Instructors: Prof. Dr. Nassir Navab, Dr. Seong Tae Kim, Ashkan Khakzar, Azade Farshad, Dr. Shahrooz Faghih Roohi
Announcements
- Due to the COVID-19, the seminar would be held in the virtual lecture room at least initially, and potentially the whole semester (we will announce the detailed information on the website).
- 23-10-2020: 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).
- The 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 1000-1500 words excluding references 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 the blog post two weeks before your presentation session! You should also submit the presentation one day right after your presentation session.
Schedule
Dec. 3 : Session 1 (COVID-19) [Knopp, Kurt, Farag]
Dec. 10: Session 2 (Supervised/Semisupervised learning) [Xu, Fang, Würsching]
Dec. 17: Session 3 (Data-efficient DL) [Parthasarathy, Cai, Chang]
Jan. 14: Session 4 (Generative models) [Guetet, Zheng]
Jan. 21: Session 5 (Reliable DL) [Rodriguez, Scholten, Kulakov]
Jan. 28: Session 6 (Reliable DL) [Zielke, Markova, Günes]
Feb. 4 : Session7 (Other advanced topics: Graph NNs, Self-supervised learning) [Li, Karabulut]
Meeting information will be announced by email/Moodle before the session.
List of Topics and Material
The list of papers:
Topic | No | Title | Conference/ Journal | Tutor | Student (Last name) | Link |
---|---|---|---|---|---|---|
COVID | 1 | Accurate Screening of COVID-19 Using Attention-Based Deep 3D Multiple Instance Learning | TMI 2020 | Anees | Knopp | https://ieeexplore.ieee.org/document/9098062 |
2 | A Weakly-Supervised Framework for COVID-19 Classification and Lesion Localization From Chest CT | TMI 2020 | Roger | Kurt | https://ieeexplore.ieee.org/document/9097297 | |
3 | Joint prediction and time estimation of COVID-19 developing severe symptoms using chest CT scan | MedIA 2021 | Yousef | Farag | https://www.sciencedirect.com/science/article/pii/S1361841520301882 | |
Supervised (also semi/weakly) | 4 | Structure Boundary Preserving Segmentation for Medical Image With Ambiguous Boundary | CVPR2020 | Seong Tae Kim | Xu | http://openaccess.thecvf.com/content_CVPR_2020/papers/Lee_Structure_Boundary_Preserving_Segmentation_for_Medical_Image_With_Ambiguous_Boundary_CVPR_2020_paper.pdf |
5 | Deep learning robotic guidance for autonomous vascular access | Nature Machine Intelligence | Maria | Fang | https://www.nature.com/articles/s42256-020-0148-7 | |
6 | Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation | MedIA | Roger | Würsching | https://arxiv.org/pdf/2006.16806.pdf | |
7 | Convolutional Sparse Coding for Compressed Sensing CT Reconstruction | TMI 2019 | Shahrooz | https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8672945&casa_token=CtgGb2ZEznIAAAAA:2C9djBp3n9k6t-hNgsH38rpOG3VjDuAPVqeUl_6GE0FZq3mY-c2ARBP9QH-vxj9cD9Fe4dw&tag=1 | ||
Unsupervised (Self-supervised) Learning | 8 | Unsupervised Learning of Visual Features by Contrasting Cluster Assignments | NeurIPS 2020 | Azade | https://arxiv.org/pdf/2006.09882.pdf | |
9 | Self-Supervised Relational Reasoning for Representation Learning | NeurIPS 2020 | Azade | Karabulut | https://arxiv.org/pdf/2006.05849.pdf | |
10 | Adversarial Self-Supervised Contrastive Learning | NeurIPS 2020 | Seong Tae Kim | https://arxiv.org/pdf/2006.07589.pdf | ||
Data Efficient DL (Augmentation, learning under noisy label) | 11 | Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data | CVPR2020 | Baochang Zhang | Parthasarathy Srikanth | https://arxiv.org/pdf/2006.00080.pdf |
12 | Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels | NeurIPS 2020 | Azade | Cai | https://arxiv.org/pdf/1910.05199.pdf | |
13 | FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation | CVPR2020 | Shahrooz | http://openaccess.thecvf.com/content_CVPR_2020/papers/Yu_FOAL_Fast_Online_Adaptive_Learning_for_Cardiac_Motion_Estimation_CVPR_2020_paper.pdf | ||
