Instructors: Prof. Dr. Nassir Navab, Dr. Shahrooz Faghihroohi, Azade Farshad, Yousef Yeganeh

Time: TBA

Registration

Registration must be done through TUM Matching Platform (please pay attention to the Deadlines)
In order to increase your priority, please also apply via our own Registration system.
The maximum number of participants: 20.

Announcements

The presentation and blogpost guidelines are available here: Guide_DLMA SS2022.pdf
The preliminary meeting slides can be found here:
The preliminary meeting is scheduled for Feb 2nd, 10:30 (Zoom link is visible on TUMonline).

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, recently published 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 2500-3000 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 actively participate.

Submission Deadline: You have to submit the blog post by the end of July 23rd.

Schedule (TBA)

Date	Session: Topics	Students
15.06	Recent Trends in Medical Image Segmentation 3D vessel segmentation Structural Continuity in Segmentation	Huang, Pei-Ran Sauer, Bjarne Güvercin, Göktug
22.06	Exploring Latest Unsupervised Computer Vision Models for Segmentation Self-supervised Volume Segmentation Self-supervised graph representation learning	Klausen, Tobias Altunbas, Begüm Oytun Demirbilek
29.06	Image Superresolution Using Generative Models Sound and Music Generative Models Sensorless US compounding	Schauer, Robert Victor Dzhagatspanyan Sharma, Devansh
6.07	Application of Diffusion Models for Medical Imaging Image to image translation with diffusion models Sampling Methods in Diffusion Models	Cheng, JiaJian Trigui Amal Yeşilkaynak, Vahit Buğra
13.07	Converting weights of 2D Vision Transformer for 3D Image Classification Natural Language Explanations for Vision and Vision-Language tasks non-rigid 2d-3d registration Image Stitching Using Unsupervised/Semi-Supervised Learning	Ben Chaaben, Zeineb Marin Ruiz, Jorge Yang, Shucheng Güven Erkaya
20.07	Physics-inspired Neural Networks Counterfactual Modelling Confidence segmentation	Wagner, Jakob Pennig, Lars Yakal, Furkan
27.07	TBA

List of Topics and Material

The proposed papers for each topic in this course are usually 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 papers (TBA)

