Seminar: Biomedical Image Analysis (Winter term 2022/2023)

This is a block pro-/seminar covering topics related biomedical image processing and analysis.
Tutors: M. Sc. Annika Engel, M. Sc. Pascal Hirsch
Dates:

Registration *	from November 07 to November 20, 2022 HERE
Kick-off meeting [mandatory]	November 29, 2022 – 10:15 am (Download slides)
Deadline to (de-)register in HISPOS OR de-register from seminar *	December 20, 2022
Deadline for feedback ** [optional]	February 19, 2023
Presentations	February 28, 2023 (place/time: see below)
Summary submission deadline (1 week after the presentations)	March 07, 2023

* If you want to de-register from the seminar, please send the tutor an email irrespectively whether you (de)registered in HISPOS or not.

**If you would like to get feedback about your slides, e.g. to improve your presentation before the talk, send your slides to the tutor before the feedback deadline. We strongly encourage you to take this opportunity. Before sending in the slides, check out our presentations guidelines. Please note: The more complete the submitted presentation the more helpful the feedback can be. Please try to avoid submitting half-finished slides.

Please note: Your slides will make up a substantial part of the final grade. Reading and paying attention to the provided presentation guidelines will help you to get an impression of which aspects are relevant for the evaluation. Disregarding many of the points listed in the guidelines may negatively affect your grade.

• presentation guidelines
• presentation guidelines checklist

Place and Time:

• E2 1, R206, time 10 am to 4 pm with a lunch break from 12 pm to 1 pm

Certificate requirements:

• Successful presentation:
  • Talk: 30 minutes for a Pro-seminar and 40 minutes for a Seminar
  • Questions from the audience after the presentation
• Submitting a summary (may have an impact on the final grade):
  • Short description of your presented topic
  • Ca. 2 pages of text, excluding title (page), references, figures, tables etc.
  • Main structure: title page, main text (with or without subsections), references
  • It is recommended to write the report using LaTeX in order to train scientific writing
• Attendance to all presentations is mandatory and the active participation in the Q&A sessions is highly recommended.

Final grade:

• Primarily based on the given presentation, slides & follow-up discussion
• Might be influenced by the quality of the submitted summary report

Topics

Nr.	Presentation	Topic	Participant
1	Seminar	Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification
2	Seminar	Vessel-CAPTCHA: An efficient learning framework for vessel annotation and segmentation	Aisiri Srinivasa
3	Seminar	UNETR: Transformers for 3D Medical Image Segmentation	Sreeja Chidambaram
4	Seminar	A U-Net Ensemble for breast lesion segmentation in DCE MRI	Nazligül Keske
5	Seminar	Unsupervised brain imaging 3D anomaly detection and segmentation with transformers	Samet Özcan
6	Seminar	Fuzzy Gray Level Difference Histogram Equalization for Medical Image Enhancement
7	Seminar	Contour proposal networks for biomedical instance segmentation
8	Seminar	QSobel: A novel quantum image edge extraction algorithm

Recommended readings

Students who either have a shallow understanding on the topic and / or want to prepare for the course should consider reading the following papers:

• A Review of Deep Learning on Medical Image Analysis
• AI in Medical Imaging Informatics: Current Challenges and Future Directions
• A Survey on Segmentation Techniques for Image Processing