Muutke küpsiste eelistusi

E-raamat: Medical Image Processing, Reconstruction and Analysis: Concepts and Methods, Second Edition

(Brno University of Technology, FEEC, Brno, Czech Republic)
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 273,00 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
  • Raamatukogudele
Medical Image Processing, Reconstruction and Analysis: Concepts and Methods, Second EditionSuurem pilt
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Differently oriented specialists and students involved in image processing and analysis need to have a firm grasp of concepts and methods used in this now widely utilized area. This book aims at being a single-source reference providing such foundations in the form of theoretical yet clear and easy to follow explanations of underlying generic concepts.

Medical Image Processing, Reconstruction and Analysis Concepts and Methods explains the general principles and methods of image processing and analysis, focusing namely on applications used in medical imaging.

The content of this book is divided into three parts:











Part I Images as Multidimensional Signals provides the introduction to basic image processing theory, explaining it for both analogue and digital image representations.





Part II Imaging Systems as Data Sources offers a non-traditional view on imaging modalities, explaining their principles influencing properties of the obtained images that are to be subsequently processed by methods described in this book. Newly, principles of novel modalities, as spectral CT, functional MRI, ultrafast planar-wave ultrasonography and optical coherence tomography are included.





Part III Image Processing and Analysis focuses on tomographic image reconstruction, image fusion and methods of image enhancement and restoration; further it explains concepts of low-level image analysis as texture analysis, image segmentation and morphological transforms. A new chapter deals with selected areas of higher-level analysis, as principal and independent component analysis and particularly the novel analytic approach based on deep learning. Briefly, also the medical image-processing environment is treated, including processes for image archiving and communication.

Features











Presents a theoretically exact yet understandable explanation of image processing and analysis concepts and methods





Offers practical interpretations of all theoretical conclusions, as derived in the consistent explanation





Provides a concise treatment of a wide variety of medical imaging modalities including novel ones, with respect to properties of provided image data
Preface xvii
Acknowledgments xxi
Author Biography xxiii
Part I Images as Multidimensional Signals
Chapter 1 Analogue (Continuous-Space) Image Representation
3(38)
1.1 Multidimensional Signals as Image Representation
3(5)
1.1.1 General Notion of Multidimensional Signals
3(2)
1.1.2 Some Important Two-Dimensional Signals
5(3)
1.2 Two-Dimensional Fourier Transform
8(7)
1.2.1 Forward Two-Dimensional Fourier Transform
8(2)
1.2.2 Inverse Two-Dimensional Fourier Transform
10(1)
1.2.3 Physical Interpretation of the Two-Dimensional Fourier Transform
