverage of the relevant data sources available for model construction (panomics), ranging from clinical or preclinical resources to basic patient and treatment characteristics, medical imaging (radiomics), and molecular biological markers such as those involved in genomics, proteomics and metabolomics. It also includes discussions on the varying methodologies for predictive model building with analytical and data-driven approaches.

This book is primarily intended to act as a tutorial for newcomers to the field of outcome modeling, as it includes in-depth how-to recipes on modeling artistry while providing sufficient instruction on how such models can approximate the physical and biological realities of clinical treatment. The book will also be of value to seasoned practitioners as a reference on the varying aspects of outcome modeling and their current applications.

Features:





Covers top-down approaches applying statistical, machine learning, and big data analytics and bottom-up approaches using first principles and multi-scale techniques, including numerical simulations based on Monte Carlo and automata techniques Provides an overview of the available software tools and resources for outcome model development and evaluation, and includes hands-on detailed examples throughout Presents a diverse selection of the common applications of outcome modeling in a wide variety of areas: treatment planning in radiotherapy, chemotherapy and immunotherapy, utility-based and biomarker applications, particle therapy modeling, oncological surgery, and the design of adaptive and SMART clinical trials
Section I Multiple Sources of Data
Chapter 1 Introduction to data sources and outcome models
3(10)
Issam El Naqa
Randall K. Ten Haken
1.1 Introduction To Outcome Modeling
4(1)
1.2 Model Definition
4(2)
1.3 Types Of Outcome Models
6(3)
1.3.1 Prognostic versus predictive models
6(1)
1.3.2 Top-down versus bottom-up models
6(1)
1.3.3 Analytical versus data-driven models
7(2)
1.4 Types Of Data Used In Outcome Models
9(1)
1.5 The Five Steps Towards Building An Outcome Model
9(2)
1.6 Conclusions
11(2)
Chapter 2 Clinical data in outcome models
13(12)
Nicholas J. Denunzio
Sarah L. Kerns
Michael T. Milano
2.1 Introduction
14(2)
2.2 Collagen Vascular Disease
16(1)
2.3 Genetic Studies
17(2)
2.4 Biological Factors Impacting Toxicity After SBRT
19(4)
2.4.1 Chest wall toxicity after SBRT
20(1)
2.4.2 Radiation-induced lung toxicity (RILT) after SBRT
20(2)
2.4.3 Radiation-induced liver damage (RILD) after SBRT
22(1)
2.5 Big Data
23(1)
2.6 Conclusions
23(2)
Chapter 3 Imaging data (radiomics)
25(8)
Issam El Naqa
3.1 Introduction
25(1)
3.2 Image Features Extraction
26(2)
3.2.1 Static image features
26(1)
3.2.2 Dynamic image features
27(1)
3.3 Radiomics Examples From Different Cancer Sites
28(3)
3.3.1 Predicting local control in lung cancer using PET/CT
28(2)
3.3.2 Predicting distant metastasis in sarcoma using PET/MR
30(1)
3.4 Conclusions
31(2)
Chapter 4 Dosimetric data
33(14)
Issam El Naqa
Randall K. Ten Haken
4.1 Introduction
34(1)
4.2 Dose Volume Metrics
35(1)
4.3 Equivalent Uniform Dose
36(2)
4.4 Dosimetric Model Variable Selection
38(1)
4.4.1 Model order based on information theory
38(1)
4.4.2 Model order based on resampling methods
38(1)
4.5 A Dosimetric Modeling Example
39(5)
4.5.1 Data set
39(1)
4.5.2 Data exploration
40(1)
4.5.3 Multivariate modeling with logistic regression
41(1)
4.5.4 Multivariate modeling with machine learning
42(1)
4.5.5 Comparison with other known models
43(1)
4.6 Software Tools For Dosimetric Outcome Modeling
44(1)
4.7 Conclusions
45(2)
Chapter 5 Pre-clinical radiobiological insights to inform modelling of radiotherapy outcome
47(6)
Peter Van Luijk
And Robert P. Coppes
5.1 Variability In Response To Highly Standardized Radio-Therapy
