AMBIOM

Department

Dr. Jianxu Chen E: jianxu.chen@isas.de T: 0231 1392-217

Fields of competence

Bioimage analysis
Artificial intelligence
Deep learning
Computer vision

The aim of the junior research group AMBIOM – Analysis of Microscopic BIOMedical Images, which is funded by the Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung, BMBF), is to enable a high analytical throughput of microscopic images. The research group plans to develop algorithms and methods (open source) by 2026 that will allow countless image data worldwide to be analysed automatically, quickly and economically.

Focus: large 3D microscopy imaging data

The research group concentrates on the development of scalable AI-based biomedical image analysis algorithms, particularly for large 3D microscopy image data. AMBIOM’s work aims to allow broad-based new studies on the development of diseases and their consequences at the level of entire organs and organ systems. Furthermore, the AI analysis methods developed at ISAS are intended to help doctors in making diagnostic and therapeutic decisions.

The MSCoreSys associated junior research group AMBIOM – Analysis of Microscopic BiOMedical Images is funded by the Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung, BMBF) under the funding reference 161L0272.

Highlights

24th January 2024

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.

Die Abbildung zeigt die 3D-Semantiksegmentierung von Osteozyten in Mäuseknochen vor und nach der Kompression des Modells mir EfficientBioAI Die Bilder wurden mittels Lichtblatt-Fluoreszenzmikroskopie aufgenommen.

28th March 2024

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.

Das Bild zeigt eine schematische Darstellung der Datenverarbeitung in der Mikroskopie.

20th December 2023

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.

Die Abbildung zeigt eine Wage und symbolisiert das Gleichgewicht zwischen Analyse und Genauigkeit bei der Validierung von biomedizinischen Aufnahmen.

27th January 2023

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.

23rd September 2022

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.

16th September 2022

Differences are Critical

What do sex-specific differences mean for health research? What role do they play in applied basic research? Five ISAS scientists with different research focuses have an answer to these questions.

Projects

3D Molecular Pathology

The aim of the work carried out by researchers in the »3D molecular pathology« project is to gain a better understanding of the influence of inflammatory cells on the course of diseases that trigger massive immune reactions.

Biochemical Annotations of Mass Spectrometry Imaging Data for Worldwide Exchange

The research groups AMBIOM and Spatial Metabolomics are working together to develop a plug-in for the multi-dimensional imaging software napari that makes it possible to visualise and biochemically annotate MSI data.

Creating 'Leibniz Mass Spectral Imaging Library' for Identification of Primary & Secondary Metabolites

The project aims at creating the first-ever open-access MSI library of over 1000 bioactive compound standards on different matrix-assisted laser desorption/ionization (MALDI) MSI platforms.

Smart Human-in-the-loop Segmentation

Scientist working on the project »Smart Human-in-the-loop Segmentation« aim to develop a powerful deep learning model that is trained with a minimum amount of human effort.

Imaging of Large Tissues

Researchers on the »Imaging of Large Tissues« project are developing a workflow to combine the various microscopy imaging methods and analytical, mass spectroscopy methods.

Cell Tracking in Microscopy Images

The research project »Cell Tracking in Microscopy Images« aims to develop new sophisticated cell detection and tracking algorithms to tackle some of the most challenging tracking problems.