A5092863850- Radiomics and Machine Learning in Medical Imaging
- Endometriosis Research and Treatment
- Endometrial and Cervical Cancer Treatments
- Allergic Rhinitis and Sensitization
- Asthma and respiratory diseases
- Ovarian cancer diagnosis and treatment
- Artificial Intelligence in Healthcare and Education
- Infrared Thermography in Medicine
- Uterine Myomas and Treatments
- AI in cancer detection
- Sinusitis and nasal conditions
- Colorectal Cancer Surgical Treatments
Azienda USL di Bologna
2023-2025
University of Bologna
2024
University of Padua
2019
Background/Objectives: The aim of this study was the early identification endometriosis-associated ovarian cancer (EAOC) versus non-endometriosis associated (NEOC) or non-cancerous tissues using pre-surgery contrast-enhanced-Computed Tomography (CE-CT) images in patients undergoing surgery for suspected (OC). Methods: A prospective trial designed to enroll OC. Volumes interest (VOIs) were semiautomatically segmented on CE-CT and classified according histopathological results. entire dataset...
There is a dearth of information regarding the histological and hematological differences between primary recurrent chronic rhinosinusitis with nasal polyps (CRSwNP). The present study analyzed changes in CRSwNP terms eosinophilic infiltrate, subepithelial edema, goblet cell hyperplasia, basement membrane thickness. Blood levels eosinophils basophils were also measured prior to surgery on both disease.Thirty-two consecutive adult patients polyposis treated who subsequently underwent revision...
Current prognostic models lack the use of pre-operative CT images to predict recurrence in endometrial cancer (EC) patients. Our study aimed investigate potential radiomic features extracted from pre-surgical scans accurately disease-free survival (DFS) among EC patients.Contrast-Enhanced (CE-CT) 81 cases were used extract semi-automatically contoured volumes interest. We employed a 10-fold cross-validation approach with 6:4 training test set and utilized data augmentation balancing...
<h3>Introduction/Background</h3> Endometriosis-associated ovarian carcinoma (EAOC) and endometriosis-related cancer (EROC) are relatively underexplored conditions characterized by the coexistence of (OC) endometriosis. The main distinction between them lies in presence transitional borderline lesions, observed EROC but absent EAOC. aim this study was to investigate elucidate differences among EROC, EAOC, OC not related or associated with endometriosis (NEOC). <h3>Methodology</h3> This...
Background: The accurate discrimination of uterine leiomyosarcomas and leiomyomas in a pre-operative setting remains current challenge. To date, the diagnosis is made by pathologist on excised tumor. aim this study was to develop machine learning algorithm using radiomic data extracted from contrast-enhanced computed tomography (CECT) images that could accurately distinguish leiomyomas. Methods: Pre-operative CECT patients submitted surgery with histological leiomyoma or leiomyosarcoma were...
<h3>Introduction/Background</h3> Women with endometriosis (EMS) present an increased risk of developing EMS-related ovarian carcinoma (EROC). To date, the definitive diagnosis relies on post-surgical assessment by a pathologist, thus limiting individualized medical approaches due to lack screening methods for timely detection EROC development. fill in this unmet clinical need, purpose study was explore capacity radiomic-based machine learning (ML) models discriminate from EMS lesions and...