11(2)
1.2.4 Properties of the Two-Dimensional Fourier Transform
13(2)
1.3 Two-Dimensional Continuous-Space Systems
15(10)
1.3.1 The Notion of Multidimensional Systems
15(2)
1.3.2 Linear Two-Dimensional Systems: Original-Domain Characterization
17(2)
1.3.3 Linear Two-Dimensional Systems: Frequency-Domain Characterization
19(2)
1.3.4 Nonlinear Two-Dimensional Continuous-Space Systems
21(4)
1.3.4.1 Point Operators
21(1)
1.3.4.2 Homomorphic Systems
22(3)
1.4 Concept of Stochastic Images
25(16)
1.4.1 Stochastic Fields as Generators of Stochastic Images
26(3)
1.4.2 Correlation and Covariance Functions
29(2)
1.4.3 Homogeneous and Ergodic Fields
31(3)
1.4.4 Two-Dimensional Spectra of Stochastic Images
34(2)
1.4.4.1 Power Spectra
34(1)
1.4.4.2 Cross-Spectra
35(1)
1.4.5 Transfer of Stochastic Images via Two-Dimensional Linear Systems
36(2)
1.4.6 Linear Estimation of Stochastic Variables-Principle of Orthogonality
38(3)
Chapter 2 Digital Image Representation
41(55)
2.1 Digital Image Representation
41(8)
2.1.1 Sampling and Digitizing Images
41(7)
2.1.1.1 Sampling
41(4)
2.1.1.2 Digitization
45(3)
2.1.2 Image Interpolation from Samples
48(1)
2.2 Discrete Two-Dimensional Operators
49(16)
2.2.1 Discrete Linear Two-Dimensional Operators
50(6)
2.2.1.1 Generic Operators
50(1)
2.2.1.2 Separable Operators
51(1)
2.2.1.3 Local Operators
52(2)
2.2.1.4 Convolutional Operators
54(2)
2.2.2 Nonlinear Two-Dimensional Discrete Operators
56(9)
2.2.2.1 Point Operators
56(1)
2.2.2.2 Homomorphic Operators
57(1)
2.2.2.3 Order Statistics Operators
58(1)
2.2.2.4 Neuronal Operators
58(7)
2.3 Discrete Two-Dimensional Linear Transforms
65(26)
2.3.1 Two-Dimensional Unitary Transforms Generally
66(2)
2.3.2 Two-Dimensional Discrete Fourier and Related Transforms
68(12)
2.3.2.1 Two-Dimensional DFT Definition
68(1)
2.3.2.2 Physical Interpretation of Two-Dimensional DFT
69(2)
2.3.2.3 Relation of Two-Dimensional DFT to Two-Dimensional Integral FT and Its Applications in Spectral Analysis
71(4)
2.3.2.4 Properties of the Two-Dimensional DFT
75(1)
2.3.2.5 Frequency Domain Convolution
76(1)
2.3.2.6 Two-Dimensional Cosine, Sine, and Hartley Transforms
77(3)
2.3.3 Two-Dimensional Hadamard-Walsh and Haar Transforms
80(4)
2.3.3.1 Two-Dimensional Hadamard-Walsh Transform
80(1)
2.3.3.2 Two-Dimensional Haar Transform
81(3)
2.3.4 Two-Dimensional Discrete Wavelet Transforms
84(5)
2.3.4.1 Two-Dimensional Continuous Wavelet Transforms
84(3)
2.3.4.2 Two-Dimensional Dyadic Wavelet Transforms
87(2)
2.3.5 Two-Dimensional Discrete Karhunen-Loeve Transform
89(2)
2.4 Discrete Stochastic Images
91(8)
2.4.1 Discrete Stochastic Fields as Generators of Stochastic Images
91(1)
2.4.2 Discrete Correlation and Covariance Functions
92(1)
2.4.3 Discrete Homogeneous and Ergodic Fields
93(1)
2.4.4 Two-Dimensional Spectra of Stochastic Images
94(1)
2.4.4.1 Power Spectra
94(1)
2.4.4.2 Discrete Cross-Spectra
95(1)
2.4.5 Transfer of Stochastic Images via Discrete Two-Dimensional Systems
95(1)
Part I References
96(3)
Part II Imaging Systems as Data Sources
Chapter 3 Planar X-Ray Imaging
99(12)
3.1 X-Ray Projection Radiography
99(10)
3.1.1 Basic Imaging Geometry
99(1)
3.1.2 Source of Radiation
