Atjaunināt sīkdatņu piekrišanu

Artificial Intelligence and Deep Learning in Pathology [Mīkstie vāki]

4.00/5 (1 ratings by Goodreads)
Edited by (PhD, MD)
  • Formāts: Paperback / softback, 288 pages, height x width: 235x191 mm, weight: 590 g
  • Izdošanas datums: 02-Jun-2020
  • Izdevniecība: Elsevier - Health Sciences Division
  • ISBN-10: 0323675387
  • ISBN-13: 9780323675383
Citas grāmatas par šo tēmu:
  • Mīkstie vāki
  • Cena: 100,22 €
  • 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
Artificial Intelligence and Deep Learning in PathologyPalielināt
  • Formāts: Paperback / softback, 288 pages, height x width: 235x191 mm, weight: 590 g
  • Izdošanas datums: 02-Jun-2020
  • Izdevniecība: Elsevier - Health Sciences Division
  • ISBN-10: 0323675387
  • ISBN-13: 9780323675383
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9780323675383.html
Keywords:

Recent advances in computational algorithms, along with the advent of whole slide imaging as a platform for embedding artificial intelligence (AI), are transforming pattern recognition and image interpretation for diagnosis and prognosis. Yet most pathologists have just a passing knowledge of data mining, machine learning, and AI, and little exposure to the vast potential of these powerful new tools for medicine in general and pathology in particular. In Artificial Intelligence and Deep Learning in Pathology, with a team of experts, Dr. Stanley Cohen covers the nuts and bolts of all aspects of machine learning, up to and including AI, bringing familiarity and understanding to pathologists at all levels of experience.

  • Focuses heavily on applications in medicine, especially pathology, making unfamiliar material accessible and avoiding complex mathematics whenever possible.

  • Covers digital pathology as a platform for primary diagnosis and augmentation via deep learning, whole slide imaging for 2D and 3D analysis, and general principles of image analysis and deep learning.
  • Discusses and explains recent accomplishments such as algorithms used to diagnose skin cancer from photographs, AI-based platforms developed to identify lesions of the retina, using computer vision to interpret electrocardiograms, identifying mitoses in cancer using learning algorithms vs. signal processing algorithms, and many more.

Recenzijas

"We do, however, need to understand AI and adapt to it. This book is a great introduction, as well as a stimulating read. It is recommended for those interested in AI, software or the future of pathology." -Dr Niall O'Neill (Bulletin of the Royal College of Pathologists, January 2021)

