TeachingWs19DLMA

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Hauptseminar/Master Seminar: Deep Learning for Medical Applications

Prof. Nassir Navab, Dr. Shadi Albarqouni; Magda Paschali, Ashkan Khakzar

Type: Advanced Seminar Course Module IN8901
Type: Master Seminar Module IN2107
SWS: 2+0
ECTS: 5 Credits
Location: CAMP Seminar Room, 03.13.010
Time: Thursdays, 12-14
Course Language: English

Announcements

  • 17-07-2019: We would like to encourage you to send us motivation e-mail with title "DLMA_Application" to dlma@mailnavab.informatik.tu-muenchen.de by the 24th of July 2019.
    We will only evaluate e-mails that follow the template:
    • Name:
    • Master's program:
    • Current Semester:
    • Related courses (if passed, mention the grade):
    • Short Motivation (Max 3 sentences. It should include related projects/publications/competitions/github repositories):
    Please do not attach any documents on your motivation e-mails. Thank you!

  • 05-07-2019: Preliminary meeting: Thursday, 18.07.2019 (13:00-14:00) in CAMP Seminar Room, 03.13.010.
  • 29-06-2019: Website is up!

Introduction

  • Deep Learning is growing tremendously in Computer Vision and Medical Imaging as well. Highly impacted journals in the medical imaging community, i.e. IEEE Transaction on Medical Imaging, published recently their special edition on Deep Learning [1]. The Seminar will propose a list of recent scientific articles related to the main current research topics in deep learning for Medical Applications together with some interesting papers from other communities.

Registration

  • Interested students should attend the introductory meeting to enlist in the course.
  • Students can only register through TUM Matching Platform themselves if the maximum number of participants hasn't been reached (please pay attention to the Deadlines).
  • A maximum number of participants: 20.

Requirements

In this Master Seminar (formerly Hauptseminar), each student is asked to send three preferences from the list, then he will be assigned one paper. In order to successfully complete the seminar, participants have to fulfill these requirements:

  • Presentation: The selected paper is presented to the other participants (20 minutes presentation 10 minutes questions). Use the CAMP templates for PowerPoint camp-tum-jhu-slides.zip, or Latex: CAMP-latex-template.
  • Blog Post: A blog post of maximum 1000 words should be submitted before the deadline.
  • Attendance: Participants have to participate actively in all seminar sessions.

The students are required to attend each seminar presentation which will be held during this course. Each presentation is followed by a discussion and everyone is encouraged to actively participate. The blog post must include all references used and must be written completely in your own words. Copy and paste will not be tolerated. Both the blog post and presentation have to be done in English.

You need to upload your presentation and blog post here. More details will be provided before the beginning of the semester.

Submission Deadline : You have to submit both the presentation and the blog post two weeks right after your presentation session.

Schedule

Date Session: Topic Slides Students
18.07.2019 (13-14) Preliminary Meeting Slides  
Online Paper Assignment    
24.10.2019 No Class!    
31.10.2019 Intro. to our DLMA Seminar    
07.11.2019 Presentation Session 1: Supervised Learning    
14.11.2019 Presentation Session 2: Self/Semi/Weakly Supervised Learning    
21.11.2019 Presentation Session 3: Interpretable ML    
28.11.2019 Presentation Session 4: Interpretable ML    
05.12.2019 Presentation Session 5: Misc. Topics: Domain adaptation - Uncertainty    
12.12.2019 Presentation Session 6: Misc. Topics: Meta Learning - Graph Convolutions    
19.12.2019 Presentation Session 7: Spatio-Temporal Learning    

List of Topics and Material

The list of papers:

Topic No Title Conference/Journal Tutor Student (Last name) Link
Supervised Learning 1 Cardiac Phase Detection in Echocardiograms with Densely Gated Recurrent Neural Networks and Global Extrema Loss TMI Maria Ismail PDF
  2 Fully Convolutional Architectures for Multiclass Segmentation in Chest Radiographs TMI Ashkan Olefir PDF
  3 Automatic multi-organ segmentation on abdominal ct with dense v-networks TMI Neda Lemonia PDF
Self/Semi/Weakly Supervised Learning 4 Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images CVPR Roger Benito PDF
  5 Self-supervised learning for medical image analysis using image context restoration MedIA? Magda Burak PDF
  6 FickleNet? Weakly and Semi Supervised Semantic Image Segmentation Using Stochastic Inference CVPR Tariq Richter PDF
Interpretable ML (Session 1) 7 Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow MedIA? Tariq Yupeng PDF
  8 Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks ICLR SeongTae Mirac PDF
  9 Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) ICML Mahdi Acosta PDF
Interpretable ML (Session 2) 10 Disentangled representation learning in cardiac image analysis MedIA? Magda Abdelhamid PDF
  11 Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation ICML Ashkan   PDF
  12 This Looks Like That: Deep Learning for Interpretable Image Recognition NeurIPS? SeongTae Berger PDF
  13 Are Disentangled Representations Helpful for Abstract Visual Reasoning? NeurIPS? Shadi Elsharnoby PDF
Misc. Topics: Domain adaptation - Uncertainty 14 Unsupervised domain adaptation for medical imaging segmentation with self-ensembling NeuroImage? Roger Clement PDF
  15 Transfusion: Understanding Transfer Learning for Medical Imaging NeurIPS? Shadi Panarit PDF
  16 Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion CVPR Shadi   PDF
  17 Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift NeurIPS? Shadi   PDF
Misc. Topics: Meta Learning - Graph Convolutions 18 Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning CVPR Azade Hongjia PDF
  19 Task Agnostic Meta-Learning for Few-Shot Learning CVPR Azade Evren PDF
  20 Exploiting Edge Features in Graph Neural Networks CVPR Hendrik Nasser PDF
Spatio-Temporal Learning 21 Prediction of Disease Progression in Multiple Sclerosis Patients using Deep Learning Analysis of MRI Data MIDL Ashkan Benetti PDF
  22 Predicting Alzheimer’s disease progression using multi-modal deep learning approach Nature Gerome Fok PDF
             
             
             
             
             


MICCAI: Medical Image Computing and Computer Assisted Intervention
CVPR: Conference on Computer Vision and Pattern Recognition
ICLR: International Conference on Learning Representations
TMI: IEEE Transaction on Medical Imaging
JBHI: IEEE Journal of Biomedical and Health Informatics
MedIA: Medical Image Analysis (Elsevier)
TPAMI: IEEE Transactions on Pattern Analysis and Machine Intelligence
BMVC: British Machine Vision Conference
MIDL: Medical Imaging with Deep Learning
NeurIPS: Neural Information Processing Systems

Literature and Helpful Links

A lot of scientific publications can be found online.

The following list may help you to find some further information on your particular topic:

Some publishers:

Libraries (online and offline):

Some further hints for working with references:

  • JabRef is a Java program for comfortable working with Bibtex literature databases. Handy feature: if you know the PubMed ID for an article, JabRef can import data from there (via "Web Search/Medline").
  • Mendeley is a cross-platform program for organising your references.

If you find useful resources that are not already listed here, please tell us, so we can add them for others. Thanks.


TeachingForm
Title: Deep Learning for Medical Applications
Professor: Prof. Nassir Navab
Tutors: Dr. Shadi Albarqouni; Magda Paschali, Ashkan Khakzar
Type: Hauptseminar
Information: Hauptseminar, SWS: 2, ECTS: 5
Term: 2019WiSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.14 - 08 Oct 2019 - 11:18 - AshkanKhakzar

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif