AMBIOM

EfficientBioAI: New Open-Source Software Makes AI Models Lighter and Greener

Artificial intelligence has become an integral part of research. However, the better and more complex the models become, the higher their energy consumption. Researchers at ISAS and Peking University have therefore developed ready-to-use and open software that compresses existing bioimaging AI models. With the help of the new toolbox, scientists can now run their models faster and with significantly lower energy consumption.

PODCAST »NACHGEFORSCHT – DIE LIVESCHALTE INS LABOR« Episode 10: Resource Awareness in Biomedical Image Analysis

Dr Jianxu Chen heads the junior research group AMBIOM - Analysis of Microscopic BIOMedical Images at ISAS. In the first English-language episode of »NACHGEFORSCHT - DIE LIVESCHALTE INS LABOR«, he talks about his path from mathematics to the life sciences and how he wants to make the analysis of biomedical data more sustainable - on many levels.

Using the Russian Doll Principle to Analyse Biological Structures

In the “AI-assisted imaging of large tissues” project, several ISAS research groups are working on combining various microscopic and mass spectrometric methods. Much like looking at a Russian doll, the team looks deeper into the biological structures of a sample with each step.

AI in Healthcare: Why Is it Better to Think Small Instead of Big?

Sustainability is an important topic when it comes to artificial intelligence in health research. A group of international researchers, including from ISAS, has been working on this topic and published a Perspective in Nature Machine Intelligence. In the interview, Prof Dr Yiyu Shi talks about the resource problem and possible solutions.

Between Progress and Footprint: Artificial Intelligence in Healthcare

The potential applications of artificial intelligence in healthcare are constantly increasing. However, with ever better and faster models, the question of sustainability is also coming to the fore. A group of international researchers, including Dr Jianxu Chen from ISAS's AMBIOM group, has been looking into the increased consumption of resources and possible solutions to the impending sustainability problem.

Fascinating Insights: Virtual World in the Classroom

What actually is reality? How do we perceive our environment? And how can augmented reality support researchers in their work? Along with class 3a of the Don Bosco elementary school in Bochum, two ISAS researchers explored these questions.

New “Green” Microscopy: Less Electricity, but More Information on Immune Cells in Return

Advanced technologies, such as high-resolution microscopes, produce large amounts of data. And these again consume large amounts of electricity. In addition, there are refrigerators for samples, fume cupboards and small technical devices. While ISAS is upgrading to become greener, researchers at the institute are already working on methods to make microscopy more energy-efficient in general.

The Art of Balancing: Accuracy in Image Analysis

What challenges in analysing microscopic images can be mastered with artificial intelligence if the latter is incorporated at an early stage? Why should researchers think about the target metrics of image analysis when planning their experiment? Dr Jianxu Chen has now put together his tips, recently published in the journal Nature Methods, as a kind of checklist for researchers.

Guest Presentation: New Framework for Stem Cell Analysis

Dr Susanne Rafelski, deputy director of scientific programme at the Allen Institute for Cell Science is a guest at ISAS on 7 February.

Hand in Hand for Successful Publications

Dr Rita Strack revealed the secret of successful publications during her talk at ISAS. Even for established scientists, much of what the Nature Methods senior editor revealed in Dortmund was new.