TU Wien:Medizinische Bildverarbeitung VO (Langs)/Prüfung 2023-05-10

1. Describe and outline the Active Shape Model search. What texture/property is considered in ASM? How does search work on new image?

2. Given two covariance matrices: A = [5 0 ; 0 1] and B = [5 1 ; 1 2].a. Sketch the two distributions of sets of points A and B, respectively, in a 2-dimensional space b. On which of the two data sets does PCA make sense?

3. Which material properties does CT measure? Which transformation is necessary to reconstruct3D imaging data from the measured signals?

4. What registration method to use if you need to examine fMRI and MRI images from 30 brains of different individuals. I.e. you want to compare the fMRI signals at corresponding positions in different persons(specify transformation and reasonable similarity measures)How do you proceed? Can you use a Talairach template for this task? 5. Which imaging modality can be used to observe nerve fibre bundles?

6. Explain the difference between a General Linear Model (GLM) und Multi Voxel Pattern Analysis(MVPA) for the study of brain function and neuroimaging. b.) Which analysis method and which imaging modality do you have to use to detect brain areas that are active if a person moves a toe?

7. How can you evaluate methods that identify aspecific disease based on patient data (i.e. aclassifier of patients). List two evaluation measures necessary to asses and compare methods. Briefly describe their relationship.

8. How can you identify groups of similar examples inthe data set with help of an Auto Encoder?

9. How can you train a decision tree in a random forest? Please sketch the process. How are the training examples selected that are used to train an individual decision tree? How are the final classification results composed?

10. Explain how an algorithm for the detection of lesions with help of a classifier can be designed. Describe both training set, training, and the application of the algorithm to new data.