Deep Learning-based Inaccuracy Compensation in Reconstruction of High Resolution XCT Data

Artificial intelligence driven 3D reconstruction for enhanced lung surgery planning

The increasing complexity of lung surgeries necessitates the need for enhanced imaging support to improve the precision and efficiency of preoperative planning. Despite the promise of 3D reconstruction, clinical adoption remains limited due to time constraints and insufficient validation. To address this, we evaluate an artificial intelligence-driven 3D reconstruction system for pulmonary vessels and bronchi in a retrospective, multi-center multi-reader multi-case study. Using a two-stage crossover design, ten thoracic surgeons assess 140 cases with and without the system's assistance. The system significantly improves the accuracy of anatomical variant identification by 8% (p < 0.01), reducing errors by 41%. Improvements in secondary endpoints are also observed. Operation procedure selection accuracy is improved by 8%, with a 35% decrease in errors. Preoperative planning time is decreased by 25%, and user satisfaction is high at 99%. These benefits are consistent across surgeons of varying experience. In conclusion, the artificial intelligence-driven 3D reconstruction system significantly improves the identification of anatomical variants, addressing a critical need in preoperative planning for thoracic surgery.

Towards full-stack deep learning-empowered data processing pipeline for synchrotron tomography experiments

Synchrotron tomography experiments are transitioning into multifunctional, cross-scale, and dynamic characterizations, enabled by new-generation synchrotron light sources and fast developments in beamline instrumentation. However, with the spatial and temporal resolving power entering a new era, this transition generates vast amounts of data, which imposes a significant burden on the data processing end. Today, as a highly accurate and efficient data processing method, deep learning shows great potential to address the big data challenge being encountered at future synchrotron beamlines. In this review, we discuss recent advances employing deep learning at different stages of the synchrotron tomography data processing pipeline. We also highlight how applications in other data-intensive fields, such as medical imaging and electron tomography, can be migrated to synchrotron tomography. Finally, we provide our thoughts on possible challenges and opportunities as well as the outlook, envisioning selected deep learning methods, curated big models, and customized learning strategies, all through an intelligent scheduling solution.

Preparation of large biological samples for high-resolution, hierarchical, synchrotron phase-contrast tomography with multimodal imaging compatibility

Imaging across different scales is essential for understanding healthy organ morphology and pathophysiological changes. The macro- and microscale three-dimensional morphology of large samples, including intact human organs, is possible with X-ray microtomography (using laboratory or synchrotron sources). Preparation of large samples for high-resolution imaging, however, is challenging due to limitations such as sample shrinkage, insufficient contrast, movement of the sample and bubble formation during mounting or scanning. Here, we describe the preparation, stabilization, dehydration and mounting of large soft-tissue samples for X-ray microtomography. We detail the protocol applied to whole human organs and hierarchical phase-contrast tomography at the European Synchrotron Radiation Facility, yet it is applicable to a range of biological samples, including complete organisms. The protocol enhances the contrast when using X-ray imaging, while preventing sample motion during the scan, even with different sample orientations. Bubbles trapped during mounting and those formed during scanning (in the case of synchrotron X-ray imaging) are mitigated by multiple degassing steps. The sample preparation is also compatible with magnetic resonance imaging, computed tomography and histological observation. The sample preparation and mounting require 24-36 d for a large organ such as a whole human brain or heart. The preparation time varies depending on the composition, size and fragility of the tissue. Use of the protocol enables scanning of intact organs with a diameter of 150 mm with a local voxel size of 1 μm. The protocol requires users with expertise in handling human or animal organs, laboratory operation and X-ray imaging.

Measurement Reduction Methods for Processing Tomographic Images

The importance of development of new methods for reconstruction of an object image given its sinogram and some additional information about the object stems from the possibility of artifact presence in the reconstructed image, or its insufficient sharpness when the used additional information does not hold. The problem of recovering artifact-free images of the studied object from tomography data is considered in the framework of the theory of computer-aided measuring systems. Methods for solving it are developed. They are based on narrowing the class of possible images using less artifact-inducing information. An example of such information is the natural condition of non-negativeness of the estimated brightnesses. The main problem that arises is the large dimensionality of the images, which prevents the use of direct algorithms. One proposed method is based on local approach, namely correction of the result of unfiltered backprojection by applying a locally (in the space of the output image) optimal linear transformation. Another method processes a sinogram directly, without using backprojection, using iterative implementation of the measurement reduction technique. Examples of use of the proposed methods for processing teeth sinograms are given.

Deep Learning-Based Image Reconstruction for Different Medical Imaging Modalities

Image reconstruction in magnetic resonance imaging (MRI) and computed tomography (CT) is a mathematical process that generates images at many different angles around the patient. Image reconstruction has a fundamental impact on image quality. In recent years, the literature has focused on deep learning and its applications in medical imaging, particularly image reconstruction. Due to the performance of deep learning models in a wide variety of vision applications, a considerable amount of work has recently been carried out using image reconstruction in medical images. MRI and CT appear as the ultimate scientifically appropriate imaging mode for identifying and diagnosing different diseases in this ascension age of technology. This study demonstrates a number of deep learning image reconstruction approaches and a comprehensive review of the most widely used different databases. We also give the challenges and promising future directions for medical image reconstruction.

Low-Cost Probabilistic 3D Denoising with Applications for Ultra-Low-Radiation Computed Tomography

We propose a pipeline for synthetic generation of personalized Computer Tomography (CT) images, with a radiation exposure evaluation and a lifetime attributable risk (LAR) assessment. We perform a patient-specific performance evaluation for a broad range of denoising algorithms (including the most popular deep learning denoising approaches, wavelets-based methods, methods based on Mumford−Shah denoising, etc.), focusing both on accessing the capability to reduce the patient-specific CT-induced LAR and on computational cost scalability. We introduce a parallel Probabilistic Mumford−Shah denoising model (PMS) and show that it markedly-outperforms the compared common denoising methods in denoising quality and cost scaling. In particular, we show that it allows an approximately 22-fold robust patient-specific LAR reduction for infants and a 10-fold LAR reduction for adults. Using a normal laptop, the proposed algorithm for PMS allows cheap and robust (with a multiscale structural similarity index >90%) denoising of very large 2D videos and 3D images (with over 107 voxels) that are subject to ultra-strong noise (Gaussian and non-Gaussian) for signal-to-noise ratios far below 1.0. The code is provided for open access.

Monitored Tomographic Reconstruction-An Advanced Tool to Study the 3D Morphology of Nanomaterials

Detailed and accurate three-dimensional (3D) information about the morphology of hierarchically structured materials is derived from multi-scale X-ray computed tomography (XCT) and subsequent 3D data reconstruction. High-resolution X-ray microscopy and nano-XCT are suitable techniques to nondestructively study nanomaterials, including porous or skeleton materials. However, laboratory nano-XCT studies are very time-consuming. To reduce the time-to-data by more than an order of magnitude, we propose taking advantage of a monitored tomographic reconstruction. The benefit of this new protocol for 3D imaging is that the data acquisition for each projection is interspersed by image reconstruction. We demonstrate this new approach for nano-XCT data of a novel transition-metal-based materials system: MoNi4 electrocatalysts anchored on MoO2 cuboids aligned on Ni foam (MoNi4/MoO2@Ni). Quantitative data that describe the 3D morphology of this hierarchically structured system with an advanced electrocatalytically active nanomaterial are needed to tailor performance and durability of the electrocatalyst system. We present the framework for monitored tomographic reconstruction, construct three stopping rules for various reconstruction quality metrics and provide their experimental evaluation.

Numerical and Experimental Study of the Mechanical Response of Diatom Frustules

Diatom frustules, with their hierarchical three-dimensional patterned silica structures at nano to micrometer dimensions, can be a paragon for the design of lightweight structural materials. However, the mechanical properties of frustules, especially the species with pennate symmetry, have not been studied systematically. A novel approach combining in situ micro-indentation and high-resolution X-ray computed tomography (XCT)-based finite element analysis (FEA) at the identical sample is developed and applied to Didymosphenia geminata frustule. Furthermore, scanning electron microscopy and transmission electron microscopy investigations are conducted to obtain detailed information regarding the resolvable structures and the composition. During the in situ micro-indentation studies of Didymosphenia geminata frustule, a mainly elastic deformation behavior with displacement discontinuities/non-linearities is observed. To extract material properties from obtained load-displacement curves in the elastic region, elastic finite element method (FEM) simulations are conducted. Young’s modulus is determined as 31.8 GPa. The method described in this paper allows understanding of the mechanical behavior of very complex structures.