Diagnostics

Medical image analysis - 25/09/2025

Powerful AI systems using synthetic training data

AI systems for image analysis are only as good as the data on which they are trained. The Göppingen-based start-up MIRA Vision has developed a novel method for generating synthetic, photorealistic images, enabling the efficient creation of large, high-quality training datasets. An intuitive platform also allows researchers to evaluate microscopy images with ease.

Why is blood cancer particularly aggressive in some patients? Researchers at Ulm University Hospital have characterised a mutation in the so-called NOTCH1 gene that significantly influences the prognosis of chronic lymphocytic leukaemia (CLL). Remarkably, this mutation is located in the non-coding region of the gene – an area of DNA long considered less relevant for disease mechanisms.

With the FeMEA project – Ferroelectric Microelectrodes for Biomedical Applications – Hahn-Schickard is setting a pioneering course in bioelectronics research. The aim of the project is to develop novel microelectrode arrays in which ferroelectric materials are used as functional interfaces in CMOS chips for the first time.

Scientists from the European Molecular Biology Laboratory (EMBL) and the German Cancer Research Center (DKFZ) have developed an AI model that assesses the long-term individual risk for more than 1,000 diseases. The model, which was trained and tested using anonymized medical data from the UK and Denmark, can predict health events over a period of more than a decade.

Researchers at Heidelberg Uni Hospital have decoded a previously unknown mechanism by which HIV-1 selects its integration targets in the human genome. A research team identified RNA:DNA hybrids as molecular signposts for the virus. These findings reveal a vulnerability in the life cycle of HIV and provide therapeutic approaches for specifically controlling HIV reservoirs in the body. This has been one of the obstacles to curative HIV therapies.

The cellular environment of a tumor can either support or sabotage recovery. The most comprehensive study to date on the tumor microenvironment in low-grade gliomas, conducted by KiTZ, Jena University Hospital, the DKFZ, and Heidelberg University Hospital, shows what a supportive or obstructive “neighborhood” looks like in childhood brain tumors. The study also provides clues as to how tumor communication might be blocked.

Fluorescence and smartphones instead of laboratories - 11/09/2025

Mobile blood-analysis system for at home medication monitoring

For many medications, regular monitoring of drug concentrations in the blood is necessary to ensure efficacy and safety. Until now, this process has been time-consuming and required laboratory personnel and resources. The Heidelberg based start up QuantiLight has developed a mobile device with innovative sensor technology that enables quick, easy measurements at home or in a doctor's surgery.

Visual areas of the brain can reveal the colors a person is seeing while watching moving color rings. This was the result of a study by the University of Tübingen. Using MRI scanning they recorded images from the brains of subjects who were observing visual stimuli, and identified signals for red, green and yellow. The pattern of brain activity appeared similar in subjects, meaning that the color they saw could be predicted simply by comparison…

Chordomas are rare bone tumors for which there are no effective drugs. A research team from the DKFZ and the NCT Heidelberg has now developed a promising approach: Tailor-made mini-proteins specifically block the driver of tumor development. In the result, slowing the growth of chordoma cells in the laboratory and in a mouse model, while also revealing further molecular vulnerabilities of the tumor that could be addressed with approved drugs.

The rapid increase in antibiotic-resistant bacteria is one of the most pressing challenges facing global health. A new transatlantic Fraunhofer research project aims to counter these threats with an innovative diagnostic approach: a microfluidic rapid test system using carbon nanotubes (SWCNT) will make bacterial resistance visible in just a few minutes, significantly faster than conventional methods.

Enhancing human perception of the imperceptible - 28/08/2025

AI-driven imaging expands possibilities in surgery

Doctors frequently experience a restricted view of the surgical field, particularly during endoscopic procedures. A novel technique developed by Prof. Dr. Lena Maier-Hein's team at the DKFZ in Heidelberg integrates spectral imaging with AI-driven data analysis. This innovation facilitates accurate tissue differentiation and delivers real-time insights into organ function.

Svenja Brodt uses MRI brain scans to investigate how impressions become memories. A better understanding of how long-term memories are formed could help Alzheimer's patients cope with their daily lives. Impaired memory formation could be compensated for by targeted repetition.