ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-12292018-190554


Tipo di tesi
Tesi di laurea magistrale LM6
Autore
MARCHINI, MATTEO
URN
etd-12292018-190554
Titolo
Valutazione radiomica con textural features di immagini di RM in pazienti affetti da neoplasie delle ghiandole salivari.
Dipartimento
RICERCA TRASLAZIONALE E DELLE NUOVE TECNOLOGIE IN MEDICINA E CHIRURGIA
Corso di studi
MEDICINA E CHIRURGIA
Relatori
relatore Prof. Neri, Emanuele
Parole chiave
  • salivary glands
  • caratteristiche di texture
  • radiomica
  • risonanza magentica
  • neoplasie
  • radiomics
  • ghiandole salivari
  • textural features magnetic resonance imaging
  • neoplasms
Data inizio appello
29/01/2019
Consultabilità
Non consultabile
Data di rilascio
29/01/2089
Riassunto
Salivary gland tumours most often present as painless enlarging masses. Most are located in the parotid glands and most are benign. The principal hurdle in their management lies in the difficulty in distinguishing benign from malignant tumours. Investigations such as fine needle aspiration cytology (FNAC) and MRI scans provide some useful information, but most cases will require surgical excision as a means of coming to a definitive diagnosis. Our aim was to investigate textural features of MSGT as a potential additional pre-surgical tool of lesion discrimination between benign and malignant major salivary gland tumours (MSGT) using a radiomic approach. This study is based on retrospective evaluation of pre-surgical MRI scans of 40 patients with MSGT. There were 30 benign (75%) and 10 malignant (25%) tumours. Histology results were available for all tumours. A Region of Interest (ROI) has been delimitated where tumor was noticeable in axial T2 weighted images; 27 radiomics features have been extracted from the ROI by QUIBIM SL, a dedicated company which is qualified in studying quantitative imaging biomarkers in medicine. Quantitative data were described by mean and standard deviation. Statistical analysis was performed to identify the radiomics features that could discriminate benign from malignant tumours, and between pleomorphic adenoma and Warthin’s tumor. In our study Grey Level – p25 Value resulted the most strictly related variable to malignancy (p= 0,044), particularly it has shown lower values in malignant tumours; Moreover Skewness Value resulted the most significant feature that could discriminate between pleomorphic adenoma and Wathin’s tumor (p= 0,015), particularly higher values were suggestive of Warthin’s tumor.
File