RISING: A new framework for model-based few-view CT image reconstruction with deep learning.

Medical image reconstruction from low-dose tomographic data is an active research field, recently revolutionized by the advent of deep learning. In fact, deep learning typically yields superior results than classical optimization approaches, but unstable results have been reported both numerically and theoretically in the literature. This paper proposes RISING, a new framework for sparse-view tomographic image reconstruction combining an early-stopped Rapid Iterative Solver with a subsequent Iteration Network-based Gaining step. In our two-step approach, the first phase executes very few iterations of a regularized model-based algorithm, whereas the second step completes the missing iterations by means of a convolutional neural network. The proposed method is ground-truth free; it exploits the computational speed and flexibility of a data-driven approach, but it also imposes sparsity constraints to the solution as in the model-based setting. Experiments performed both on a digitally created and on a real abdomen data set confirm the numerical and visual accuracy of the reconstructed RISING images in short computational times. These features make the framework promising to be used on real systems for clinical exams.

DeepCEL0 for 2D single-molecule localization in fluorescence microscopy.

MOTIVATION: In fluorescence microscopy, single-molecule localization microscopy (SMLM) techniques aim at localizing with high-precision high-density fluorescent molecules by stochastically activating and imaging small subsets of blinking emitters. Super resolution plays an important role in this field since it allows to go beyond the intrinsic light diffraction limit. RESULTS: In this work, we propose a deep learning-based algorithm for precise molecule localization of high-density frames acquired by SMLM techniques whose ℓ2-based loss function is regularized by non-negative and ℓ0-based constraints. The ℓ0 is relaxed through its continuous exact ℓ0 (CEL0) counterpart. The arising approach, named DeepCEL0, is parameter-free, more flexible, faster and provides more precise molecule localization maps if compared to the other state-of-the-art methods. We validate our approach on both simulated and real fluorescence microscopy data. AVAILABILITY AND IMPLEMENTATION: DeepCEL0 code is freely accessible at https://github.com/sedaboni/DeepCEL0.

A Model-Based Optimization Framework for Iterative Digital Breast Tomosynthesis Image Reconstruction.

Digital Breast Tomosynthesis is an X-ray imaging technique that allows a volumetric reconstruction of the breast, from a small number of low-dose two-dimensional projections. Although it is already used in the clinical setting, enhancing the quality of the recovered images is still a subject of research. The aim of this paper was to propose and compare, in a general optimization framework, three slightly different models and corresponding accurate iterative algorithms for Digital Breast Tomosynthesis image reconstruction, characterized by a convergent behavior. The suggested model-based implementations are specifically aligned to Digital Breast Tomosynthesis clinical requirements and take advantage of a Total Variation regularizer. We also tune a fully-automatic strategy to set a proper regularization parameter. We assess our proposals on real data, acquired from a breast accreditation phantom and a clinical case. The results confirm the effectiveness of the presented framework in reconstructing breast volumes, with particular focus on the masses and microcalcifications, in few iterations and in enhancing the image quality in a prolonged execution.

A Green Prospective for Learned Post-Processing in Sparse-View Tomographic Reconstruction.

Deep Learning is developing interesting tools that are of great interest for inverse imaging applications. In this work, we consider a medical imaging reconstruction task from subsampled measurements, which is an active research field where Convolutional Neural Networks have already revealed their great potential. However, the commonly used architectures are very deep and, hence, prone to overfitting and unfeasible for clinical usages. Inspired by the ideas of the green AI literature, we propose a shallow neural network to perform efficient Learned Post-Processing on images roughly reconstructed by the filtered backprojection algorithm. The results show that the proposed inexpensive network computes images of comparable (or even higher) quality in about one-fourth of time and is more robust than the widely used and very deep ResUNet for tomographic reconstructions from sparse-view protocols.

Monitoring Italian COVID-19 spread by a forced SEIRD model.

Due to the recent evolution of the COVID-19 outbreak, the scientific community is making efforts to analyse models for understanding the present situation and for predicting future scenarios. In this paper, we propose a forced Susceptible-Exposed-Infected-Recovered-Dead (fSEIRD) differential model for the analysis and forecast of the COVID-19 spread in Italian regions, using the data from the Italian Protezione Civile (Italian Civil Protection Department) from 24/02/2020. In this study, we investigate an adaptation of fSEIRD by proposing two different piecewise time-dependent infection rate functions to fit the current epidemic data affected by progressive movement restriction policies put in place by the Italian government. The proposed models are flexible and can be quickly adapted to monitor various epidemic scenarios. Results on the regions of Lombardia and Emilia-Romagna confirm that the proposed models fit the data very accurately and make reliable predictions.

Turbidimetric detection method in flow-assisted separation of dispersed samples.

Characterization of dispersed samples is an outstanding trend in analytical science. Among flow-assisted separation techniques for dispersed samples, size exclusion chromatography, hydrodynamic chromatography, and field-flow fractionation are the most widely applied. With dispersed analytes separated by these techniques, the UV/vis spectrophotometric detectors work as turbidimeters. To directly convert the analytical signal for quantitative analysis, the extinction properties of the dispersed analyte must be known. A new method is proposed to experimentally obtain-by single-run, flow-assisted separation with UV/vis diode-array detectors-the mass-size (or number-size) distribution function of the analytes when a retention-to-size relationship is either theoretically or empirically available for the chosen separation technique. This approach needs neither standards nor reliance on a method to predict the optical properties of the analytes. Theory and original algorithms are presented. Algorithms are then tested to optimize the numerical routines. Accuracy and robustness of the method are evaluated by simulation, and limitations for the application to experimental data are described. Finally, first application to field-flow fractionation shows validity of the method when applied to a few real cases.