UCSD - University of California - San Diego

01/27/2026 | Press release | Distributed by Public on 01/27/2026 12:21

New AI Tool Accelerates Hearing Research with Unprecedented 3D Views of Sensory Cells

Published Date

January 27, 2026

Article Content

The cochlea is the spiral-shaped structure within the inner ear responsible for our sense of hearing. To fully understand hearing functions and open the door to new hearing loss treatments, scientists require intricately detailed views of hair cells within the cochlea that allow us to detect the range of sounds around us.

University of California San Diego biologists have now leveraged artificial intelligence to create a tool that provides previously unseen 3D views of cochlear hair cells.

Within cochlea cells, bundles of protrusions called stereocilia are organized to detect sound and movement. UC San Diego postdoctoral scholar Yasmin Kassim, Biological Sciences Assistant Professor Uri Manor and their colleagues developed Vision Analysis StereoCilia, or VASCilia, using deep learning-based models trained on cochlear data. The new tool, described in PLOS Biology, accelerates the imaging process by 50-fold, automating what was previously a slow and labor-intensive process of manually interpreting images of microscopic hair cell bundles.

Manor's lab uses cutting-edge imaging tools to probe the structures and functions of hearing hair cells down to the level of individual molecules. Such precision offers scientists new ways to understand how hearing cells function under normal hearing conditions as well as damaged states caused by blasts of sound from sources such as construction work, jet engines and loud music.

"Understanding how stereocilia bundles get disorganized over time, or after exposure to certain environmental stresses, is very important in hearing loss research," said Manor, a faculty member in the Department of Cell and Developmental Biology (School of Biological Sciences) and faculty director of UC San Diego's Goeddel Family Technology Sandbox.

To help unravel the core biological functions of stereocilia, as well as set a foundation for new gene therapy experiments to reverse hair misalignments, scientists require tools to fully measure as many cells as possible with precise detail. "There are children who were born deaf that can now hear because of gene therapy and we expect those treatments for hearing loss to grow," said Manor. "That was another big motivating factor for us developing VASCilia, in addition to understanding the biology of these cells. For gene therapy experiments VASCilia allows us to measure all the cells and we can quantify them very consistently and accurately."

The strings of harp instruments are positioned so that longer strings produce lower sound frequencies and shorter strings emit higher pitches. Similarly, stereocilia are positioned so that longer hairs interpret lower frequencies and shorter hairs decode higher frequencies.

A sped up demonstration of Vision Analysis StereoCilia, or VASCilia, an AI tool that provides previously unseen 3D views of cochlear hair cells.

"We would like to more fully understand how these patterns are disrupted during disease, for hearing research on noise damage and aging," said Manor. "By visual inspection we can see that the normal bundle patterns tend to fall apart. Some of them become longer and others shorter. We want to understand exactly how this is happening."

VASCilia provides a method of visualizing and quantifying these cells in 3D using AI advancements. Kassim, a computer scientist and a Schmidt AI Postdoctoral Fellow, trained VASCilia on sets of stereocilia data obtained through expert-annotated datasets from mice. Five deep learning-based models streamlined the tool's cell analysis process.

"We've reduced the amount of time it takes to analyze the length of these cells by a factor of 50, enabling many additional 2D and 3D quantitative measurements that can be acquired in minutes - work that would otherwise require years of manual analysis," said Kassim. "VASCilia can also generate other perspectives, such as the orientation of the cells, which is useful since hair bundles sometimes don't align after aging or damage. Further, VASCilia can detect and quantify subtle patterns of cellular disorganization that are difficult for humans to measure manually."

The researchers hope the open-source nature of VASCilia will eventually lead to a comprehensive atlas of cochlea hair cell images.

"Ultimately, this initiative will support the development of foundational models adaptable to various species, markers and imaging scales to accelerate advances within the hearing research community," the authors conclude in the paper.

The authors of the study are: Yasmin M. Kassim, David B. Rosenberg, Samprita Das, Xiaobo Wang, Zhuoling Huang, Samia Rahman, Ibraheem M. Al Shammaa, Samer Salim, Kevin Huang, Alma Renero, Yuzuru Ninoyu, Rick A. Friedman, Artur Indzhykulian and Uri Manor.

The research was supported by the Chan Zuckerberg Initiative DAF (CZI Imaging Scientist Award DOI:10.37921/694870itnyzk), the National Science Foundation (NSF NeuroNex Award 2014862), the David F. And Margaret T. Grohne Family Foundation, the G. Harold & Leila Y. Mathers Foundation and the National Institute on Deafness and Other Communication Disorders (NIDCD grants R018566-03S1 and R01 DC021075-01). Microscopy was supported by the Waitt Advanced Biophotonics Core of the Salk Institute with funding from the Waitt Foundation, the NIH National Cancer Institute (NCI CCSG P30 014195) and the San Diego Nathan Shock Center.

Learn more about research and education at UC San Diego in: Artificial Intelligence

UCSD - University of California - San Diego published this content on January 27, 2026, and is solely responsible for the information contained herein. Distributed via Public Technologies (PUBT), unedited and unaltered, on January 27, 2026 at 18:21 UTC. If you believe the information included in the content is inaccurate or outdated and requires editing or removal, please contact us at [email protected]