Cennamo, Michele (2025) Identification of Clinically Significant Prostate Cancer Using a Combinatorial Neural Network Analysis: The Synergistic Behaviour of Multiparametric Magnetic Resonance and Prostate Health Index. [Tesi di dottorato]
![[thumbnail of Michele_Cennamo_Dottorato.pdf]](https://www.fedoa.unina.it/style/images/fileicons/other.png "Michele_Cennamo_Dottorato.pdf") |
Documento PDF
Michele_Cennamo_Dottorato.pdf Visibile a [TBR] Amministratori dell'archivio Download (518kB) | Richiedi una copia |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | Identification of Clinically Significant Prostate Cancer Using a Combinatorial Neural Network Analysis: The Synergistic Behaviour of Multiparametric Magnetic Resonance and Prostate Health Index |
| Autori: | Autore Email Cennamo, Michele MICHELECENNAMO1@GMAIL.COM |
| Data: | 2025 |
| Numero di pagine: | 23 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dottorato: | Medicina clinica e sperimentale |
| Ciclo di dottorato: | 38 |
| Coordinatore del Corso di dottorato: | nome email Beguinot, Francesco beguino@unina.it |
| Tutor: | nome email Terracciano, Daniela [non definito] |
| Data: | 2025 |
| Numero di pagine: | 23 |
| Parole chiave: | Neural Network, Prostate Cancer, PCa |
| Settori scientifico-disciplinari del MIUR: | Area 06 - Scienze mediche > MED/02 - Storia della medicina |
| Informazioni aggiuntive: | Ciclo 38° |
| Depositato il: | 09 Gen 2026 10:09 |
| Ultima modifica: | 12 Ago 2026 05:39 |
| URI: | https://www.fedoa.unina.it/id/eprint/17119 |
Abstract
In the present study we performed the evaluation of the combination of phi and multiparametric magnetic resonance in the identification of aggressive prostate cancer, to improve the choice of therapy in a patient-tailored manner. We analyzed data from 177 patients that underwent radical prostatectomy. Our findings demonstrate that combining phi and multiparametric magnetic resonance allows for a better estimation risk category assessment of prostate cancer patients at diagnosis, allowing personalized treatment. Background: The overuse of prostate specific antigen (PSA) accounts for a high rate of overdiagnosis, this leads to unnecessary definitive treatments of prostate cancer (PCa) with detrimental effect associated to it, such as erectile dysfunction and urinary incontinence. Aim: The aim of the present study is to evaluate the performance of an artificial neural network-based approach in the development of a combinatorial model including prostate health index (PHI) and multiparametric magnetic resonance (mpMRI) for the early recognition of clinically significant PCa. Methods: 177 patients that underwent radical prostatectomy and received PHI assessment and mpMRI before surgery, were enrolled. An artificial neural network was developed to efficiently identify aggressive PCa, receiving as inputs, PHI plus and Prostate Imaging Reporting and Data System (PI-RADS) score. Results: The output of this model is an estimation of the presence of a low or high Gleason score. After training on a dataset of 135 samples and optimization of the variables, the model achieved values of sensitivity as high as 80% and 68% specificity. Conclusions: Our study suggests that combining mpMRI and PHI may help to better estimate the risk category of PCa at initial diagnosis, allowing a personalized treatment approach. The efficiency of the method can be improved even further by training the model on larger datasets.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
