3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction.

Autor:	Gitto S; Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy., Corino VDA; Department of Electronics, Information and Bioengineering (DEIB), Politecnico Di Milano, Milan, Italy.; Cardiotech Lab, Centro Cardiologico Monzino IRCCS, Milan, Italy., Annovazzi A; Nuclear Medicine Unit, IRCCS Regina Elena National Cancer Institute, Rome, Italy., Milazzo Machado E; International Medical School, Università degli Studi di Milano, Milan, Italy., Bologna M; Department of Electronics, Information and Bioengineering (DEIB), Politecnico Di Milano, Milan, Italy., Marzorati L; Department of Electronics, Information and Bioengineering (DEIB), Politecnico Di Milano, Milan, Italy., Albano D; IRCCS Istituto Ortopedico Galeazzi, Milan, Italy., Messina C; Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy.; IRCCS Istituto Ortopedico Galeazzi, Milan, Italy., Serpi F; Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy., Anelli V; Radiology and Diagnostic Imaging Unit, IRCCS Regina Elena National Cancer Institute, Rome, Italy., Ferraresi V; Sarcomas and Rare Tumours Departmental Unit, IRCCS Regina Elena National Cancer Institute, Rome, Italy., Zoccali C; Department of Anatomical, Histological, Forensic and Musculoskeletal System Sciences, Sapienza University of Rome, Rome, Italy.; Oncological Orthopaedics Unit, IRCCS Regina Elena National Cancer Institute, Rome, Italy., Aliprandi A; Istituti Clinici Zucchi, Monza, Italy., Parafioriti A; Pathology Department, ASST Pini - CTO, Milan, Italy., Luzzati A; IRCCS Istituto Ortopedico Galeazzi, Milan, Italy., Biagini R; Oncological Orthopaedics Unit, IRCCS Regina Elena National Cancer Institute, Rome, Italy., Mainardi L; Department of Electronics, Information and Bioengineering (DEIB), Politecnico Di Milano, Milan, Italy., Sconfienza LM; Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy.; IRCCS Istituto Ortopedico Galeazzi, Milan, Italy.
Jazyk:	angličtina
Zdroj:	Frontiers in oncology [Front Oncol] 2022 Dec 02; Vol. 12, pp. 1016123. Date of Electronic Publication: 2022 Dec 02 (Print Publication: 2022).
DOI:	10.3389/fonc.2022.1016123
Abstrakt:	Objective: The extent of response to neoadjuvant chemotherapy predicts survival in Ewing sarcoma. This study focuses on MRI radiomics of skeletal Ewing sarcoma and aims to investigate feature reproducibility and machine learning prediction of response to neoadjuvant chemotherapy. Materials and Methods: This retrospective study included thirty patients with biopsy-proven skeletal Ewing sarcoma, who were treated with neoadjuvant chemotherapy before surgery at two tertiary sarcoma centres. 7 patients were poor responders and 23 were good responders based on pathological assessment of the surgical specimen. On pre-treatment T1-weighted and T2-weighted MRI, 2D and 3D tumour segmentations were manually performed. Features were extracted from original and wavelet-transformed images. Feature reproducibility was assessed through small geometrical transformations of the regions of interest mimicking multiple manual delineations, and intraclass correlation coefficient >0.75 defined feature reproducibility. Feature selection also consisted of collinearity and significance analysis. After class balancing in the training cohort, three machine learning classifiers were trained and tested on unseen data using hold-out cross-validation. Results: 1303 (77%) 3D and 620 (65%) 2D radiomic features were reproducible. 4 3D and 4 2D features passed feature selection. Logistic regression built upon 3D features achieved the best performance with 85% accuracy (AUC=0.9) in predicting response to neoadjuvant chemotherapy. Conclusion: Compared to 2D approach, 3D MRI radiomics of Ewing sarcoma had superior reproducibility and higher accuracy in predicting response to neoadjuvant chemotherapy, particularly when using logistic regression classifier. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2022 Gitto, Corino, Annovazzi, Milazzo Machado, Bologna, Marzorati, Albano, Messina, Serpi, Anelli, Ferraresi, Zoccali, Aliprandi, Parafioriti, Luzzati, Biagini, Mainardi and Sconfienza.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu