A5028086260- Medical Image Segmentation Techniques
- AI in cancer detection
- Brain Tumor Detection and Classification
- Multiple Sclerosis Research Studies
- Digital Imaging for Blood Diseases
- Image Processing Techniques and Applications
- Orthopedic Infections and Treatments
- Orthopaedic implants and arthroplasty
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Advanced X-ray and CT Imaging
- Functional Brain Connectivity Studies
- Radiomics and Machine Learning in Medical Imaging
- Optical Imaging and Spectroscopy Techniques
- COVID-19 Clinical Research Studies
- Infective Endocarditis Diagnosis and Management
- Gene expression and cancer classification
University of Catania
2023-2024
Magnetic resonance imaging is a fundamental tool to reach diagnosis of multiple sclerosis and monitoring its progression. Although several attempts have been made segment lesions using artificial intelligence, fully automated analysis not yet available. State-of-the-art methods rely on slight variations in segmentation architectures (e.g. U-Net, etc.). However, recent research has demonstrated how exploiting temporal-aware features attention mechanisms can provide significant boost...
The accurate detection of Covid-19 from chest Computed Tomography (CT) images can assist in early diagnosis and management the disease. This paper presents a solution for detection, presented challenge 3rd competition, inside "AI-enabled Medical Image Analysis Workshop" organized by IEEE International Conference on Acoustic, Speech Signal Processing (ICASSP) 2023. In this work, application deep learning models CT image analysis was investigated, focusing use ResNet as backbone network...
Accurate segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) scans is crucial for clinical diagnosis and effective treatment planning. In this work, we investigate the effectiveness Diffusion Models (DM) in achieving pixel-wise MS lesions. DM significantly improves sensitivity, especially regions with subtle abnormalities. We conducted extensive experiments using magnetic resonance volumes a public dataset, encompassing various imaging modalities. Our...
Brain age is a critical measure that reflects the biological ageing process of brain. The gap between brain and chronological age, referred to as PAD (Predicted Age Difference), has been utilized investigate neurodegenerative conditions. can be predicted using MRIs machine learning techniques. However, existing methods are often sensitive acquisition-related variabilities, such differences in acquisition protocols, scanners, MRI sequences, resolutions, significantly limiting their...
This report summarizes the outcomes of ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation (MSLesSeg). The competition aimed to develop methods capable automatically segmenting multiple sclerosis lesions in MRI scans. Participants were provided with a novel annotated dataset comprising heterogeneous cohort MS patients, featuring both baseline and follow-up scans acquired at different hospitals. MSLesSeg focuses developing algorithms that can independently segment an unexamined...
This paper presents our solution for the first challenge of 3rd Covid-19 competition, which is part "AI-enabled Medical Image Analysis Workshop" organized by IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 2023. Our proposed based a Resnet as backbone network with addition attention mechanisms. The provides an effective feature extractor classification task, while mechanisms improve model's ability to focus important regions interest within images. We...
Early detection of an infection prior to prosthesis removal (e.g., hips, knees or other areas) would provide significant benefits patients. Currently, the task is carried out only retrospectively with a limited number methods relying on biometric medical data. The automatic periprosthetic joint from tomography imaging never addressed before. This study introduces novel method for early hip infections analyzing Computed Tomography images. proposed solution based ResNeSt Convolutional Neural...
Magnetic resonance imaging is a fundamental tool to reach diagnosis of multiple sclerosis and monitoring its progression. Although several attempts have been made segment lesions using artificial intelligence, fully automated analysis not yet available. State-of-the-art methods rely on slight variations in segmentation architectures (e.g. U-Net, etc.). However, recent research has demonstrated how exploiting temporal-aware features attention mechanisms can provide significant boost...