Muutke küpsiste eelistusi

Stochastic Modeling for Medical Image Analysis [Pehme köide]

(University of Louisville, Kentucky, USA), (Global Biomedical Technologies, Inc., Roseville, USA), (University of Auckland, New Zealand)
  • Formaat: Paperback / softback, 304 pages, kõrgus x laius: 234x156 mm, kaal: 521 g, 188 Illustrations, color
  • Ilmumisaeg: 13-Dec-2021
  • Kirjastus: CRC Press
  • ISBN-10: 1032237546
  • ISBN-13: 9781032237541
Teised raamatud teemal:
  • Pehme köide
  • Hind: 54,89 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 73,19 €
  • Säästad 25%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 3-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
  • Raamatukogudele
Stochastic Modeling for Medical Image AnalysisSuurem pilt
  • Formaat: Paperback / softback, 304 pages, kõrgus x laius: 234x156 mm, kaal: 521 g, 188 Illustrations, color
  • Ilmumisaeg: 13-Dec-2021
  • Kirjastus: CRC Press
  • ISBN-10: 1032237546
  • ISBN-13: 9781032237541
Teised raamatud teemal:
Teised raamatud sellest sooduspakkumisest: Kevadine sooduspakkumine - kuni 31. maini üle miljoni raamatu kuni 25% soodsamalt
Püsilink: https://www.kriso.ee/db/9781032237541.html
Märksõnad:

This book provides a brief introduction to medical imaging, stochastic modeling, and model-guided image analysis. It presents the latest state of the art in stochastic modeling for medical image analysis while incorporating fully tested experimental results throughout. This valuable resource details efficient stochastic modeling techniques, incl



Stochastic Modeling for Medical Image Analysis provides a brief introduction to medical imaging, stochastic modeling, and model-guided image analysis.

Today, image-guided computer-assisted diagnostics (CAD) faces two basic challenging problems. The first is the computationally feasible and accurate modeling of images from different modalities to obtain clinically useful information. The second is the accurate and fast inferring of meaningful and clinically valid CAD decisions and/or predictions on the basis of model-guided image analysis.

To help address this, this book details original stochastic appearance and shape models with computationally feasible and efficient learning techniques for improving the performance of object detection, segmentation, alignment, and analysis in a number of important CAD applications.

The book demonstrates accurate descriptions of visual appearances and shapes of the goal objects and their background to help solve a number of important and challenging CAD problems. The models focus on the first-order marginals of pixel/voxel-wise signals and second- or higher-order Markov-Gibbs random fields of these signals and/or labels of regions supporting the goal objects in the lattice.

This valuable resource presents the latest state of the art in stochastic modeling for medical image analysis while incorporating fully tested experimental results throughout.