Contributors xiii
Preface xv
Chapter 1 The evolution of machine learning: past, present, and future
1(12)
Stanley Cohen
Introduction
1(1)
Rules-based versus machine learning: a deeper look
2(2)
Varieties of machine learning
4(2)
General aspects of machine learning
6(1)
Deep learning and neural networks
7(2)
The role of AI in pathology
9(3)
Limitations of AI
10(1)
General aspects of AI
11(1)
References
12(1)
Chapter 2 The basics of machine learning: strategies and techniques
13(28)
Stanley Cohen
Introduction
13(2)
Shallow learning
15(8)
Geometric (distance-based) models
16(3)
The K-Means Algorithm (KM)
19(1)
Probabilistic models
20(2)
Decision Trees and Random Forests
22(1)
The curse of dimensionality and principal component analysis
23(1)
Deep learning and the artificial neural network
24(11)
Neuroscience 101
25(2)
The rise of the machines
27(2)
The basic ANN
29(2)
The weights in an ANN
31(1)
Learning from examples; Backprop and stochastic gradient descent
31(3)
Convolutional Neural Networks
34(1)
Overfitting and underfitting
35(3)
Things to come
38(1)
References
39(2)
Chapter 3 Overview of advanced neural network architectures
41(16)
Benjamin R. Mitchell
Introduction
41(1)
Network depth and residual connections
41(2)
Autoencoders and unsupervised pretraining
43(3)
Transfer learning
46(1)
Generative models and generative adversarial networks
47(1)
Recurrent neural networks
48(1)
Reinforcement learning
49(2)
Ensembles
51(2)
Genetic algorithms
53(2)
References
55(2)
Chapter 4 Complexity in the use of artificial intelligence in anatomic pathology
57(20)
Stanley Cohen
Introduction
57(1)
Life before machine learning
58(1)
Multilabel classification
59(2)
Single object detection
60(1)
Multiple objects
61(1)
Advances in multilabel classification
62(1)
Graphical neural networks
63(2)
Capsule networks
64(1)
Weakly supervised learning
65(2)
Synthetic data
67(1)
N-shot learning
68(1)
One-class learning
69(2)
Risk analysis
70(1)
General considerations
71(2)
Summary and conclusions
73(1)
References
74(3)
Chapter 5 Dealing with data: strategies of preprocessing data
77(16)
Stanley Cohen
Introduction
77(1)
Overview of preprocessing
78(1)
Feature selection, extraction, and correction
79(2)
Feature transformation, standardization, and normalization
81(1)
Feature engineering
81(1)
Mathematical approaches to dimensional reduction
82(5)
Dimensional reduction in deep learning
87(1)
Imperfect class separation in the training set
87(1)
Fairness and bias in machine learning
88(3)
Summary
91(1)
References
91(2)
Chapter 6 Digital pathology as a platform for primary diagnosis and augmentation via deep learning
93(26)
Anil V. Parwani
Introduction
93(1)
Digital imaging in pathology
94(1)
Telepathology
95(1)
Whole slide imaging
96(2)
Whole slide image viewers
98(1)
Whole slide image data and workflow management
99(2)
Selection criteria for a whole slide scanner
101(1)
Evolution of whole slide imaging systems
102(1)
Infrastructure requirements and checklist for rolling out high-throughput whole slide imaging workflow solution
103(1)
Whole slide imaging and primary diagnosis
104(1)
Whole slide imaging and image analysis
105(1)
Whole slide imaging and deep learning
106(3)
Conclusions
109(1)
References
110(9)
Chapter 7 Applications of artificial intelligence for image enhancement in pathology
119(30)
Tanishq Abraham
Austin Todd
Daniel A. Orringer
Richard Levenson
Introduction
119(1)
Common machine learning tasks
120(1)
Classification
120(1)
Segmentation
120(1)
Image translation and style transfer
121(1)
Commonly used deep learning methodologies
121(3)
Convolutional neural networks
121(2)
U-nets
123(1)
Generative adversarial networks and their variants
123(1)
Common training and testing practices
124(1)
Dataset preparation and preprocessing
124(1)
Loss functions
124(1)
Metrics
125(1)
Deep learning for microscopy enhancement in histopathology
125(14)
Stain color normalization
125(4)
Mode switching
129(4)
In silico labeling
133(3)
Super-resolution, extended depth-of-field, and denoising
136(3)
Deep learning for computationally aided diagnosis in histopathology
139(5)
A rationale for Al-assisted imaging and interpretation
139(1)
Approaches to rapid histology interpretations
140(4)
Future prospects
144(1)
References
144(5)
Chapter 8 Precision medicine in digital pathology via image analysis and machine learning
149(26)
Peter D. Caie
Neofytos Dimitriou
Ognjen Arandjelovic
Introduction
149(2)
Precision medicine
149(1)
Digital pathology
150(1)
Applications of image analysis and machine learning
151(8)
Knowledge-driven image analysis
151(1)
Machine learning for image segmentation
151(1)
Deep learning for image segmentation
152(4)
Spatial resolution
156(1)
Machine learning on extracted data
157(1)
Beyond augmentation
158(1)
Practical concepts and theory of machine learning
159(6)
Machine learning and digital pathology
159(1)
Common techniques
160(1)
Supervised learning
160(4)
Unsupervised learning
164(1)
Image-based digital pathology
165(3)
Conventional approaches to image analysis
166(1)
Deep learning on images
167(1)
Regulatory concerns and considerations
168(2)
Acknowledgments
170(1)
References
170(5)
Chapter 9 Artificial intelligence methods for predictive image-based grading of human cancers
175(36)
Gerardo Fernandez
Abishek Sainath Madduri
Bahram Marami
Marcel Prastawa
Richard Scott
Jack Zeineh
Michael Donovan
Introduction
175(2)
Tissue preparation and staining
177(1)
Image acquisition
178(1)
Stain normalization
179(1)
Unmixing of immunofluorescence spectral images
180(1)
Automated detection of tumor regions in whole-slide images
181(3)
Localization of diagnostically relevant regions of interest in whole-slide images
181(1)
Tumor detection
182(2)
Image segmentation
184(5)
Nuclear and epithelial segmentation in IF images
184(1)
Nuclei detection and segmentation in H&E images
185(1)
Epithelial segmentation in H&E images
186(1)
Mitotic figure detection
187(1)
Ring segmentation
188(1)
Protein biomarker features
189(2)
Morphological features for cancer grading and prognosis
191(4)
Modeling
195(6)
Cox proportional hazards model
197(1)
Neural networks
197(1)
Decision trees and random forests
198(1)
SVM-based methods: Survival-SVM, SVCR, and SVRc
198(2)
Feature selection tools
200(1)
Ground truth data for Al-based features
201(1)
Conclusion
202(1)
References
203(8)
Chapter 10 Artificial intelligence and the interplay between tumor and immunity
211(26)
Joel Haskin Saltz
Rajarsi Gupta
Introduction
211(1)
Immune surveillance and immunotherapy
212(3)
Identifying TILs with deep learning
215(7)
Multiplex immunohistochemistry with digital pathology and deep learning
222(3)
Vendor platforms
225(1)
Conclusion
226(1)
References
226(11)
Chapter 11 Overview of the role of artificial intelligence in pathology: the computer as a pathology digital assistant
237(26)
John E. Tomaszewski
Introduction
237(1)
Computational pathology: background and philosophy
237(3)
The current state of diagnostics in pathology and the evolving computational opportunities: "why now?"
237(2)
Digital pathology versus computational pathology
239(1)
Data on scale
239(1)
Machine learning tools in computational pathology: types of artificial intelligence
240(2)
The need for human intelligence---artificial intelligence partnerships
242(1)
Human transparent machine learning approaches
243(3)
Explainable artificial intelligence
244(1)
Cognitive artificial intelligence
244(1)
Human in the loop
245(1)
One-shot learning
246(1)
Image-based computational pathology
246(2)
Core premise of image analytics: what is a high-resolution image?
246(1)
The targets of image-based calculations
247(1)
First fruits of computational pathology: the evolving digital assistant
248(10)
The digital assistant for quality control
248(1)
The digital assistant for histological object segmentation
249(4)
The digital assistant in immunohistochemistry
253(1)
The digital assistant in tissue classification
253(1)
The digital assistant in finding metastases
254(1)
The digital assistant in predictive modeling and precision medicine
255(1)
The digital assistant for anatomical simulation learning
256(1)
The digital assistant for image-omics data fusion
256(2)
Artificial intelligence and regulatory challenges
258(2)
Educating machines---educating us: learning how to learn with machines
260(1)
References
260(3)
Index 263
Dr. Cohen is currently interested in integrating computational imaging with digital workflows. He previously served as President of the American Society for Investigative Pathology (ASIP) and Treasurer and Member of the Executive Board of FASEB. Science-related activities also include chairmanships of study sections for the NIH and DOD and membership on multiple editorial boards. He is currently the Associate Editor for digital and computational pathology and artificial intelligence topic category for the American Journal of Pathology. He is a Senior Fellow of the Association of Pathology Chairs and Co-Chair of the ASIP Special Interest Group on Digital and Computational Pathology. Awards include the Gold-Headed Cane (ASIP) and the Golden Goose Award (AAAS). He is a member of the Digital Pathology Association (DPA), the Board of the International Academy of Digital Pathology (IADP), and Chair of the External Advisory Board of the Alpert Foundation.