Segmentation of Cardiac Delayed Enhancement Magnetic Resonance Images / (Record no. 8825)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 09919nam a22002537a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 210112b2010 a|||f mb|| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE | |
| Original cataloging agency | EG-CaNU |
| Transcribing agency | EG-CaNU |
| 041 0# - Language Code | |
| Language code of text | eng |
| Language code of abstract | eng |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 610 |
| 100 0# - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Mostafa Ahmed Ibrahim AlAttar |
| 245 1# - TITLE STATEMENT | |
| Title | Segmentation of Cardiac Delayed Enhancement Magnetic Resonance Images / |
| Statement of responsibility, etc. | Mostafa Ahmed Ibrahim AlAttar |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Date of publication, distribution, etc. | 2010 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 130 p. |
| Other physical details | ill. |
| Dimensions | 21 cm. |
| 500 ## - GENERAL NOTE | |
| Materials specified | Supervisor: Nael Osman |
| 502 ## - Dissertation Note | |
| Dissertation type | Thesis (M.A.)—Nile University, Egypt, 2010 . |
| 504 ## - Bibliography | |
| Bibliography | "Includes bibliographical references" |
| 505 0# - Contents | |
| Formatted contents note | Contents:<br/>INTRODUCTION .............................................................................................................. 1<br/>1.1. Motivation ...................................................................................................... 1<br/>1.2. Problem Statement ......................................................................................... 4<br/>1.3. Thesis Objective ............................................................................................. 4<br/>1.4. Thesis Overview ............................................................................................. 5<br/>BACKGROUND ................................................................................................................ 5<br/>2.1. Physiology Review ......................................................................................... 5<br/>2.1.1. Heart Anatomy ........................................................................................ 5<br/>2.1.2. Physiological Measurements .................................................................. 7<br/>2.2. MRI concepts and data material ..................................................................... 8<br/>2.2.1. History of MRI ........................................................................................ 8<br/>2.2.3. Cardiac MRI.......................................................................................... 20<br/>2.2.4. Cardiac MRI Imaging Methods: ........................................................... 21<br/>RELATED WORK ........................................................................................................... 26<br/>3.1. Thresholding ................................................................................................. 26<br/>3.2. Region Growing ........................................................................................... 28<br/>3.3. Classifiers ..................................................................................................... 30<br/>3.4. Clustering ..................................................................................................... 33<br/>3.5. Graph-based segmentation ........................................................................... 35<br/>3.6. Active contour models ACMs ...................................................................... 35<br/>3.7. Active shape models ASMs ......................................................................... 36<br/>3.8. Active appearance models AAMs ................................................................ 37<br/>3.9. Level-set segmentation ................................................................................. 37<br/>CINE BRIGHT BLOOD IMAGES SEGMENTATION METHODS.............................. 38<br/>4.1. Multi Seeded Region Growing (Experiment 1) ........................................... 38<br/>4.1.1. Standard region growing algorithm (RG) ............................................. 38<br/>4.1.2. Limitations of region growing .............................................................. 39<br/>4.1.3. Multi-Seeded Region Growing (MSRG) .............................................. 40<br/>xvi<br/>4.1.4. Morphological Operations .................................................................... 44<br/>4.1.5. Epicardial Control Points ...................................................................... 48<br/>4.1.6. Refinement of the Contours using ACMs ............................................. 51<br/>4.1.7. Proposed Algorithm .............................................................................. 54<br/>4.2. Adaptive Multi Seeded Region Growing (Experiment 2) ............................ 55<br/>4.2.1. Multi-Seeded Region Growing ............................................................. 55<br/>4.2.2. Seed Points and Constraining Areas Selection ..................................... 55<br/>4.2.3. K-Means ................................................................................................ 55<br/>4.2.4. Proposed Algorithm .............................................................................. 57<br/>4.3. Automatic Evaluation Methods .................................................................... 58<br/>4.3.1. Average perpendicular distance ............................................................ 