About me

I am currently a Ph.D. student at the German Cancer Research Center (DKFZ) in the division of Medical Image Computing (MIC) under the supervision of Klaus H. Maier-Hein, where I am fortunate to work with great colleagues like Fabian Isensee and Paul Jäger. Prior, I received my M.Sc. at Karlsruhe Institute of Technology (KIT) in electrical engineering and information theory in 2019, in which I focused on navigation and control theory, before getting involved in perception with deep neural networks.

My research focuses on machine learning and its applications in medical image analysis, with a particular interest in understanding the representations learned by deep neural networks and guiding their development. This led me to explore self-supervised learning for 3D medical imaging, where I aim to develop general-purpose representations applicable to various downstream tasks. Notably, I recently collaborated with the German start-up FLOY to develop a large pre-trained brain MRI model. I am also currently leading the development of pre-training methods for The Human Radiome Project, a pilot project of the Helmholtz Foundation Model Initiative, which seeks to create a vision foundation model for 3D radiology. Furthermore, I am currently working on curating a large-scale dataset, establishing a benchmark, and maintaining a comprehensive repository of the most relevant 3D SSL methods to accelerate the 3D medical SSL community.

News

• [Feb. 2025] The paper on 3D CNN masked auto-encoder self-supervised pretraining was accepted to CVPR 2025!
• [Jan. 2025] Our clinical paper on the importance of annotation quality is published and available on European Radiology: Experimental!
• [Jan. 2025] The ReSi Benchmark was Accepted at ICLR 25!
• [Sept. 2024] Our paper on decoupling semantic similarity from spatial alignment was accepted at NeurIPS 2024.
• [Oct. 2023] Our paper about multi dataset learning was chosen for Oral at MICCAI 2023.
• Show more
• [Oct. 2023] My student Jonathan Deissler & I won the LNQ MICCAI 2023 challenge.
• [Jul. 2023] Our paper about representation recycling was accepted to WACV 2024 early.
• [Jul. 2023] Our paper about modeling COPD detection as OOD problem was accepted to MICCAI 2023.
• [Jul. 2023] Our paper about multi dataset learning was accepted to MICCAI 2023.
• [Jul. 2023] I'll be holding two orals at the BVM workshop 2022 about Brain Metastasis segmentation and our AMOS2022 solution.
• [Jun. 2023] Our workshop paper about learning diverse representation was accepted at SCIS 2023.
• [Apr. 2023] Within a day we wrote a quick evaluation of Meta's SAM for a MIDL short paper.
• [Feb. 2023] I joined the Heidelberg AI organizing team.
• [Oct. 2022] Fabian Isensee, Constantin Ulrich and I won the AMOS2022 MICCAI challenge.
• [Feb. 2022] Two colleagues and I won the "AI-HERO Hackathon for Energy-Efficient AI".

Publications[Google Scholar]

Publications (Co-authored) [Google Scholar]

Challenges & Hackathons

Miscellaneous

• Reviewer of NeurIPS, ICLR and CVPR among others.
• Reviewer of UniReps NeurIPS 2023 Workshop.
• Maintainer of nnU-Net, the self-configuring medical segmentation pipeline.
• Speaker: Advanced deep learning Tutorial @ BVM2022. Tutorial on multi-task learning for medical image analysis
• 'Assisting' Reviewer for Nature Methods 2023
• 'Assisting' Reviewer for MICCAI 2022
• Reviewer for BVM 2020 and 2022

Contact

Address: Im Neuenheimer Feld 223, 69120 Heidelberg, Germany
Office Location: Forschungszentrum für Bildgebung und Radioonkologie (REZ), F.01.079
Email: tassilo.wald (at) dkfz-heidelberg.de

Powered by Jekyll and based off Minimal Light theme.