14 | Personalized Federated Learning: A Meta-Learning Approach | NeurIPS 2020 | Yousef | https://arxiv.org/pdf/2002.07948.pdf | ||
15 | Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization | NeurIPS 2020 | Yousef | Chang | https://arxiv.org/pdf/2007.07481.pdf | |
Generative Models | 16 | A disentangled generative model for disease decomposition in chest X-rays via normal image synthesis | MedIA 2021 | Shahrooz | Guetet | https://www.sciencedirect.com/science/article/pii/S1361841520302036 |
17 | Explainable Anatomical Shape Analysis through Deep Hierarchical Generative Models | TMI 2020 | Shahrooz | https://ieeexplore.ieee.org/iel7/42/4359023/08950467.pdf?casa_token=3WJN5VTAb7wAAAAA:ioGgb3K-yZ2AAXxB_co9LdGyh03z39lR-ABHmktVcxMaRTHhxfynZxJA-DZWa5TIDBrypJw | ||
18 | Subsampled brain MRI reconstruction by generative adversarial neural networks | MedIA 2020 | Shahrooz | Zheng | https://www.sciencedirect.com/science/article/abs/pii/S1361841520301110 | |
Reliable AI | 19 | Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation | ECCV2020 | Seong Tae Kim | Rodriguez Venegas | https://arxiv.org/pdf/2003.08440 |
20 | ||||||
21 | On Completeness-aware Concept-Based Explanations in Deep Neural Networks | NeurIPS 2020 | Ashkan | https://arxiv.org/pdf/1910.07969 | ||
23 | Compositional Explanations of Neurons | NeurIPS 2020 | Ashkan | Scholten | https://arxiv.org/pdf/2006.14032 | |
24 | Do Adversarially Robust ImageNet Models Transfer Better? | 2020 arxiv | Ashkan | Zielke | https://arxiv.org/pdf/2007.08489 | |
25 | Contrastive Training for Improved Out-of-Distribution Detection | arxiv 2020 (submitted to NeurIPS) | Magda | Kulakov | https://arxiv.org/abs/2007.05566 | |
26 | Neural encoding with visual attention | NeurIPS 2020 | Magda | Markova | https://arxiv.org/abs/2010.00516 | |
27 | Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty | arxiv 2020 | Tobias | Günes | https://arxiv.org/abs/2006.06015 | |
Misc. Topics: Graphs | 28 | Predicting Lymph Node Metastasis Using Histopathological Images Based on Multiple Instance Learning With Deep Graph Convolution | CVPR2020 | Anees | Li | http://openaccess.thecvf.com/content_CVPR_2020/papers/Zhao_Predicting_Lymph_Node_Metastasis_Using_Histopathological_Images_Based_on_Multiple_CVPR_2020_paper.pdf |
Misc. Topics: registration | 29 | DeepFLASH: An Efficient Network for Learning-Based Medical Image Registration | CVPR2020 | Farid | http://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_DeepFLASH_An_Efficient_Network_for_Learning-Based_Medical_Image_Registration_CVPR_2020_paper.pdf |
CVPR: Conference on Computer Vision and Pattern Recognition
ICLR: International Conference on Learning Representations
NeurIPS: Neural Information Processing Systems
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
MICCAI: Medical Image Computing and Computer Assisted Intervention
BMVC: British Machine Vision Conference
MIDL: Medical Imaging with Deep Learning
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:
- Microsoft Academic Search
- Google Scholar
- CiteSeer
- CiteULike
- Collection of Computer Science Bibliographies
Some publishers:
- ScienceDirect (Elsevier Journals)
- IEEE Journals
- ACM Digital Library
Libraries (online and offline):
- http://rzblx1.uni-regensburg.de/ezeit/ (Elektronische Zeitschriften Bibliothek)
- Verbundkatalog des Bibliotheksverbundes Bayern (BVB)
- Computer ORG
- http://www.ub.tum.de/ (TUM Library)
- To get access onto the electronic library, see http://www.ub.tum.de/medien/ejournals/readme.html
- "proxy.biblio.tu-muenchen.de" mit Port 8080 (nur fuer http). Damit klappen zumindest portal.acm.org und computer.org meistens
- Various proceedings of conferences in our AR-Lab, 03.13.036 (These proceedings are not for lending!)
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.