Notations ix
Preface xiii
Abbreviations xvii
1 Medical Imaging Modalities
1(24)
1.1 Magnetic Resonance Imaging
1(8)
1.1.1 Structural MRI
3(1)
1.1.2 Dynamic Contrast-Enhanced MRI
4(1)
1.1.3 Diffusion MRI
5(1)
1.1.4 Functional MRI
6(1)
1.1.5 Magnetic Resonance Angiography
7(1)
1.1.6 Tagged MRI, MRS, and PWI
8(1)
1.1.7 MRI: Pros and Cons
9(1)
1.2 Computed Tomography
9(4)
1.2.1 Structural CT
10(1)
1.2.2 Contrast-Enhanced CT
10(1)
1.2.3 CT Angiography
11(1)
1.2.4 Microtomography
11(1)
1.2.5 CT Imaging: Pros and Cons
12(1)
1.3 Ultrasound Imaging
13(4)
1.4 Nuclear Medical Imaging (Nuclide Imaging)
17(4)
1.5 Bibliographic and Historical Notes
21(4)
2 From Images to Graphical Models
25(38)
2.1 Basics of Image Modeling
26(9)
2.1.1 Digital Images, Videos, and Region Maps
26(2)
2.1.2 Image Homogeneity
28(1)
2.1.3 Probability Models of Images and Region Maps
29(2)
2.1.4 Optimal Statistical Inference
31(1)
2.1.5 Unessential Image Deviations
32(3)
2.2 Pixel/Voxel Interactions and Neighborhoods
35(9)
2.2.1 Markov Random Field (MRF)
37(3)
2.2.2 Basic Stochastic Modeling Scenarios
40(1)
2.2.3 Invariance to Unessential Deviations
41(1)
2.2.3.1 Multiple Second- and Higher-Order Interactions
42(1)
2.2.3.2 Contrast/Offset-Invariant MGRFs
43(1)
2.3 Exponential Families of Probability Distributions
44(6)
2.3.1 Learning an Exponential Family
48(2)
2.4 Appearance and Shape Modeling
50(5)
2.5 Bibliographic and Historical Notes
55(8)
2.5.1 Shape Modeling with Deformable Models
58(5)
3 IRF Models: Estimating Marginals
63(34)
3.1 Basic Independent Random Fields
63(2)
3.2 Supervised and Unsupervised Learning
65(3)
3.2.1 Parametric Versus Nonparametric Models
68(1)
3.3 Expectation-Maximization to Identify Mixtures
68(3)
3.4 Gaussian Linear Combinations Versus Mixtures
71(7)
3.4.1 Sequential Initialization of an LCG/LCDG Model
73(2)
3.4.2 Refinement of an LCG/LCDG Model
75(2)
3.4.3 Model Partitioning by Allocating Subordinate Terms
77(1)
3.5 Pseudo-Marginals in Medical Image Analysis
78(16)
3.5.1 Synthetic Checkerboard Images
79(4)
3.5.2 Modeling Lungs on Spiral LDCT Chest Scans
83(3)
3.5.3 Modeling Blood Vessels on TOF-MRA Images
86(3)
3.5.4 Modeling Brain Tissues on MRI
89(1)
3.5.5 Modeling Brain Blood Vessels on PC-MRA Images
90(1)
3.5.6 Aorta Modeling on CTA Images
91(3)
3.6 Bibliographic and Historical Notes
94(3)
4 Markov-Gibbs Random Field Models: Estimating Signal Interactions
97(32)
4.1 Generic Kth-Order MGRFs
97(7)
4.1.1 MCMC Sampling of an MGRF
100(1)
4.1.2 Gibbs and Metropolis-Hastings Samplers
101(3)
4.2 Common Second- and Higher-Order MGRFs
104(15)
4.2.1 Nearest-Neighbor MGRFs
105(6)
4.2.2 Gaussian and Gauss-Markov Random Fields
111(2)
4.2.3 Models with Multiple Pairwise Interactions
113(4)
4.2.4 Higher-Order MGRFs
117(2)
4.3 Learning Second-Order Interaction Structures
119(4)
4.4 Bibliographic and Historical Notes
123(6)
4.4.1 Image Filtering
126(1)
4.4.2 Image Sampling
127(1)
4.4.3 Model Learning
127(2)
5 Applications: Image Alignment
129(14)
5.1 General Image Alignment Frameworks
129(2)
5.2 Global Alignment by Learning an Appearance Prior
131(3)
5.3 Bibliographic and Historical Notes
134(9)
6 Segmenting Multimodal Images
143(30)
6.1 Joint MGRF of Images and Region Maps
144(3)
6.2 Experimental Validation
147(20)
6.2.1 Synthetic Data
147(3)
6.2.2 Lung LDCT Images
150(4)
6.2.3 Blood Vessels in TOF-MRA Images
154(4)
6.2.4 Blood Vessels in PC-MRA Images
158(3)
6.2.5 Aorta Blood Vessels in CTA Images
161(1)
6.2.6 Brain MRI
162(5)
6.3 Bibliographic and Historical Notes
167(2)
6.4 Performance Evaluation and Validation
169(4)
7 Segmenting with Deformable Models
173(24)
7.1 Appearance-Based Segmentation
173(10)
7.1.1 Experimental Validation
175(1)
7.1.1.1 Starfish
175(1)
7.1.1.2 Hand
176(2)
7.1.1.3 Bones
178(1)
7.1.1.4 Various Other Objects
178(5)
7.2 Shape and Appearance-Based Segmentation
183(10)
7.2.1 Learning a Shape Model
185(1)
7.2.2 Experimental Validation
185(1)
7.2.2.1 Starfish
185(4)
7.2.2.2 Kidney
189(4)
7.3 Bibliographic and Historical Notes
193(4)
8 Segmenting with Shape and Appearance Priors
197(12)
8.1 Learning a Shape Prior
197(3)
8.2 Evolving a Deformable Boundary
200(1)
8.3 Experimental Validation
201(2)
8.4 Bibliographic and Historical Notes
203(6)
9 Cine Cardiac MRI Analysis
209(24)
9.1 Segmenting Myocardial Borders
210(4)
9.2 Wall Thickness Analysis
214(3)
9.2.1 GGMRF-Based Continuity Analysis
215(2)
9.3 Experimental Results
217(10)
9.3.1 LV Wall Correspondences
218(1)
9.3.2 LV Wall Segmentation
219(6)
9.3.3 Wall Thickening
225(2)
9.4 Bibliographic and Historical Notes
227(6)
10 Sizing Cardiac Pathologies
233(24)
10.1 LV Wall Segmentation
236(5)
10.2 Identifying the Pathological Tissue
241(1)
10.3 Quantifying the Myocardial Viability
242(1)
10.4 Performance Evaluation and Validation
243(10)
10.4.1 Segmentation Accuracy
244(1)
10.4.2 Transmural Extent Accuracy
244(3)
10.4.3 Pathology Delineation Accuracy
247(2)
10.4.4 Clinically Meaningful Effects
249(4)
10.5 Bibliographic and Historical Notes
253(4)
10.5.1 Appearance and Shape Priors
253(1)
10.5.2 Myocardial Viability Metrics
254(3)
References 257(20)
Index 277
Ayman El-Baz, PhD, associate professor, Department of Bioengineering, University of Louisville, Kentucky, USA

Georgy Gimelfarb, professor of computer science, University of Auckland, New Zealand

Jasjit S. Suri, PhD, MBA, CEO, Global Biomedical Technologies, Inc., Roseville, California, USA