Course Detail
Course Description
| Course | Code | Semester | T+P (Hour) | Credit | ECTS |
|---|---|---|---|---|---|
| MEDICAL IMAGE ANALYSIS | EEE4213125 | Spring Semester | 3+0 | 3 | 6 |
| Course Program |
| Prerequisites Courses | |
| Recommended Elective Courses |
| Language of Course | English |
| Course Level | First Cycle (Bachelor's Degree) |
| Course Type | Elective |
| Course Coordinator | Assist.Prof. Cihan Bilge KAYASANDIK |
| Name of Lecturer(s) | Assist.Prof. Cihan Bilge KAYASANDIK |
| Assistant(s) | |
| Aim | The course aims to show how to identify the problems in medical sciences and how to approach them. We will introduce mathematical techniques to extract information from medical images. We will show how to analyze medical images according to different purposes and help diagnose diseases. Medical image analysis is a highly interdisciplinary field involving medicine, computer science, mathematics, biology, statistics, probability, psychology, and other fields. The course includes topics in medical image acquisitions: basics of Xray CT, Ultrasound, MRI and fMRI; image preprocessing: image denoising, image filtering, and basic filter design, image enhancement, feature extraction; image segmentation: local and adaptive thresholding, active contour and level set methods, edge detection, basic texture analysis; image registration, tracking; machine learning and deep learning for the feature extraction and segmentation purposes in medical images. This course will be application-oriented. Assignments will be based on a literature review, paper presentation, and computer implementations. |
| Course Content | This course contains; Course Introduction ,Medical Data Acquisition, ,Introduction to Computer vision and signal processing ,Data Preprocessing ,Convolution and special filters , Image Segmentation with Conventional Methods ,Student Paper presentations ,Machine Learning basics ,Machine Learning methods on image analysis ,Validation methods for small data analysis ,Artificial neural networks/ Autoencoders I ,Artificial neural networks/ Autoencoders II ,Deep learning applications for medical data ,Deep learning applications for medical data II . |
| Dersin Öğrenme Kazanımları | Teaching Methods | Assessment Methods |
| 1. Ability to identify problems and deficiencies in medical data analysis and create solution routes for existing problems | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| 2. Ability to identify and apply filters and filtering methods appropriate to the features to be extracted from an image. | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| 3. Being able to use a mathematical perspective and put it into practice in order to obtain the necessary information in medical data analysis. | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| 4. Ability to use deep learning methods from machine learning and artificial neural networks in medical data analysis | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| Teaching Methods: | 10: Discussion Method, 14: Self Study Method, 16: Question - Answer Technique, 18: Micro Teaching Technique, 19: Brainstorming Technique, 2: Project Based Learning Model, 3: Problem Baded Learning Model, 9: Lecture Method |
| Assessment Methods: | A: Traditional Written Exam, D: Oral Exam, F: Project Task |
Course Outline
| Order | Subjects | Preliminary Work |
|---|---|---|
| 1 | Course Introduction | Lecture slides, reading assigned papers |
| 2 | Medical Data Acquisition, | Lecture slides, reading assigned papers |
| 3 | Introduction to Computer vision and signal processing | Lecture slides, reading assigned papers |
| 4 | Data Preprocessing | Lecture slides, reading assigned papers |
| 5 | Convolution and special filters | Lecture slides, reading assigned papers |
| 6 | Image Segmentation with Conventional Methods | Lecture slides, reading assigned papers |
| 7 | Student Paper presentations | Lecture slides, reading assigned papers |
| 8 | Machine Learning basics | Lecture slides, reading assigned papers |
| 9 | Machine Learning methods on image analysis | Lecture slides, reading assigned papers |
| 10 | Validation methods for small data analysis | Lecture slides, reading assigned papers |
| 11 | Artificial neural networks/ Autoencoders I | Lecture slides, reading assigned papers |
| 12 | Artificial neural networks/ Autoencoders II | Lecture slides, reading assigned papers |
| 13 | Deep learning applications for medical data | Lecture slides, reading assigned papers |
