9 results match your criteria: "University of Cassino and Southern Latium[Affiliation]"

This paper explores the potential of leveraging electronic health records (EHRs) for personalized health research through the application of artificial intelligence (AI) techniques, specifically Named Entity Recognition (NER). By extracting crucial patient information from clinical texts, including diagnoses, medications, symptoms, and lab tests, AI facilitates the rapid identification of relevant data, paving the way for future care paradigms. The study focuses on Non-small cell lung cancer (NSCLC) in Italian clinical notes, introducing a novel set of 29 clinical entities that include both presence or absence (negation) of relevant information associated with NSCLC.

View Article and Find Full Text PDF

Learnable DoG convolutional filters for microcalcification detection.

Artif Intell Med

September 2023

Department of Electrical and Information Engineering, University of Cassino and Southern Latium, Cassino, FR 03043, Italy. Electronic address:

Difference of Gaussians (DoG) convolutional filters are one of the earliest image processing methods employed for detecting microcalcifications on mammogram images before machine and deep learning methods became widespread. DoG is a blob enhancement filter that consists in subtracting one Gaussian-smoothed version of an image from another less Gaussian-smoothed version of the same image. Smoothing with a Gaussian kernel suppresses high-frequency spatial information, thus DoG can be regarded as a band-pass filter.

View Article and Find Full Text PDF

Convolutional Neural Networks (CNN) have received a large share of research in mammography image analysis due to their capability of extracting hierarchical features directly from raw data. Recently, Vision Transformers are emerging as viable alternative to CNNs in medical imaging, in some cases performing on par or better than their convolutional counterparts. In this work, we conduct an extensive experimental study to compare the most recent CNN and Vision Transformer architectures for whole mammograms classification.

View Article and Find Full Text PDF

Addressing class imbalance in deep learning for small lesion detection on medical images.

Comput Biol Med

May 2020

Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, Fisciano, SA 84084, Italy. Electronic address:

Deep learning methods utilizing Convolutional Neural Networks (CNNs) have led to dramatic advances in automated understanding of medical images. However, in many medical image classification tasks, lesions occupy only a few pixels of the image. This results in a significant class imbalance between lesion and background.

View Article and Find Full Text PDF

Due to the limited field of view of the microscopes, acquisitions of macroscopic specimens require many parallel image stacks to cover the whole volume of interest. Overlapping regions are introduced among stacks in order to make it possible automatic alignment by means of a 3D stitching tool. Since state-of-the-art microscopes coupled with chemical clearing procedures can generate 3D images whose size exceeds the Terabyte, parallelization is required to keep stitching time within acceptable limits.

View Article and Find Full Text PDF

Recyclable aggregates of mesoporous titania with different anatase-rutile ratios have been prepared by thermal treatments of either amorphous or peptized precursors. These last two have been obtained by hydrolysis of either Ti(OC₂H₅)₄ or of Ti(OC₂H₅)₄ in mixture with 5 mol % Zr(OC₃H₇)₄ at room temperature in the presence of NH₄OH as a catalyzing agent. The anatase-rutile ratio, the recyclable aggregates of the nano-sized particles, the mesoporosity, the surface area and the crystallinity of the resulting crystallized products of titania can be controlled by the synthesis parameters including: concentration of ammonia catalyst, stirring time and concentration of the peptizing HNO₃, drying method of peptized precursors, calcination temperature, and finally the ramp rate up to the titania crystallization temperature.

View Article and Find Full Text PDF

Habitual physical activity has beneficial effects on cardiovascular risk reduction by improving vascular function but the underlying mechanism is still unclear. To address this issue, we performed a cross-sectional study comparing 50 physically active (PA) adults with 50 sedentary controls matched for age, sex, and cardiovascular risk factors. PA subjects had significantly higher flow-mediated dilation (FMD) than controls and higher serum levels of nitrite/nitrate, a marker of nitric oxide generation.

View Article and Find Full Text PDF

Vascular dysfunction-associated with Alzheimer's disease.

Clin Hemorheol Microcirc

March 2017

Department of Human Sciences, Society and Health, University of Cassino and Southern Latium, V. S. Angelo Th., Polo Didattico della Folcara, Cassino (FR), Italy.

Our attention is focused on the study of a new model based on the red blood cell (RBC) and on its interaction with amyloid beta peptide 1-42 (Aβ). RBC are highly deformable to assist blood flow in the microcirculation. For this reasons RBC abnormalities could contribute to Alzheimer's disease (AD) by obstructing oxygen delivery to brain, causing hypoxia.

View Article and Find Full Text PDF

Magnetite nanoparticles (Fe₃O₄) represent the most promising materials in medical applications. To favor high-drug or enzyme loading on the nanoparticles, they are incorporated into mesoporous materials to form a hybrid support with the consequent reduction of magnetization saturation. The direct synthesis of mesoporous structures appears to be of interest.

View Article and Find Full Text PDF