Instructors: Prof. Dr. Nassir NavabDr. Shahrooz Faghih Roohi,  Ashkan Khakzar, Azade Farshad, Yousef Yeganeh


Time: TBA

Registration

Announcements

  • It is highly recommended to attend the seminar in person. However, for those who cannot attend in person, the online link via Zoom will be provided (the meeting link will be shared with participants via email and on the moodle).
  • The presentation and blogpost guidelines are available here: Guide_DLMA WS2022_23.pdf

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 (CVPR, NeurIPS, ICCV, ICLR, ICML, ...).

Course Structure

In this Master Seminar (Hauptseminar), students select one scientific topic from the list provided by course organizers. The students should read the proposed sample papers by the tutors, find the topic-related articles, summarize and compare them in their presentation and blogpost:

  • Presentation: The selected paper is presented to the other participants (Maximum 25 minutes presentation, 10 minutes questions). You can use the CAMP templates for PowerPoint TUM-Template.pptx.
  • Blog Post: A blog post of 2000-2500 words, excluding references should be submitted before the deadline. The blog post must include all references used and must be written completely in your own words. Copy and paste will not be tolerated
  • Attendance: Participants have to participate actively in all seminar sessions. Each presentation is followed by a discussion and everyone is encouraged to participate actively.

Submission Deadline: You have to submit the first draft of the blog post one week before your presentation session. However, you would have time to modify it until the last session. You should also submit the presentation one day right after your presentation session.

Schedule

TBA

DateSession: TopicSlidesStudents
21/07Preliminary Meeting

08/12

Uncertainty estimation for medical segmentation

Curvilinear structures segmentation


Yao, Junting

Sotela, Sebastian

15/12

Motion Compensation for Electromagnetically Tracked Catheters

Transformers in Image Registration


Wally, Youssef

Ünlü Idil

22/12

Self-supervised Vessel Segmentation

Automated Semantic/Anatomical Vessel labeling

Masking Techniques for Computer Vision and Medical Imaging


Avendano-Prieto, Natalia

Otto, Julia

Anil Kul

12/01

Representation Learning using Generative Models

Graph / Scene Graph representation learning

Incremental Learning in Medical Image Analysis:


Sun Mei

Bigom, Andreas

Dozono, Kohei

19/01

Self-Supervised/Unsupervised Image and Medical Imaging Segmentation

Unsupervised Domain Adaptation in Medical Image Analysis

SSL representation learning by/for object detection


Palmisano Patrizio

Posada Cárdenas, Andrea

Jiajun Wang

26/01

Cross-modal learning

Contrastive Language-Image Models in Medical Image Understanding

Multimodal Image Synthesis


Duman, Serdar

Diery, Kristina

Karoui, Yasmine

02/02

Diffusion Models for Medical Imaging

Physics Informed Neural Network for Computer Vision and Medical Imaging

NeRF Applications in Medical Imaging


Zhang, Yifan

He, Xinyi

Matiunina Daria

List of Topics and Material

Papers in this course are selected from the following venues/publications:


CVPR: Conference on Computer Vision and Pattern Recognition
ICLR: International Conference on Learning Representations
NeurIPS: Neural Information Processing Systems

TPAMI: IEEE Transactions on Pattern Analysis and Machine Intelligence

TMI: IEEE Transaction on Medical Imaging
JBHI: IEEE Journal of Biomedical and Health Informatics
MedIA: Medical Image Analysis (Elsevier)

MICCAI: Medical Image Computing and Computer-Assisted Intervention
BMVC: British Machine Vision Conference
MIDL: Medical Imaging with Deep Learning


List of topics


NoTopicSample PapersJournal/ ConferenceTutorStudentLink
1Learning-based Statistical Shape Model

Deep implicit statistical shape models for 3d medical image delineationAAAI 2022Nonehttps://ojs.aaai.org/index.php/AAAI/article/view/20110
Deep Structural Causal Shape ModelsECCV 2022https://arxiv.org/abs/2208.10950
Leveraging unsupervised image registration for discovery of landmark shape descriptorMedIA 2021https://www.sciencedirect.com/science/article/abs/pii/S1361841521002036
2Representation Learning using Generative Models

