Purpose: To determine diagnostic performance of MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor (ALT) of the extremities. Material and methods: This retrospective study was performed at three tertiary sarcoma centers and included 150 patients with surgically treated and histology-proven lesions. The training-validation cohort consisted of 114 patients from centers 1 and 2 (n = 64 lipoma, n = 50 ALT). The external test cohort consisted of 36 patients from center 3 (n = 24 lipoma, n = 12 ALT). 3D segmentation was manually performed on T1- and T2-weighted MRI. After extraction and selection of radiomic features, three machine learning classifiers were trained and validated using nested fivefold cross-validation. The best-performing classifier according to previous analysis was evaluated and compared to an experienced musculoskeletal radiologist in the external test cohort. Results: Eight features passed feature selection and were incorporated into the machine learning models. After training and validation (74% ROC-AUC), the best-performing classifier (Random Forest) showed 92% sensitivity and 33% specificity in the external test cohort with no statistical difference compared to the radiologist (p = 0.474). Conclusion: MRI radiomics-based machine learning may classify deep-seated lipoma and ALT of the extremities with high sensitivity and negative predictive value, thus potentially serving as a non-invasive screening tool to reduce unnecessary referral to tertiary tumor centers.

MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor of the extremities / S. Gitto, M. Interlenghi, R. Cuocolo, C. Salvatore, V. Giannetta, J. Badalyan, E. Gallazzi, M.S. Spinelli, M. Gallazzi, F. Serpi, C. Messina, D. Albano, A. Annovazzi, V. Anelli, J. Baldi, A. Aliprandi, E. Armiraglio, A. Parafioriti, P.A. Daolio, A. Luzzati, R. Biagini, I. Castiglioni, L.M. Sconfienza. - In: LA RADIOLOGIA MEDICA. - ISSN 1826-6983. - (2023), pp. 1-10. [Epub ahead of print] [10.1007/s11547-023-01657-y]

MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor of the extremities

S. Gitto
Primo
;
V. Giannetta;J. Badalyan;E. Gallazzi;F. Serpi;C. Messina;D. Albano;L.M. Sconfienza
Ultimo
2023

Abstract

Purpose: To determine diagnostic performance of MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor (ALT) of the extremities. Material and methods: This retrospective study was performed at three tertiary sarcoma centers and included 150 patients with surgically treated and histology-proven lesions. The training-validation cohort consisted of 114 patients from centers 1 and 2 (n = 64 lipoma, n = 50 ALT). The external test cohort consisted of 36 patients from center 3 (n = 24 lipoma, n = 12 ALT). 3D segmentation was manually performed on T1- and T2-weighted MRI. After extraction and selection of radiomic features, three machine learning classifiers were trained and validated using nested fivefold cross-validation. The best-performing classifier according to previous analysis was evaluated and compared to an experienced musculoskeletal radiologist in the external test cohort. Results: Eight features passed feature selection and were incorporated into the machine learning models. After training and validation (74% ROC-AUC), the best-performing classifier (Random Forest) showed 92% sensitivity and 33% specificity in the external test cohort with no statistical difference compared to the radiologist (p = 0.474). Conclusion: MRI radiomics-based machine learning may classify deep-seated lipoma and ALT of the extremities with high sensitivity and negative predictive value, thus potentially serving as a non-invasive screening tool to reduce unnecessary referral to tertiary tumor centers.
Artificial intelligence; Lipoma; Liposarcoma; Machine learning; Radiomics; Soft-tissue; Tumor;
Settore MED/36 - Diagnostica per Immagini e Radioterapia
2023
19-giu-2023
Article (author)
File in questo prodotto:
File Dimensione Formato  
s11547-023-01657-y.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 1.04 MB
Formato Adobe PDF
1.04 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/2434/979108
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 5
social impact