100(3)
3.1.3 Interaction of X-Rays with Imaged Objects
103(1)
3.1.4 Image Detection
104(3)
3.1.5 Post-measurement Data Processing in Projection Radiography
107(2)
3.2 Subtractive Angiography
109(2)
Chapter 4 X-Ray Computed Tomography
111(20)
4.1 Imaging Principle and Geometry
111(6)
4.1.1 Principle of a Slice Projection Measurement
111(2)
4.1.2 Variants of Measurement Arrangement
113(4)
4.2 Measuring Considerations
117(2)
4.2.1 Technical Equipment
117(1)
4.2.2 Attenuation Scale
118(1)
4.3 Imaging Properties
119(4)
4.3.1 Spatial Two-Dimensional and Three-Dimensional Resolution and Contrast Resolution
119(1)
4.3.2 Imaging Artifacts
120(3)
4.4 Postmeasurement Data Processing in Computed Tomography
123(2)
4.5 Spectral Computed Tomography
125(6)
4.5.1 Double-Energy CT
126(2)
4.5.2 Multi-Band (Spectral) CT
128(3)
Chapter 5 Magnetic Resonance Imaging
131(52)
5.1 Magnetic Resonance Phenomena
131(7)
5.1.1 Magnetization of Nuclei
131(2)
5.1.2 Stimulated NMR Response and Free Induction Decay
133(2)
5.1.3 Relaxation
135(3)
5.1.3.1 Chemical Shift and Flow Influence
137(1)
5.2 Response Measurement and Interpretation
138(8)
5.2.1 Saturation Recovery (SR) Techniques
139(1)
5.2.2 Spin-Echo Techniques
140(4)
5.2.3 Gradient-Echo Techniques
144(2)
5.3 Basic MRI Arrangement
146(2)
5.4 Localization and Reconstruction of Image Data
148(22)
5.4.1 Gradient Fields
148(1)
5.4.2 Spatially Selective Excitation
149(2)
5.4.3 RF Signal Model and General Background for Localization
151(4)
5.4.4 One-Dimensional Frequency Encoding: Two-Dimensional Reconstruction from Projections
155(4)
5.4.5 Two-Dimensional Reconstruction via Frequency and Phase Encoding
159(4)
5.4.6 Three-Dimensional Reconstruction via Frequency and Double Phase Encoding
163(1)
5.4.7 Fast MRI
164(6)
5.4.7.1 Multiple-Slice Imaging
165(1)
5.4.7.2 Low Flip-Angle Excitation
165(1)
5.4.7.3 Multiple-Echo Acquisition
166(1)
5.4.7.4 Echo-Planar Imaging
167(3)
5.5 Image Quality and Artifacts
170(5)
5.5.1 Noise Properties
170(1)
5.5.2 Image Parameters
171(2)
5.5.3 Point-Spread Function
173(1)
5.5.4 Resolving Power
173(1)
5.5.5 Imaging Artifacts
174(1)
5.6 Post-measurement Data Processing in MRI
175(2)
5.7 Functional Magnetic Resonance Imaging (fMRI)
177(6)
Chapter 6 Nuclear Imaging
183(26)
6.1 Planar Gamma Imaging
184(8)
6.1.1 Gamma Detectors and Gamma Camera
185(4)
6.1.2 Inherent Data Processing and Imaging Properties
189(3)
6.1.2.1 Data Localization and System Resolution
189(2)
6.1.2.2 Total Response Evaluation and Scatter Rejection
191(1)
6.1.2.3 Data Post-processing
191(1)
6.2 Single-Photon Emission Tomography
192(5)
6.2.1 Principle
192(1)
6.2.2 Deficiencies of SPECT Principle and Possibilities of Cure
193(4)
6.3 Positron Emission Tomography
197(12)
6.3.1 Principles of Measurement
197(3)
6.3.2 Imaging Arrangements
200(2)
6.3.3 Post-processing of Raw Data and Imaging Properties
202(8)
6.3.3.1 Attenuation Correction
203(1)
6.3.3.2 Random Coincidences
204(1)
6.3.3.3 Scattered Coincidences
205(1)
6.3.3.4 Dead-Time Influence
205(1)
6.3.3.5 Resolution Issues
206(1)
6.3.3.6 Ray Normalization
207(1)
6.3.3.7 Comparison of PET and SPECT Modalities
208(1)
Chapter 7 Ultrasonography
209(44)
7.1 Two-Dimensional Echo Imaging
