Hakkak Moghadam Torbati, Armin (2023) Machine learning and texture analysis of 18F-FDG PET/CT images for the prediction of distant metastases in non-small cell lung cancer patients. [Tesi di dottorato]

Anteprima	Testo Hakkak Moghadam Torbati_Armin_36_PARZIALE.pdf Download (314kB) | Anteprima
	Testo Hakkak Moghadam Torbati_Armin_36.pdf Visibile a [TBR] Amministratori dell'archivio Download (511kB)

Abstract

The aim of our study was to predict the occurrence of distant metastases in non-small cell lung cancer (NSCLC) patients using machine learning methods and texture analysis of [18F]FDG PET/CT images. In this retrospective and single center study, we evaluated 79 patients with advanced NSCLC who had undergone [18F]FDG PET/CT scan at diagnosis before any therapy. Patients were divided in two independent training (n=44) and final testing (n=35) cohorts. Texture features of primary tumors and lymph node metastases were extracted from [18F]FDG PET/CT images using LIFEx program. Six machine learning methods were applied to the training dataset using the entire panel of features. Dedicated selection methods were used to generate different combinations of five features. The performance of selected machine learning methods applied to the different combinations of features was determined using accuracy, confusion matrix, receiver operating characteristic (ROC) curves and area under curve (AUC). A total of 104 and 78 lesions were analysed in the training and final testing cohorts, respectively. Support vector machine (SVM) and decision tree methods showed the highest accuracy in the training cohort. Seven combinations of 5 features were obtained and introduced in the models subsequently applied to the training and final testing cohorts using SVM and decision tree. Accuracy and AUC of decision tree method were higher than those obtained with SVM in the final testing cohort. The best combination of features included shape sphericity, grey level run length matrix_run length non-uniformity (GLRLM_RLNU), Total Lesion Glycolysis (TLG), Metabolic Tumor Volume (MTV) and shape compacity. The combination of these features with the decision tree method could predict the occurrence of distant metastases with an accuracy of 74.4% and an AUC of 0.63 in NSCLC patients.

Downloads

Actions (login required)

Modifica documento