| 000 | 13056nam a22002537a 4500 | ||
|---|---|---|---|
| 008 | 210112b2014 a|||f mb|| 00| 0 eng d | ||
| 040 |
_aEG-CaNU _cEG-CaNU |
||
| 041 | 0 |
_aeng _beng |
|
| 082 | _a610 | ||
| 100 | 0 |
_aMai Wael _9271 |
|
| 245 | 1 |
_aAutomatic interpretation for cardiac magnetic resonance images _cMai Wael |
|
| 260 | _c2014 | ||
| 300 |
_a 77 p. _bill. _c21 cm. |
||
| 500 | _3Supervisor: Ahmed Fahmy | ||
| 502 | _aThesis (M.A.)—Nile University, Egypt, 2014 . | ||
| 504 | _a"Includes bibliographical references" | ||
| 505 | 0 | _aContents: Chapter 1 Introduction ............................................................................................ 1 1. Introduction .................................................................................................................. 1 2. Motivation and Challenges ............................................................................................ 3 3. Objectives and Contribution .......................................................................................... 5 4. Thesis Outlines ............................................................................................................. 5 References ........................................................................................................................ 7 Chapter 2 Background ............................................................................................ 8 1. Human Heart................................................................................................................. 8 1.1 Heart Anatomy ........................................................................................................ 8 1.2 Heart Function ...................................................................................................... 10 1.3 Cardiac Electrical Cycle ....................................................................................... 10 1.4 Segmentation of the Left Ventricle ........................................................................ 11 2. Cardiac Failure............................................................................................................ 12 2.1 Ischemic heart disease .......................................................................................... 12 2.2 Myocardial Infarction ............................................................................................ 12 2.3 Cardiomyopathy ................................................................................................... 13 2.4 Pulmonary Hypertension ....................................................................................... 14 3. Medical Imaging ......................................................................................................... 15 4. Magnetic Resonance Imaging (MRI) ........................................................................... 16 4.1 MRI scanning process .......................................................................................... 16 4.2 MRI benefits and limitations ................................................................................. 17 5. Cardiac MRI ............................................................................................................... 17 5.1 Cardiac imaging planes ......................................................................................... 17 5.1.1 Long Axis plane .................................................................................... 18 5.1.2 Short Axis plane .................................................................................... 19 5.2 Cardiac imaging techniques ................................................................................... 5.2.1 Steady-State Free Precession (SSFP) Cine Technique ............................ 19 5.2.2 Tagged MRI .......................................................................................... 20 5.2.3 Strain Encoded MRI (SENC) ................................................................. 21 5.2.4 Perfusion MRI ....................................................................................... 22 6. Digital Image Storage format ...................................................................................... 23 6.1 Data Storage ......................................................................................................... 23 6.2 Image formats ....................................................................................................... 23 6.2.1 Digital Imaging and Communication in Medicine (DICOM) .................. 23 DICOM file format .................................................................................... 24 DICOM header .......................................................................................... 24 6.2.2 Other image formats .............................................................................. 25 JPEG (Joint Photographic Expert Guide) ................................................... 25 TIFF (Tagged Image File Format) .............................................................. 25 GIF (Graphical Interchange Format) .......................................................... 25 PNG (Portable Networks Graphics) ........................................................... 25 7. Automatic Interpretation of Medical Images ................................................................ 26 7.1 Content Based Image Retrieval (CBIR) ................................................................. 26 7.1.1 CBIR Techniques .................................................................................. 27 Color ......................................................................................................... 27 Texture ...................................................................................................... 27 Shape ........................................................................................................ 27 7.2 Computer Aided Diagnosis (CAD) ........................................................................ 26 References ...................................................................................................................... 30 Chapter 3 Classification of cardiac MRI image types .......................................... 33 1. Introduction ................................................................................................................ 33 2. Methodology ............................................................................................................... 34 2.1 Classification Algorithm ....................................................................................... 34 2.2 Extraction of feature vectors .................................................................................. 35 2.3 Feature Classification ............................................................................................ 39 2.4 Testing and Validation .......................................................................................... 40 3. Results and Discussion ................................................................................................ 4. Conclusion .................................................................................................................. 41 References ..................................................................................................................... 42 Chapter 4 Texture based classification for cardiac MRI types and orientations 43 1. Introduction ................................................................................................................ 43 2. Methodology ............................................................................................................... 44 2.1 Dataset .................................................................................................................. 44 2.2 Preprocessing ........................................................................................................ 45 2.3 Local Binary Pattern.............................................................................................. 46 2.3.1 LBP derivation....................................................................................... 47 2.4 Edge Orientation Histogram .................................................................................. 48 2.5 Training and Similarity measurement .................................................................... 49 3. Results and Discussion ................................................................................................ 49 4. Conclusion .................................................................................................................. 51 References ...................................................................................................................... 52 Chapter 5 Detection of cardiac function abnormality using normalized wall thickness patterns .................................................................................................. 54 1. Introduction ................................................................................................................ 54 2. Method ....................................................................................................................... 56 2.1 Dataset .................................................................................................................. 56 2.2 Normalized Wall Thickness (NWT) ...................................................................... 57 2.3 Feature Vectors and PCA ...................................................................................... 57 2.4 Classification ........................................................................................................ 58 2.5 Experiments .......................................................................................................... 59 3. Results and Discussion ................................................................................................ 60 4. Conclusion .................................................................................................................. 62 References ............................................................................................................ 63 Chapter 6 Summary and Future work ................................................................. | |
| 520 | 3 | _aAbstract: The enormous increase in digital images, especially in medical field, acquired using different modalities and techniques, makes it necessary to develop tools and techniques that help and support dealing with the huge amount of the available data. The automatic interpretation of medical images is an active research aims to provide the necessary information to help the physician or the radiologist in his diagnosis. Content Based Image Retrieval (CBIR) and classification is the first part of the medical image interpretation, where recognition of such imaging modality or image acquisition technique will facilitate the data access. Besides that it is considered as the prerequisite for the second interpretation part, which called Computer Aided Diagnosis (CAD). The CAD objective is to provide a second opinion to the radiologist to help him in his diagnostic decision. Thus, CBIR with CAD represent a complete medical image interpretation system. In particular, Cardiac Magnetic Resonance Imaging (MRI) can provide thousands of images during one exam for one patient, with several cardiac orientations and different acquisition types to represent heart structure and function. In this thesis, we represent an automatic interpretation for cardiac MRI images. The proposed method starts by two approaches for automatic classification and retrieval for cardiac MRI different image types as cine, tagged, SENC, and perfusion MRI. First one is based on statistical features with a decision tree algorithm for classification. The second approach is based on a texture feature descriptor, namely, the Local Binary Pattern (LBP). This approach is to overcome the problem with the first one, where it may fail in case of intensity variations occurring across different machines. We also proposed classification and labeling algorithm for different orientations or cross sections of the heart as long axis and short axis views. The Edge Orientation Histogram (EOH) is used to extract the differences between the long axis and short axis views. Following that, assessment of the cardiac wall motion abnormalities is proposed. A novel feature is introduced to represent the regional wall motion variations in normal cases and in different diseases affect the myocardium. | |
| 546 | _aText in English, abstracts in English. | ||
| 650 | 4 |
_aInformatics-IFM _9266 |
|
| 655 | 7 |
_2NULIB _aDissertation, Academic _9187 |
|
| 690 |
_aInformatics-IFM _9266 |
||
| 942 |
_2ddc _cTH |
||
| 999 |
_c8798 _d8798 |
||