210(19)
7.1.1 Echo Measurement
210(11)
7.1.1.1 Principle of Echo Measurement
210(1)
7.1.1.2 Ultrasonic Transducers
211(5)
7.1.1.3 Ultrasound Propagation and Interaction with Tissue
216(2)
7.1.1.4 Echo Signal Features and Processing
218(3)
7.1.2 B-Mode Imaging
221(8)
7.1.2.1 Two-Dimensional Scanning Methods and Transducers
221(3)
7.1.2.2 Format Conversion
224(1)
7.1.2.3 Two-Dimensional Image Properties and Processing
225(2)
7.1.2.4 Contrast Imaging and Harmonic Imaging
227(2)
7.2 Flow Imaging
229(9)
7.2.1 Principles of Flow Measurement
229(5)
7.2.1.1 Doppler Blood Velocity Measurement (Narrowband Approach)
229(4)
7.2.1.2 Cross-Correlation Blood Velocity Measurement (Wideband Approach)
233(1)
7.2.2 Color Flow Imaging
234(4)
7.2.2.1 Autocorrelation-Based Doppler Imaging
234(3)
7.2.2.2 Movement Estimation Imaging
237(1)
7.2.2.3 Contrast-Based Flow Imaging
237(1)
7.2.2.4 Post-processing of Flow Images
237(1)
7.3 Three-Dimensional Ultrasonography
238(5)
7.3.1 Three-Dimensional Data Acquisition
238(3)
7.3.1.1 Two-Dimensional Scan-Based Data Acquisition
238(2)
7.3.1.2 Three-Dimensional Transducer Principles
240(1)
7.3.2 Three-Dimensional and Four-Dimensional Data Post-Processing and Display
241(2)
7.3.2.1 Data Block Compilation
241(1)
7.3.2.2 Display of Three-Dimensional Data
242(1)
7.4 Plane Wave (Ultra-Fast) Ultrasonic Imaging
243(10)
7.4.1 Principle of Plane-Wave Imaging
244(4)
7.4.1.1 Individual Frame Data Acquisition
244(3)
7.4.1.2 Individual Image Reconstruction
247(1)
7.4.2 Image Compounding
248(2)
7.4.3 Shear Wave Visualization and Elastography
250(3)
Chapter 8 Other Modalities
253(15)
8.1 Optical and Infrared Imaging
253(5)
8.1.1 Three-Dimensional Confocal Microscopy
254(2)
8.1.2 Optical Coherence Tomography (OCT)
256(1)
8.1.3 Body Surface Infrared Imaging
257(1)
8.2 Electron Microscopy
258(7)
8.2.1 Scattering Phenomena in the Specimen Volume
259(1)
8.2.2 Transmission Electron Microscopy
259(3)
8.2.3 Scanning Electron Microscopy
262(2)
8.2.4 Post-processing of EM Images
264(1)
8.3 Electrical Impedance Tomography
265(3)
Part II References
268(5)
Part III Image Processing and Analysis
Chapter 9 Reconstructing Tomographic Images
273(36)
9.1 Reconstruction from Near-Ideal Projections
273(24)
9.1.1 Representation of Images by Projections
273(4)
9.1.2 Algebraic Methods of Reconstruction
277(7)
9.1.2.1 Discrete Formulation of the Reconstruction Problem
277(2)
9.1.2.2 Iterative Solution
279(2)
9.1.2.3 Reprojection Interpretation of the Iteration
281(2)
9.1.2.4 Simplified Reprojection Iteration
283(1)
9.1.2.5 Other Iterative Reprojection Approaches
284(1)
9.1.3 Reconstruction via Frequency Domain
284(2)
9.1.3.1 Projection Slice Theorem
284(1)
9.1.3.2 Frequency-Domain Reconstruction
285(1)
9.1.4 Reconstruction from Parallel Projections by Filtered Back-Projection
286(6)
9.1.4.1 Underlying Theory
286(3)
9.1.4.2 Practical Aspects
289(3)
9.1.5 Reconstruction from Fan Projections
292(5)
9.1.5.1 Rebinning and Interpolation
293(1)
9.1.5.2 Weighted Filtered Back-Projection
293(3)
9.1.5.3 Algebraic Methods of Reconstruction
296(1)
9.2 Reconstruction from Non-ideal Projections
297(7)
9.2.1 Reconstruction under Nonzero Attenuation
297(3)
9.2.1.1 SPECT Type Imaging
