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)
- 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: TBA
- The preliminary meeting slides can be found here TBA
- The preliminary meeting is scheduled for Tuesday, 09.07.2024, from 15:30 hrs. - 16:00 hrs.
The sessions will be conducted in room 03.11.018
And on Zoom: https://tum-conf.zoom-x.de/j/61658068830?pwd=CfoK4edebnJA3fKzpm44SyEImONnk1.1
Meeting ID: 616 5806 8830
Passcode: 242869
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 3000-3500 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 first presentation date and can modify it a bit until the last session of the course.
Schedule (TBA)
Date | Session: Topics | Students |
---|---|---|
12.12.2024 | Learning Physiology in neural networks Physics-informed Multimodal Networks Acoustic Signal Analysis | Sweilam Abdullah, Abdelrahman Fazakas, Borbala Salerno, Giovanni Karl Alberto |
19.12.2024 | Deep Learning in Echocardiography Coronary Stenosis Detection in Cardiac Imaging Deep Learning in Ultrasound Elastography | Valera, Patris Thees, Christoph Jostan, Jonas |
16.01.2025 | LLMs for disease prediction based on non-imaging data, Best practices for report generation via LLMs based on template Knowledge Graphs for Medical Applications | Elghitany, Asmaa Pospelova, Maria Chen, Zixi |
23.01.2025 | PointNeRF (Point clouds and NeRF) Mesh Reconstruction for 3D Medical Imaging Video anomaly detection/generation Using Prompt | Sahin, Volkan Temiz, Kazım Muhammet Bamel, Parag |
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 | Coronary Stenosis Detection in Cardiac Imaging | BMC Medical Imaging 2024 | BMC Medical Imaging 2024 | Thees, Christoph | https://link.springer.com/content/pdf/10.1186/s12880-024-01403-4.pdf | |
Frontiers in Cardiovascular Medicine 2023 | Frontiers in Cardiovascular Medicine 2023 | https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2023.944135/full | ||||
JACC: Advances 2024 | JACC: Advances 2024 | https://www.sciencedirect.com/science/article/pii/S2772963X24000395 | ||||
2 | PointNeRF (Point clouds and NeRF) | Point-nerf: Point-based neural radiance fields | CVPR 2022 | Sahin, Volkan | ||
Pointnerf++: A multi-scale, point-based neural radiance field | ECCV 2024 | https://link.springer.com/chapter/10.1007/978-3-031-72920-1_13 | ||||
Points2nerf: Generating neural radiance fields from 3d point cloud | Pattern Recognition Letters 2024 | |||||
3 | Reflection modelling with NeRF | Merf: Memory-efficient radiance fields for real-time view synthesis in unbounded scenes | ACM Transactions on Graphic 2023 | -------------- | https://arxiv.org/pdf/2302.12249 | |
NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections | SIGGRAPH 2024 | https://arxiv.org/abs/2405.14871 | ||||
Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering | ArXiv 2024 | https://arxiv.org/abs/2409.05867 | ||||
4 | Acoustic Signal Analysis | A Comprehensive Overview of Heart Sound Analysis Using Machine Learning Methods | IEEE Access 2024 | Salerno, Giovanni Karl Alberto | https://ieeexplore.ieee.org/abstract/document/10606233 | |
Non-Invasive Assessment of Cartilage Damage of the Human Knee Using Acoustic Emission Monitoring: A Pilot Cadaver Study | IEEE Transactions on Biomedical Engineering 2023 | https://ieeexplore.ieee.org/abstract/document/10089156 | ||||
Knee acoustic emissions as a noninvasive biomarker of articular health in patients with juvenile idiopathic arthritis: a clinical validation in an extended study population | Pediatric Rheumatology, 2023 | https://link.springer.com/article/10.1186/s12969-023-00842-7 | ||||
5 | Learning Physiology in neural networks | Neuron Structure Modeling for Generalizable Remote Physiological Measurement | CVPR 2023 | Sweilam Abdullah, Abdelrahman | ||
Physics-informed neural networks for modeling physiological time series for cuffless blood pressure estimation | npj Digital Medicine 2023 | https://www.nature.com/articles/s41746-023-00853-4 | ||||
Leveraging physiology and artificial intelligence to deliver advancements in health care | Physiological Reviews 2023 | https://ieeexplore.ieee.org/abstract/document/10667569 | ||||
6 | Knowledge Graphs for Medical Applications | Medical Knowledge Graph: Data Sources, Construction, Reasoning, and Applications | Big Data Mining and Analytics 2023 | Chen, Zixi | https://ieeexplore.ieee.org/abstract/document/10026520 | |
