Searcharxiv⌕ Search

arXiv subjects

Alessandra Retico

Publications and source records attributed to Alessandra Retico.

10 recordsLinked to original sources
arXiv2025

Hardware acceleration for ultra-fast Neural Network training on FPGA for MRF map reconstruction

Magnetic Resonance Fingerprinting (MRF) is a fast quantitative MR Imaging technique that provides multi-parametric maps with a single acquisition. Neural Networks (NNs) accelerate reconstruction but require significant resources for training. We propose an FPGA-based NN for real-time brain parameter reconstruction from MRF data. Training the NN takes an estimated 200 seconds, significantly faster than standard CPU-based training, which can be up to 250 times slower. This method could enable real-time brain analysis on mobile devices, revolutionizing clinical decision-making and telemedicine.

cs.AR↗
arXiv2025

Convergent transcriptomic and neuroimaging signature of Autism Spectrum Disorder

Autism Spectrum Disorder (ASD) is a multi-factorial neurodevelopmental disorder, whose causes are still poorly understood. Effective therapies to reduce all the heterogeneous symptoms of the disorder do not exists yet, but behavioural programs started at a very young age may improve the quality of life of the patients. For this reason, many efforts have been dedicated to the research of a reliable biomarker for early diagnosis. Machine learning approaches to distinguish ASDs from healthy controls based on their brain Magnetic Resonance Images (MRIs) have been plagued by the problem of confounders, showing poor classification performance and inconsistency in the biomarker definition. Brain transcriptomics studies, instead, showed some converging results, but being based on data that can be acquired only post-mortem they are not useful for diagnosis. In this work, using an imaging transcriptomics approach, the following results have been obtained. 1) A deep learning based classifier resilient to confounders and able to exploit the temporal dimension of resting state functional MRIs has been developed, reaching an AUC of 0.89 on an independent test set. 2) Five gene network modules involved in ASD have been identified, by analyzing brain transcriptomics data of subjects with ASD and healthy controls. 3) By comparing the brain regions relevant for the classifier obtained in the first step and the brain-wide gene expression profiles of the modules of interest obtained in the second step, it has been proved that the regions that characterize ASD brain at the neuroimaging level are those in which four out of the five gene modules take a significantly high absolute value of expression. These results prove that, despite the heterogeneity of the disorder, it is possible to identify a neuroimaging-based biomarker of ASD, confirmed by transcriptomics.

q-bio.NC↗
arXiv2023

DeLTA-BIT: an open-source probabilistic tractography-based deep learning framework for thalamic targeting in functional neurological disorders

In the last years in-vivo tractography has assumed an important role in neurosciences, for both research and clinical applications such as non-invasive investigation of brain connectivity and presurgical planning in neurosurgery. In more recent years there has been a growing interest in the applications of diffusion tractography for target identification in functional neurological disorders for an increasingly tailored approach. The growing diffusion of well-established neurosurgical procedures, such as deep brain stimulation or trans-cranial Magnetic Resonance-guided Focused Ultrasound, favored this trend. Tractography can indeed provide more accurate, patient-specific, information about the targeted region if compared to stereotactic atlases. On the other hand, this tractography-based approach is not very physician-friendly, and its heavily time consuming since it needs several hours for Magnetic Resonance Imaging data processing. In this study we propose a novel open-source deep learning framework called DeLTA-BIT (acronym of Deep-learning Local TrActography for BraIn Targeting) for fast target predictions, based on probabilistic tractography. The proposed framework exploits a convolutional neural network (CNN) to predict the location of the Ventral Intermediate Nucleus of the thalamus (VIM). The CNN was trained on the Human Connectome Project (HCP) dataset. The model capability in predicting the VIM location was tested both on the HCP (internal validation) and clinical data (external validation). Results from the internal validation have shown good capability in predicting the VIM region (mean DSC = 0.62+- 0.15, mean sDSC=0.76+- 0.17) by using just T1 images as input, in a time scale of fraction of second per subject. As for the clinical data, results have been compared with an atlas-based method demonstrating similar performance, but within a significantly shorter timeframe.

physics.med-ph↗
arXiv2021

Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade oftwo U-nets: training and assessment on multipledatasets using different annotation criteria

