ASTIH: A collection of axon and myelin segmentation datasets from multiple histology studies

Armand Collin, Mathieu Boudreau, Julien Cohen-Adad

Keywords: Histology, Axon, Myelin, Open Dataset, Segmentation, Microscopy.

TL;DR: ASTIH provides a standardized benchmark of over 69,000 manually segmented fibers across diverse modalities (TEM, SEM, Bright-field) and species to facilitate high-throughput neurohistology analysis.

Abstract: Large-scale analysis of axon and myelin morphometry in nervous tissues is fundamental to neuroscience research, yet manual quantification remains a profound bottleneck, limiting the scale and efficiency of studies. To address this, we introduce the Axon Segmentation Training Initiative for Histology (ASTIH), a publicly accessible resource designed to propel the development and validation of automated histomorphometry tools. ASTIH comprises five meticulously curated datasets, standardized for machine learning applications, featuring over 69,000 manually segmented axon fibers. These datasets exhibit significant diversity, spanning three microscopy modalities (TEM, SEM, bright-field), three species (mouse, rat, rabbit), and three distinct anatomical regions (brain, spinal cord, peripheral nerves) with varying pixel resolutions (from ~0.2 to 0.002 $\mu m/px$). All datasets contain detailed annotations with standardized boundary delineation between adjacent fibers, enabling effective use for both semantic and instance segmentation tasks. We also provide thoroughly evaluated baseline segmentation models for every dataset in the collection to facilitate future benchmarking.

Primary Subject Area: Segmentation

Secondary Subject Area: Application: Neuroimaging

Registration Requirement: Yes

Reproducibility: https://axondeepseg.github.io/ASTIH/

Visa & Travel: No

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Replace NNN with your OpenReview submission ID., Includes \documentclass{midl}, \jmlryear{2026}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package., Did not use the times package., Use the correct spelling and format, avoid Unicode characters, and use LaTeX equivalents instead., Any math in the title and abstract must be enclosed within $...$., Did not override the bibliography style defined in midl.cls and did not use \begin{thebibliography} directly to insert references., Avoid using \scalebox; use \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., No separate supplementary PDF uploads., Acknowledgements, references, and appendix must start after the main content.

Submission Number: 336