48(1)
5.2 Variation In Sensitivity To Radiation
49(1)
5.3 Understanding Dose-Response Of Tissues And Organs
50(1)
5.4 Animal Models To Study Radiation Response
50(1)
5.5 Processes Governing Outcome
51(1)
5.6 Patient-Individual Factors/Co-Morbidity
52(1)
5.7 Use In Models
52(1)
5.8 Conclusion
52(1)
Chapter 6 Radiogenomics
53(12)
Issam El Naqa
Sarah L. Kerns
James Coates
Yi Luo
Corey Speers
Randall K. Ten Haken
Catharine M.L. West
Barry S. Rosenstein
6.1 Introduction
54(1)
6.2 Biomarkers And The World Of "-Omics"
54(5)
6.2.1 Structural variations
56(1)
6.2.1.1 Single nucleotide polymorphisms (SNPs)
56(1)
6.2.1.2 Copy number variations (CNVs)
56(1)
6.2.2 Gene expression: mRNA, miRNA, 1ncRNA
57(1)
6.2.3 Protein expression
57(2)
6.2.4 Metabolites
59(1)
6.3 Resources For Biological Data
59(1)
6.4 Examples Of Radiogenomic Modeling
60(2)
6.4.1 Prostate cancer
60(1)
6.4.2 Breast cancer
61(1)
6.4.3 Lung cancer
61(1)
6.5 Conclusions
62(3)
Section II Top-down Modeling Approaches
Chapter 7 Analytical and mechanistic modeling
65(20)
Vitali Moiseenko
Jimm Grimm
James D. Murphy
David J. Carlson
Issam El Naqa
7.1 Introduction
66(1)
7.2 Track Structure And DNA Damage
67(2)
7.3 Linear-Quadratic Model
69(4)
7.4 Kinetic Reaction Rate Models
73(4)
7.4.1 Repair-misrepair and lethal-potentially-lethal models
73(1)
7.4.2 Refined models
74(1)
7.4.3 The Giant LOop Binary LEsion (GLOBE)
75(1)
7.4.4 Local Effect Model (LEM)
75(1)
7.4.5 Microdosimetric-kinetic model (MKM)
76(1)
7.4.6 The Repair-misrepair-fixation model
76(1)
7.5 Mechanistic Modeling Of Stereotactic Radiosurgery (SRS) And Stereotactic Body Radiotherapy (SBRT)
77(4)
7.5.1 LQ limitations and alternative models
79(2)
7.6 Incorporating Biological Data To Describe And Predict Biological Response
81(1)
7.7 Conclusions
82(3)
Chapter 8 Data driven approaches I: conventional statistical inference methods, including linear and logistic regression
85(44)
Tiziana Rancati
Claudio Fiorino
8.1 What Is A Regression
86(1)
8.2 Linear Regression
87(14)
8.2.1 Mathematical formalism
88(1)
8.2.2 Estimation of regression coefficients
88(1)
8.2.3 Accuracy of coefficient estimates
89(1)
8.2.4 Rejecting the null hypothesis
89(1)
8.2.5 Accuracy of the model
90(1)
8.2.6 Qualitative predictors
91(1)
8.2.7 Including interactions between variables
92(1)
8.2.8 Linear regression: example
93(8)
8.3 Logistic Regression
101(8)
8.3.1 Modelling of qualitative (binary) response
101(2)
8.3.2 Mathematical formalism
103(2)
8.3.3 Estimation of regression coefficients
105(1)
8.3.4 Accuracy of coefficient estimates
105(1)
8.3.5 Rejecting the null hypothesis, testing the significance of a model
106(1)
8.3.6 Accuracy of the model
106(2)
8.3.7 Qualitative predictors
108(1)
8.3.8 Including interaction between variables
108(1)
8.3.9 Statistical power for reliable predictions
108(1)
8.3.10 Time consideration
109(1)
8.4 Model Validation
109(4)
8.4.1 Apparent validation
111(1)
8.4.2 Internal validation
111(1)
8.4.3 External validation
112(1)
8.5 Evaluation Of An Extended Model
113(1)
8.6 Feature Selection
113(14)
8.6.1 Classical approaches
114(1)
8.6.2 Shrinking and regularization methods: LASSO
115(1)
8.6.3 Bootstrap methods
116(2)
8.6.4 Logistic regression: example
118(9)
8.7 Conclusions
127(2)
Chapter 9 Data driven approaches II: Machine Learning
129(18)
Sarah Gulliford
9.1 Introduction
130(2)
9.2 Feature Selection
132(2)
9.2.1 Principal Component Analysis (PCA)
132(1)
9.2.1.1 When should you use them?
133(1)
9.2.1.2 Who has already used them?
133(1)
9.3 Flavors Of Machine Learning
134(8)
9.3.1 Artificial Neural Networks
134(1)
9.3.1.1 The basics
134(1)
9.3.1.2 When should you use them?
136(1)
9.3.1.3 Who has already used them?
136(1)
9.3.2 Support Vector Machine
137(1)
9.3.2.1 The basics
137(1)
9.3.2.2 When should you use them?
137(1)
