News

  • Machine learning methods are applied to process enormous quantities of data. Image: iStockphoto.com / Amiak

    Artificial intelligence in biomedicine

    A key to analyzing millions of individual cells

    23 January 2025 | Our bodies are made up of around 75 billion cells. But what function does each individual cell perform and how greatly do a healthy person’s cells differ from those of someone with a disease? To draw conclusions, enormous quantities of data must be analyzed and interpreted. For this purpose, machine learning methods are applied. Researchers at TUM and Helmholtz Munich have now tested self-supervised learning as a promising approach for testing 20 million cells or more.

  • Prof. Dr. Can Dincer, Professor for Sensors and Wearables for Healthcare Image: Andreas Heddergott / TUM

    Interview with Prof. Can Dincer on wearable medical sensors

    Continuous health monitoring with wearables

    18 December 2024 | Wearables such as smart watches or sensor rings are already a routine part of everyday life and are also popular Christmas gifts. They track our pulse rate, count our steps or analyze our sleep patterns. How can they already influence our behavior today and what future developments are possible? In this interview, Can Dincer, who holds a Professorship of Sensors and Wearables for Healthcare at TUM and is a PI at MIBE, offers insights into his research.

  • The time of a stroke is currently usually determined using CT scans. The darker the damaged region, the longer ago the stroke occurred. A new AI-supported procedure can determine the time much more precisely. Image: sudok1 / istockphoto.com

    Algorithm for particularly precise assessment of brain damage

    AI pinpoints stroke timing with high accuracy

    16 December 2024 | Quick action after a stroke hits can significantly reduce permanent damage. However, it is crucial to determine the exact time of the event to decide on the best treatment. A research team, including expertise from TUM, has developed an algorithm that can determine the timing of a stroke with exceptional precision, outperforming current approaches by a factor of two.

  • Matthias Hebrok, Professor for Applied Stem Cell and Organoid Systems. Image: Andreas Heddergott / TUM

    Regulating the immune response in a targeted and localized way

    Engineered immune cells may be able to tame inflammation

    12 December 2024 | Whether it's type 1 diabetes, other autoimmune diseases or organ transplants – when the immune system gets out of balance, it can be dangerous. Instead of suppressing the entire system as a consequence and risking severe side effects, it would be preferable to regulate it in a targeted and localized manner. This is precisely what researchers have now engineered regulatory immune cells for.

  • Leibniz Awardee 2025: Prof. Daniel Rückert. Image: Juli Eberle / TUM

    Most important German research prize for TUM professor

    Medical AI researcher Daniel Rückert receives Leibniz Prize

    11 December 2024 | Computer scientist and AI researcher Prof. Daniel Rückert receives the Gottfried Wilhelm Leibniz Prize 2025. The professor of AI in Medicine and Healthcare at TUM is being honored for his research on AI-assisted medical imaging. The most important German research prize is endowed with 2.5 million euros by the DFG.

  • Stained pancreatic cancer organoid. The newly developed organoids mimic the varied and complex structures of pancreatic cancer in the body. Image: Aris Papargyriou / TUM

    Foundation for new cancer treatment strategies

    Organoids represent the complex cell landscape of pancreatic cancer

    11 December 2024 | A team led by researchers at TUM has, for the first time, grown tumor organoids that mimic the different structures and characteristics of pancreatic cancer. The scientists investigated how the various tumor organoids react to established and novel treatments. This opens the door to the development of effective new therapies.

  • The Dies Academicus 2024 in the TUM Audimax with around 1000 guests. Image: Andreas Heddergott / TUM

    Dies Academicus under the motto "Facta non verba - deeds instead of words"

    TUM celebrates a successful 2024

    06 December 2024 | TUM celebrated the end of an extraordinarily successful 2024 with the Dies Academicus. Students, employees, and partners of TUM, including Prof. Hendrik Dietz and Prof. Oliver Hayden, PIs at MIBE, gathered in the Audimax at the main campus in Munich under the motto "Facta non verba" - deeds instead of words.

  • Daniel Cremers, Professor of Computer Vision & Artificial Intelligence Image: Astrid Eckert / TUM

    Interview with Prof. Daniel Cremers on the future of AI

    “The goal of AI is to make our lives easier”

    05 December 2024 | Technologies based on AI are already affecting our everyday lives – from the systems that facilitate movie and music selections to language assistants that formulate emails. But what developments will come along in the coming years? Daniel Cremers, a professor of Computer Vision and AI at TUM, offers insights into the future of AI.

  • Professors Simon Jacob and Julijana Gjorgjieva will each receive an ERC Consolidator Grant for their research in neuroscience. Additionally, three other TUM researchers have been awarded these renownded grants. Image: Astrid Eckert / TUM

    Neuroscience, quantum computing and artificial intelligence

    Five ERC Consolidator Grants awarded to TUM researchers

    03 December 2024 | How do feedback loops in the brain work and how do they shape everyday behaviour? The team surrounding Prof. Julijana Gjorgjieva, Principal Investigator at MIBE, would like to answer these questions among others, and is one of five research teams at TUM which are supported by the renowned ERC Consolidator Grants.

  • The team developed a new method to design large new proteins. Left: Christopher Frank, first author of the new study. Right: Prof. Hendrik Dietz. Image: Andreas Heddergott / TUM

    Designing large new proteins with AI

    New method for designing artificial proteins

    21 November 2024 |  An international research team has developed a method for designing large new proteins better than before and producing them with the desired properties in the laboratory. Their approach involves a new way of using the capabilities of the AI-based software Alphafold2.