297(2)
9.2.1.2 PET Type Imaging
299(1)
9.2.2 Reconstruction from Stochastic Projections
300(4)
9.2.2.1 Stochastic Models of Projections
300(2)
9.2.2.2 Principle of Maximum-Likelihood Reconstruction
302(2)
9.3 Other Approaches to Tomographic Reconstruction
304(5)
9.3.1 Image Reconstruction in Magnetic Resonance Imaging
304(2)
9.3.1.1 Projection-Based Reconstruction
304(1)
9.3.1.2 Frequency-Domain (Fourier) Reconstruction
305(1)
9.3.2 Image Reconstruction in Ultrasonography
306(4)
9.3.2.1 Reflective (Echo) Ultrasonography
306(1)
9.3.2.2 Transmission Ultrasonography
307(1)
9.3.2.3 Plane Wave Ultrasonography and Elastography
308(1)
Chapter 10 Image Fusion
309(54)
10.1 Ways to Consistency
310(29)
10.1.1 Geometrical Image Transformations
312(8)
10.1.1.1 Rigid Transformations
312(2)
10.1.1.2 Flexible Transformations
314(4)
10.1.1.3 Piece-Wise Transformations
318(2)
10.1.2 Image Interpolation
320(7)
10.1.2.1 Interpolation in the Spatial Domain
321(5)
10.1.2.2 Spatial Interpolation via Frequency Domain
326(1)
10.1.3 Image Similarity Criteria
327(12)
10.1.3.1 Direct Intensity-Based Criteria
328(4)
10.1.3.2 Information-Based Criteria
332(7)
10.2 Disparity Analysis
339(6)
10.2.1 Disparity Evaluation
339(5)
10.2.1.1 Disparity Definition and Evaluation Approaches
339(2)
10.2.1.2 Nonlinear Matched Filters as Sources of Similarity Maps
341(3)
10.2.2 Computation and Representation of Disparity Maps
344(1)
10.2.2.1 Organization of the Disparity Map Computation
344(1)
10.2.2.2 Display and Interpretation of Disparity Maps
344(1)
10.3 Image Registration
345(8)
10.3.1 Global Similarity
346(3)
10.3.1.1 Intensity-Based Global Criteria
347(1)
10.3.1.2 Point-Based Global Criteria
348(1)
10.3.1.3 Surface-Based Global Criteria
349(1)
10.3.2 Transform Identification and Registration Procedure
349(2)
10.3.2.1 Direct Computation
350(1)
10.3.2.2 Optimization Approaches
350(1)
10.3.3 Registration Evaluation and Approval
351(2)
10.4 Image Fusion
353(10)
10.4.1 Image Subtraction and Addition
353(1)
10.4.2 Vector-Valued Images
354(2)
10.4.2.1 Presentation of Vector-Valued Images
355(1)
10.4.3 Three-Dimensional Data from Two-Dimensional Slices
356(1)
10.4.4 Panorama Fusion
356(1)
10.4.5 Stereo Surface Reconstruction
357(2)
10.4.6 Time Development Analysis
359(3)
10.4.6.1 Time Development via Disparity Analysis
359(1)
10.4.6.2 Time Development via Optical Flow
360(2)
10.4.7 Fusion-Based Image Restoration
362(1)
Chapter 11 Image Enhancement
363(32)
11.1 Contrast Enhancement
363(10)
11.1.1 Piece-Wise Linear Contrast Adjustments
365(2)
11.1.2 Nonlinear Contrast Transforms
367(2)
11.1.3 Histogram Equalization
369(3)
11.1.4 Pseudocoloring
372(1)
11.2 Sharpening and Edge Enhancement
373(12)
11.2.1 Discrete Difference Operators
374(4)
11.2.2 Local Sharpening Operators
378(3)
11.2.3 Sharpening via Frequency Domain
381(2)
11.2.4 Adaptive Sharpening
383(2)
11.3 Noise Suppression
385(9)
11.3.1 Narrowband Noise Suppression
386(1)
11.3.2 Wideband "Gray" Noise Suppression
387(4)
11.3.2.1 Adaptive Wideband Noise Smoothing
389(2)
11.3.3 Impulse Noise Suppression
391(3)
11.4 Geometrical Distortion Correction
394(1)
Chapter 12 Image Restoration
395(40)
12.1 Correction of Intensity Distortions
