Muutke küpsiste eelistusi

Machine Learning: Methods and Applications to Brain Disorders [Pehme köide]

4.00/5 (2 hinnangut Goodreads-ist)
Edited by (Professor of Early Intervention in Mental Health at the Institute of Psychiatry, Psychology & Neuroscience, Kings College London, UK), Edited by (Researcher at the Institute of Psychiatry, Psychology & Neuroscience, Kings College London, UK)
  • Formaat: Paperback / softback, 408 pages, kõrgus x laius: 229x152 mm, kaal: 610 g
  • Ilmumisaeg: 15-Nov-2019
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0128157399
  • ISBN-13: 9780128157398
Teised raamatud teemal:
Machine Learning: Methods and Applications to Brain DisordersSuurem pilt
  • Formaat: Paperback / softback, 408 pages, kõrgus x laius: 229x152 mm, kaal: 610 g
  • Ilmumisaeg: 15-Nov-2019
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0128157399
  • ISBN-13: 9780128157398
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780128157398.html
Märksõnad:

Machine Learning is an area of artificial intelligence involving the development of algorithms to discover trends and patterns in existing data; this information can then be used to make predictions on new data. A growing number of researchers and clinicians are using machine learning methods to develop and validate tools for assisting the diagnosis and treatment of patients with brain disorders. Machine Learning: Methods and Applications to Brain Disorders provides an up-to-date overview of how these methods can be applied to brain disorders, including both psychiatric and neurological disease. This book is written for a non-technical audience, such as neuroscientists, psychologists, psychiatrists, neurologists and health care practitioners.

  • Provides a non-technical introduction to machine learning and applications to brain disorders
  • Includes a detailed description of the most commonly used machine learning algorithms as well as some novel and promising approaches
  • Covers the main methodological challenges in the application of machine learning to brain disorders
  • Provides a step-by-step tutorial for implementing a machine learning pipeline to neuroimaging data in Python

Arvustused

"This is a fantastic resource for researchers and clinicians interested in the application of artificial intelligence to brain disorders. The most up-to-date approaches are covered, using a rigorous yet accessible language. The step-by-step practical guide will be particularly useful to those taking their first steps in this field." --Qiyong Gong, MD, PhD

