# Computer Vision-Assisted Data Analysis for Correlative Electron Microscopy and Secondary Ion Mass Spectrometry Imaging

## TL;DR

This paper introduces a computer vision pipeline to automate the analysis of electron microscopy and NanoSIMS data, enabling faster and more accurate study of subcellular structures and protein turnover.

## Contribution

A deep learning-based pipeline for automated segmentation and correlation of EM and NanoSIMS data, improving throughput and reducing bias.

## Key findings

- The YOLOv8 model accurately segmented six major organelle types in EM images.
- Automated analysis reduced processing time from hours to minutes while matching manual results.
- Differentiated neurons showed slower protein turnover compared to hNPCs in specific organelles.

## Abstract

Correlative imaging is a powerful analytical approach
in bioimaging,
as it offers complementary information on the samples measured by
different modalities. Particularly, correlative transmission electron
microscopy (EM) and nanoscale secondary ion mass spectrometry (NanoSIMS)
imaging enable high-resolution morphological and chemical analysis
at the subcellular level. However, manual segmentation and correlation
of regions of interest (ROIs) in large EM and NanoSIMS data sets are
time-consuming, prone to user bias, and limited in throughput. To
address this, we developed a computer vision-assisted image analysis
pipeline for automatic classification and segmentation of subcellular
organelles in EM images, enabling rapid and reproducible correlation
with NanoSIMS ion data. Using human neuronal progenitor cells (hNPCs)
and differentiated postmitotic neurons, we trained a YOLOv8 deep learning
model to recognize six major organelle types. The pipeline included
EM image preprocessing, segmentation via YOLOv8, morphological filtering,
and image registration with NanoSIMS ion maps. Performance evaluation
demonstrated a robust model accuracy. We applied the pipeline to measure 15N-leucine abundance to study protein turnover in single organelles
across different cell states. Results showed distinct turnover dynamics
among organelles, with slower turnover observed in differentiated
neurons compared to hNPCs. The automated pipeline significantly reduced
the analysis time (from hours to minutes) while maintaining consistency
with manual segmentation. Our approach demonstrates how computer vision
can streamline correlative imaging workflows, improve data quality,
and enable deeper insights into subcellular processes such as protein
turnover, making it especially valuable for SIMS users and broader
bioimaging applications.