58<br/>4.3.2. Dice metric ............................................................................................ 60<br/>4.3.3. Accuracy Measurements ....................................................................... 61<br/>4.3.4. Visual (Manual) Evaluation Method .................................................... 61<br/>4.3.5. Another Parameters that’s taken into account ...................................... 61<br/>CINE BLACK BLOOD IMAGES CLASSIFICATION .................................................. 62<br/>5.1. Modified STEAM for Black Blood Imaging ............................................... 62<br/>5.2. Stochastic Model .......................................................................................... 63<br/>5.3. Classification Techniques ............................................................................ 65<br/>5.3.1. Bayesian Classifier................................................................................ 65<br/>5.3.2. Linear Classifier L1-Norm .................................................................... 65<br/>5.3.3. Quadratic Classifier L2-Norm ............................................................... 66<br/>5.3.4. Rectangular Classifier Linf-Norm .......................................................... 67<br/>5.4. Numerical Simulation .................................................................................. 67<br/>5.4.1. Case1: Background Signal .................................................................... 68<br/>5.4.2. Case2: Tissue Signal ............................................................................. 69<br/>5.5. Real Images Test .......................................................................................... 70<br/>5.6. Further Processing ........................................................................................ 72<br/>5.7. Performance Evaluation Methods ................................................................ 74<br/>CINE BRIGHT BLOOD SEGMENTATION RESULTS & DISCUSSION ................... 75<br/>6.1. Multi Seeded Region Growing (Experiment 1) Results............................... 75<br/>6.1.1. Simple Region Growing ....................................................................... 76<br/>6.1.2. Multi Seeded Region Growing constrained by Overlapped Sectors .... 77<br/>xvii<br/>6.1.3. Evaluation of the MSRG Coefficients .................................................. 77<br/>6.1.4. Resulted Contour Refinement using ACM and CPR ............................ 80<br/>6.1.5. Final Results.......................................................................................... 80<br/>6.2. Adaptive Multi Seeded Region Growing (Experiment 2) Results ............... 85<br/>6.2.1. Selecting the sectors sizes and positions using k-means ...................... 85<br/>6.2.2. Quantitative Analysis ............................................................................ 86<br/>6.2.3. Final Results: ........................................................................................ 87<br/>CINE BLACK BLOOD CLASSIFICATION RESULTS & DISCUSSION ................... 92<br/>7.1. Simulated Data Results ................................................................................ 92<br/>7.2. Real Images Results ..................................................................................... 95<br/>CONCLUSION ............................................................................................................... 101<br/>8.1. Future Work ............................................................................................... 103<br/>REFERENCES ............................................................................................................... |
| 520 3# - Abstract | |
| Abstract | Abstract:<br/>Imaging the heart using Cine Bright Blood MRI and Cine Black-blood MRI<br/>sequences is very important to evaluate the cardiac global and regional function. In<br/>the first type of imaging which is Cine Bright Blood MRI, Manual segmentation of<br/>the contours in all images through different slices is a cumbersome task. Therefore,<br/>methods were proposed to automatically or semi-automatically analyze and segment<br/>the contours from short-axis images and derive useful clinical information from them<br/>is highly desirable. In this thesis, we have proposed two algorithms to segment LV<br/>and they are Multi-Seeded Region Growing (MSRG) and adaptive MSRG. Their<br/>performance has been evaluated also in this thesis. The second type of images which<br/>is Cine Black Blood images suffers from the low signal-to-noise ratio SNR in<br/>general. In this thesis, a probabilistic model of blood and tissue signals is developed<br/>and used to build a Bayesian decision function to identify and filter the noise from the<br/>background signal. Numerical simulation and real MRI images were used to test and<br/>validate the proposed method. Also, the proposed method is compared to other<br/>conventional techniques. |
| 546 ## - Language Note | |
| Language Note | Text in English, abstracts in English. |
| 650 #4 - Subject | |
| Subject | Informatics-IFM |
| 655 #7 - Index Term-Genre/Form | |
| Source of term | NULIB |
| focus term | Dissertation, Academic |
| 690 ## - Subject | |
| School | Informatics-IFM |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Koha item type | Thesis |
| 650 #4 - Subject | |
| -- | 266 |
| 655 #7 - Index Term-Genre/Form | |
| -- | 187 |
| 690 ## - Subject | |
| -- | 266 |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Date acquired | Total Checkouts | Full call number | Date last seen | Price effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | Not For Loan | Main library | Main library | 01/12/2021 | 610/ MA.S 2010 | 01/12/2021 | 01/12/2021 | Thesis |