Chest X-rays are a crucial diagnostic tool, but their interpretation can be time-consuming. Deep learning offers a promising solution, but requires large, well-annotated datasets, which are often limited by privacy issues and data access restrictions. Federated learning (FL) allows hospitals to collaboratively train deep learning models without data sharing, addressing these limitations. In this paper, we propose an FL model based on lightweight ConvNeXt architecture and Federated Averaging to analyze both performance and interpretability as the number of clients increases, while maintaining the same total amount of data in an independent identically distributed (IID) scenario for chest X-ray imaging. The results demonstrate superior performance of the FL models compared to the local one, and the interpretability analysis shows that FL models produce better alignment with ground truth compared to local models. However, both performance and interpretability decline as the number of clients increases. These findings highlight the need for strategies to mitigate performance degradation in high-client scenarios to improve the clinical applicability of FL-based systems.

Deep Learning approaches show promise for improving tomosynthesis reconstruction but require paired CT and tomosynthesis datasets that are difficult to obtain. This work presents ChestXsim, an open-source Python framework that enable the simulation of digital chest tomosynthesis (DCT) from chest CT data. Its modular design includes the preprocessing pipeline to adapt helical chest CT volumes to a standard tomosynthesis positioning and the simulation of polychromatic projections with noise modelling. Additionally, ChestXsim provides reconstruction techniques (FDK/SART) and leverages GPU acceleration through open-source ASTRA kernels. ChestXsim offers a fast and efficient method for simulating DCT from standard chest CT data, making it a valuable tool for generating paired datasets.

Magnetic Resonance Imaging (MRI) plays an important role in the diagnosis and monitoring of central nervous system (CNS) pathologies. There are various MRI modalities that enable the visualization of distinct structural features in neoplasms. Among these modalities, contrastenhanced weighted T1 images (T1W-CE) are widely utilized, as they clearly delineate tumor boundaries and highlight cerebral vasculature. This modality relies on gadolinium-based contrast agents (GBCAs). However, due to risk of deposition in tissues after repeated administration and expensiveness, it is recommended to limit their use. To address this limitation, this study proposes a deep learning (DL) algorithm that generates synthetic T1W-CE images from non-contrast MRI sequences. The preliminary evaluation was performed using conventional, quantitative metrics and qualitative assessment by an expert neuroradiologist. This evaluation supports the potential feasibility of the proposed method in reconstructing synthetic T1W-CE MRI scans that closely resemble real contrastenhanced images.

The field of view (FOV) in Cone Beam Computed tomography (CT) is limited by the detector size, often leading to truncation artifacts that obscure anatomical structures and compromise diagnostic accuracy. While several deep learning solutions have demonstrated success in extending the FOV, they primarily rely on spatial inpainting and do not fully exploit the frequency-domain characteristics of sinograms. Besides, some of the most successful solutions are slow as they work both in the projection and reconstruction domain or use heavy networks, hindering their implementation in real clinical practice. In this work we propose a new deep learning method that works in the sinogram domain solely to achieve accurate and efficient sinogram completion, reducing truncation artifacts while maintaining real-time clinical feasibility. The method is based on a recurrent network that incorporates Fast Fourier Convolution blocks at early feature extraction stages to enhance sinogram extrapolation by leveraging spectral domain information. The proposed method holds potential for improving CT image reconstruction quality, enhancing diagnostic accuracy, and expanding the applicability of C -arm CT systems in various medical fields.

In Cone Beam CT (CBCT) systems, each acquisition is carried out with a stationary bed. Therefore, the field of view is limited by the size of the detector. To overcome this limitation, it is common to perform successive acquisitions for different bed positions, which are subsequently combined to increase the field of view in the longitudinal direction. To avoid the appearance of double edges in the resulting volume, it is necessary to calculate the exact bed displacement, which has traditionally been obtained by prior geometric calibrations with calibration phantoms. This implies that the calibration must be repeated periodically to adapt to any changes that the equipment may undergo. As an alternative, in this work we propose the use of an automatic calibration algorithm capable of obtaining the misalignment parameters in real time, allowing to obtain multibed images in small and regular animal CBCT systems without the need of a previous calibration.

In computed tomography (CT) systems it is common to acquire several consecutive datasets for different bed positions, which are subsequently combined to enlarge the field of view in the longitudinal direction. For this combination, the geometric calibration of the bed motion is necessary to avoid double edges in the overlaped area. This calibration is performed periodically using calibration phantom with markers to guide parameter esti-mation. This work presents a novel correlation-based automatic bed stitching tool for CT that avoids the need of the calibration step. Our approach exploits the massive parallelism offered by GPUs and features an optimized memory model that allows large volumes to be stitched in near-real time. Evaluation in rodent studies demonstrates not only that the offered implementation is able to paste tomographic studies in reduced time, but also that it reduces the memory footprint.

CT images are often affected by beam-hardening artifacts due to the polychromatic nature of the X-ray spectra. These artifacts appear in the image as cupping in homogeneous areas and as dark bands between dense regions such as bones. This paper proposes a simplified statistical reconstruction method for X-ray CT based on Poisson statistics that accounts for the non-linearities caused by beam hardening. The main advantages of the proposed method over previous algorithms are that it avoids the preliminary segmentation step, which can be tricky, especially for low-dose scans, and it does not require knowledge of the whole source spectrum, which is often unknown. Each voxel attenuation is modeled as a mixture of bone and soft tissue by defining density-dependent tissue fractions and maintaining one unknown per voxel. We approximate the energy-dependent attenuation corresponding to different combinations of bone and soft tissues, the so-called beam-hardening function, with the 1D function corresponding to water plus two parameters that can be tuned empirically. Results on both simulated data with Poisson sinogram noise and two rodent studies acquired with the ARGUS/CT system showed a beam hardening reduction (both cupping and dark bands) similar to analytical reconstruction followed by post-processing techniques but with reduced noise and streaks in cases with a low number of projections, as expected for statistical image reconstruction.

BACKGROUND: Standard cone-beam computed tomography (CBCT) involves the acquisition of at least 360 projections rotating through 360 degrees. Nevertheless, there are cases in which only a few projections can be taken in a limited angular span, such as during surgery, where rotation of the source-detector pair is limited to less than 180 degrees. Reconstruction of limited data with the conventional method proposed by Feldkamp, Davis and Kress (FDK) results in severe artifacts. Iterative methods may compensate for the lack of data by including additional prior information, although they imply a high computational burden and memory consumption. RESULTS: pixels) using partitioning strategies in forward- and back-projection operations. We evaluated the algorithm on small-animal data for different scenarios with different numbers of projections, angular span, and projection size. Reconstruction time varied linearly with the number of projections and quadratically with projection size but remained almost unchanged with angular span. Forward- and back-projection operations represent 60% of the total computational burden. CONCLUSION: Efficient implementation using parallel processing and large-memory management strategies together with GPU kernels enables the use of advanced reconstruction approaches which are needed in limited-data scenarios. Our GPU implementation showed a significant time reduction (up to 48 ×) compared to a CPU-only implementation, resulting in a total reconstruction time from several hours to few minutes.

Diffusion MRI data are generally acquired using hyperpolarized gases during patient breath-hold, which yields a compromise between achievable image resolution, lung coverage, and number of -values. In this paper, we propose a novel method that accelerates the acquisition of diffusion MRI data by undersampling in both the spatial and -value dimensions and incorporating knowledge about signal decay into the reconstruction (SIDER). SIDER is compared with total variation (TV) reconstruction by assessing its effect on both the recovery of ventilation images and the estimated mean alveolar dimensions (MADs). Both methods are assessed by retrospectively undersampling diffusion data sets ( =8) of healthy volunteers and patients with Chronic Obstructive Pulmonary Disease (COPD) for acceleration factors between x2 and x10. TV led to large errors and artifacts for acceleration factors equal to or larger than x5. SIDER improved TV, with a lower solution error and MAD histograms closer to those obtained from fully sampled data for acceleration factors up to x10. SIDER preserved image quality at all acceleration factors, although images were slightly smoothed and some details were lost at x10. In conclusion, we developed and validated a novel compressed sensing method for lung MRI imaging and achieved high acceleration factors, which can be used to increase the amount of data acquired during breath-hold. This methodology is expected to improve the accuracy of estimated lung microstructure dimensions and provide more options in the study of lung diseases with MRI.

The apparition of new paradigms, programming models, and languages that offer better programmability and better performance turns the implementation of current scientific applications into a less time-consuming task than years ago. One significant example of this trend is the MapReduce programming model and its implementation using Apache Spark. Nowadays, this programming model is mainly used for data analysis and machine learning applications, although it has been expanded to its usage in the HPC community. On the side of programming languages, Python has positioned itself as an alternative to other scientific programming languages, such as Matlab or Julia. In this work we explore the capabilities of Python and Apache Spark as partners in the implementation of the backprojection operator of a CT reconstruction application. We present two interesting approaches with two different types of architectures: a heterogeneous architecture including NVidia GPUs and a full performance CPU mode with the compatibility with C/C++ native source code. We experimentally demonstrate that current CPU-based implementations scale with the number of computational units.

In the above paper (ibid., vol. 34, no. 11, pp. 2394-2403, Nov. 2015), the first footnote should have appeared as presented here.

Positron range (PR) is a significant factor that limits PET image resolution, especially with some radionuclides currently used in clinical and preclinical studies such as (82)Rb, (124)I and (68)Ga. The use of an accurate model of the PR in the image reconstruction may minimize its impact on the image quality. Nevertheless, PR distributions are difficult to model, as they may be different at each voxel and direction, depending on the materials that the positron flies through. Several approximated methods have been proposed, considering only one or several propagating media without taking into account boundaries effects. In some regions, like lungs or trachea, these methods may not be accurate enough and yield artifacts. In this work, we present an efficient method to accurately incorporate spatially-variant PR corrections. The method is based on pre-computing voxel-dependent PR kernels using a CT or a manually segmented image, and a model of the dependence of the PR on each material derived from Monte Carlo simulations. The images are convoluted with these kernels in the forward-projection step of the iterative reconstruction algorithm. This implementation of the algorithm adds a modest overhead to the overall reconstruction time and it obtains artifact-free PR-corrected images, even when the activity is concentrated at tissue boundaries with extreme changes of density. We verified the method with the preclinical Argus PET/CT scanner, but it can be also applied to other scanners and improve the image quality in clinical PET studies using isotopes with large PR.

Most small-animal X-ray computed tomography (CT) scanners are based on cone-beam geometry with a flat-panel detector orbiting in a circular trajectory. Image reconstruction in these systems is usually performed by approximate methods based on the algorithm proposed by Feldkamp, Davis and Kress (FDK). Currently there is a strong need to speedup the reconstruction of X-Ray CT data in order to extend its clinical applications. The evolution of the semiconductor detector panels has resulted in an increase of detector elements density, which produces a higher amount of data to process. This work focuses on future high-resolution studies (density up to 4096 pixeles), in which multiple level of parallelism will be needed in the reconstruction. In addition, this paper addresses the future challenges of processing high-resolution images in many-core and distributed architectures. In our evaluation section we demonstrate that our solution is 17% faster than recent related works.

Most small-animal X-ray computed tomography (CT) scanners are based on cone-beam geometry with a flat-panel detector orbiting in a circular trajectory. Image reconstruction in these systems is usually performed by approximate methods based on the algorithm proposed by Feldkamp et al. Currently there are a strong need to speed-up the reconstruction of XRay CT data in order to extend its clinical applications. We present an efficient modular implementation of an FDK-based reconstruction algorithm that takes advantage of the parallel computing capabilities and the efficient bilinear interpolation provided by general purpose graphic processing units (GPGPU). The proposed implementation of the algorithm is evaluated for a high-resolution micro-CT and achieves a speed-up of 46, while preserving the reconstructed image quality.

BACKGROUND: Analysis of the plethora of metabolites found in the NMR spectra of biological fluids or tissues requires data complexity to be simplified. We present a graphical user interface (GUI) for NMR-based metabonomic analysis. The "Metabonomic Package" has been developed for metabonomics research as open-source software and uses the R statistical libraries. RESULTS: The package offers the following options: Raw 1-dimensional spectra processing: phase, baseline correction and normalization. Importing processed spectra. Including/excluding spectral ranges, optional binning and bucketing, detection and alignment of peaks. Sorting of metabolites based on their ability to discriminate, metabolite selection, and outlier identification. Multivariate unsupervised analysis: principal components analysis (PCA). Multivariate supervised analysis: partial least squares (PLS), linear discriminant analysis (LDA), k-nearest neighbor classification. Neural networks.Visualization and overlapping of spectra. Plot values of the chemical shift position for different samples. Furthermore, the "Metabonomic" GUI includes a console to enable other kinds of analyses and to take advantage of all R statistical tools. CONCLUSION: We made complex multivariate analysis user-friendly for both experienced and novice users, which could help to expand the use of NMR-based metabonomics.

We propose a new spatio-temporal elastic registration algorithm for motion reconstruction from a series of images. The specific application is to estimate displacement fields from two-dimensional ultrasound sequences of the heart. The basic idea is to find a spatio-temporal deformation field that effectively compensates for the motion by minimizing a difference with respect to a reference frame. The key feature of our method is the use of a semi-local spatio-temporal parametric model for the deformation using splines, and the reformulation of the registration task as a global optimization problem. The scale of the spline model controls the smoothness of the displacement field. Our algorithm uses a multiresolution optimization strategy to obtain a higher speed and robustness. We evaluated the accuracy of our algorithm using a synthetic sequence generated with an ultrasound simulation package, together with a realistic cardiac motion model. We compared our new global multiframe approach with a previous method based on pairwise registration of consecutive frames to demonstrate the benefits of introducing temporal consistency. Finally, we applied the algorithm to the regional analysis of the left ventricle. Displacement and strain parameters were evaluated showing significant differences between the normal and pathological segments, thereby illustrating the clinical applicability of our method.

This work presents a new algorithm (NIC; nonuniform intensity correction) for the correction of intensity inhomogeneities in magnetic resonance images. The algorithm has been validated by means of realistic phantom images and a set of 24 real images. Evaluation using previously proposed phantom images for inhomogeneity correction algorithms allowed us to obtain results fully comparable to the previous literature on the topic. This new algorithm was also compared, using a real image dataset, to other widely used methods which are freely available in the Internet (N3, SPM'99 and SPM2). Standard quality criteria have been used for determining the goodness of the different methods. The new algorithm showed better results removing the intensity inhomogeneities and did not produce degradation when used on images free from this artifact.