A5071486062- AI in cancer detection
- Cell Image Analysis Techniques
- Photoacoustic and Ultrasonic Imaging
- Remote Sensing in Agriculture
- 3D Printing in Biomedical Research
- Infrared Thermography in Medicine
- Pancreatic and Hepatic Oncology Research
- Molecular Biology Techniques and Applications
- Atmospheric and Environmental Gas Dynamics
- Spectroscopy Techniques in Biomedical and Chemical Research
- Plant Water Relations and Carbon Dynamics
- Urban Heat Island Mitigation
- Human Pose and Action Recognition
- Fire effects on ecosystems
- Digital Imaging for Blood Diseases
- Laser-Ablation Synthesis of Nanoparticles
- Atmospheric Ozone and Climate
- Photochromic and Fluorescence Chemistry
- Forest Management and Policy
- Nonlinear Optical Materials Studies
- Cancer Cells and Metastasis
- Collagen: Extraction and Characterization
- Advanced Neural Network Applications
- Gene expression and cancer classification
- Advanced Fluorescence Microscopy Techniques
Max Planck Institute for Multidisciplinary Sciences
2024-2025
Tissue Dynamics (Israel)
2024
University of Milano-Bicocca
2019-2023
Tumor organoids are three-dimensional in vitro models which can recapitulate the complex mutational landscape and tissue architecture observed cancer patients, providing a realistic model for testing novel therapies, including immunotherapies. A significant challenge organoid research oncology lies developing efficient reliable methods segmenting images, quantifying growth, regression response to treatments, as well predicting behavior of systems. Up now, curated dataset co-cultured with...
Second Harmonic Generation (SHG) microscopy has gained much interest in the histopathology field since it allows label-free imaging of tissues simultaneously providing information on their morphology and collagen microarchitecture, thereby highlighting onset pathologies diseases. A wide request image analysis tools is growing, with aim to increase reliability huge amount acquired data assist pathologists a user-independent way during diagnosis. In this light, we exploit here set...
Abstract Super-resolution image acquisition has turned photo-activated far-infrared thermal imaging into a promising tool for the characterization of biological tissues. By sub-diffraction localization sparse temperature increments primed by sample absorption modulated focused laser light, distribution (endogenous or exogenous) photo-thermal biomarkers can be reconstructed at tunable ∼10−50 μm resolution. We focus here on theoretical modeling laser-primed variations and provide guidelines to...
We present a new AI-based method for the quantification of liver fibrosis in tissue sections stained with Picro Sirius Red which highlights collagen. The segments and quantifies collagen, marker fibrotic response, through deep learning model trained on 20 whole-slide images. results show Dice score > 90% compared to manual annotations, demonstrating its potential aid during diagnosis. Furthermore, our approach can be extended other staining protocols.
The recent successes in analyzing images with deep neural networks are almost exclusively achieved Convolutional Neural Networks (CNNs). training of these CNNs, and fact all network architectures, uses the backpropagation algorithm where output is compared desired result difference then used to tune weights towards outcome. In a 2022 preprint, Geoffrey Hinton suggested an alternative way which passes results together at input network. This so called Forward (FF) has up now only been fully...
ABSTRACT Tumor organoids are three-dimensional in vitro models which can recapitulate the complex mutational landscape and tissue architecture observed cancer patients, providing a realistic tumor microenvironment for testing novel therapies, including immunotherapies. A significant challenge organoid research oncology lies developing efficient reliable methods segmenting images, quantifying growth, regression response to treatments, as well predicting behavior of systems. Up now, curated...
Under the Paris Agreement, countries are encouraged to preserve and enhance existing carbon sinks, especially forests, thereby including LULUCF (Land Use, Land Use Change Forestry) sector in international climate mitigation targets. In particular, Europe has set target reach neutrality, i.e. a balance between anthropogenic emissions by sources removals 2050. A prerequisite these goals is an accurate credible estimation of both large fluxes. However, recent works highlighted uncertainty...
The accurate retrieval of Solar-Induced chlorophyll Fluorescence (SIF) is a pivotal target for Earth Observation since SIF can be easily monitored through optical remote sensing and provides unique information concerning the vegetation health status. Here, we propose i-φ-MaLe (metti il nome per esteso), novel algorithm, which couples Fourier analysis with supervised machine learning-based procedure trained atmosphere-canopy radiative transfer (RT) SCOPE model....
H&E stained sections are the gold standard for disease diagnosis but, unfortunately, staining process is time-consuming and expensive. In an effort to overcome these problems, here, we propose a virtual algorithm, able predict Hematoxylin/Eosin (H&E) image, usually exploited during clinical evaluations, starting from autofluorescence signal of entire liver tissue acquired by confocal microscope. The color texture contents generated virtually images have been analyzed through phasor-based...
Despite their key-role during the histopathological diagnosis, staining procedures are expensive and time-consuming. Label-free microscopy provides an alternative since it allows visualization of endogenous proteins without need extrinsic dyes. SuperµMAPPS, a novel AI-based method, analyzes Polarized Second Harmonic Generation signal from collagen to characterize its micro-architecture in terms fibrils mean orientation θF anisotropy γ, related tumor development. After proper validation on...