In this paper, a deep learning technique for tumor detection in a microwave tomography framework is proposed. Providing an easy and effective imaging technique for breast cancer detection is one of the main focuses for biomedical researchers. Recently, microwave tomography gained a great attention due to its ability to reconstruct the electric properties maps of the inner breast tissues, exploiting nonionizing radiations. A major drawback of tomographic approaches is related to the inversion algorithms, since the problem at hand is nonlinear and ill-posed. In recent decades, numerous studies focused on image reconstruction techniques, in same cases exploiting deep learning. In this study, deep learning is exploited to provide information about the presence of tumors based on tomographic measures. The proposed approach has been tested with a simulated database showing interesting performances, in particular for scenarios where the tumor mass is particularly small. In these cases, conventional reconstruction techniques fail in identifying the presence of suspicious tissues, while our approach correctly identifies these profiles as potentially pathological. Therefore, the proposed method can be exploited for early diagnosis purposes, where the mass to be detected can be particularly small.

Background: microwave imaging (MWI) has emerged as a promising modality for breast cancer screening, offering cost-effective, rapid, safe and comfortable exams. However, the practical application of MWI for tumor detection and localization is hampered by its inherent low resolution and low detection capability. Methods: this study aims to generate an accurate tumor probability map directly from the scattering matrix. This direct conversion makes the probability map independent of specific image formation techniques and thus potentially complementary to any image formation technique. An approach based on a convolutional neural network (CNN) is used to convert the scattering matrix into a tumor probability map. The proposed deep learning model is trained using a large realistic numerical dataset of two-dimensional (2D) breast slices. The performance of the model is assessed through visual inspection and quantitative measures to assess the predictive quality at various levels of detail. Results: the results demonstrate a remarkably high accuracy (0.9995) in classifying profiles as healthy or diseased, and exhibit the model’s ability to accurately locate the core of a single tumor (within 0.9 cm for most cases). Conclusion: overall, this research demonstrates that an approach based on neural networks (NN) for direct conversion from scattering matrices to tumor probability maps holds promise in advancing state-of-the-art tumor detection algorithms in the MWI domain.

The proposed paper investigates the use of deep learning schemes to perform fast quantitative microwave imaging in the framework of breast cancer detection to support medical decisions. Nowadays, Conventional approaches have some drawbacks related to patient’s safety, processing time and cost, and in this framework microwave imaging can represent a valid alternative due to the use of non-ionising radiations and its affordability. In this framework, deep learning can considerably speed up the inversion procedure, making three-dimensional imaging more convenient and manageable for future perspective.

Magnetic Resonance Imaging (MRI) is a useful diagnostic method for producing anatomical images of the body. It differentiates tissues thanks to the measure of their proton density and relaxation times and . Since pathological tissues often present altered , and with respect to the physiological ones, MRI is largely used for the detection of large number of conditions. In addition, MRI scan presents an effective resolution able to detect very small anatomical elements, making the imaging system well suitable in contexts like prevention and early diagnosis. Nevertheless, system resolution imposes pathological volume to be larger than the voxel dimension. Since in some pathologies and conditions it could be very helpful to find tissues even smaller than the voxel dimension, this manuscript proposes an algorithm able to analyze voxel content and detect which one presents more than one tissue in its volume (i.e., which one is heterogeneous). More in detail, a machine learning algorithm is proposed, able to highlight, in the MR image, which pixel corresponds to an heterogeneous voxel. Method shows to be promising in combining good results and near real‐time processing in both simulated and real scenario.

In the context of neurodegenerative diseases, finger tapping is a gold-standard test used by clinicians to evaluate the severity of the condition. The finger tapping test involves repetitive tapping between the index finger and thumb. Subjects affected by neurodegenerative diseases, such as Parkinson’s disease, often exhibit symptoms like bradykinesia, rigidity, and tremor. As a result, when these individuals perform the finger tapping task, instability in both the tap rate and finger displacement can be observed. Currently, clinicians assess bradykinesia by visually observing the patient’s finger tapping movements and qualitatively rating their severity. In this work, we present a novel ultrasound contactless system that provides quantitative measurements of finger tapping, including tap rate and finger displacements. The system functions as an ultrasound sonar capable of measuring the Doppler spectrum of waves reflected by the hand. From this spectrum, various characteristics of the hand movement can be extracted through appropriate processing techniques. Specifically, by performing time–frequency analysis and applying specialized data processing, tapping rates and finger displacements can be estimated. The system has been tested in real-world scenarios involving volunteer finger tapping sessions, demonstrating its potential for accurately measuring both tap rates and displacements.

Background: Parkinson’s disease (PD) is a progressive neurodegenerative disorder that manifests through motor and non-motor symptoms. Understanding the alterations in brain connectivity associated with PD remains a challenge that is crucial for enhancing diagnosis and clinical management. Methods: This study utilized Magnetoencephalography (MEG) to investigate brain connectivity in PD patients compared to healthy controls (HCs) by applying eigenvector centrality (EC) measures across different frequency bands. Results: Our findings revealed significant differences in EC between PD patients and HCs in the alpha (8–12 Hz) and beta (13–30 Hz) frequency bands. To go into further detail, in the alpha frequency band, PD patients in the frontal lobe showed higher EC values compared to HCs. Additionally, we found statistically significant correlations between EC measures and clinical impairment scores (UPDRS-III). Conclusions: The proposed results suggest that MEG-derived EC measures can reveal important alterations in brain connectivity in PD, potentially serving as biomarkers for disease severity.