Hauptseminar/Master Seminar:
Image-based Biomedical Modeling
Bjoern Menze (TUM), Marie Piraud (TUM), and external lecturers.
Type: Master Seminar Module IN2107SWS: 2+0
ECTS: 5 Credits
Location: IMETUM Seminar Room
Time: Wednesday 1300-1500
Course Language: English
Announcements
- [10.07.2017] If you were unable to attend the intro meeting, have a look at the Slides. You can still register via the central seminar assignment system.
- [03.07.2017] Info on the seminar will be given on Wednesday 12.07.2017, 1400h, at the IMETUM/GSB in room 1.211.
Content
Many clinical imaging sequences include image modalities that provide unique insights into the human body: describing blood flow pattern or water diffusion, visualizing micro-structural tissue properties, or quantifying metabolic processes that have been found to be relevant for specific diseases. To access and explore the rich biological information of such multimodal CT, PET, and MR image data sets, different approaches from biophysical modeling and computational physiology are used. The topic of this seminar is to survey such computational models by reading, discussing and understanding key publications in this field, for example, on:- spatial atlases that encode the variation of anatomy throughout the population in a probabilistic fashion,
- dynamical models that describe blood flow patterns in MR and CT, or the the dynamics of metabolic pathways as measured via PET,
- spatio-temporal models that describe cardiac electro-physiological excitations, or the growth patterns of tumors,
- global probabilistic models that relate image features with clinical information or genetic variables.
Regulations
In this Master Seminar (formerly Hauptseminar), each student is asked to select one paper from a list. 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 CAMPmaster.pot, or Latex: CAMP-latex-template.zip. All papers will be presented at two occasions. After the first presentation we will discuss presentation and presentation style, after the second presentation we will discuss the research topic of the paper.
- Written Handout: A document of 4-8 pages is written and handed in two days before the presentation (i.e., on the Monday morning before the final presentation). Please download and use the llncs2e.zip Latex template. It can be edited and updated following comments in the final presentation.
- Attendance: Participants have to participate actively in all seminar sessions.
Schedule
The seminar consists of an introductory meeting and seminar sessions. Each of the sessions will consist of several student presentations. All seminar participants are expected to be present at every session and to actively participate in the discussion.List of Papers
The papers that we are going to discuss in the seminar belong to four different research areas:| Area | Description | Presenter | Tutor  |
|---|---|---|---|
| Dhamala et al. Quantifying the uncertainty in model parameters using Gaussian process based Markov chain Monte Carlo: an application to cardiac electrophysiological models. Miccai 2017l | Aschenbrenner | Zimmermann | |
| Wang et al. Automatic labeling of vascular structures with topological constraints via HMM. Miccai 2017 | Fischer | Wels | |
| Owen et al. Anatomy-driven modelling of spatial correlation for regularisation of arterial spin labelling images. Miccai 2017 | Bartol | Ulas | |
| Radiomic biomarkers | Schlegl et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. Ipmi 2017 | Einarsson | Tetteh |
| Marinescu et al. A vertex clustering model for disease progression: application to cortical thickness images. Ipmi 2017 | Eisawy | Shi | |
| Parisot et al. Spectral graph convolutions on population graphs for disease prediction. Miccai 2017 | Andriamanga | Shi | |
| Dalca et al. Population based image imputation. Ipmi 2017 | El Husseini | Sekuboyina | |
| Rempfler et al. Cell Lineage tracing in lens-free microscopy videos. Miccai 2017 | Ebert | Rempfler | |
| Kong et al. Cancer metastasis detection via spatially structured deep network. Ipmi 2017 | Kayalıbay | Piraud | |
| Disease modeling | Venkatraghavan et al. A discriminative event based model for Alzheimer's disease progression modeling. Ipmi 2017 | Nagy | Piraud |
| Models & uncertainty | Tanno et al. Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution. Miccai 2017 | Kim | Gomez |
| Chen et al. The active brain atlas: combining 3D anatomical models with texture detectors. Miccai 2017 | Boghiu | Alberts | |
| Doyle et al. Predicting future disease activity and treatment responders for Multiple Sclerosis patients using a bag-of-lesions brain representation. Miccai 2017 | Pita | Alberts | |
| Anatomical atlases & populations | Arnaudon et al. A Stochastic large deformation model for computational anatomy. Ipmi 2017 | ||
| Mirikharaji et al. Globally-optimal anatomical tree extraction from 3D medical images using pictorial structures and minimal paths. Miccai 2017 | |||
| Heinrich et al. BRIEFnet: Deep Pancreas Segmentation Using Binary Sparse Convolutions. Miccai 2017 | |||
| Heinrich et al. Multi-Organ Segmentation using Vantage Point Forests and Binary Context Features. Miccai 2016 | |||
| Vessels & networks | Moriconi et al. VTrails: inferring vessels with geodesic connectivity trees. Ipmi 2017 | ||
| Matejek et al. Compresso: Efficient compression of segmentation data for connectomics. Miccai 2017 | |||
| Elbaz et al. Hierarchical Shape Distributions for Automatic Identification of 3D Diastolic Vortex Rings from 4D Flow MRI. Miccai 2015 | |||
| Chang et al. Personalized pancreatic tumor growth prediction via group learning. Miccai 2017 | |||
| Giroux et al. Biomechanical Patient-specific model of the respiratory system based on 4D CT scans and controlled by personalized physiological compliance. Miccai 2017 | |||
| Yao et al. Deep correlational learning for survival prediction from multi-modality data. Miccai 2017 | |||
| Antunes et al. Radiomic spatial textai descriptor (RADISTAT): Characterizing intra-tumoral heterogeneity for response & outcome prediction. Miccai 2017 | |||
| Chen et al. Multi-label inductive matrix completion for joint MGMT and IDH1 status prediction for glioma patients. Miccai 2017 |
Schedule
The seminar consists of an introductory meeting and seminar sessions. Each of the sessions will consist of several student presentations. All seminar participants are expected to be present at every session and to actively participate in the discussion.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
- ScienceDirect (Elsevier Journals)
- IEEE Journals
- ACM Digital Library
- 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!)
- 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.
| TeachingForm | |
|---|---|
| Title: | Image based biomedical modeling seminar |
| Professor: | Bjoern Menze |
| Tutors: | Marie Piraud |
| Type: | Hauptseminar |
| Information: | Hauptseminar, SWS: 2, ECTS: 5 |
| Term: | 2017WiSe |
| Abstract: | |