No	Topic	Sample Papers	Journal/ Conference	Tutor	Student	Link
1	Counterfactual Modelling	COUNTERFACTUAL GENERATIVE NETWORKS	ICLR 2021	Azade Farshad Yeganeh, Y. M.	Pennig, Lars	https://arxiv.org/pdf/2101.06046.pdf
		Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions	ICML 2021			https://arxiv.org/pdf/2107.09734.pdf
		ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging	ArXiv 2023			https://arxiv.org/pdf/2303.15421.pdf
2	Sampling Methods in Diffusion Models	Fast Sampling of Diffusion Models with Exponential Integrator	ICLR 2023	Azade Farshad Yeganeh, Y. M.	Yeşilkaynak, Vahit Buğra	https://arxiv.org/pdf/2204.13902.pdf
		DENOISING DIFFUSION IMPLICIT MODELS	ICLR 2021			https://arxiv.org/pdf/2010.02502.pdf
		PSEUDO NUMERICAL METHODS FOR DIFFUSION MODELS ON MANIFOLDS	ICLR 2022			https://arxiv.org/pdf/2202.09778.pdf
3	Image Stitching Using Unsupervised/Semi-Supervised Learning	Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation	IEEE Transactions on CSVT 2022	Shahrooz Faghihroohi	Güven Erkaya	https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9605632
		Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images	TIP 2021			https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9472883
		Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint	AAAI 2023			https://arxiv.org/abs/2212.02763
4	Image Superresolution Using Generative Models	Deep Constrained Least Squares for Blind Image Super-Resolution	CVPR 2022	Shahrooz Faghihroohi	Schauer, Robert	https://openaccess.thecvf.com/content/CVPR2022/html/Luo_Deep_Constrained_Least_Squares_for_Blind_Image_Super-Resolution_CVPR_2022_paper.html
		Progressive Residual Learning with Memory Upgrade for Ultrasound Image Blind Super-resolution	IEEE BHI 2022			https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9684683
		Blind Image Super-Resolution: A Survey and Beyond	PAMI 2023			https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9870558
5	Sound and Music Generative Models	Noise2Music: Text-conditioned Music Generation with Diffusion Models	ArXive 2023	Sasan Matinfar	Victor Dzhagatspanyan	https://arxiv.org/pdf/2302.03917.pdf
		AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head	ArXive 2023			https://arxiv.org/pdf/2304.12995.pdf
		AudioGen: Textually Guided Audio Generation	ICLR 2023			https://openreview.net/forum?id=CYK7RfcOzQ4
6	3D vessel segmentation	3D vessel-like structure segmentation in medical images by an edge-reinforced network	MedIA	Agnieszka Tomczak	Sauer, Bjarne	https://www.sciencedirect.com/science/article/abs/pii/S1361841522002201
		3D Graph-Connectivity Constrained Network for Hepatic Vessel Segmentation	IEEE JBHI			https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6221020
		Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation	MICCAI 2021			https://arxiv.org/pdf/2106.01860.pdf
7	Sensorless US compounding	3D freehand ultrasound without external tracking using deep learning	MedIA 2018	Mohammad Farid Azampour	Sharma, Devansh	https://www.sciencedirect.com/science/article/abs/pii/S1361841518303712
		Development of Implicit Representation Method for Freehand 3D Ultrasound Image Reconstruction of Carotid Vessel	IUS 2022			https://ieeexplore.ieee.org/abstract/document/9958448
		RecON: Online learning for sensorless freehand 3D ultrasound reconstruction	MedIA 2023			https://www.sciencedirect.com/science/article/abs/pii/S1361841523000713
8	Image to image translation with diffusion models	DUAL DIFFUSION IMPLICIT BRIDGES FOR IMAGE-TO-IMAGE TRANSLATION	ICLR 2023	Mohammad Farid Azampour	Trigui Amal	https://arxiv.org/pdf/2203.08382.pdf
		DIFFUSION-BASED IMAGE TRANSLATION USING DISENTANGLED STYLE AND CONTENT REPRESENTATION	ICLR 2023			https://arxiv.org/pdf/2209.15264.pdf
		Palette: Image-to-Image Diffusion Models	ArXiv 2022			https://arxiv.org/abs/2111.05826
9	Structural Continuity in Segmentation	Directional Connectivity-based Segmentation of Medical Images	CVPR 2023	Azade Farshad Yeganeh, Y. M.	Güvercin, Göktug	https://arxiv.org/pdf/2304.00145.pdf
		Introducing Soft Topology Constraints in Deep Learning-based Segmentation using Projected Pooling Loss	SPIE Medical Imaging 2023			https://inria.hal.science/hal-03832309/file/proceedings_version.pdf
		Exploring Discontinuity for Video Frame Interpolation	CVPR 2023			https://arxiv.org/pdf/2202.07291.pdf
10	Self-supervised Volume Segmentation	Masked Supervised Learning for Semantic Segmentation	BMVC 2022	Azade Farshad Yeganeh, Y. M.	Altunbas, Begüm	https://bmvc2022.mpi-inf.mpg.de/0417.pdf
		Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images	MICCAI 2021			https://arxiv.org/pdf/2201.01266.pdf
		Volumetric Optimal Transportation by Fast Fourier Transform	ICLR 2023			https://openreview.net/forum?id=EVrz7UM-ZDm
11	Physics-inspired Neural Networks	Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos	CVPR 2023	Azade Farshad Yeganeh, Y. M.	Wagner, Jakob	https://arxiv.org/pdf/2303.16897.pdf
		Phase2vec: dynamical systems embedding with a physics-informed convolutional network	ICLR 2023			https://arxiv.org/pdf/2212.03857.pdf
		DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics	ICLR 2023			https://arxiv.org/pdf/2210.13066.pdf
12	Exploring Latest Unsupervised Computer Vision Models for Segmentation	Emerging Properties in Self-Supervised Vision Transformers	ArXiv 2023	Yordanka Velikova	Klausen, Tobias	https://arxiv.org/pdf/2104.14294.pdf
		DINOv2: Learning Robust Visual Features without Supervision	ArXiv 2023			https://arxiv.org/pdf/2304.07193.pdf
		Segment Anything	ArXiv 2023			https://arxiv.org/pdf/2304.02643.pdf
13	Recent Trends in Medical Image Segmentation	Attention-enhanced Disentangled Representation Learning for Unsupervised Domain Adaptation in Cardiac Segmentation	MICCAI 2022	Unbekannter Benutzer (ge94wiy)	Huang, Pei-Ran	https://rdcu.be/cVRXJ
		CRISP- Reliable Uncertainty Estimation for Medical Image Segmentation	MICCAI 2022			https://rdcu.be/cVVp2
		Domain Specific Convolution and High Frequency Reconstruction Based Unsupervised Domain Adaptation for Medical Image Segmentation	MICCAI 2022			https://rdcu.be/cVRXA
14	non-rigid 2d-3d registration	A Weakly Supervised Framework for 2D/3D Vascular Registration Oriented to Incomplete 2D Blood Vessels	IEEE Transactions on Medical Robotics and Bionics. 2022	Baochang Zhang	Yang, Shucheng	https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9765532&casa_token=Hn0z5R7rWjYAAAAA:QyRY1H7CqD_bC40pAj7us2I74SjInCFI5tEcMj3geniECBfv9Wqw0EY9Zp4Arw1pRyOZU7Qtllc
		Non-rigid registration based on hierarchical deformation of coronary arteries in CCTA images	Biomedical Engineering Letters. 2023			https://link.springer.com/article/10.1007/s13534-022-00254-8
		CNN-based real-time 2D-3D deformable registration from a single X-ray projection	ArXiv 2022			https://arxiv.org/pdf/2212.07692.pdf
15	Converting weights of 2D Vision Transformer for 3D Image Classification	Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?	Arxiv	Matthias Keicher	Ben Chaaben, Zeineb	[2209.07026] Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer? (arxiv.org)
		Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation	Arxiv			[2302.04303] Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation (arxiv.org)
		COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings	ECCV 22 Workshop			COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings \| SpringerLink
16	Learning-based Statistical Shape Model	Deep implicit statistical shape models for 3d medical image delineation	AAAI 2022	Shahrooz Faghihroohi	None	https://ojs.aaai.org/index.php/AAAI/article/view/20110
		Deep Structural Causal Shape Models	ECCV 2022			https://arxiv.org/abs/2208.10950
		Leveraging unsupervised image registration for discovery of landmark shape descriptor	MedIA 2021			https://www.sciencedirect.com/science/article/abs/pii/S1361841521002036
17	Application of Diffusion Models for Medical Imaging	Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic Model	SPIE Medical Imaging 2022	Michael Sommersperger Shervin Dehghani	Cheng, JiaJian	https://arxiv.org/abs/2201.11760
		On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models	Arxiv			https://arxiv.org/pdf/2205.03859.pdf
		Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models	MICCAI 2022			https://link.springer.com/chapter/10.1007/978-3-031-16452-1_67
18	Self-supervised graph representation learning	Prototype-based Embedding Network for Scene Graph Generation	CVPR 2023	Azade Farshad Yeganeh, Y. M.	Oytun Demirbilek	https://arxiv.org/pdf/2303.07096.pdf
		Unbiased Scene Graph Generation in Videos	CVPR 2023			https://arxiv.org/pdf/2304.00733.pdf
		Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization	ICLR 2023			https://openreview.net/forum?id=1tHAZRqftM
19	Natural Language Explanations for Vision and Vision-Language tasks	NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks	CVPR 2022	David Bani-Harouni	Marin Ruiz, Jorge	https://openaccess.thecvf.com/content/CVPR2022/html/Sammani_NLX-GPT_A_Model_for_Natural_Language_Explanations_in_Vision_and_CVPR_2022_paper.html
		CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations	ICML 2022 workshop			https://link.springer.com/chapter/10.1007/978-3-031-04083-2_5
		ALICE: Active Learning with Contrastive Natural Language Explanations	EMNLP 2020			https://aclanthology.org/2020.emnlp-main.355/
20	Confidence segmentation	Automated and real-time segmentation of suspicious breast masses using convolutional neural network	PloS one, 2018	Vanessa Gonzalez Duque	Yakal, Furkan	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5955504/pdf/pone.0195816.pdf
		Leveraging Uncertainty Estimates to Improve Segmentation Performance in Cardiac MR	Miccai 2021			https://hal.science/hal-03349833/document
		NOVEL STRUCTURAL-SCALE UNCERTAINTY MEASURES AND ERROR RETENTION CURVES: APPLICATION TO MULTIPLE SCLEROSIS	ISBI 2023			https://arxiv.org/pdf/2211.04825.pdf

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):

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.

Seitenhierarchie

DLMA: Summer 2023