Towards electronic health record-based medical knowledge graph construction, completion, and applications: A literature study | Journal of Biomedical Informatics 2023 | https://www.sciencedirect.com/science/article/pii/S1532046423001247 | ||||
Building a knowledge graph to enable precision medicine | Scientific Data 2023 | https://www.nature.com/articles/s41597-023-01960-3 | ||||
7 | Physics-informed Multimodal Networks | Unsupervised physics-informed disentanglement of multimodal data | Foundations of Data Science 2024 | Fazakas, Borbala | https://www.aimsciences.org/article/doi/10.3934/fods.2024019 | |
Advancing Temporal Multimodal Learning with Physics Informed Regularization | CISS 2023 | https://dl.acm.org/doi/full/10.1145/3689037 | ||||
Physics-Informed Computer Vision: A Review and Perspectives | ACM Computing 2024 | https://dl.acm.org/doi/full/10.1145/3689037 | ||||
8 | Deep Learning in Ultrasound Elastography | Deep learning in ultrasound elastography imaging: A review | Medical Physics 2022 | Jostan, Jonas | https://aapm.onlinelibrary.wiley.com/doi/10.1002/mp.15856 | |
An unsupervised learning approach to ultrasound strain elastography with spatio-temporal consistency | Physics in Medicine & Biology 2021 | https://iopscience.iop.org/article/10.1088/1361-6560/ac176a | ||||
Artificial intelligence - based ultrasound elastography for disease evaluation - a narrative review | Frontiers in Oncology 2023 | https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1197447/full | ||||
9 | Mesh Reconstruction for 3D Medical Imaging | OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields | CVPR 2023 | Temiz, Kazım Muhammet | ||
Multi-class point cloud completion networks for 3D cardiac anatomy reconstruction from cine magnetic resonance images | MedIA 2023 | https://www.sciencedirect.com/science/article/pii/S1361841523002359 | ||||
X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods | IEEE Access 2024 | https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10493004 | ||||
10 | Video anomaly detection/generation Using Prompt | Generating anomalies for video anomaly detection with prompt-based feature mapping | CVPR 2023 | Bamel, Parag | ||
Learning prompt-enhanced context features for weakly-supervised video anomaly detection | TIP 2024 | https://arxiv.org/pdf/2306.14451 | ||||
Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection | CVPR 2024 | |||||
11 | Deep Learning in Echocardiography | AI-driven View Guidance System in Intra-cardiac Echocardiography Imaging | ArXiv 2024 | Valera, Patris | https://arxiv.org/abs/2409.16898 | |
From Sparse to Precise: A Practical Editing Approach for Intracardiac Echocardiography Segmentation | MICCAI 2023 | https://link.springer.com/chapter/10.1007/978-3-031-43901-8_73 | ||||
CoReEcho: Continuous Representation Learning for 2D+Time Echocardiography Analysis | MICCAI 2024 | https://link.springer.com/chapter/10.1007/978-3-031-72083-3_55 | ||||
12 | LLMs for disease prediction based on non-imaging data | Health-LLM: Personalized Retrieval-Augmented Disease Prediction System | ArXiv 2024 | Elghitany, Asmaa | https://arxiv.org/abs/2402.00746 | |
Large Language Models for Disease Diagnosis: A Scoping Review | ArXiv 2024 | https://arxiv.org/pdf/2409.00097 | ||||
LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction | ArXiv 2024 | https://arxiv.org/html/2403.15464v1 | ||||
13 | Best practices for report generation via LLMs based on template | Explainability for Large Language Models: A Survey | ACM Transactions on Intelligent Systems and Technology 2024 | Pospelova, Maria | https://dl.acm.org/doi/10.1145/3639372 | |
XAI for all: Can large language models simplify explainable AI? | ArXiv 2024 | https://arxiv.org/pdf/2401.13110 | ||||
Commonsense reasoning and explainable artificial intelligence using large language models | European Conference on Artificial Intelligence 2023 | https://link.springer.com/chapter/10.1007/978-3-031-50396-2_17 | ||||
14 | Uncertainty Quantification in Neural Fields | FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information | ECCV2024 | -------------------- | https://arxiv.org/abs/2311.17874 | |
Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields | CVPR2024 | |||||
UMedNeRF: Uncertainty-Aware Single View Volumetric Rendering For Medical Neural Radiance Fields | ISBI2024 | https://arxiv.org/abs/2311.05836 |