Automatic Differentiation for Inverse Problems in X-ray Imaging and Microscopy

ssc-cdi: A Memory-Efficient, Multi-GPU Package for Ptychography with Extreme Data

We introduce ssc-cdi, an open-source software package from the Sirius Scientific Computing family, designed for memory-efficient, single-node multi-GPU ptychography reconstruction. ssc-cdi offers a range of reconstruction engines in Python version 3.9.2 and C++/CUDA. It aims at developing local expertise and customized solutions to meet the specific needs of beamlines and user community of the Brazilian Synchrotron Light Laboratory (LNLS). We demonstrate ptychographic reconstruction of beamline data and present benchmarks for the package. Results show that ssc-cdi effectively handles extreme datasets typical of modern X-ray facilities without significantly compromising performance, offering a complementary approach to well-established packages of the community and serving as a robust tool for high-resolution imaging applications.

How auto-differentiation can improve CT workflows: classical algorithms in a modern framework

Many of the recent successes of deep learning-based approaches have been enabled by a framework of flexible, composable computational blocks with their parameters adjusted through an automatic differentiation mechanism to implement various data processing tasks. In this work, we explore how the same philosophy can be applied to existing "classical" (i.e., non-learning) algorithms, focusing on computed tomography (CT) as application field. We apply four key design principles of this approach for CT workflow design: end-to-end optimization, explicit quality criteria, declarative algorithm construction by building the forward model, and use of existing classical algorithms as computational blocks. Through four case studies, we demonstrate that auto-differentiation is remarkably effective beyond the boundaries of neural-network training, extending to CT workflows containing varied combinations of classical and machine learning algorithms.

Soft X-ray Microscopy in Cell Biology: Current Status, Contributions and Prospects

The recent advances achieved in microscopy technology have led to a significant breakthrough in biological research. Super-resolution fluorescent microscopy now allows us to visualize subcellular structures down to the pin-pointing of the single molecules in them, while modern electron microscopy has opened new possibilities in the study of protein complexes in their native, intracellular environment at near-atomic resolution. Nonetheless, both fluorescent and electron microscopy have remained beset by their principal shortcomings: the reliance on labeling procedures and severe sample volume limitations, respectively. Soft X-ray microscopy is a candidate method that can compensate for the shortcomings of both technologies by making possible observation of the entirety of the cellular interior without chemical fixation and labeling with an isotropic resolution of 40-70 nm. This will thus bridge the resolution gap between light and electron microscopy (although this gap is being narrowed, it still exists) and resolve the issue of compatibility with the former, and possibly in the near future, the latter methods. This review aims to assess the current state of soft X-ray microscopy and its impact on our understanding of the subcellular organization. It also attempts to look into the future of X-ray microscopy, particularly as relates to its seamless integration into the cell biology toolkit.