Tesi etd-10162023-174053 |
Link copiato negli appunti
Tipo di tesi
Tesi di specializzazione (4 anni)
Autore
GODDI, ANTONIO
URN
etd-10162023-174053
Titolo
The prognostic value of radiomic features in liver-limited metastatic colorectal cancer patients from the TRIBE2 study
Dipartimento
RICERCA TRASLAZIONALE E DELLE NUOVE TECNOLOGIE IN MEDICINA E CHIRURGIA
Corso di studi
RADIODIAGNOSTICA
Relatori
relatore Prof. Neri, Emanuele
Parole chiave
- liver-limited metastatic colorectal cancer
- radiomics features
- prognostic factor
- first-line chemotherapy plus bevacizumab
Data inizio appello
07/11/2023
Consultabilità
Non consultabile
Data di rilascio
07/11/2026
Riassunto
Aims
Evaluating the prognostic role of radiomic features in liver-limited mCRC treated with first-line therapy at baseline and best response among patients undergoing resection.
Patients and methods
Among patients enrolled in TRIBE2 (NCT02339116), the association of clinical and radiomic data, extracted by SOPHiA-DDM™, with PFS/OS in the overall population and with DFS/post-resection OS in those undergoing resection was investigated.
Results
Among 98 patients, radiomic parameters improved the prediction accuracy of our model for OS (AUC=0.83, sensitivity=0.85, specificity=0.73, accuracy=0.78), but not PFS.
Of 46 resected patients, small distance high grey level emphasis was associated with shorter DFS, high grey level zone emphasis/higher kurtosis with shorter post-resection OS.
Conclusions
Radiomic features should be implemented in tools of outcome prediction for LL-mCRC.
Evaluating the prognostic role of radiomic features in liver-limited mCRC treated with first-line therapy at baseline and best response among patients undergoing resection.
Patients and methods
Among patients enrolled in TRIBE2 (NCT02339116), the association of clinical and radiomic data, extracted by SOPHiA-DDM™, with PFS/OS in the overall population and with DFS/post-resection OS in those undergoing resection was investigated.
Results
Among 98 patients, radiomic parameters improved the prediction accuracy of our model for OS (AUC=0.83, sensitivity=0.85, specificity=0.73, accuracy=0.78), but not PFS.
Of 46 resected patients, small distance high grey level emphasis was associated with shorter DFS, high grey level zone emphasis/higher kurtosis with shorter post-resection OS.
Conclusions
Radiomic features should be implemented in tools of outcome prediction for LL-mCRC.
File
| Nome file | Dimensione |
|---|---|
La tesi non è consultabile. |
|