Scribd
Upload
79 views4 pages

CS-578 - Medical Image Analysis

The course CS-578 – Medical Image Analysis is designed to introduce students to concepts, tools, and techniques for analyzing medical images to develop automated diagnostic tools. The course will teach foundations and emerging trends in medical image analysis using Python. Students will learn to read, process, extract features from, and classify medical images with machine learning. By the end of the course students will be able to propose their own method for identifying abnormalities in medical images. The tentative scheme of study includes topics like image preprocessing, edge detection, features extraction, content-based image retrieval, machine learning classifiers, and applications of medical image analysis. Students will complete assignments, quizzes, exams, and a final project to demonstrate their competencies and receive a grade

Uploaded by

ahsan puri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
79 views4 pages

CS-578 - Medical Image Analysis

The course CS-578 – Medical Image Analysis is designed to introduce students to concepts, tools, and techniques for analyzing medical images to develop automated diagnostic tools. The course will teach foundations and emerging trends in medical image analysis using Python. Students will learn to read, process, extract features from, and classify medical images with machine learning. By the end of the course students will be able to propose their own method for identifying abnormalities in medical images. The tentative scheme of study includes topics like image preprocessing, edge detection, features extraction, content-based image retrieval, machine learning classifiers, and applications of medical image analysis. Students will complete assignments, quizzes, exams, and a final project to demonstrate their competencies and receive a grade

Uploaded by

ahsan puri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

CS-578 – Medical Image Analysis FALL – 2022

CS-578 – Medical Image Analysis

Instructor: Dr. Zobia Suhail

Semester: FALL 2022 Campus: New Campus

Course Description:

The course of CS-578 – Medical Image Analysis is particularly designed to introduce students with
the concepts, tools and techniques required to analyze medical images in order to develop
automated tools to be used in diagnostic process. Medical Image Analysis is an active area of
research as well as an interesting field of study with the aim to help humanity by developing tools
and methods that can used by doctors and radiologists to assist them in disease diagnostics. This
course is designed as a graduate level elective for M. Phil. in Computer science which will teach
students the foundations as well as emerging trends in the fields of medical image analysis.

Goals and Objectives:

On the completion of this course students would be able to meet following objectives.

• Reading and analyzing the medical images

• Do the basic processing of medical images using Python programming language

• To extract the useful features from the images

• Use those features to classify the images using machine learning techniques

• To use the built-in machine learning tools available in Python as well as to use the third party
machine learning software.

Big Aim: To propose their own method for identification / classification of certain
abnormalities in medical images

Student’s competence in these objectives will determine his/her grade in the subject Medical Image
Analysis.

Related Text / Reading Material:

• Pattern Recognition and Machine Learning, Christopher M. Bishop.

• Research in Medical Imaging Using Image Processing Techniques (By Yousif Mohamed Y.
Abdullah and Tariq Alqahtani)

• Fundamentals of Medical Imaging, Thomas M. Deserno


Tentative Scheme of Study:

Week # Lecture # Topic


1 1 Basic Introduction of the course. Why this course is
needed to be studied?
2 Basic concept of Python language. How to read and
access the image using Python? How to install and
use Python using Spyder.

2 3 More about Python:


• ImageIO
• Numpy

4 More about Python:


• Scipy
• Matplotlib

3 5 Image Intensities
Histograms

6 Masks
Applying masks to images

4 7 Image Preprocessing
• contrast enhancement
• histogram equalization

8 Image Preprocessing
• filtering
• sharpening
• etc.

5 9 Resizing images and Interpolation

10 Resizing images and Interpolation (Continued)

6 11 Edge Detection techniques


Canny edge detectors

12 Edge Detection techniques


Sobel Edge detectors
Prewitt Edge Detection

7 13 Image Features
Basic image features
Gradient features

14 Image Features
Texture features
Statistical Features

8 15 Content Based Image Retrieval (CBIR)


16 Content Based Image Retrieval (CBIR) – advantages
and uses

9 17 Machine Learning for image processing

18 Basic Classifier: e.g. K-Means

Project Assignment / paper title selection

10 19 Evaluating Classifier:

20 Cross Validation
Leave one out

11 21 Metrics for Classifier’s accuracy:


Accuracy, Precision, Recall, False Positive, False
negative ……

22 Statistical measures of accuracy


Decision Matrix
12 23 Practical applications of medical image processing

24 Practical applications of medical image processing


(Continued)
Deliverable-1 Submission with targeted approach and brief literature review
13 25 What is a Dataset?
What is Ground Truth?

26 Some discussion about the available medical dataset


and their related problems.
Some discussion on only challenges for medical
images.

14 27 Limitations and Drawbacks of medical image analysis


in diagnostic process.
Problems on medical data availability.

28 BIG AIM of Medical Image Processing.

15 Deliverable-2 submission & Final Project Presentations


16 Deliverable-2 submission & Final Project Presentations
Grading Scheme/Criteria:

Assignments: 10 %

Quizes: 10 %

Mid term Exam : 30 %

Final Exam: 30 %

Project / Paper and their presentations : 15 % + 5 %

You might also like