BIFOLD at Berlin Science Week 2024
From foundational research in Machine Learning and Data Management to real-world AI solutions
BIFOLD will present four AI-themed demonstrations over two days at the Berlin Science Week CAMPUS, in the research fields of Medicine (digital pathology, hospital intensive care unit), Neuroscience and Earth Observation (content-based image retrieval). All BIFOLD presentations will be accompanied by BIFOLD researchers, who will answer the audience's questions in German and English. The Berlin Science Week CAMPUS is located at the Museum für Naturkunde Berlin, Invalidenstr. 43, Berlin. On November 1st the CAMPUS will be open to public from 9am - 6pm. On November 2nd from 10am - 7pm. A ticket is required for access and can be bought here.
Digital Pathology
On Friday 01. November we will kick off with an AI-enhanced Pathology project presented by Dr. Mina Jamshidi Idaji and Jonas Dippel. As part of BIFOLD's Machine Learning group, they focus on developing and applying AI tools for digital pathology, particularly in analyzing histopathological slides (tissue images) and integrating so called “omics-data”. In this demo, the researchers utilize publicly available data from the CAMELYON dataset to demonstrate how AI significantly improves the speed and efficiency of cell counting compared to manual methods. Additionally, they showcase how explainable AI can enhance tumor detection, providing transparency in the AI decision-making process.
Efficiently query satellite image archives
Friday afternoon, Dr. Genc Hoxha, Jakob Hackstein, and Mathis Adler will let the audience delve into the EarthQube project, AI-enhanced Satellite Image analyses. EarthQube allows users to query images based on query criteria and semantic content efficiently and effectively. It further facilitates data exploration by visualizing satellite data with a user-friendly interface. Demo visitors will interact with EarthQube, playing the role of different users who search images in a large-scale remote sensing archive using their semantic content and applying other filters.
AI-enhanced ICU
On the morning of November 2nd, Kyle Stephen Krüger and Taha Tekdogan will showcase the NEEDMI project, an AI-enhanced co-pilot for the hospital intensive care unit (ICU). NEEDMI is a digital platform that processes patient data from a wide range of data sources in real-time and analyzes it using AI. The software proactively warns of possible complications and generates intelligent recommendations for the ICU staff. Using the end-to-end data management system Nebula Stream, the project is realized in close cooperation between the Charité – Universitätsmedizin Berlin and BIFOLD.
Neuroscience in everyday life
Saturday afternoon, the team members of the Intelligent Biomedical Sensing Lab - Shakiba Moradi, Christian Tesch and Josef Cole Cutler - offer a glimpse into the future of modern neuroscience. The Lab develops miniaturized wearable neurotechnology and body-worn sensors for unobtrusive monitoring of the embodied brain in the everyday world. It uses machine learning on the multimodal sensor data, together with environmental context information, to contribute to a paradigm shift in individualized comprehensive understanding of physical and mental health: Toward intelligent monitoring of physical and mental states and early assessment of risk factors.
About Science Week
The Berlin Science Week is an annual event of the Falling Walls Foundation transforming the city into a vibrant festival of scientific ideas, exploration, and experimentation. This year's event will take place from November 1st to 10th, 2024, and its theme is COMMON GROUND. The festival sets up events, talks, workshops, etc., to show that science can transcend borders, ideologies, and cultures. By openly sharing knowledge, science can tackle the world's most pressing challenges together. BIFOLD is looking forward to be part of this community celebrating the potential of science to unite, strengthen, and enlighten society.
