Purpose To investigate radiomics and machine learning (ML) as possible tools to enhance MRI-based risk stratification in patients with endometrial cancer (EC). Method From two institutions, 133 patients (Institution1=104 and Institution2=29) with EC and pre-operative MRI were retrospectively enrolled and divided in two a low-risk and a high-risk group according to EC stage and grade. T2-weighted (T2w) images were three-dimensionally annotated to obtain volumes of interest of the entire tumor. A PyRadiomics based and previously validated pipeline was used to extract radiomics features and perform feature selection. In particular, feature stability, variance and pairwise correlation were analyzed. Then, the least absolute shrinkage and selection operator technique and recursive feature elimination were used to obtain the final feature set. The performance of a Support Vector Machine (SVM) algorithm was assessed on the dataset from Institution 1 via 2-fold cross-validation. Then, the model was trained on the entire Institution 1 dataset and tested on the external test set from Institution 2. Results In total, 1197 radiomics features were extracted. After the exclusion of unstable, low variance and intercorrelated features least absolute shrinkage and selection operator and recursive feature elimination identified 4 features that were used to build the predictive ML model. It obtained an accuracy of 0.71 and 0.72 in the train and test sets respectively. Conclusions Whole-lesion T2w-derived radiomics showed encouraging results and good generalizability for the identification of low-risk EC patients.

MRI radiomics: a machine learning approach for the risk stratification of endometrial cancer patients

Travaglino, Antonio;
2022-01-01

Abstract

Purpose To investigate radiomics and machine learning (ML) as possible tools to enhance MRI-based risk stratification in patients with endometrial cancer (EC). Method From two institutions, 133 patients (Institution1=104 and Institution2=29) with EC and pre-operative MRI were retrospectively enrolled and divided in two a low-risk and a high-risk group according to EC stage and grade. T2-weighted (T2w) images were three-dimensionally annotated to obtain volumes of interest of the entire tumor. A PyRadiomics based and previously validated pipeline was used to extract radiomics features and perform feature selection. In particular, feature stability, variance and pairwise correlation were analyzed. Then, the least absolute shrinkage and selection operator technique and recursive feature elimination were used to obtain the final feature set. The performance of a Support Vector Machine (SVM) algorithm was assessed on the dataset from Institution 1 via 2-fold cross-validation. Then, the model was trained on the entire Institution 1 dataset and tested on the external test set from Institution 2. Results In total, 1197 radiomics features were extracted. After the exclusion of unstable, low variance and intercorrelated features least absolute shrinkage and selection operator and recursive feature elimination identified 4 features that were used to build the predictive ML model. It obtained an accuracy of 0.71 and 0.72 in the train and test sets respectively. Conclusions Whole-lesion T2w-derived radiomics showed encouraging results and good generalizability for the identification of low-risk EC patients.
2022
2022
Machine Learning; Endometrial Neoplasm; Magnetic Resonance Imaging
Mainenti, Pier Paolo; Stanzione, Arnaldo; Cuocolo, Renato; Grosso, Renata Del; Danzi, Roberta; Romeo, Valeria; Raffone, Antonio; Sardo, Attilio Di Spi...espandi
File in questo prodotto:
File Dimensione Formato  
MRI radiomics A machine learning approach for the risk stratification of endometrial cancer patients.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Copyright dell'editore
Dimensione 885.34 kB
Formato Adobe PDF
885.34 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11383/2166233
Citazioni
  • ???jsp.display-item.citation.pmc??? 11
  • Scopus 23
  • ???jsp.display-item.citation.isi??? 20
social impact