Whole-Body Analysis
MouseMapper automatically segments 31 organs and tissue types in a mouse while simultaneously mapping neural and immune cells throughout the body. This enables comprehensive multi-organ analyses in intact mice.
Image Credit: © Ertürk Lab | Helmholtz Munich
Scientific Frontline: Extended "At a Glance" Summary: MouseMapper AI-Powered Whole-Body Analysis
The Core Concept: MouseMapper is an advanced, AI-powered imaging and analytical system that enables the whole-body analysis of mice down to the single-cell level. It automatically maps neural pathways, immune cells, and organs to visualize pathological changes throughout the entire organism.
Key Distinction/Mechanism: Unlike classical AI systems built for single tasks, MouseMapper utilizes "foundation models"—large AI models trained on vast datasets to recognize general patterns. Combined with tissue clearing and light-sheet microscopy, this deep learning framework flexibly adapts to various datasets to systematically compare changes across 31 different organs and tissues.
Major Frameworks/Components:
- Tissue Clearing and Light-Sheet Microscopy: Imaging techniques utilized to process and visualize the complex anatomy of the organism at high resolutions.
- Foundation Models: Deep learning AI structures trained to recognize generalized patterns, allowing the flexible mapping of the finest nerve structures and immune cell accumulations.
- Molecular Analysis Integration: The system flags conspicuous regions for further molecular examination to connect cellular damage to specific signaling pathways.
Branch of Science: Computational Biology, Neuroscience, Pathology, Artificial Intelligence (Machine Learning), and Immunology.
Future Application: The framework aims to create comprehensive "digital twins"—virtual models of biological organisms that simulate the body at the cellular level. This technology could allow researchers to simulate diseases and test novel therapies entirely on computers, accelerating drug development and potentially reducing the need for animal testing.
Why It Matters: MouseMapper opens new possibilities for detecting diseases at very early stages before symptoms emerge. In its initial application, the system discovered previously unknown structural damage to sensory facial nerves and widespread inflammatory responses in mice subjected to a fatty diet—observations directly linked to molecular patterns also found in human obesity.
An international research team led by LMU professor Ali Ertürk has developed a new AI-powered method that enables whole-body analysis of mice down to the single-cell level. Helmholtz Munich and LMU served as the lead institutions for the project, which also involved additional researchers worldwide. Dubbed "MouseMapper," the novel system combines advanced tissue clearing, light-sheet microscopy, and deep learning to automatically map neural pathways, immune cells, and 31 different organs and tissues throughout the body, as the researchers report in the journal Nature.
"For the first time, MouseMapper allows us to visualize pathological changes at the cellular level throughout the entire body," says Professor Ali Ertürk from the Institute for Stroke and Dementia Research at LMU and Helmholtz Munich. "This opens up entirely new possibilities for detecting diseases at very early stages—long before the first symptoms appear."
Ertürk's team is making the complete whole-body data available online to other researchers worldwide.
Whole-Body Analysis MouseMapper automatically segments 31 organs and tissue types in a mouse while simultaneously mapping neural and immune cells throughout the body. This enables comprehensive multi-organ analyses in intact mice. © Ertürk Lab | Helmholtz Munich
AI Automatically Maps Nerves, Immune Cells, and Organs
Technologically, MouseMapper relies on foundation models—large AI models trained on vast datasets to recognize general patterns. Unlike classical AI systems, they are not built for a single task but can be flexibly adapted to many different applications. Accordingly, the system is not limited to a specific disease or imaging method but can be flexibly applied to other datasets.
The AI automatically recognizes the finest nerve structures, accumulations of immune cells, and anatomical regions throughout the body. Researchers can thus systematically compare changes and isolate conspicuous regions for further molecular analyses.
Unexpected Nerve Damage as a Result of a High-Fat Diet
Among other applications, the researchers used MouseMapper to investigate the effects of obesity on the entire murine organism. In the process, they discovered previously unknown structural damage to sensitive facial nerves of the trigeminal system. This particularly affected the infraorbital nerve, which is responsible for tactile perception via the whiskers. Mice fed a high-fat diet had significantly fewer nerve branches and exhibited diminished responses to neural stimuli.
Additional molecular analyses revealed changes in signaling pathways associated with inflammation, remodeling, and the degeneration of nerve cells. It was particularly noteworthy that scientists had already found the same molecular patterns in tissue samples from humans with obesity, establishing the first direct connection between observations in the mouse model and changes in humans.
"Our finding that obesity can clearly damage sensory facial nerves was particularly surprising," explains Dr. Doris Kaltenecker, first author of the study. "The fact that the same molecular patterns were found in humans makes the results all the more relevant."
In addition to nerve damage, MouseMapper documented extensive inflammatory processes in various organs of obese animals. Adipose tissue, the liver, and the abdominal cavity were most strongly affected. The researchers found larger accumulations of immune cells in these areas—an indication of chronic inflammatory responses throughout the organism.
Outlook: Simulating Diseases with Digital Twins
The long-term goal of Ertürk's team is to create comprehensive cell atlases of healthy and diseased organisms. "We want to build digital cell atlases of the body that function like virtual twins," says the scientist. "In the future, this could enable us to analyze diseases computationally and test novel therapies much faster than is currently the case."
Digital twins are virtual models of biological organisms that simulate the body as realistically as possible at the cellular level using AI, imaging, and molecular data. This could allow researchers to simulate diseases, digitally test therapies, and better understand pathological processes in the future—even without additional animal experiments in some cases.
Published in journal: Nature
Title: A deep-learning framework reveals whole-body perturbations at cell level
Authors: Doris Kaltenecker, Izabela Horvath, Rami Al-Maskari, Ying Chen, Zeynep Ilgin Kolabas, Luciano Hoeher, Mihail Todorov, David-Paul Minde, Saketh Kapoor, Sena Gül Turhan, Louis B. Kuemmerle, Hanno Steinke, Tim Wohlgemuth, Mayar Ali, Florian Kofler, Pauline Morigny, Julia Geppert, Denise Jeridi, Bastian Wittmann, Jie Luo, Suprosanna Shit, Carolina Cigankova, Victor Miro Kolenic, Nilsu Gür, Eren Aydeniz, Alara Yücecan, Melissa Ertürk, Laurent H. A. Simons, Chenchen Pan, Marie Piraud, Daniel Rueckert, Maria Rohm, Farida Hellal, Markus Elsner, Harsharan Singh Bhatia, Ingo Bechmann, Bjoern H. Menze, Stephan Herzig, Johannes Christian Paetzold, Mauricio Berriel Diaz, and Ali Ertürk
Source/Credit: Ludwig-Maximilians-Universität München
Edited by: Scientific Frontline
Reference Number: cobi052126_01
.jpg)