Contributors xi
Preface xiii
Part 1
1 Introduction to machine learning
Sandra Vieira
Walter Hugo Lopez Pinaya
Andrea Mechelli
1.1 Introduction
1(1)
1.2 From human learning to machine learning
2(2)
1.3 What is machine learning?
4(1)
1.4 How is machine learning relevant to brain disorders?
5(4)
1.5 Different types of machine learning
9(4)
1.6 Conclusion
13(1)
1.7 Key points
14(1)
References
14(7)
2 Main concepts in machine learning
Sandra Vieira
Walter Hugo Lopez Pinaya
Andrea Mechelli
2.1 Introduction
21(1)
2.2 Problem formulation
22(1)
2.3 Data preparation
23(1)
2.4 Feature engineering
23(5)
2.5 Model training
28(8)
2.6 Model evaluation
36(5)
2.7 Post hoc analysis
41(1)
2.8 Conclusion
42(1)
2.9 Key points
42(1)
References
43(2)
3 Applications of machine learning to brain disorders
Cristina Scarpazza
Lea Baecker
Sandra Vieira
Andrea Mechelli
3.1 Introduction
45(1)
3.2 Why are people interested in machine learning?
45(5)
3.3 What are the main challenges in machine learning studies of psychiatric and neurological disorders?
50(5)
3.4 How good is good enough?
55(2)
3.5 Is machine learning ready to be applied in psychiatry and neurology?
57(2)
3.6 Future directions and concluding remarks
59(1)
3.7 Key points
60(1)
References
60(7)
Part 2
4 Linear regression
Thomas M.H. Hope
4.1 Introduction
67(2)
4.2 Method description
69(5)
4.3 Applications to brain disorders
74(5)
4.4 Conclusions
79(1)
4.5 Key points
80(1)
References
80(3)
5 Linear methods for classification
Andre F. Marquand
Seyed Mostafa Kia
5.1 Introduction
83(2)
5.2 Method description
85(6)
5.3 Applications to brain disorders
91(5)
5.4 Conclusion
96(1)
5.5 Key points
97(1)
References
97(4)
6 Support vector machine
Derek A. Pisner
David M. Schnyer
6.1 Introduction
101(1)
6.2 Method description
102(7)
6.3 Applications to brain disorders
109(8)
6.4 Conclusion
117(1)
6.5 Key points
117(1)
References
118(3)
Further reading
121(2)
7 Support vector regression
Fan Zhang
Lauren J. O'Donnell
7.1 Introduction
123(2)
7.2 Method description
125(6)
7.3 Applications to brain disorders
131(5)
7.4 Conclusion
136(1)
7.5 Key points
137(1)
References
137(4)
8 Multiple kernel learning
Letizia Squarcina
Umberto Castellani
Paolo Brambilla
8.1 Introduction
141(2)
8.2 Method description
143(5)
8.3 Applications to brain disorders
148(5)
8.4 Conclusion
153(1)
8.5 Key points
153(1)
Acknowledgments
154(1)
References
154(3)
9 Deep neural networks
Sandra Vieira
Walter Hugo Lopez Pinaya
Rafael Garcia-Dias
Andrea Mechelli
9.1 Introduction
157(2)
9.2 Method description
159(7)
9.3 Applications to brain disorders
166(3)
9.4 Conclusion
169(1)
9.5 Key points
170(1)
References
170(3)
10 Convolutional neural networks
Walter Hugo Lopez Pinaya
Sandra Vieira
Rafael Garcia-Dias
Andrea Mechelli
10.1 Introduction
173(2)
10.2 Method description
175(9)
10.3 Applications to brain disorders
184(4)
10.4 Conclusion
188(1)
10.5 Key points
189(1)
References
189(4)
11 Autoencoders
Walter Hugo Lopez Pinaya
Sandra Vieira
Rafael Garcia-Dias
Andrea Mechelli
11.1 Introduction
193(1)
11.2 Method description
194(7)
11.3 Applications to brain disorders
201(5)
11.4 Conclusion
206(1)
11.5 Key points
207(1)
References
207(2)
12 Principal component analysis
Ferath Kherif
Adeliya Latypova
12.1 Introduction
209(3)
12.2 Method description
212(6)
12.3 Applications to brain disorders
218(6)
12.4 Conclusion
224(1)
12.5 Key points
224(1)
References
224(3)
13 Clustering analysis
Rafael Garcia-Dias
Sandra Vieira
Walter Hugo Lopez Pinaya
Andrea Mechelli
13.1 Introduction
227(3)
13.2 Method description
230(10)
13.3 Applications to brain disorders
240(4)
13.4 Conclusion
244(1)
13.5 Key points
245(1)
References
245(4)
Part 3
14 Dealing with missing data, small sample sizes, and heterogeneity in machine learning studies of brain disorders
Rajat M. Thomas
Willem Bruin
Paul Zhutovsky
Guido van Wingen
14.1 Introduction
249(2)
14.2 Data simulation
251(2)
14.3 Algorithms and procedures
253(9)
14.4 Conclusions
262(2)
14.5 Key points
264(1)
Acknowledgments
264(1)
References
264(3)
15 Working with high-dimensional feature spaces: the example of voxel-wise encoding models
Mohammad Babakmehr
Ghislain St-Yves
Thomas Naselaris
15.1 Introduction
267(1)
15.2 Voxel-wise encoding modeling
268(10)
15.3 Applications to brain disorders
278(1)
15.4 Conclusion
279(1)
15.5 Key points
280(1)
References
280(2)
Further reading
282(1)
16 Multimodal integration
Sandra Vieira
Walter Hugo Lopez Pinaya
Rafael Garcia-Dias
Andrea Mechelli
16.1 Introduction
283(4)
16.2 Early multimodal data integration: data fusion
287(4)
16.3 Intermediate multimodal integration: kernel-based methods and deep learning
291(3)
16.4 Late multimodal integration: ensemble methods
294(2)
16.5 Application to brain disorders
296(5)
16.6 Conclusion
301(1)
16.7 Key points
302(1)
References
302(5)
17 Bias, noise, and interpretability in machine learning: from measurements to features
Hugo Schnack
17.1 Introduction
307(2)
17.2 Main sources of bias and noise in machine learning
309(2)
17.3 Data processing
311(7)
17.4 Applications to brain disorders
318(6)
17.5 Conclusion
324(1)
17.6 Key points
325(1)
Acknowledgments
325(1)
References
325(4)
18 Ethical issues in the application of machine learning to brain disorders
Philipp Kellmeyer
18.1 Introduction
329(1)
18.2 Applications of machine learning to brain disorders
330(1)
18.3 Ethical tensions from using machine learning in brain disorders
331(7)
18.4 Conclusion
338(1)
18.5 Key points
339(1)
References
339(3)
Further reading
342(1)
Part 4
19 A step-by-step tutorial on how to build a machine learning model
Sandra Vieira
Rafael Garcia-Dias
Walter Hugo Lopez Pinaya
19.1 Introduction
343(1)
19.2 Installing Python and main libraries
344(1)
19.3 How to read this chapter
345(1)
19.4 Using brain morphometry to classify patients with schizophrenia and healthy controls
345(2)
19.5 Sample code
347(21)
19.6 Conclusion
368(2)
References
370 (1)
Glossary 371(8)
Index 379
Andrea Mechelli is a clinical psychologist and a neuroscientist with an interest in the early detection and treatment of mental illness. After studying Psychology at the University of Padua (1999), he completed a PhD in Neurological Sciences at University College London in 2002 and became an academic member of staff at King's College London in 2004. He currently holds the position of Professor of Early Intervention in Mental Health at the Institute of Psychiatry, Psychology & Neuroscience at King's College London. Prof. Mechelli's research involves the application of advanced machine learning methods to clinical, neuroimaging and smartphone data, with the aim of developing and validating novel tools for early detection and treatment. Sandra Vieira is a postdoctoral researcher at the Institute Psychiatry, Psychology & Neuroscience (King's College London). After completing a degree in Psychology (2009) and a Masters in Clinical Psychology (2011) at the University of Coimbra, she joined the Institute Psychiatry, Psychology & Neuroscience. Here she obtained a Masters in Psychiatric Research in 2014 and a PhD in Psychosis Studies in 2019. Her research focuses on the integration of advanced machine learning methods and multi-modal neuroimaging to investigate the neural basis of mental illness and develop imaging-based clinical tools.