| 14 | Deep learning applications for medical data II | Lecture slides, reading assigned papers |
| Resources |
| 1. Fundamentals of Medical Imaging, Suetens, P., Cambridge University Press, 2. Insight into Images: Principles and Practice for Segmentation, Registration and Image Analysis, Yoo, Terry S., CRC Pressö 3. Duda, R. O., & Hart, P. E. (2006). Pattern classification. John Wiley & Sons. |
Course Contribution to Program Qualifications
| Course Contribution to Program Qualifications | |||||||
| No | Program Qualification | Contribution Level | |||||
| 1 | 2 | 3 | 4 | 5 | |||
| 1 | An ability to apply knowledge of mathematics, science, and engineering | ||||||
| 2 | An ability to identify, formulate, and solve engineering problems | X | |||||
| 3 | An ability to design a system, component, or process to meet desired needs within realistic constraints such as economic, environmental, social, political, ethical, health and safety, manufacturability, and sustainability | X | |||||
| 4 | An ability to use the techniques, skills, and modern engineering tools necessary for engineering practice | X | |||||
| 5 | An ability to design and conduct experiments, as well as to analyze and interpret data | X | |||||
| 6 | An ability to function on multidisciplinary teams | ||||||
| 7 | An ability to communicate effectively | ||||||
| 8 | A recognition of the need for, and an ability to engage in life-long learning | ||||||
| 9 | An understanding of professional and ethical responsibility | ||||||
| 10 | A knowledge of contemporary issues | ||||||
| 11 | The broad education necessary to understand the impact of engineering solutions in a global, economic, environmental, and societal context | ||||||
Assessment Methods
| Contribution Level | Absolute Evaluation | |
| Rate of Midterm Exam to Success | 30 | |
| Rate of Final Exam to Success | 70 | |
| Total | 100 | |
| ECTS / Workload Table | ||||||
| Activities | Number of | Duration(Hour) | Total Workload(Hour) | |||
| Course Hours | 14 | 3 | 42 | |||
| Guided Problem Solving | 0 | 0 | 0 | |||
| Resolution of Homework Problems and Submission as a Report | 6 | 2 | 12 | |||
| Term Project | 4 | 2 | 8 | |||
| Presentation of Project / Seminar | 2 | 6 | 12 | |||
| Quiz | 0 | 0 | 0 | |||
| Midterm Exam | 8 | 6 | 48 | |||
| General Exam | 8 | 8 | 64 | |||
| Performance Task, Maintenance Plan | 0 | 0 | 0 | |||
| Total Workload(Hour) | 186 | |||||
| Dersin AKTS Kredisi = Toplam İş Yükü (Saat)/30*=(186/30) | 6 | |||||
| ECTS of the course: 30 hours of work is counted as 1 ECTS credit. | ||||||
Detail Informations of the Course
Course Description
| Course | Code | Semester | T+P (Hour) | Credit | ECTS |
|---|---|---|---|---|---|
| MEDICAL IMAGE ANALYSIS | EEE4213125 | Spring Semester | 3+0 | 3 | 6 |
| Course Program |
| Prerequisites Courses | |
| Recommended Elective Courses |
| Language of Course | English |
| Course Level | First Cycle (Bachelor's Degree) |
| Course Type | Elective |
| Course Coordinator | Assist.Prof. Cihan Bilge KAYASANDIK |
| Name of Lecturer(s) | Assist.Prof. Cihan Bilge KAYASANDIK |
| Assistant(s) | |
| Aim | The course aims to show how to identify the problems in medical sciences and how to approach them. We will introduce mathematical techniques to extract information from medical images. We will show how to analyze medical images according to different purposes and help diagnose diseases. Medical image analysis is a highly interdisciplinary field involving medicine, computer science, mathematics, biology, statistics, probability, psychology, and other fields. The course includes topics in medical image acquisitions: basics of Xray CT, Ultrasound, MRI and fMRI; image preprocessing: image denoising, image filtering, and basic filter design, image enhancement, feature extraction; image segmentation: local and adaptive thresholding, active contour and level set methods, edge detection, basic texture analysis; image registration, tracking; machine learning and deep learning for the feature extraction and segmentation purposes in medical images. This course will be application-oriented. Assignments will be based on a literature review, paper presentation, and computer implementations. |
