RUSSO, CAMILLA (2023) Fusemedml: exploring the potential for a new cognitive computing tool in identification and classification of brain tumors starting from magnetic resonance imaging. [Tesi di dottorato]
Anteprima |
Testo
Russo_Camilla_XXXV.pdf Download (7MB) | Anteprima |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | Fusemedml: exploring the potential for a new cognitive computing tool in identification and classification of brain tumors starting from magnetic resonance imaging |
| Autori: | Autore Email RUSSO, CAMILLA camilla.russo@unina.it |
| Data: | 5 Giugno 2023 |
| Numero di pagine: | 67 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Ingegneria Elettrica e delle Tecnologie dell'Informazione |
| Dottorato: | Information and Communication Technology for Health |
| Ciclo di dottorato: | 35 |
| Coordinatore del Corso di dottorato: | nome email RICCIO, DANIELE daniele.riccio@unina.it |
| Tutor: | nome email MARESCA, PAOLO [non definito] |
| Data: | 5 Giugno 2023 |
| Numero di pagine: | 67 |
| Parole chiave: | Neuroncology; Glioblastoma; Solitary Brain Metastasis; Neuroradiology; Magnetic Resonance Imaging; Computer-aided diagnosis; Diagnostic performance; Human performance; Artificial Intelligence; Machine Learning; Convolutional Neural Network; FuseMedML. |
| Settori scientifico-disciplinari del MIUR: | Area 09 - Ingegneria industriale e dell'informazione > ING-INF/05 - Sistemi di elaborazione delle informazioni Area 06 - Scienze mediche > MED/37 - Neuroradiologia |
| Depositato il: | 15 Giu 2023 09:09 |
| Ultima modifica: | 09 Apr 2025 13:15 |
| URI: | http://www.fedoa.unina.it/id/eprint/15016 |
Abstract
This document describes preliminary results of the research activities carried out within the PhD in Information and Communication Technology for Health (ICTH) on the topic of Delivery Manager of Cognitive Computing for Neuroncology at the Department of Electrical Engineering and Information Technologies (DIETI) of the University of Naples “Federico II”. Primary endpoint of this research line is the evaluation of an innovative computational system based on cognitive computing technologies, namely the open-source PyTorch-based deep learning framework for medical data named FuseMedML, for the analysis of magnetic resonance imaging derived data in patients with brain neoplasm of unknown origin; main goal is to obtain a semisupervised binary classification model which allows the timely identification of the two most common malignant brain tumours of the adulthood, requiring therapeutic strategies and clinical-radiological monitoring different the one from the other. Secondary endpoint is to test whether the proposed binary classification model can predict brain tumour classification more accurately than conventional assessment carried out by trained human readers, in order to determine if the prediction model based on cognitive computing technologies can be able to supplement information and support neuroradiologists in decision-making for daily clinical practice in Neuroncology.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
