The development of radiomics tools allows the extraction of quantitative features from medical images, thus enhancing the available information for clinicians. However, to date, these tools do not allow the user to complete the radiomics workflow by stopping at the feature extraction step. Therefore, a new software, namely matRadiomics, was developed as a user-friendly tool with the aim of allowing the user to carry out all the steps of a radiomics study. Using a single tool, i) biomedical images can be imported and inspected, ii) the target can be identified and segmented, iii) features can be extracted from the target, iv) reduced and selected, and v) used to build a predictive model using machine learning algorithms. As result, two different feature extractors can be chosen, a Matlab-based extractor, and the Pyradiomics extractor naturally integrated into matRadiomics. Extracted features can be selected using a hybrid descriptive-inferential method, while selected features can be used to train three different classifiers: Linear Discriminant Analysis, K-Nearest Neighbors, and Support Vector Machines. Models' validation is performed using K-Fold Cross Validation and K-Fold Stratified Cross Validation. Finally, the performance metrics of each model are shown in the graphical interface of matRadiomics. In conclusion, the result of this study was the development, implementation, and validation of an innovative and complete radiomics tool that accompanies the researcher throughout the whole radiomics workflow.

matRadiomics: From biomedical image visualization to predictive model implementation / Pasini, G; Bini, F; Russo, G; Marinozzi, F; Stefano, A. - 13373:(2022), pp. 374-385. (Intervento presentato al convegno 21st International Conference on Image Analysis and Processing , ICIAP 2022 tenutosi a Lecce, Italy) [10.1007/978-3-031-13321-3_33].

matRadiomics: From biomedical image visualization to predictive model implementation

Pasini, G;Bini, F
Secondo
;
Marinozzi, F;
2022

Abstract

The development of radiomics tools allows the extraction of quantitative features from medical images, thus enhancing the available information for clinicians. However, to date, these tools do not allow the user to complete the radiomics workflow by stopping at the feature extraction step. Therefore, a new software, namely matRadiomics, was developed as a user-friendly tool with the aim of allowing the user to carry out all the steps of a radiomics study. Using a single tool, i) biomedical images can be imported and inspected, ii) the target can be identified and segmented, iii) features can be extracted from the target, iv) reduced and selected, and v) used to build a predictive model using machine learning algorithms. As result, two different feature extractors can be chosen, a Matlab-based extractor, and the Pyradiomics extractor naturally integrated into matRadiomics. Extracted features can be selected using a hybrid descriptive-inferential method, while selected features can be used to train three different classifiers: Linear Discriminant Analysis, K-Nearest Neighbors, and Support Vector Machines. Models' validation is performed using K-Fold Cross Validation and K-Fold Stratified Cross Validation. Finally, the performance metrics of each model are shown in the graphical interface of matRadiomics. In conclusion, the result of this study was the development, implementation, and validation of an innovative and complete radiomics tool that accompanies the researcher throughout the whole radiomics workflow.
2022
21st International Conference on Image Analysis and Processing , ICIAP 2022
radiomics; software package; machine learning; image analysis; PET; MRI; CT
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
matRadiomics: From biomedical image visualization to predictive model implementation / Pasini, G; Bini, F; Russo, G; Marinozzi, F; Stefano, A. - 13373:(2022), pp. 374-385. (Intervento presentato al convegno 21st International Conference on Image Analysis and Processing , ICIAP 2022 tenutosi a Lecce, Italy) [10.1007/978-3-031-13321-3_33].
File allegati a questo prodotto
File Dimensione Formato  
Pasini_matRadiomics_2022.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.05 MB
Formato Adobe PDF
1.05 MB Adobe PDF   Contatta l'autore

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/11573/1659662
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact