A5035149865- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Diagnosis and Treatment
- MRI in cancer diagnosis
- Advanced MRI Techniques and Applications
- Ultrasound and Hyperthermia Applications
- Hepatocellular Carcinoma Treatment and Prognosis
- Prostate Cancer Treatment and Research
- Urinary and Genital Oncology Studies
- Pediatric Urology and Nephrology Studies
- Advanced X-ray and CT Imaging
- Urologic and reproductive health conditions
- Sarcoma Diagnosis and Treatment
- Renal cell carcinoma treatment
- Biliary and Gastrointestinal Fistulas
- Liver Disease Diagnosis and Treatment
- Genetic and Kidney Cyst Diseases
- Bladder and Urothelial Cancer Treatments
- AI in cancer detection
- Medical Imaging and Pathology Studies
- Glioma Diagnosis and Treatment
- Liver Disease and Transplantation
- Pancreatic and Hepatic Oncology Research
- Ultrasound Imaging and Elastography
- Structural Health Monitoring Techniques
- Kidney Stones and Urolithiasis Treatments
University of Palermo
2014-2024
Azienda Ospedaliera Universitaria Policlinico "Paolo Giaccone" di Palermo
2004-2021
Tecnologie Avanzate (Italy)
2018
Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and radiomics studies whose purpose to identify associations between imaging features patient outcomes. Because manual delineation a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), residual factorized convNet (ERFNet), aim tackle the fully-automated, real-time, 3D process of gland on T2-weighted MRI. While UNet used in many...
Intraoperative ultrasound (IOUS) is becoming progressively more common during brain tumor surgery. We present data from our case series of surgery performed with the aid IOUS in order to identify advantages and crucial aspects that may improve management neurosurgical procedures for tumors. From January 2021 September 2021, 17 patients different tumors underwent aided by use IOUS. During surgery, procedure was supported multiples ultrasonographic modalities addition standard B-mode: Doppler,...
For decades, wavelet theory has attracted interest in several fields dealing with signals. Nowadays, it is acknowledged that not very suitable to face aspects of multidimensional data like singularities and this led the development other mathematical tools. A recent application radiomics, an emerging field aiming improve diagnostic, prognostic predictive analysis various cancer types through features extracted from medical images. In paper, for a radiomics study prostate magnetic resonance...
Abstract In healthcare industry 4.0, a big role is played by radiomics. Radiomics concerns the extraction and analysis of quantitative information not visible to naked eye, even expert operators, from biomedical images. involves management digital images as data matrices, with aim extracting number morphological predictive variables, named features, using automatic or semi‐automatic methods. Multidisciplinary methods machine learning deep are fully involved in this field. However, large...
OBJECTIVE. The purpose of this study was to evaluate the effectiveness contrast-enhanced sonography in comparison with conventional differentiating muscle-infiltrating and superficial neoplasms urinary bladder.
Cystic renal lesions are a common incidental finding on routinely imaging examinations. Although benign simple cyst is usually easy to recognize, the same not true for complex and multifocal cystic lesions, whose differential diagnosis includes both neoplastic non-neoplastic conditions. In this review, we will show series of cases in order provide tips identify cysts differentiate them from malignant ones.
To investigate whether MRI-based texture analysis improves diagnostic performance for the diagnosis of parotid gland tumors compared to conventional radiological approach.Patients with who underwent salivary glands MRI between 2008 and 2019 were retrospectively selected. included a qualitative assessment by two radiologists (one which subspecialized on head neck imaging), various sequences. Diagnostic performances including sensitivity, specificity, area under receiver operating...
The volume estimation of retroperitoneal sarcoma (RPS) is often difficult due to its huge dimensions and irregular shape; thus, it requires manual segmentation, which time-consuming operator-dependent. This study aimed evaluate two fully automated deep learning networks (ENet ERFNet) for RPS segmentation. retrospective included 20 patients with who received an abdominal computed tomography (CT) examination. Forty-nine CT examinations, a total 72 lesions, were included. Manual segmentation...