Generative Flow Networks for Discrete Probabilistic ModelingICML 2022 SpotlightSun Meihttps://proceedings.mlr.press/v162/zhang22v.html
Flamingo: a Visual Language Model for Few-Shot LearningDeepMindhttps://arxiv.org/pdf/2204.14198.pdf
Object Scene Representation TransformerNeurIPS 2022https://arxiv.org/pdf/2206.06922.pdf
3Graph / Scene Graph representation learning

VARSCENE: A Deep Generative Model for Realistic Scene Graph SynthesisICML 2022 SpotlightBigom, Andreashttps://proceedings.mlr.press/v162/verma22b/verma22b.pdf
Self-Supervised Representation Learning via Latent Graph PredictionICML 2022 Spotlighthttps://proceedings.mlr.press/v162/xie22e.html
Iterative Scene Graph GenerationNeurIPS 2022https://arxiv.org/pdf/2207.13440.pdf
4Motion Compensation for Electromagnetically Tracked Catheters

A survey of catheter tracking concepts and methodologiesMedical Image AnalysisWally, Youssefhttps://doi.org/10.1016/j.media.2022.102584
Respiratory motion compensation with tracked internal and external sensors during CT-guided proceduresComputer Aided Surgeryhttps://doi.org/10.3109/10929080600740871
Position Control of Motion Compensation Cardiac CathetersIEEE Transactions on Roboticshttps://doi.org/10.1109/TRO.2011.2160467
5Diffusion Models for Medical Imaging

Diffusion Deformable Model for 4D Temporal Medical Image GenerationMICCAI 2022Zhang, Yifanhttps://arxiv.org/pdf/2206.13295.pdf
Diffusion Models for Medical Anomaly DetectionMICCAI 2022http://arxiv.org/abs/2203.04306
Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion ModelsMICCAI 2022http://arxiv.org/abs/2206.03461
6Symbolic Regression

Discovering Symbolic Models from Deep Learning with Inductive BiasesNeurIPS 2020None

https://proceedings.neurips.cc/paper/2020/hash/c9f2f917078bd2db12f23c3b413d9cba-Abstract.html

End-to-end symbolic regression with transformersArXiv 2022https://arxiv.org/pdf/2204.10532.pdf
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularityNeurIPS 2020

https://proceedings.neurips.cc/paper/2020/hash/33a854e247155d590883b93bca53848a-Abstract.html

7Uncertainty estimation for medical segmentation

Layer Ensembles: A Single-Pass Uncertainty Estimation in Deep Learning for SegmentationMICCAI 2022Yao, Juntinghttps://arxiv.org/pdf/2203.08878.pdf
Efficient Bayesian Uncertainty Estimation for nnU-NetMICCAI 2022https://link.springer.com/chapter/10.1007/978-3-031-16452-1_51
CRISP - Reliable Uncertainty Estimation for Medical Image SegmentationMICCAI 2022https://arxiv.org/abs/2206.07664
8Cross-modal learning

Learning Explicit and Implicit Dual Common Subspaces for Audio-Visual Cross-Modal RetrievalTOMM 2022Duman, Serdarhttps://dl.acm.org/doi/pdf/10.1145/3564608

VISUALVOICE: Audio-Visual Speech Separation with Cross-Modal Consistency (2021)

CVPR 2021https://arxiv.org/pdf/2101.03149.pdf
Visually Guided Sound Source Separation and Localization Using Self-Supervised Motion RepresentationsIEEE/CVF/WACV 2022

https://openaccess.thecvf.com/content/WACV2022/papers/Zhu_Visually_Guided_Sound_Source_Separation_and_Localization_Using_Self-Supervised_Motion_WACV_2022_paper.pdf

9Curvilinear structures segmentationCS2-Net: Deep learning segmentation of curvilinear structures in medical imagingMedIA 2021


Sotela, Sebastianhttps://www.sciencedirect.com/science/article/abs/pii/S1361841520302383
3D vessel-like structure segmentation in medical images by an edge-reinforced networkMedIA 2022https://www.sciencedirect.com/science/article/abs/pii/S1361841522002201
10Transformers in Image RegistrationDeformer: Towards Displacement Field Learning for Unsupervised Medical Image RegistrationMICCAI 2022Ünlü Idil https://link.springer.com/chapter/10.1007/978-3-031-16446-0_14
TransMorph: Transformer for unsupervised medical image registrationMedIA 2022https://www.sciencedirect.com/science/article/abs/pii/S1361841522002432
Affine Medical Image Registration With Coarse-To-Fine Vision TransformerCVPR 2022

https://openaccess.thecvf.com/content/CVPR2022/html/Mok_Affine_Medical_Image_Registration_With_Coarse-To-Fine_Vision_Transformer_CVPR_2022_paper.html

