Lehrveranstaltung Medical Image Processing (Vorlesung)

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.

Learning Outcomes

The course will introduce types and formats of medical image data (ultrasound, MRI, CT, histological images, …) with their characteristic properties and requirements for preprocessing.

Techniques for the extraction and quantification of anatomical structures as well as functional information (motion, bloodflow, perfusion) will be introduced and explored in the exercises.

Participants will learn

- How spatio-temporal information is represented in medical imaging

- How to segment and model anatomical structures

- How to extract physiological information from 4D image data

- How to implement and integrate these techniques

Content

Segmentation of tubular structures, organs and pathological tissue with tracking, methods, morphological and classification approaches such as Gaussian mixture models and Markov random fields, deformable models; time series analysis including registration, motion tracking, (model-based) change assessment; machine learning in medical image processing

Description of Teaching and Learning Methods

The lecture will introduce typical problems and approaches related to the extraction of information from medical image data. The relevant algorithmic approaches will be theoretically explained. Participants are expected to rehearse the content after class in preparation for the exercises.

The exercises focus on the practical work at the computer in order to enable the participants to implement and explore algorithmic approaches.

Homeworks will consist of specific tasks assigned to small groups and focus on theoretical questions as well as programming solutions.

Exam information

The oral exams will take place at the end of the summer semester 2023.