9.3.2.3 Who has already used them?
138(1)
9.3.3 Decision Trees and Random Forests
138(1)
9.3.3.1 The basics
138(1)
9.3.3.2 When should you use them?
139(1)
9.3.3.3 Who has already used them?
139(1)
9.3.4 Bayesian approaches
140(1)
9.3.4.1 The basics
140(1)
9.3.4.2 When should you use them?
140(1)
9.3.4.3 Who has already used them?
141(1)
9.4 Practical Implementation
142(1)
9.4.1 The data
142(1)
9.4.2 Model fitting and assessment
142(1)
9.5 Conclusions
143(1)
9.6 Resources
143(4)
Section III Bottom-up Modeling Approaches
Chapter 10 Stochastic multi-scale modeling of biological effects induced by ionizing radiation
147(34)
Werner Friedland
Pavel Kundrat
10.1 Introduction
148(3)
10.2 Particle Tracks: Physical Stage
151(10)
10.3 Particle Tracks: Physicochemical And Chemical Stage
161(4)
10.4 Multi-Scale DNA And Chromatin Models
165(4)
10.5 Induction Of DBA And Chromatin Damage
169(3)
10.6 Dna Damage Response
172(7)
10.7 Modeling Beyond Single-Cell Level
179(1)
10.8 Conclusions
180(1)
Chapter 11 Multi-scale modeling approaches: application in chemo- and immuno-therapies
181(16)
Issam El Naqa
11.1 Introduction
182(1)
11.2 Medical Oncology Treatments
183(2)
11.2.1 From chemotherapy to molecular targeted agents
183(1)
11.2.2 Immunotherapy
184(1)
11.3 Modeling Types
185(5)
11.3.1 Continuum tumor modeling
185(3)
11.3.2 Discrete tumor modeling
188(1)
11.3.3 Hybrid tumor modeling
189(1)
11.4 Modeling Examples
190(3)
11.4.1 Modeling of chemotherapy
190(2)
11.4.2 Modeling of immunotherapy
192(1)
11.5 Software Tools For Multi-Scale Modeling
193(1)
11.6 Conclusions
194(3)
Section IV Example Applications in Oncology
Chapter 12 Outcome modeling in treatment planning
197(28)
X. Sharon Qi
Mariana Guerrero
X. Allen Li
12.1 Introduction
199(3)
12.1.1 Review of the history and dose-volume based treatment plan- ning and its limitations
199(1)
12.1.2 Emerging dose-response modeling in treatment planning and advantages
200(2)
12.2 Dose-Response Models
202(6)
12.2.1 Generalized equivalent uniform dose (gEUD)
202(1)
12.2.1.1 Serial and parallel organ models
202(1)
12.2.2 Linear-Quadratic (LQ) Model
203(1)
12.2.3 Biological effective dose (BED)
204(1)
12.2.4 Tumor control probability (TCP) models
204(2)
12.2.5 Normal Tissue Complication Model (NTCP) models
206(1)
12.2.5.1 Lyman-Kutcher-Burman (LKB) model
206(1)
12.2.5.2 Relative seriality (RS) model
207(1)
12.2.5.3 Model parameters and Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC)
207(1)
12.2.6 Combined TCP/NTCP models -Uncomplicated tumor control model (UTCP or P+)
208(1)
12.3 Dose-Response Models For Stereotactic Body Radiotherapy (SBRT)
208(6)
12.3.1 Linear-Quadratic (LQ) model applied to SBRT
208(1)
12.3.2 Universal survival curve (USC) model
209(1)
12.3.3 Linear-Quadratic-Linear (LQL) model
210(1)
12.3.4 Regrowth model
211(1)
12.3.5 Dose limits for SBRT treatments
211(3)
12.4 Biological Models In Treatment Planning
214(2)
12.4.1 Plan evaluation
214(1)
12.4.2 Plan optimization
215(1)
12.4.3 Dose summation using biological models
215(1)
12.4.4 Selection of outcome models and model parameters
216(1)
12.5 Commercially Available Treatment Planning Systems (TPS) Employing Outcome Models
216(8)
12.5.1 Elekta Monaco system (Maryland Heights, MO)
216(2)
12.5.2 Philips Pinnacle system (Andover, MA)
218(1)
12.5.2.1 Sensitivity of model parameters
219(1)
12.5.3 Varian Eclipse system (Palo Alto, CA)
220(1)
12.5.3.1 Objective functions in plan optimization
220(1)
12.5.3.2 Plan evaluation
221(1)
12.5.3.3 Sensitivity of model parameters
222(1)
12.5.4 RaySearch RayStation (Stockholm, Sweden)
222(1)
12.5.4.1 Plan evaluation tools
222(1)
12.5.4.2 Plan optimization tools
222(1)
12.5.5 MIM (MIM Software Inc., Cleveland, OH)
222(1)
12.5.5.1 Plan summation
223(1)
12.5.5.2 Plan evaluation
223(1)
12.6 Conclusions
224(1)
Chapter 13 A utility based approach to individualized and adaptive radiation therapy
225(10)
Matthew J. Schipper
13.1 Introduction
226(1)
13.2 Background
226(3)
13.2.1 Treatment planning in radiation therapy
226(1)
13.2.2 Biomarkers in RT
227(2)
13.3 Utility Approach To Plan Optimization
229(5)
13.3.1 In phase I trials
229(1)
13.3.2 In RT treatment planning
229(2)
13.3.3 Choice of the tradeoff parameter
231(1)
13.3.4 Virtual clinical trial
231(3)
13.4 Conclusions
234(1)
Chapter 14 Outcome modeling in Particle therapy
235(24)