| Course Content | This course contains; Course Introduction ,Medical Data Acquisition, ,Introduction to Computer vision and signal processing ,Data Preprocessing ,Convolution and special filters , Image Segmentation with Conventional Methods ,Student Paper presentations ,Machine Learning basics ,Machine Learning methods on image analysis ,Validation methods for small data analysis ,Artificial neural networks/ Autoencoders I ,Artificial neural networks/ Autoencoders II ,Deep learning applications for medical data ,Deep learning applications for medical data II . |
| Dersin Öğrenme Kazanımları | Teaching Methods | Assessment Methods |
| 1. Ability to identify problems and deficiencies in medical data analysis and create solution routes for existing problems | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| 2. Ability to identify and apply filters and filtering methods appropriate to the features to be extracted from an image. | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| 3. Being able to use a mathematical perspective and put it into practice in order to obtain the necessary information in medical data analysis. | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| 4. Ability to use deep learning methods from machine learning and artificial neural networks in medical data analysis | 10, 14, 16, 18, 19, 2, 3, 9 | A, D, F |
| Teaching Methods: | 10: Discussion Method, 14: Self Study Method, 16: Question - Answer Technique, 18: Micro Teaching Technique, 19: Brainstorming Technique, 2: Project Based Learning Model, 3: Problem Baded Learning Model, 9: Lecture Method |
| Assessment Methods: | A: Traditional Written Exam, D: Oral Exam, F: Project Task |
Course Outline
| Order | Subjects | Preliminary Work |
|---|---|---|
| 1 | Course Introduction | Lecture slides, reading assigned papers |
| 2 | Medical Data Acquisition, | Lecture slides, reading assigned papers |
| 3 | Introduction to Computer vision and signal processing | Lecture slides, reading assigned papers |
| 4 | Data Preprocessing | Lecture slides, reading assigned papers |
| 5 | Convolution and special filters | Lecture slides, reading assigned papers |
| 6 | Image Segmentation with Conventional Methods | Lecture slides, reading assigned papers |
| 7 | Student Paper presentations | Lecture slides, reading assigned papers |
| 8 | Machine Learning basics | Lecture slides, reading assigned papers |
| 9 | Machine Learning methods on image analysis | Lecture slides, reading assigned papers |
| 10 | Validation methods for small data analysis | Lecture slides, reading assigned papers |
| 11 | Artificial neural networks/ Autoencoders I | Lecture slides, reading assigned papers |
| 12 | Artificial neural networks/ Autoencoders II | Lecture slides, reading assigned papers |
| 13 | Deep learning applications for medical data | Lecture slides, reading assigned papers |
| 14 | Deep learning applications for medical data II | Lecture slides, reading assigned papers |
| Resources |
| 1. Fundamentals of Medical Imaging, Suetens, P., Cambridge University Press, 2. Insight into Images: Principles and Practice for Segmentation, Registration and Image Analysis, Yoo, Terry S., CRC Pressö 3. Duda, R. O., & Hart, P. E. (2006). Pattern classification. John Wiley & Sons. |
Course Contribution to Program Qualifications
| Course Contribution to Program Qualifications | |||||||
| No | Program Qualification | Contribution Level | |||||
| 1 | 2 | 3 | 4 | 5 | |||
| 1 | An ability to apply knowledge of mathematics, science, and engineering | ||||||
| 2 | An ability to identify, formulate, and solve engineering problems | X | |||||
| 3 | An ability to design a system, component, or process to meet desired needs within realistic constraints such as economic, environmental, social, political, ethical, health and safety, manufacturability, and sustainability | X | |||||
| 4 | An ability to use the techniques, skills, and modern engineering tools necessary for engineering practice | X | |||||
| 5 | An ability to design and conduct experiments, as well as to analyze and interpret data | X | |||||
| 6 | An ability to function on multidisciplinary teams | ||||||
| 7 | An ability to communicate effectively | ||||||
| 8 | A recognition of the need for, and an ability to engage in life-long learning | ||||||
| 9 | An understanding of professional and ethical responsibility | ||||||
| 10 | A knowledge of contemporary issues | ||||||
| 11 | The broad education necessary to understand the impact of engineering solutions in a global, economic, environmental, and societal context | ||||||
Assessment Methods
| Contribution Level | Absolute Evaluation | |
| Rate of Midterm Exam to Success | 30 | |
| Rate of Final Exam to Success | 70 | |
| Total | 100 | |