396(3)
12.1.1 Global Corrections
397(1)
12.1.2 Field Homogenization
397(3)
12.1.2.1 Homomorphic Illumination Correction
399(1)
12.2 Geometrical Restitution
399(1)
12.3 Inverse Filtering
400(9)
12.3.1 Blur Estimation
400(5)
12.3.1.1 Analytical Derivation of PSF
400(1)
12.3.1.2 Experimental PSF Identification
401(4)
12.3.2 Identification of Noise Properties
405(1)
12.3.3 Actual Inverse Filtering
406(3)
12.3.3.1 Plain Inverse Filtering
406(2)
12.3.3.2 Modified Inverse Filtering
408(1)
12.4 Restoration Methods Based on Optimization
409(21)
12.4.1 Image Restoration as Constrained Optimization
409(2)
12.4.2 Least Mean Square Error Restoration
411(9)
12.4.2.1 Formalized Concept of LMS Image Estimation
411(1)
12.4.2.2 Classical Formulation of Wiener Filtering for Continuous-Space Images
412(6)
12.4.2.3 Discrete Formulation of the Wiener Filter
418(2)
12.4.2.4 Generalized LMS Filtering
420(7)
12.4.3 Methods Based on Constrained Deconvolution
422(1)
12.4.3.1 Classical Constrained Deconvolution
422(3)
12.4.3.2 Maximum Entropy Restoration
425(2)
12.4.4 Constrained Optimization of Resulting PSF
427(1)
12.4.5 Bayesian Approaches
428(2)
12.4.5.1 Maximum a Posteriori Probability Restoration
429(1)
12.4.5.2 Maximum-Likelihood Restoration
430(1)
12.5 Homomorphic Filtering and Deconvolution
430(2)
12.5.1 Restoration of Speckled Images
431(1)
12.6 Fusion Based Blind Restoration
432(3)
12.6.1 Blind Deconvolution and Registration of Fused Images
432(3)
Chapter 13 Lower-Level Image Analysis
435(60)
13.1 Local Feature Analysis
435(15)
13.1.1 Local Features
436(2)
13.1.1.1 Parameters Provided by Local Operators
436(1)
13.1.1.2 Parameters of Local Statistics
436(1)
13.1.1.3 Local Histogram Evaluation
437(1)
13.1.1.4 Frequency-Domain Features
437(1)
13.1.2 Edge Detection
438(7)
13.1.2.1 Gradient-Based Detectors
439(2)
13.1.2.2 Laplacian-Based Zero-Crossing Detectors
441(1)
13.1.2.3 Laplacian-of-Gaussian-Based Detectors
442(1)
13.1.2.4 Combined Approaches to Edge and Corner Detection
443(1)
13.1.2.5 Line Detectors
444(1)
13.1.3 Texture Analysis
445(5)
13.1.3.1 Local Features as Texture Descriptors
447(1)
13.1.3.2 Co-Occurrence Matrices
447(1)
13.1.3.3 Run-Length Matrices
448(1)
13.1.3.4 Autocorrelation Evaluators
448(1)
13.1.3.5 Texture Models
448(1)
13.1.3.6 Syntactic Texture Analysis
449(1)
13.1.3.7 Textural Parametric Images and Textural Gradient
450(1)
13.2 Image Segmentation
450(28)
13.2.1 Parametric Image-Based Segmentation
451(5)
13.2.1.1 Intensity-Based Segmentation
451(3)
13.2.1.2 Binary (Black and White) Segmentation
454(1)
13.2.1.3 Segmentation of Vector-Valued Parametric, Color, or Multimodal Images
455(1)
13.2.1.4 Texture-Based Segmentation
456(1)
13.2.2 Region-Based Segmentation
456(7)
13.2.2.1 Segmentation via Region Growing
456(1)
13.2.2.2 Segmentation via Region Merging
457(1)
13.2.2.3 Segmentation via Region Splitting and Merging
458(2)
13.2.2.4 Watershed-Based Segmentation
460(3)
13.2.3 Edge-Based Segmentation
463(8)
13.2.3.1 Borders via Modified Edge Representation
463(3)
13.2.3.2 Borders via Hough Transform
466(4)
13.2.3.3 Boundary Tracking
470(1)
13.2.3.4 Graph Searching Methods
471(1)
13.2.4 Segmentation by Pattern Comparison