The automatic assignment of a severity score to the CT scans of patients affected by COVID-19 pneumonia could reduce the workload in radiology departments. This study aims at exploiting Artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. We investigated the effects of using multiple datasets, heterogeneously populated and annotated according to different criteria. We developed an automated analysis pipeline, the LungQuant system, based on a cascade of two U-nets. The first one (U-net_1) is devoted to the identification of the lung parenchyma, the second one (U-net_2) acts on a bounding box enclosing the segmented lungs to identify the areas affected by COVID-19 lesions. Different public datasets were used to train the U-nets and to evaluate their segmentation performances, which have been quantified in terms of the Dice index. The accuracy in predicting the CT-Severity Score (CT-SS) of the LungQuant system has been also evaluated. Both Dice and accuracy showed a dependency on the quality of annotations of the available data samples. On an independent and publicly available benchmark dataset, the Dice values measured between the masks predicted by LungQuant system and the reference ones were 0.95$\pm$0.01 and 0.66$\pm$0.13 for the segmentation of lungs and COVID-19 lesions, respectively. The accuracy of 90% in the identification of the CT-SS on this benchmark dataset was achieved. We analysed the impact of using data samples with different annotation criteria in training an AI-based quantification system for pulmonary involvement in COVID-19 pneumonia. In terms of the Dice index, the U-net segmentation quality strongly depends on the quality of the lesion annotations. Nevertheless, the CT-SS can be accurately predicted on independent validation sets, demonstrating the satisfactory generalization ability of the LungQuant.

eess.IV↗
arXiv2019

Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI)

Over the years, there has been growing interest in using Machine Learning techniques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called confounders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to handle confounders, ranging from data selection, to normalization techniques, up to the use of training algorithm for learning with imbalanced data. However, all these solutions require the confounders to be known a priori. To this aim, we introduce a novel index that is able to measure the confounding effect of a data attribute in a bias-agnostic way. This index can be used to quantitatively compare the confounding effects of different variables and to inform correction methods such as normalization procedures or ad-hoc-prepared learning algorithms. The effectiveness of this index is validated on both simulated data and real-world neuroimaging data.

cs.LG↗
arXiv2002

B_{s,d} -> l^+ l^- and K_L -> l^+ l^- in SUSY models with non-minimal sources of flavour mixing

We present a general analysis of B_{s,d}-> l^+ l^- and K_L -> l^+ l^- decays in supersymmetric models with non-minimal sources of flavour mixing. In spite of the existing constraints on off-diagonal squark mass terms, these modes could still receive sizeable corrections, mainly because of Higgs-mediated FCNCs arising at large tan(beta). The severe limits on scenarios with large tan(beta) and non-negligible {tilde d}^i_{R(L)}-{d-tilde}^j_{R(L)} mixing imposed by the present experimental bounds on these modes and Delta B=2 observables are discussed in detail. In particular, we show that scalar-current contributions to K_L -> l^+ l^- and B-{bar B} mixing set non-trivial constraints on the possibility that B_s -> l^+ l^- and B_d -> l^+ l^- receive large corrections.

hep-ph↗
arXiv2002

Scalar flavour-changing neutral currents in the large-tan(beta) limit

We analyse scalar flavour-changing neutral currents of down-type quarks in models with two Higgs doublets, coupled separately to up- and down-type quarks, in the limit where the ratio of the two expectation values ($\tan β= v_u/v_d$) is large. We clarify the origin of this phenomenon, both in $ΔF=1$ and $ΔF=2$ processes, analysing differences and analogies between supersymmetric and non-supersymmetric models. We confirm previous findings of a sizeable enhancement at large $\tanβ$ of specific $ΔF=1$ and $ΔF=2$ amplitudes in the MSSM and, in these cases, we discuss how large-$\tanβ$ corrections can be controlled beyond lowest order. Finally, we emphasize the unique role of the rare processes $B_{s,d} \to τ^+ τ^-$ and $B_{s,d} \to μ^+ μ^-$ in probing this scenario.

hep-ph↗
arXiv2002

T-odd correlations in charged Kl4 decays

We analyse the sensitivity to physics beyond the SM of T-odd correlations in $K_{\ell 4}$ decays, which do not involve the lepton polarization. We show that a combined analysis of $K^+_{μ4}$ and $K^-_{μ4}$ decays can lead to new constraints about CP violation in $ΔS=1$ charged-current interactions, complementary to those obtained from the transverse muon polarization in $K_{μ3}$ and of comparable accuracy.

hep-ph↗
arXiv2001

An Estimate of the K0-K0bar Mixing Amplitude

We computed the B_K parameter on the lattice by using a non-perturbatively improved Wilson action. From our quenched simulation, in the MSbar scheme and at mu=2 GeV, we obtain B_K=0.73(7)^{+0.05}_{-0.01}. To gain some insight in the systematic errors due to the use of the quenched approximation, we also made the unquenched computation with Wilson fermions. We do not observe any significant deviation with respect to the quenched result.

hep-lat↗