Prediction of cancer trajectories by statistical learning on radiomic features

Carlini, Gianluca (2021) Prediction of cancer trajectories by statistical learning on radiomic features. [Laurea magistrale], Università di Bologna, Corso di Studio in Physics [LM-DM270]
Documenti full-text disponibili:
[img] Documento PDF (Thesis)
Disponibile con Licenza: Creative Commons: Attribuzione - Non commerciale - Non opere derivate 4.0 (CC BY-NC-ND 4.0)

Download (5MB)

Abstract

Radiomics refers to the analysis of quantitative features extracted from medical images including Positron Emission Tomography (PET), Computerized Tomography (CT), Magnetic Resonance Imaging (MRI), and other medical imaging techniques. Radiomic features can be used to build models providing diagnostic, prognostic, and predictive information. The aim of this work was to build a machine learning model able to predict survival probability in 85 cervical cancer patients, using the radiomics features extracted from CT and PET medical images. A thorough feature selection process was conducted employing different techniques to select the best predictors among the original features in the dataset. In particular, the Genetic Algorithm revealed to be the best of the feature selection methods employed, with promising applications in the field of radiomics. Two different survival models have been developed, a Cox proportional hazard model and a Random Survival Forest. A Decision Tree Classifier was also implemented as a further model to evaluate. All the models were trained on 80% of the available data and tested on the remaining 20%. The Concordance Index (CI) was used as the evaluation metric for the two survival models, while the area under the Receiver Operating Characteristic curve (ROC AUC) was used as the evaluation metric for the classifier. The Cox model trained using 9 selected CT features was superior to all the other models tested. It achieved a Concordance Index score of 0.71 on the test set, showing promising predictive capabilities on external data. Finally, the recurrence outcome was used as an additional feature, producing a general improvement of all the models.

Abstract
Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Carlini, Gianluca
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Indirizzo
Applied Physics
Ordinamento Cds
DM270
Parole chiave
Radiomics,PET,CT,Feature Selection,Genetic Algorithms,Machine Learning
Data di discussione della Tesi
26 Marzo 2021
URI

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento

^