471(1)
13.2.5 Segmentation via Flexible Contour Optimization
471(7)
13.2.5.1 Parametric Flexible Contours
472(2)
13.2.5.2 Geometric Flexible Contours - Level Sets
474(2)
13.2.5.3 Active Shape Contours
476(2)
13.3 Generalized Morphological Transforms
478(17)
13.3.1 Basic Notions
478(3)
13.3.1.1 Image Sets and Threshold Decomposition
478(1)
13.3.1.2 Generalized Set Operators and Relations
479(1)
13.3.1.3 Distance Function
480(1)
13.3.2 Morphological Operators
481(10)
13.3.2.1 Erosion
483(2)
13.3.2.2 Dilation
485(1)
13.3.2.3 Opening and Closing
486(2)
13.3.2.4 Fit-and-Miss Operator
488(1)
13.3.2.5 Derived Operators
488(2)
13.3.2.6 Geodesic Operators
490(1)
13.3.3 Some Applications
491(4)
Chapter 14 Selected Higher-Level Image Analysis Methods
495(38)
14.1 Image Decomposition Using Principal and Independent Component Analyses
496(11)
14.1.1 Principal Component Analysis
496(7)
14.1.2 Independent Component Analysis
503(4)
14.1.2.1 ICA Based on Minimization of Mutual Information
505(1)
14.1.2.2 ICA Based on Maximization of Non-Gaussianity
506(1)
14.2 Deep Learning-Based Image Analysis
507(10)
14.2.1 Introduction to Deep Learning
507(1)
14.2.2 Deep Feed-Forward (Back-Propagation) Neural Networks
508(5)
14.2.3 Convolutional Neural Networks
513(4)
14.2.3.1 Generic Structure
514(1)
14.2.3.2 Convolutional Layers
515(1)
14.2.3.3 Nonlinear Layers
516(1)
14.2.3.4 Pooling Layers
517(1)
14.2.4 Modifications of Convolutional Neural Networks
517(4)
14.2.4.1 Neuron Nonlinearities
518(1)
14.2.4.2 Tendencies in CNN Architectures
518(1)
14.2.4.3 Inception Concept
519(1)
14.2.4.4 Residual Concept
520(1)
14.2.5 Matrix-Output Type Convolutional Neural Networks
521(3)
14.2.6 Applications of Convolutional Neural Networks
524(6)
14.2.6.1 Supervised Learning from Limited Databases
525(1)
14.2.6.2 Unsupervised Learning
526(1)
14.2.6.3 Image Classification
526(1)
14.2.6.4 Semantic Segmentation
527(2)
14.2.6.5 Blind Learning Based Restoration
529(1)
14.2.7 Recurrent Neural Networks
530(3)
Chapter 15 Medical Image Processing Environment
533(19)
15.1 Hardware and Software Features
533(6)
15.1.1 Hardware Features
533(3)
15.1.2 Software Features
536(3)
15.2 Principles of Image Compression for Archiving and Communication
539(11)
15.2.1 Philosophy of Image Compression
539(1)
15.2.2 Generic Still-Image Compression System
540(1)
15.2.3 Principles of Lossless Compression
541(2)
15.2.3.1 Predictive Coding
542(1)
15.2.4 Principles of Lossy Compression
543(7)
15.2.4.1 Pixel-Oriented Methods
544(1)
15.2.4.2 Block-Oriented Methods
545(3)
15.2.4.3 Global Compression Methods
548(2)
15.3 Present Trends in Medical Image Processing
550(2)
Part III References
552(5)
Index 557
Jiri Jan is a full Professor within the Department of Biomedical Engineering at Brno University in the Czech Republic. He has been an active researcher and educator in medical image processing and analysis over the past thirty years. He is the founding president of the European Association of Medical Imaging and has written over 200 peer reviewed journal articles, 30 book chapters and authored/edited four books within medical imaging.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97813513879102e.html
Märksõnad: