Master seminar Machine learning in Neuroimaging

Instructors: Prof. Dr. Christian Wachinger, Anne-Marie Rickmann, Tom Nuno Wolf, Fabian Bongratz

Contact

If you have any questions regarding this seminar contact seminars@ai-med.de.

Announcements

🏆Best three blog posts honorable mention
- ⭐3: Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference (SuStain) by Lisa Schmierer
- ⭐8: Robust, Primitive, and Unsupervised Quality Estimation for Segmentation Ensembles by Pablo Crespo
- ⭐12: Spherical U-Net on Cortical Surfaces: Methods and Applications by Milena Eisemann

Deadline for deregistration is October 4, 2022, 23:59.
August 5, 2022: Matching results have been released.
The pre-course meeting takes place on July 18, 2022 at 1pm via Zoom (link can be found on TUM Online). Slides are here.
Slides from the kickoff are here.

Timeline

July 18, 2022, 1pm: pre-course meeting
August 5, 2022: Release of matching results
October 4, 2022, 23:59: Deadline for deregistration
October 24, 1pm: Kickoff (attendance mandatory)
Before Christmas: Meet your supervisor (optional but recommended)
9/10 January 2023, 9-13: Block seminar (attendance is mandatory)

Topics

Paper ID	Title	Published in	Link	Additional material	Supervisor	Student
1	Single Subject Prediction of Brain Disorders in Neuroimaging: Promises and Pitfalls	NeuroImage	https://www.sciencedirect.com/science/article/abs/pii/S105381191600210X		Christian Wachinger	Andres Zapata
2	Building better biomarkers: brain models in translational neuroimaging	Nature Neuroscience	https://www.nature.com/articles/nn.4478		Christian Wachinger	Ding Zhou
3	Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference (SuStain)	Nature Communications	https://www.nature.com/articles/s41467-018-05892-0#MOESM1	https://www.youtube.com/watch?v=-ZCqEqInabQ https://github.com/ElsevierSoftwareX/SOFTX-D-21-00098/blob/master/notebooks/SuStaIn%20tutorial%20using%20simulated%20data.ipynb	Christian Wachinger	Lisa Schmierer
4	~~Conditional VAEs for Confound Removal and Normative Modelling of Neurodegenerative Disease~~	MICCAI 2022	https://link.springer.com/chapter/10.1007/978-3-031-16431-6_41	https://github.com/alawryaguila/normativecVAE	Nuno Wolf
5	Disentangling Normal Aging from Severity of Disease via Weak Supervision on Longitudinal MRI	IEEE TMI	https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9754514&tag=1	https://github.com/ouyangjiahong/longitudinal-direction-disentangle	Nuno Wolf	Tabea Lüdde
6	Deep learning-based unlearning of dataset bias for MRI harmonisation and confound removal	NeuroImage	https://www.sciencedirect.com/science/article/pii/S1053811920311745	https://github.com/nkdinsdale/Unlearning_for_MRI_harmonisation	Nuno Wolf	Efe Berk Ergüleç
7	~~Are 2.5D approaches superior to 3D deep networks in whole~~ ~~brain segmentation?~~	MIDL 2022	https://openreview.net/forum?id=Ob62JPB_CDF	https://github.com/Deep-MI/3d-neuro-seg	Fabian Bongratz
8	Robust, Primitive, and Unsupervised Quality Estimation for Segmentation Ensembles	Frontiers in Neuroscience	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8757043/pdf/fnins-15-752780.pdf		Fabian Bongratz	Pablo Darriba
9	Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation	Frontiers in Neuroscience	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7156850/pdf/fnins-14-00282.pdf		Fabian Bongratz	Robin Falter
10	Goal-specific brain MRI harmonization	NeuroImage	https://www.sciencedirect.com/science/article/pii/S1053811922006851		Anne-Marie Rickmann	Jiajun Wang
11	Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis	MIDL 2022	https://openreview.net/pdf?id=mpp843Bsf-	https://2022.midl.io/papers/b3	Anne-Marie Rickmann	Nian Li
12	Spherical U-Net on Cortical Surfaces: Methods and Applications	IPMI 2019	https://link.springer.com/chapter/10.1007/978-3-030-20351-1_67	https://github.com/zhaofenqiang/Spherical_U-Net	Anne-Marie Rickmann	Milena Eisemann