Love, pain, joy, fear, desire: the full spectrum of emotion resides in facial expression. We grasp this almost intuitively. However, we still lack a quantifiable understanding of the nuanced relationship between the face and the brain. We haven鈥檛 yet found a way to precisely measure and reliably interpret the full complexity of facial expressions in mice, let alone humans. Or have we? 黑料吃瓜资源 (CSHL) Assistant Professor Helen Hou and her team have developed a new tool that should help set science and medicine off in that direction.
In a study published in Nature Neuroscience, the Hou lab introduces a discovery platform called . This innovative camera and computer vision system tracks even the subtlest changes in mouse facial expression. Then, using AI, it quantifies those changes so scientists can methodically study and interpret them.
Where did the idea come from? According to Hou, it was born of necessity. 鈥淲hen I started my lab, we were really excited to capture the rich repertoire of facial behavior,鈥� she says. Experienced veterinarians can often 鈥渞ead鈥� an animal鈥檚 well-being from its face. However, until now, there hasn鈥檛 been a reliable, automated way to measure facial expression with a level of detail that might offer insight into brain function.
A brief overview of the Cheese3D setup. According to a study published in Nature Neuroscience, the system 鈥渃aptures high-speed 3D motion of the entire mouse face (including ears, eyes, whisker pad, and jaw, while covering both sides of the face).鈥�
Over the past three decades, CSHL has helped establish mice as vital models for studying the brain and how it controls behavior. But as everyone knows, there are clear distinctions between humans鈥� and mice鈥檚 faces. For one, theirs are cone-shaped.
To confront this challenge, the Hou lab worked with CSHL鈥檚 Core Facilities. Together, they rigged up a high-tech system of six tiny cameras that simultaneously film a mouse鈥檚 facial movements from multiple perspectives. Machine learning models compile the movies together like an expert film editor. Meanwhile, the rig also tracks electrical activity in the mouse鈥檚 brain.
Of course, it wasn鈥檛 merely a matter of having mice 鈥渟ay cheese.鈥� To demonstrate the system鈥檚 accuracy, the used Cheese3D to monitor several important behaviors, including eating. Perhaps most crucially, they ran the system on mice that had gone under anesthesia. Impressively, they could use Cheese3D to measure how deeply 鈥渁wake鈥� or 鈥渁sleep鈥� the mice were at a given moment. In collaboration with CSHL鈥檚 , they matched the accuracy of gold standard EEG methods. Plus, they did it without disturbing the animal.
鈥淰ery subtle changes in facial muscle tone teach us a lot,鈥� Hou explains. 鈥淪o, we can predict depth of anesthesia in a non-invasive way using the face.鈥�
Given the potential clinical implications, Hou is also starting to look into facial expressions during specific disease states. Additionally, she points out, 鈥渇acial movement is one of the first milestones of development. We can smile long before we can crawl or walk. So, how do we learn to move our faces socially?鈥� Any new answer would have major implications for autism and behavioral therapy. With Cheese 3D, Hou and colleagues Kyle Daruwalla and Irene Nozal Martin have built a new way to ask the question.
Written by: Samuel Diamond, Senior Communications Strategist | [email protected] | 516-367-5055
Funding
Brain and Behavior Research Foundation, Schmidt Futures NeuroAI Fund, Fulbright Program
Citation
Daruwalla, K., Nozal Martin, I., et al., 鈥淐heese3D enables sensitive detection and analysis of whole-face movement in mice鈥�, Nature Neuroscience, April 27, 2026. DOI:
Core Facilites
鈥淭丑别 Animal Imaging Shared Resource provides researchers with both expertise and access to state-of-the-art, non-invasive preclinical imaging modalities. These include optical, ultrasound, CT, SPECT, and PET. These scanners collectively offer the researcher a high degree of experimental flexibility to non-invasively visualize and quantitate in vivo biology.鈥� 鈥� Director Scott Lyons, Ph.D.
鈥淭丑别 Machine Shop at CSHL provides an in-house workshop for the custom design and fabrication of scientific equipment. We also provide in-house training for researchers to independently use the shop鈥檚 machining tools, as well as the water-jet cutter, the laser cutter/engraver, and the shop鈥檚 high-resolution 3D printer. We aim to foster the learning of technical skills and mediate the sharing of technologies and custom solutions across the CSHL campus.鈥� 鈥� Director Robert Eifert
鈥淭丑别 Neuro-Imaging and Behavior Core Facility helps bridge the gap between recent innovations in optical or ultrasound imaging and the state-of-the-art rodent behavioral and neural circuit models and technologies at CSHL. We bring together state-of-the-art imaging and photo-stimulation solutions for neuroscience research in rodent models.鈥� 鈥� Director Sanjeev Kaushalya