Abstract
Synchrotron-based X-ray tomography offers the potential for rapid large-scale reconstructions of the interiors of materials and biological tissue at fine resolution. However, for radiation sensitive samples, there remain fundamental trade-offs between damaging samples during longer acquisition times and reducing signals with shorter acquisition times. We present a deep convolutional neural network (CNN) method that increases the acquired X-ray tomographic signal by at least a factor of 10 during low-dose fast acquisition by improving the quality of recorded projections. Short-exposure-time projections enhanced with CNNs show signal-to-noise ratios similar to long-exposure-time projections. They also show lower noise and more structural information than low-dose short-exposure acquisitions post-processed by other techniques. We evaluated this approach using simulated samples and further validated it with experimental data from radiation sensitive mouse brains acquired in a tomographic setting with transmission X-ray microscopy. We demonstrate that automated algorithms can reliably trace brain structures in low-dose datasets enhanced with CNN. This method can be applied to other tomographic or scanning based X-ray imaging techniques and has great potential for studying faster dynamics in specimens
Highlights
Beginning with the advent of X-ray computerized tomography (CT) for routine scanning back in the early 1970s1, X-ray CT has grown into a powerful imaging modality that can provide the internal three-dimensional (3D) morphology of representative volumes of biological tissues and material science specimens
To quantitatively evaluate improvements obtained using our convolutional neural network (CNN)-based approach, we first created a synthetic dataset - a solid cube with 1000 sphere shaped particles randomly distributed throughout a 512 × 512 × 512 volume (see Fig. 1(a) for details)
The synthetic dataset served as ground truth and allowed us to model different exposure conditions through adding noise to the data
Summary
Beginning with the advent of X-ray computerized tomography (CT) for routine scanning back in the early 1970s1, X-ray CT has grown into a powerful imaging modality that can provide the internal three-dimensional (3D) morphology of representative volumes of biological tissues and material science specimens. CNNs have been widely used for image denoising[21,22,23], super-resolution microscopy[24,25,26,27], and even post-hoc denoising of low-dose X-ray tomography reconstructions[18]. Despite their promise, CNNs have not yet been used to enhance acquisition data by learning corresponding ‘maps’ between features in low-dose and high-dose images of the same sample, and applying these learned maps to low-dose projections from the same sample. Since both the training and raw images are collected from the same dataset, it is unnecessary to estimate an additive noise model to correct the data
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
