MEDICAL IMAGING

International Teaching MEDICAL IMAGING

0622900012
DIPARTIMENTO DI INGEGNERIA DELL'INFORMAZIONE ED ELETTRICA E MATEMATICA APPLICATA
EQF7
DIGITAL HEALTH AND BIOINFORMATIC ENGINEERING
2021/2022



OBBLIGATORIO
YEAR OF COURSE 2
YEAR OF DIDACTIC SYSTEM 2018
PRIMO SEMESTRE
CFUHOURSACTIVITY
1IMAGE ANALYSIS - MOD.1
324LESSONS
2MEDICAL IMAGING APPLICATION - MOD.2
324LAB
324EXERCISES
Objectives
THE COURSE PROVIDES THEORETICAL AND TECHNOLOGICAL KNOWLEDGE ABOUT THE MAIN TYPES OF MEDICAL IMAGES AND ON THE METHODOLOGIES FOR PROCESSING SUCH IMAGES, IMPROVING THEIR QUALITY AND EXTRACTING INFORMATION RELEVANT FOR THEIR DIAGNOSIS.

KNOWLEDGE AND UNDERSTANDING
PHASES OF AN IMAGE PROCESSING SYSTEM, WITH PARTICULAR FOCUS ON THE PHASES OF LOW LEVEL PROCESSING (ACQUISITION, FILTERING), INTERMEDIATE LEVEL PROCESSING (EXTRACTION OF REGIONS AND CONTOURS) AND HIGH LEVEL PROCESSING (SHAPE RECOGNITION), TOGETHER WITH THE BASIC TECHNIQUES FOR IMPLEMENTING THESE FUNCTIONS WITH EXISTING LIBRARIES AND FRAMEWORKS; CHARACTERISTICS OF THE TYPES OF IMAGES USED IN THE MEDICAL FIELD (RADIOGRAPHIC IMAGES, CT, PET, MRI AND ULTRASOUND IMAGES) AND THEIR REPRESENTATION; MAIN FRAMEWORKS FOR IMAGE ANALYSIS.

APPLYING KNOWLEDGE AND UNDERSTANDING
DESIGNING AND IMPLEMENTING APPLICATIONS BASED ON THE ANALYSIS AND INTERPRETATION OF MEDICAL IMAGES, USING DEDICATED FRAMEWORKS AND LIBRARIES.
Prerequisites
THE KNOWLEDGE OF A PROGRAMMING LANGUAGE SUCH AS C OR PYTHON IS BENEFICIAL
Contents
DIGITAL MEDICAL IMAGES (LECTURE / PRACTICE / LABORATORY HOURS 6/2/0)
ACQUISITION AND STANDARD FORMATS

POINT AND LOCAL OPERATIONS (LECTURE / PRACTICE / LABORATORY HOURS 6/2/0)
BRIGHTNESS AND CONTRAST TRANSFORMATIONS. AUTOMATIC IMAGE EQUALIZATION. GAMMA CORRECTION.

TWO-DIMENSIONAL FILTERS (LECTURE / PRACTICE / LABORATORY HOURS 4/4/0)
LOW PASS AND HIGH PASS FILTERS. DIGITAL GRADIENTS. MEDIAN FILTER. SPECIAL TECHNIQUES FOR NOISE REMOVAL. (THEORY HOURS: 4; EXERCISE HOURS: 4)

MORPHOLOGICAL SEGMENTATION TECHNIQUES (LECTURE / PRACTICE / LABORATORY HOURS 8/4/0)
EROSION, DILATION, OPENING, CLOSURE

CLUSTERING AND CLASSIFICATION TECHNIQUES (LECTURE / PRACTICE / LABORATORY HOURS 4/2/0)
K-MEANS AND MEAN SHIFT ALGORITHMS

IMAGE REGISTRATION TECHNIQUES. (LECTURE / PRACTICE / LABORATORY HOURS 4/2/0)

DEEP LEARNING TECHNIQUES FOR SEGMENTATION AND CLASSIFICATION OF MEDICAL IMAGES. (LECTURE / PRACTICE / LABORATORY HOURS 12/12/0)

TOTAL LECTURE / PRACTICE / LABORATORY HOURS 44/28/0
Teaching Methods
TEACHING ACTIVITIES INCLUDE THEORETICAL LESSONS, EXERCISES AND LABS. STUDENTS WILL BE ASSIGNED BOTH INDIVIDUAL AND GROUP PROJECTS, IN WHICH THEY WILL USE METHODOLOGIES AND DEVELOPMENT TOOLS PRESENTED IN THE COURSE. LABS ARE AIMED AT IMPLEMENTING THE PROPOSED PROJECTS.

IN ORDER TO BE ABLE TO SUPPORT THE FINAL PROFIT VERIFICATION AND ACHIEVE THE CFU RELATED TO THE TRAINING ACTIVITY, THE STUDENT MUST HAVE ATTENDED
AT LEAST 70% OF THE HOURS PROVIDED FOR ASSISTED EDUCATIONAL ACTIVITIES.
Verification of learning
THE EXAM IS AIMED AT EVALUATING IF THE STUDENT MASTERS THE TOPICS PRESENTED IN THE COURSE AND IF SHE/HE IS ABLE TO APPLY THE ACQUIRED KNOWLEDGE TO THE RESOLUTION OF REAL PROBLEMS.

THE EXAM REQUIRES THE REALIZATION OF A PROJECT WHOSE CONTENT IS PREVIOUSLY AGREED WITH THE TEACHER AND IS RELATED TO ONE OF THE TOPICS PRESENTED IN THE COURSE: THE DESIGN AND METHODOLOGICAL CHOICES MADE ARE CONSIDERED FOR THE ASSESSMENT.
Texts
R.C. GONZALEZ, R.E. WOODS, DIGITAL IMAGE PROCESSING, 4TH ED., PEARSON COLLEGE DIV., 2017

A. WEBB, INTRODUCTION TO BIOMEDICAL IMAGING, IEEE PRESS, 2004

SUPPLEMENTARY TEACHING MATERIAL WILL BE AVAILABLE ON THE UNIVERSITY E-LEARNING PLATFORM (HTTP://ELEARNING.UNISA.IT) ACCESSIBLE TO STUDENTS USING THEIR OWN UNIVERSITY CREDENTIALS.
More Information
THE COURSE IS HELD IN ENGLISH
  BETA VERSION Data source ESSE3