Using automatic differentiation as a general framework for ptychographic reconstruction

Kandel, Saugat; Maddali, Siddharth; Allain, Marc; Hruszkewycz, S. O.; Jacobsen, Chris; Nashed, Youssef S. G.

doi:10.1364/oe.27.018653

Cited by 67 publications

(35 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, our employment of automatic differentiation through the widely used software package TensorFlow renders the implementation highly accessible and flexible. On the top of the first reports of using AD in phase retrieval problems (15)(16)(17), our work reinforces the vast potential of AD for a large variety of computational imaging tasks.…”

Section: Introductionsupporting

confidence: 71%

“…The above stated characteristics have led to increasing attention to automatic differentiation in the optics community, and other work has explored the use of automatic differentiation for several other coherent diffraction imaging modalities (17). Another point needing attention is that while the full-field mode and the ptychography mode are different in terms of acquisition method and processing wall time, the results they give are sometimes not equivalent as well.…”

Section: Discussionmentioning

confidence: 99%

“…Automatic differentiation (AD) (45) provides another approach which was suggested for use in phase retrieval problems (46), and then successfully implemented for x-ray ptychography (15,16). More recently, the adaptability of automatic differentiation to a variety of coherent diffraction imaging methods has been demonstrated (17), and a variety of software toolkits are now available to utilize this method (spurred on by their use for constructing the trainer module in supervised machine learning programs). We use this AD approach to reconstruct beyond-depth-of-field imaging in two successful imaging methods, and thus gain insight on their relative advantages and complications.…”

Section: Formulation Of the Image Reconstruction Problemmentioning

confidence: 99%

See 2 more Smart Citations

Three dimensions, two microscopes, one code: Automatic differentiation for x-ray nanotomography beyond the depth of focus limit

Nashed

Kandel

et al. 2020

Sci. Adv.

Self Cite

View full text Add to dashboard Cite

Conventional tomographic reconstruction algorithms assume that one has obtained pure projection images, involving no within-specimen diffraction effects nor multiple scattering. Advances in x-ray nanotomography are leading towards the violation of these assumptions, by combining the high penetration power of x-rays which enables thick specimens to be imaged, with improved spatial resolution which decreases the depth of focus of the imaging system. We describe a reconstruction method where multiple scattering and diffraction effects in thick samples are modeled by multislice propagation, and the 3D object function is retrieved through iterative optimization. We show that the same proposed method works for both full-field microscopy, and for coherent scanning techniques like ptychography. Our implementation utilizes the optimization toolbox and the automatic differentiation capability of the open-source deep learning package TensorFlow, which demonstrates a much straightforward way to solve optimization problems in computational imaging, and endows our program great flexibility and portability.

show abstract

Section: Introductionsupporting

confidence: 71%

Section: Discussionmentioning

confidence: 99%

Section: Formulation Of the Image Reconstruction Problemmentioning

confidence: 99%

See 1 more Smart Citation

Three dimensions, two microscopes, one code: Automatic differentiation for x-ray nanotomography beyond the depth of focus limit

Nashed

Kandel

et al. 2020

Sci. Adv.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to efficiently minimize the cost function C for the three different imaging methods of NFH, FFP and NFP, we have chosen to use an automatic differentiation (AD) approach (Rall, 1981) so that we do not need to calculate gradients of C by hand for the two imaging methods and regularizers. The use of AD in CDI was suggested before powerful parallelized toolkits were widely available (Jurling & Fienup, 2014), but it has since been used for image reconstruction in FFP (Nashed et al, 2017), in Bragg and near-field ptychography (Kandel et al, 2019), and in NFH and FFP of thick specimens (Du et al, 2020).…”

Section: Image Reconstruction Methodsmentioning

confidence: 99%

Near, far, wherever you are: simulations on the dose efficiency of holographic and ptychographic coherent imaging

Du¹,

Gürsoy²,

Jacobsen³

2020

J Appl Crystallogr

Self Cite

View full text Add to dashboard Cite

Different studies in X-ray microscopy have arrived at conflicting conclusions about the dose efficiency of imaging modes involving the recording of intensity distributions in the near (Fresnel regime) or far (Fraunhofer regime) field downstream of a specimen. A numerical study is presented on the dose efficiency of near-field holography, near-field ptychography and far-field ptychography, where ptychography involves multiple overlapping finite-sized illumination positions. Unlike what has been reported for coherent diffraction imaging, which involves recording a single far-field diffraction pattern, it is found that all three methods offer similar image quality when using the same fluence on the specimen, with far-field ptychography offering slightly better spatial resolution and a lower mean error. These results support the concept that (if the experiment and image reconstruction are done properly) the sample can be near or far; wherever you are, photon fluence on the specimen sets one limit to spatial resolution.

show abstract

“…Our reconstruction algorithm is is based on Automatic Di erentiation Ptychography [38,39], using the forward model defined in Eq. (1).…”

Section: Reconstruction Algorithmmentioning

confidence: 99%

Single-frame far-field diffractive imaging with randomized illumination

et al. 2020

View full text Add to dashboard Cite

We introduce a single-frame di ractive imaging method called randomized probe imaging (RPI). In RPI, a sample is illuminated by a structured probe field containing speckles smaller than the sample's typical feature size. Quantitative amplitude and phase images are then reconstructed from the resulting far-field di raction pattern. The experimental geometry of RPI is straightforward to implement, requires no near-field optics, and is applicable to extended samples. When the resulting data are analyzed with a complimentary algorithm, reliable reconstructions which are robust to missing data are achieved. To realize these benefits, a resolution limit associated with the numerical aperture of the probe-forming optics is imposed. RPI therefore o ers an attractive modality for quantitative X-ray phase imaging when temporal resolution and reliability are critical but spatial resolution in the tens of nanometers is su cient. We discuss the method, introduce a reconstruction algorithm, and present two proof-of-concept experiments: one using visible light, and one using soft X-rays.

show abstract

Using automatic differentiation as a general framework for ptychographic reconstruction

Cited by 67 publications

References 58 publications

Three dimensions, two microscopes, one code: Automatic differentiation for x-ray nanotomography beyond the depth of focus limit

Three dimensions, two microscopes, one code: Automatic differentiation for x-ray nanotomography beyond the depth of focus limit

Near, far, wherever you are: simulations on the dose efficiency of holographic and ptychographic coherent imaging

Single-frame far-field diffractive imaging with randomized illumination

Contact Info

Product

Resources

About