11Masking Techniques for Computer Vision and Medical ImagingResolution-robust large mask inpainting with fourier convolutionsWACV 2022Anil Kul

https://openaccess.thecvf.com/content/WACV2022/html/Suvorov_Resolution-Robust_Large_Mask_Inpainting_With_Fourier_Convolutions_WACV_2022_paper.html

Image inpainting for irregular holes using partial convolutionsECCV 2018

https://openaccess.thecvf.com/content_ECCV_2018/html/Guilin_Liu_Image_Inpainting_for_ECCV_2018_paper.html

Incremental transformer structure enhanced image inpainting with masking positional encodingCVPR 2022

https://openaccess.thecvf.com/content/CVPR2022/html/Dong_Incremental_Transformer_Structure_Enhanced_Image_Inpainting_With_Masking_Positional_Encoding_CVPR_2022_paper.html

12Self-Supervised/Unsupervised Image and Medical Imaging Segmentation

Self-Supervised Learning for Few-Shot Medical Image SegmentationTMI 2022Palmisano Patriziohttps://ieeexplore.ieee.org/abstract/document/9709261
Mix-and-match tuning for self-supervised semantic segmentationAAAI 2018https://ojs.aaai.org/index.php/AAAI/article/view/12331
Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial RegularizationRAL 2021https://ieeexplore.ieee.org/abstract/document/9476978
13Physics Informed Neural Network for Computer Vision and Medical Imaging

Physics-Informed Neural Networks for Brain Hemodynamic Predictions Using Medical ImagingTMI 2022He, Xinyihttps://ieeexplore.ieee.org/abstract/document/9740143
Physics-informed neural networks for myocardial perfusion MRI quantificationMedIA 2022https://www.sciencedirect.com/science/article/pii/S1361841522000512
Physics-Informed Neural Networks for Cardiac Activation MappingFrontiers 2020https://www.frontiersin.org/articles/10.3389/fphy.2020.00042/full
14NeRF Applications in Medical Imaging

ImplicitAtlas: Learning Deformable Shape Templates in Medical ImagingCVPR 2022Matiunina Daria

https://openaccess.thecvf.com/content/CVPR2022/html/Yang_ImplicitAtlas_Learning_Deformable_Shape_Templates_in_Medical_Imaging_CVPR_2022_paper.html

3D Ultrasound Spine Imaging with Application of Neural Radiance Field MethodIUS 2021https://ieeexplore.ieee.org/abstract/document/9593917
Implicit Neural Representations for Medical Imaging SegmentationMICCAI 2022https://link.springer.com/chapter/10.1007/978-3-031-16443-9_42
15Contrastive Language-Image Models in Medical Image Understanding

Contrastive Learning of Medical Visual Representations from Paired Images and Textarxiv 2020/ revised 2022Diery, Kristinahttps://arxiv.org/abs/2010.00747
RepsNet: Combining Vision with Language for Automated Medical ReportsMICCAI 2022https://link.springer.com/chapter/10.1007/978-3-031-16443-9_68
Radiological Reports Improve Pre-training for Localized Imaging Tasks on Chest X-RaysMICCAI 2022https://link.springer.com/chapter/10.1007/978-3-031-16443-9_62
16Multimodal Image Synthesis

Multimodal Image Synthesis and Editing: A SurveyPAMI 2022Karoui, Yasminehttps://arxiv.org/pdf/2112.13592.pdf
Hi-net: hybrid-fusion network for multi-modal MR image synthesisTMI 2020

https://ieeexplore.ieee.org/abstract/document/9004544?casa_token=SYs20FbHRhoAAAAA:70Y144_PegoGTyAMVIGQQQVsbvzQl3UNnTXOupAltYwNi9Uq-PprnuZzr9ipsvDhKOAFwsGH

ResViT: residual vision transformers for multimodal medical image synthesisTMI 2022

https://ieeexplore.ieee.org/abstract/document/9758823?casa_token=8dOgxSKO9Q0AAAAA:yRBCMUON5vvyRFcp_WQgbt6MTAkWJRQYc2EDTaaY-tF0UddF5DstvKaeMmhFt0IwKENtqWeW

