SimAQ: Mitigating Experimental Artifacts in Soft X-Ray Tomography using Simulated Acquisitions

TL;DR

SimAQ is a simulation pipeline that generates realistic synthetic data with artifacts for soft X-ray tomography, enabling effective neural network training and transfer learning for accurate cell segmentation without large labeled datasets.

Contribution

We introduce SimAQ, a novel simulation pipeline that creates realistic synthetic datasets with artifacts for training and transfer learning in soft X-ray tomography.

Findings

Neural networks trained on synthetic data perform well on real data.

SimAQ enables effective few-shot and zero-shot transfer learning.

Our approach allows accurate segmentation without large labeled datasets.

Abstract

Soft X-ray tomography provides detailed structural insight into whole cells but is hindered by experimental artifacts such as the missing wedge and by limited availability of annotated datasets. We present SimAQ, a simulation pipeline that generates realistic yeast phantoms and applies synthetic imaging artifacts to produce paired noisy volumes, sinograms, and reconstructions. We validate our approach by training a neural network primarily on synthetic data and demonstrate effective few-shot and zero-shot transfer learning on real X-ray tomograms. Our model delivers accurate segmentations, enabling quantitative analysis of noisy tomograms without relying on large labeled datasets.