J. Schuemann
A.L. Mcnamara
C. Grassberger
14.1 How Are Particles Different From Photons?
236(2)
14.2 Linear Energy Transfer (LET)
238(2)
14.2.1 Dose averaging, track averaging and limitations
238(2)
14.3 Relative Biological Effectiveness
240(8)
14.3.1 The 1.1 conundrum in proton therapy
241(1)
14.3.2 LET based RBE models
242(2)
14.3.3 Non-LET based
244(1)
14.3.3.1 Track structure (8-ray) model
246(1)
14.3.4 Uncertainties
247(1)
14.4 The Role Of Monte Carlo
248(5)
14.4.1 Understanding dose and LET distributions
248(1)
14.4.1.1 Range uncertainties
248(1)
14.4.1.2 Considerations for dose and DVH
250(1)
14.4.1.3 LET
250(2)
14.4.2 RBE modeling
252(1)
14.4.3 Example MC simulations using TOPAS
252(1)
14.4.3.1 2-spot pencil setup
252(1)
14.4.3.2 Expansion to include patient setup, dose, LET and one RBE scorer
253(1)
14.5 Implications Of Particle Therapy For Outcome Models
253(2)
14.5.1 Target effects
254(1)
14.5.2 Normal Tissue effects
255(1)
14.6 Application In Treatment Planning
255(5)
14.6.1 Vision for the future
256(3)
Chapter 15 Modeling response to oncological surgery
259(24)
J. Jesus Naveja
Leonardo Zapata-Fonseca
Flavio F. Contreras-Torres
15.1 Introduction To Oncological Surgery
260(2)
15.1.1 Clinical and surgical factors modifying patients' outcomes
260(1)
15.1.2 Complementary therapies to oncological surgery
261(1)
15.2 Modeling Of Oncological Surgery
262(5)
15.2.1 Computational oncology models
262(2)
15.2.2 Mechanistic models from physical oncology
264(1)
15.2.2.1 Relevant variables
264(1)
15.2.2.2 Implemented models
266(1)
15.3 Example: A Bidimensional Oncological Surgery Simulation Model
267(7)
15.3.1 Step 1: diffusion of nutrients
268(1)
15.3.2 Step 2: CA rules and tumor growth constrained by the nutrients concentration and immune system response
269(2)
15.3.3 Step 3: surgery
271(3)
15.4 Discussion
274(1)
15.5 Conclusions And Perspectives
274(1)
15.6 Appendix 1: R Code
275(8)
Chapter 16 Tools for the precision medicine era: developing highly adaptive and personalized treatment recommendations using SMARTS
283(82)
Elizabeth F. Krakow
Erica E.M. Moodie
16.1 Introduction
284(1)
16.2 Studying Treatments In Sequence
285(5)
16.2.1 Adaptive treatment strategies
285(1)
16.2.2 Decision rules
285(1)
16.2.3 Tailoring variables are key for personalized recommendations
285(3)
16.2.4 Machine learning "teaches" us the optimal ATS
288(2)
16.3 Comparison To Traditional Methods
290(4)
16.3.1 Why might RCTs fail to identify good treatment sequences?
290(1)
16.3.2 Why can't we combine results from separate, single-stage RCTs?
291(2)
16.3.3 What are the advantages of SMARTs?
293(1)
16.3.4 Motivating example
294(1)
16.4 Validating A Proposed ATS
294(3)
16.4.1 If we find an optimal ATS with a SMART, do we still need an RCT?
294(2)
16.4.2 Are SMARTs used in cancer?
296(1)
16.5 Challenges And Opportunities
297(68)
Index 365
Issam El Naqa is an Associate Professor of Radiation Oncology at the University of Michigan at Ann Arbor, USA.