CochleaNet: deep learning-based image analysis for cochlear connectomics and gene therapy
In brief
CochleaNet automates cochlear cell mapping and gene therapy analysis across species
In light-sheet images, CochleaNet reconstructs the cochlea and maps hair cells, neurons, synapses, and fluorescent expression patterns. It matched manual analysis, outperformed earlier segmentation methods, and worked on data from mice, gerbils, and marmosets, including lower-resolution images. The framework could speed preclinical assessment, but its accuracy and usefulness in broader gene therapy studies remain to be established.
- Journal
- Molecular therapy : the journal of the American Society of Gene Therapy (Q1)
- Published
- 23 October 2026
- Study design
- Unclassified
- Evidence level
- Level 5, Expert Opinion (CEBM 5)
- Authors
- Lennart Roos, Aleyna Miraç Diniz, Elisabeth Koert, Martin Schilling, Mara Uhl, Anupriya Thirumalai, et al.
- PMID
- 42920300
- DOI
- 10.1016/j.ymthe.2026.10.025
Why clinicians should know about it
- Picked for Histology (top studies of the week, 25 October 2026): Light-sheet cochlear anatomy with automated cellular quantification
Abstract
With the emergence of gene and optogenetic therapies targeting deafness, the comprehensive analysis of the molecular anatomy and physiology of the cochlea has become ever more important. Here, we introduce CochleaNet, a deep learning-based framework to analyze volumetric imaging data obtained by light-sheet microscopy of decalcified, cleared and fluorescently labeled cochleae. CochleaNet covers the workflow from reconstruction of the cochlea to segmentation of inner hair cells, spiral ganglion neurons and their afferent synapses, to the analysis of tonotopy and specific fluorescent expression patterns. We validated CochleaNet by comparison to manual image analysis, also demonstrating its superiority to prior segmentation methods. We then analyzed different spiral ganglion neuron types and validated different gene therapy products with CochleaNet. Trained on high isotropic resolution mouse data, CochleaNet was also applicable to the cochlea of the gerbil, another relevant animal model, and lower-resolution mouse and marmoset data from a commercially available microscope. We conclude that the combination of light-sheet microscopy and image analysis with CochleaNet paves the way for rapid and reliable quantification of cochlear molecular anatomy and preclinical gene therapy outcomes.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.