Block-Seminar on Deep Learning for Bio-Medical Image Analysis

apl. Prof. Olaf Ronneberger (Google DeepMind)

In this seminar you will learn about relevant bio-medical research fields and the most recent methods (mainly based on deep learning) that have been already applied to bio-medical data, or that have a large potential in this field. For each paper there will be one person, who performs a detailed investigation of a research paper and its background and will give a presentation. The presentation is followed by a discussion with all participants about the merits and limitations of the respective paper. You will learn to read and understand contemporary research papers, to give a good oral presentation, to ask questions, and to openly discuss a research problem.

(2 SWS)
Room: t.b.a.
Places: max. 10 students
Contact person: Özgün Çiçek

Introduction: Thursday, October 19, 2017, 10:15
Room: 52-2-17
Introduction and allocation of seminar topics
Will be held jointly with Seminar on Current Works in Computer Vison

Mid-Semester Meeting: most probably close to Christmas holidays
Room: t.b.a.
Introduction to Neural Networks by apl. Prof. Olaf Ronneberger (Google DeepMind)

ECTS Credits: 4

Recommended semester:

6 (Bachelor), any (Master)
Requirements: Background in computer vision

Remarks: This course is offered to both Bachelor and Master students. The language of this course is English. All presentations must be given in English.

Topics will be assigned in the first meeting. Please register for the seminar online before the first meeting. If there are more interested students than places, places will be assigned by a mixture of motivation in the first meeting and priority suggestions of the system. The date of registration is NOT important. In particular, we want to avoid that people grab a topic and then jump off during the semester. Please have a coarse look at all available papers to make an informed decision in the first meeting.

There is a related Seminar on Current Works in Computer Vision offered by Prof. Thomas Brox

All participants must read all papers and answer a few questions. The questions will be available here within a month. The answers must be sent to the corresponding adviser until mid-semester (t.b.a.). We highly recommend to read and understand all papers first, before you start to prepare your presentation.

Papers (please note that we only have 10 places):

Time Paper Presenting student   Advisor Slides
GANs for Biological Image Synthesis
GANs for fluorescence cell image generation, sounds interesting, could be used for dense pdf estimation of cell population and finding outliers.
Squeeze-and-Excitation Networks
Nice idea. New best score on ImageNet classification.
Philipp Jund Maxim Tatarchenko
Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images
- nice paper: achieves better performance on Gland segmentation challenge with semi-supervised learning - adversarial only sees predicted segmentations, but has to decide whether they come from the labelled or unlabelled training set.
Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
Nice approach to adapt a segmentation network to a new imaging device with unlabelled data.
Arlette Perez Yassin Marrakchi
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
The uncertainty of a decision in a medical applications is important to combine the results with other diagnostic insights.
Understanding Black-box Predictions via Influence Functions
This got the ICML best paper award. It traces a model's decision back to its training data.
One of the Winners of the COCO challenges at ICCV 2017 (will be a segmentation or detection paper)
Detect to Track and Track to Detect
Conceptional simple but powerful tracking architecture. Tracking is in important task in many biomedical applications.
Simon Geitlinger Anton Böhm
More papers to follow...