17Incremental Learning in Medical Image Analysis:

Continual Class Incremental Learning for CT Thoracic SegmentationMICCAI 2020Dozono, Koheihttps://link.springer.com/chapter/10.1007/978-3-030-60548-3_11
Mnemonics Training: Multi-Class Incremental Learning without ForgettingCVPR 2020

https://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Mnemonics_Training_Multi-Class_Incremental_Learning_Without_Forgetting_CVPR_2020_paper.html

Class-Incremental Learning by Knowledge Distillationwith Adaptive Feature ConsolidationCVPR 2022

https://openaccess.thecvf.com/content/CVPR2022/html/Kang_Class-Incremental_Learning_by_Knowledge_Distillation_With_Adaptive_Feature_Consolidation_CVPR_2022_paper.html

18 Unsupervised Domain Adaptation in Medical Image Analysis

S-CUDA: Self-cleansing unsupervised domain adaptation for medical image segmentationMedIA 2021Posada Cárdenas, Andreahttps://www.sciencedirect.com/science/article/pii/S1361841521002590
Data Efficient Unsupervised Domain Adaptationfor Cross-Modality Image SegmentationMICCAI 2019https://link.springer.com/chapter/10.1007/978-3-030-32245-8_74
Unsupervised Domain Adaptation for Medical Image Segmentation by Disentanglement Learning and Self-TrainingTMI 2022

https://ieeexplore.ieee.org/abstract/document/9832940?casa_token=yGbhV329fgcAAAAA:X3SvyVJ_3agzwZUb_OHZQHl_J-_3YPBcuoVnl9QQHisVrqCGPpoVFQYdk74i8nvR9b9smtV8

19Self-supervised Vessel Segmentation
Self-supervised vessel segmentation via adversarial learningICCV2021Avendano-Prieto, Natalia

https://openaccess.thecvf.com/content/ICCV2021/html/Ma_Self-Supervised_Vessel_Segmentation_via_Adversarial_Learning_ICCV_2021_paper.html

Diffusion Adversarial Representation Learning for Self-supervised Vessel SegmentationArxiv 2022https://arxiv.org/abs/2209.14566
20Automated Semantic/Anatomical Vessel labeling
Automated anatomical labeling of a topologically variant abdominal arterial system via probabilistic hypergraph matchingMIA2022Otto, Juliahttps://www.sciencedirect.com/science/article/abs/pii/S1361841521002942
CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary ArterieCVPR2020

https://openaccess.thecvf.com/content_CVPR_2020/html/Yang_CPR-GCN_Conditional_Partial-Residual_Graph_Convolutional_Network_in_Automated_Anatomical_Labeling_CVPR_2020_paper.html

Automated anatomical labeling of coronary arteries via bidirectional tree LSTMsIJCARS 2019https://link.springer.com/article/10.1007/s11548-018-1884-6
21Out of Distribution (OOD) robustness

An impartial take to the cnn vs transformer robustness contestECCV 2022Nonehttps://arxiv.org/abs/2207.11347
Plex: Towards Reliability using Pretrained Large Model ExtensionsArxiv 2022 (Google AI)https://arxiv.org/abs/2207.07411
Smoothness in neural network approximators: the good, the bad, the uglyNeurIPS 2020 (Deepmind)

https://www.deepmind.com/publications/smoothness-in-neural-network-approximators-the-good-the-bad-the-ugly

22SSL representation learning by/for object detection

Object discovery and representation networksECCV 2022Jiajun Wanghttps://arxiv.org/abs/2203.08777
Unsupervised part discovery from contrastive reconstructionNeurIPS 2021https://arxiv.org/abs/2111.06349
Efficient Visual Pretraining with Contrastive DetectionArxivhttps://arxiv.org/abs/2103.10957
23Continual Learning

Architecture Matters in Continual LearningArxiv 2022 (Deepmind)Nonehttps://arxiv.org/abs/2202.00275
Efficient Continual Learning in Neural Network SubspacesArxiv 2022 (Deepmind)https://arxiv.org/abs/2202.09826
Wide Neural Networks Forget Less CatastrophicallyArxiv 2022 (Deepmind)https://arxiv.org/abs/2110.11526






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.


  • No labels